From c7aa0701dc79518b0616d0840a02ac1d0e8ee3a0 Mon Sep 17 00:00:00 2001
From: xiaoruiliu <xiaoruiyliu@gmail.com>
Date: Mon, 2 Sep 2024 19:15:13 -0700
Subject: [PATCH] make week 2 course notes public + searchable

---
 _quarto.yml                                   |   4 +-
 ...nciples-and-Techniques-of-Data-Science.pdf | Bin 0 -> 142761 bytes
 docs/index.html                               |  12 +
 docs/pandas_1/pandas_1.html                   | 232 +++-----------
 docs/pandas_2/pandas_2.html                   | 286 +++++-------------
 docs/search.json                              | 110 +++++++
 6 files changed, 243 insertions(+), 401 deletions(-)
 create mode 100644 docs/Principles-and-Techniques-of-Data-Science.pdf

diff --git a/_quarto.yml b/_quarto.yml
index c06d8eac2..29a6a122f 100644
--- a/_quarto.yml
+++ b/_quarto.yml
@@ -17,8 +17,8 @@ book:
     chapters:
         - index.md
         - intro_lec/introduction.qmd
-        # - pandas_1/pandas_1.qmd
-        # - pandas_2/pandas_2.qmd
+        - pandas_1/pandas_1.qmd
+        - pandas_2/pandas_2.qmd
         # - pandas_3/pandas_3.qmd
         # - eda/eda.qmd
         # - regex/regex.qmd
diff --git a/docs/Principles-and-Techniques-of-Data-Science.pdf b/docs/Principles-and-Techniques-of-Data-Science.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..7beef688c1b1f6416f45d9ddb8f8348094b72990
GIT binary patch
literal 142761
zcma&MLv$`+mxUSJ*tTsuH#WZ5ys>TDwr$(CZQHif)vJ3@wW<dH>>clY@VsYjGI<d(
zIwpEHXtJZb>o;gFLPkPc0}E(gUIsC9D<@+I1~IFDPR1g}hPFn=3^K+xrcP#rtc)Cd
ze9(?g4#xkiq1`r;6*~b#jEGn7(7%1@-fNaxLR4`;;qX*=1)TIj5dpupYtJP9JUadf
z$%dw`CZ>OHHuFKf=g1Z?w$7zp<*;*qb#F~wKf_}BBITVPFVeimhVkO&U@$lsYF&Zi
zf&T!3n9~A1?erMVv4Ph4z{o<N&s*_6S1kh)awKw~cba)CkDHB^VYeq8VvrQ%60RF=
z&I<FT>Yas$yHS3Yu@;}$`8z}3Gjv7t3`iHH<GlYU^b2}XE`aGFuaqQ_qD49eKu^I3
zo)V&|@29ETH@ZQa@5QJ(Mn=fa|KM(h$+jsIp<q#5B0?n=7jYV2J)&9kde~dHqLHRi
zE^F8Z1CJJ~`#*sgHpJh1$~GM$whm>GPwMYgcRQl<)E;sYexh0>jboJ5thH%1b~1r{
z`|D)Hk5oa$Ro}IJR#PS44B=VG@jV-zpH#5yM6B3!H;X1nr))8r8#24Xkpr^h*<F**
zkjf*EiC)?^M*?{4H~t_jovcO#Rn<^c@m&y_+m?fW_jFtQu@b{9S;grxcuUPB2vt8h
zhc>n``u`pJuh;);DeHgaEfWVP%YQfbI&<9Sh#gVj_C4YU*l~<F5=Q@tNPt|x2G|S6
z;moGfaf0aA7wT0-Q5xUY5a!T-d1V0ky+U1!;D@IUwE1^U(EmF>bh7tl@%H7Hzp>ZX
zo73xa23{aM$uBhY(w~VK5y3SAMfQDv|Gw5!s+bSEu6I3HaW4s4mMZiRFLmJuE&aP_
zi^7<{pX*DMcjGgvvj$h1^XL0+biXx}OAwPR1X~qmAdMLFSpI5k-P^0AW`x_*y~8wi
z7F7Z&;wFEK7CQJDQ~+tZsXLcNC^%eB-;{%HlxNPKy~tOOha_uvRHJPK>(SR=$r;c2
zQ85=S)s1~dH@#VbkQ|l?+cR9A;5Kf7!DUGIbX-aOUu1H&r{@~o09;*(xj3nWil*3P
z5Yh;ff_V}NczW@0H-k2)7yxZc5?J!PrA(NGdUaMF(i~DW{n!Ns<H!^>>)fwYpD!!w
zDnTU>Y#a<#82D5SOPRNF0PUtK;htWn@;k^uLNdxI&`D2`OIJXaol=NpAK7*{Vh{d0
z8#}Cs(@z<AI4DePbzPPSg&K^87pxd^#Sy@i;%8pG=I`#Tp8=I>0LmzaY}sq#7k>&H
zl{~@2&<_GeNDFH&ZF9ZIOI#K%?}h0KaR}GCZgSDu2eO1HI*dzO3LDuqG<}9$4M~?0
zbnFO&zoVH2iwJBGXVuEdA0x?AoMqehhZFdSB~88erkJrFI64HCbq;e$`_#TZmOP|h
zZ~!mbRCqz=2wNgy5=MIi5sO>mD+EPnM=3lgvGan2PyIZaQIZm4P~y{|_j?{ZFJl;4
zZqra8E=u4fdzR{th|keePYaEG<ajt{zv_^eP*7Se*6@5~PCNuK*_9x=bJ#}_{0kjf
z4DJsAu4`*aLvXD@BOn<s565Mfh(8V;k~Cq`Cz$+PGf&ELVBSexL)K32?L~*}HBXHv
zgWklL1Rxol#(xQZ7+^>B5Piq_>?Bz<<RCj(?%f6p>K;u?HMUc(uexs(kNBmJ^gS;r
zk&a)w1ER=n#03L6HIt?KJ>_lA-~d{AUF6@YU+FChNdG$rS|vPS06cAMxf)ZK*@+M)
z-zuVoWMJm%!xlK#wB2|zx!t+LT3tob)NobTjR3eN?o+1w2TZ{@RP%xhARE8WsxDD4
zHc7%uiZx5#APca*r^66Hgopyrbk&)1OG%_Hyc1n{{XuIaFTXmbIxg?iME<hl+JTzy
zl)I@y9^bBjsii`79S9rUpgK$hr0;ebb_ElwdZbFpWq~NHbYGd=qqs?vplfM+#w64w
zobsz-HDfZ3EK9yf3{?>Fn?hhYY!nsBYk-#RlWjRyZ9StM7ra!z99>@ua~d=a?<Ryu
zpn?VkPR?jB5{`epv5Kjf+4fICrI!p<8?-Qx`j*xiZ)KS0Gdt*}ne}{yt&YE;L5>{&
zsj^#6@UehQv68SFGj=0tQHxf2Zq9C$#zIpNt_P%@{E_-q4pmo4cKU`R;z@B$HUlzj
zXD)g(cog1=vx!fCobfS4Wx+WdyR+8R8PH}~sXICn-JPg65w|KiVTog|YUZ^i9F{0R
zJdrr>em+2H7d<+qE@gy)?P6fe(iFY$^G}{*6h<X5IX4A0Qa7ks1vOah$KK--s4y@p
z=V*>AGJf?N8h!#)b<}p$)SPo}e*upPUb3m;khEQtY2<;i0?U6VeWON2Rd$us616W6
zU>RS*Fr_pcsgfW}VnZ`1;lsjam(nBvUAJ|1ej@c_&tWD4wOS?!nMIn?k7u!?kqMVx
zlw25b?7W+hIcw69Hs0nqK9<(gG}F)PMgFb0&hTa1HUc4h&Y^$arhkfQcDS~9Ou1kr
ztS9p(LPd_pDMpc3nH87P<Vr)9?;lxF;g`v*{{0bZ6P|Ccq_7AooddoB4PlMCjC0AJ
zNAW+mTCpU$O5EsSzSVn&Nd_Bj);(-CR%{{%hfoBN&8xJZ+nftoim<b!TEwo5Gm0u2
zxl9|G)!x1G0XmH%p=e(t4B}ikglmJBfQC~}RGN@jQ#t@*)VCI`lR-26(&#|#;^!@i
zt1+FosswYY(PmcWuA-}E>L2Aib*js`-@)=2k|z(B+DL{+2uE~=Yh^ax@8XUIUt6rU
zt%sitdvIq_J|7@%`e9Re8=!8b$$Q5)mq)Q`$wIkTbqpa6!FoFrjfD>>=vD&%P$U9S
zQaal_;|v~$xM5N%0%rn>32(^-$~{Yx4I$3F<t@<r$)uJ;Zm>ioQL{xQYegiBg&J#m
zBHomH8gjH>?wa4w!j7-2;%&vRjOWeCS5MbCP`~9BK*(lyZB5%&pha1|P+jTYs#=Aj
zae0Vu4TCd8)5Oe0$rH5@*4oLDli-%6W6!n<f4+`=*LQUg|M&7_WBpISh?$M;zwgfD
zq;3Ex6YQvK&H#g5f9`u+1#B`<I2;v@L7tkv!QOW&_o)BG`~q-VMWpfRjPGcKFSi>g
z$Wtg`Jwwp_vMYxT!|qo{|8X<$KT37T4HnE-#E_o}=%(v$XeK^l&7DV0f{kkF#U5p+
zgag_P<n_Pp;;jcSL20}tND7~?bOm==rZ)D}Ud!-KV&ef8x=kkS@btWqVLp1sJ==$m
zYR!mb^fnqFSL~(BSwiFlNS2IKFdjw9wG&%B@e}6HGyM=a7qDih|CAu&bBYgT<j#}6
z1jP7b-0iQp;_pkNz9>}m$eq$E7Jn(xp|k#koOP9#$j!tgcXX}+o2elt{cjD~8UGUv
zIXM4^hS92jZMPU<w?Ao~AgUya_<#q6{mBJd(Oc2*4zz2PLSKFn&_owfvUO3mpjwR1
z@8i9StbK57wLjex^S`s*-<M6~tiQTEzulM+Vt4!+sRUV5Gw*joFsGB|(L+xhzS((F
zzXN)7kg{Ngxzw{Gd$wzvTD*F_*mLP$`@HKgk)!tTyXZvcy@i3b$(>jRODu7k>56z4
zbyyrOLyW+3LcMF?FmppN+%?nfJVfhIB1d?%be@H(t}Ta%H6e7viU(3a3uTB7x(-kJ
zXx)=(PfY92oP5*L@tC6hA;9V&9Fi}cfu9$9@6NN%Sf_Xm8DjVbJKRfMsITSuf<!z=
zl;fQ>)gn95jzv15#H(@X=HBCH)4j#ptkb@n^h-62Lef$|29mBq8${dc$C7K+Jzr>5
zt<D8;gp;rGC@d4QCsuFF8^a+JP^MT18)Mvp4W6o4{Qi0p)vHmz<=hsvVK1tE7-kV9
zjONJcMECK{`?X*T#ZpFe<I{-U_`q^Y;xM1a7}DaS#t@y__%lZu)CM#%PvV6hHpp~m
zJ^pf0^s)^26K#(!JRVFfWk3kU70KT}>$4fgT}*`njyVNO6lV!zq#xXqxq(0Ht*<nD
z?&YJIIH%RmVTx{e{!-z2&FY`#JVmXH`+di7Bbh=g%>d>{DPC#HMlGR%kX3@_dlk~V
z0@9HH`5Lbl>ksyeHTj*&&%B<64P>FA1KjBI0ydU~PYLfIq#V9K%ksiU5!R|!kQ?W>
z81Pw&;A3*lZTC8|xYjQBR?11-?hxn)8nwt(SuhkGEc!7`8O8pigcU|qm;Q}XM*_=e
zTy6gX@UK|J8@b(T>d$Z2G6%}fUP_v945(O2dd%#Si55H~>Cxm;M)K)QcoFE3i<jQl
zQaa8A)|1?Q%bj8M_n{jrKXgs4S^rWY#5zyyX@qCC9WQgT&#S+*q>GU0D6Q&T;Tqo$
zOsa+Wj7jA3d#y?2)|#7uZdrF=rrjvm6~|XM&+}1U@08B%)8@6tX$6yx$yRCTSv=zp
zr6TwO8%ASM{2yJ#`JZ$ZGY31<e;-ZP*yAy@t=BoVWsZJS(x}ofjF^9b6CmE$`+>MH
z`Pxbs8A4A9UEtrpC5WjMDlUw1A?#B)Y87-eDQ_}8-v8A{j{CYm#r<X;e}8_xQ2Fxd
zdH=jvzhAt%05^IdY(BVXRO#4nrj+ijm~B0{{G6<(!Rh8O7JtE6|71nqQ~Ao|)HBG<
zoItf5`SSu(WQb5E8sAU0+Uha%dRm&g@E+6ROksObLjKk*IXmwgsHPsYe0ft1KJ8Y8
z?7nZ(%<>}1`zTA)#^Sj<mTL6q_Pn$6&$vI9e!Y7Ep#rVI9UkZhCk5S#2tzn~{{k!4
zevLkT3yr&I2$Y-2+1>cYT*0Z@4$K1B<KK+BCpD8FdO3T%dTG^8d!if{mlmVj`B5TS
zEZ8}<;HheNs@bv2Xx{$1n=<ygsfFFO*-*J{vbXrZ8VfpAB8-<C>rGJBob^{UhizIU
zyw(#i!Xm+=6+}(A>pkV^FUL|!xUx=Yg%EpAT9QS%B&&TqxoUjqay^Y2ze}shLXMn{
znkaH{^@o_hGhOzn`F?x7Pk*|y+x~vF{x&}IY5i-iGY(YLP9U1n7C|YLKMUNBfq<BD
zpQ@Utz_<hwuyY6c*Z8k5Ta1}Jorry-=S*7A5N4!=ozx6!59={LC!~~EB2qURENpMX
zUL$}VNJzLGZt9>^p`<-w4IBpp+wE_Gk#FC!%+T>_!TE4xxMHHzZ!6T*LNqrP<S@L_
z%5uR3mC2>5YId`me!p)^RPfEX@%N^172S+Me_IJ1eo4J0x{@S9{e=wrJOLjb><=ZB
zO>mk_1NR_Wlx2jaPR8R>hw~y&KcEv9+)#VQ>6)i_kc^E!-PXNB2@su4bKaQ0)pj&Y
z#$V%pAMWCjHk*7pn<(_nESf2}xo4|F39&WGHWV;}u38sQc87m6IX%1#Ji~K+4tBsI
zeI$ZR?LhiIpCu<664wj%3$mYXq-LyP1WhU&^^Ub6MTjZ7aYM{4U~BBX2rZ2mnBQ2z
zo>n8>_m-?v2uN1Ky;K<HRQ+pV2bTE&?rRWM&byfb%TV;-E^rxq8+gJ$_8KSauyMW{
zj^5^!@fR|L*)`kNqxw?SN#fhbmCJcH7NqeEI6|a7;rbIg_L5f1D;+M!b-3d}&vdjl
z!L7%qPZxU%v%&Of>RW@rA+1Z8zgpmgxjR1VNxMFc5ZAPPK=j4=497+Hpxx55g&_oe
zX1gK+|L)94B|torgJJWfikC?#fv!yxsh>kiSRYhZ&u+mDO*>e;JGQ=5?@(<e=(b60
zQf7XhdEr1Lp^;;1w}3O5wCXlW1QE1$LIt;0OFFwhC8-P;^bE6f;C>^V$p9k?>VU;P
zsSjWD3;evsEp>hoQ5(T4f^%|aBLt7Y?^?nkAz&ayEsyR1SYH8AC}!m!%4-x5ej07`
zj`Dg7h<7N!hPjqH;_?-s1BrgG238wK{k2HQ__Cen-3sJJsJew*8u%mwO*KK=kryq&
zsi>p8-ET5xTS&t;tHU(Wf$UU4y|hgSyHVrosQzHLO^FLJS)<8jr^-vckHN%xLh!EQ
zI7S1^;jwjTv^^(RG6XXgkq$z(3v#G#ZV*VRd61>j2=63NUPjGiBNYLPVbKQ8A%8P8
zn_a<y1M3s@h<xl}LX1==+LZWERw~KlHf;2Iiq91;qwllYZOT;AV;P&8W}#M8L(ciG
z6N2!Ue`Q9t2O$o8s=_7>JzUOv=;0$8_h|7VK`Vz41DLSelE4!hsK~+5&t5e&cx49P
zE2a~Nd>fJ6y!#xuWaBm%P>nwa^&r${rpK7Ek0mva7dxxdH7(XX$7)c!h(9vvdh()!
z><F%qJ4&eD%~Q>Hi^7o)JL`B~_)eG;z6;pUN2`POi;DQe)h3P{zCeu<^T362d+b=U
zIdFA>y<}5ENBy{j*aY*QOlLpE8^9SKsZaV!vLmx%G>}z_&DACtm0{ppfx#Rs-QMIZ
zJqDIMno&Ngtvy_qWRq*gpH57NzbM=oFh1U{30s;I5GIU~_4r=@kuU%W(@4R7PngAh
zsB$7kq`nf7d7b>2gCVLiRzs8=fgk&qZd=%X#Qq{DOX?=e{ZE>DRDXFGN9b8XwMYX8
z4Pur<ZjT@(wD@k21SSCS^A=vsB;rTy69I2!6j@<}%ISlp@n{R@Vpk4je?E+rbf`WM
z0L~+tRES%`&^I!#?8kypi}%z5<}x?-8KA;M-T*h`WVAWH)p*?@1QS6hX*Hy@D}0dh
zmtcGt%WQJhpd-;|5s5&y7s|$&iFQAMp%srpR)0P)q92yzZw@iitPW1OPuqlLoTIRs
zG0LZ*{meP?!}<ZRv*IRZCcAM3UELc~9V$VP*pVhneuo^zjg#(eOkEjdBoS62$?Wz|
zrLg6nCG6mNR5`)VJ9n$o@Z%NCNVsxoTTBV>rpa8Mh68yhnw3H^ud|e4YG0#p!18uc
zQTC;<dhEcp3u5Ric1K|@%{I4UvOF(`j41wabeX-`C;WEx)Qm!aoiL^bO;VY+Bh;!H
zaqz3K`QrNSBYbx$nXGdz;4RoSJ150q9?Nk+UEKDKI=L2p00#%JqQX*=^<7yqlpmcV
zgF-c(S=StH-=%hD#9E1qp}H1H(l|oJAK>X*@mJrTze_73zj4MzTGK5nN8*CgC32I#
zLj~9Mhsj0vB|vh~e%1y?3{IH8gP&WeT``2KDZO-U!OftC9im7o;j8XAn5bR{TB-Kq
z*eq#Sddy+&Q_Wypt7;&Y0f|$`o@j?CpRxUr#nYY&%5B97dni-Fji#Mkq9&d8RYSA0
z;K0AMhO!!;e2lwA%>!Z-+X+MPO@+Ii=;CkZR-quWp{4n1eV<V{y<_s6GPAeQaMI1F
zxKN3tt8huxM(NcO$z}7uVUG)Tcc~$F@k`4lW@8&*r!6udE&!Z)Q}Y?bl;=6gfa>rL
zaH|;iO}iU+Bz53Qhtiu}hQr*fJEc#nYIKv|xvAZUqQMm|T+iAR9n84qf`Xc9t<Vzg
zTC3#YHoN%}9ZVLDLWVDI-&hPf7Sqk$M(0BwZ$ck=#g<?I*=w2jzHC*xi>>3!LRqr1
z6hy3L`OjE#e;53+@h(*&EbI<Juca`-3gVVrn<b9xPot}~K?Gf3R6~zg@O6sMvHPy_
z7gI&yv?>sP@WsE<){gWNVu*j<wRyye+cl^rc^@hky7L({d&>~Hxi-^36?z=}TuxH!
zf7Mo4H==Myrb;}NaBJA_?}#67sv&b{pc(ve1y?H@A_%#Ue=`uoIoQlS6n)5qkW5a+
zmF<}cx7<CK)cWZDAY2{~$hJwU8=mS<`_AtP1}bPre-HufBFU?8Z2gN$W$Ew^3OZ4S
zxM!P6<_^0RKCwwpj0ti3k%HIJn)+s!2u-yB5$$TaoZgM((@IUfex(Z8*X*F<=vXAN
zLX3tnrF#!Fy4mSh+P1qBe$dGn7W0Qxvq?m}hS1z@>iBqV1fVYs&lz|96(q<NPYBiN
zpe?I2EqDHsN|AM9Exg<IobOn_GXIvp+dDf}F5JG{h=y16j#X_JO<%?UEEmeGs`TWO
zRRkxxrcG{DtF$w8Z?1qu)??JNRJbg&=(u^;#h$oaU#N0PV-d;1jq27@$s<5=42~$|
zbt2tm=}aQL=Xk-Rg*{ASx}ptT*8Tu9$OIVwZye@e`Ok2ejq!iru$FWzX)9dMsoD~k
zfF;=l94xk=pBwNlxjG@lAjE5wr=vQAy~Efp0#$^^lJYCy^=0jF{n@6oMZG{o5tYnm
zSkp&ms^C6WgLqG`oA)cg_4fYte!RJrO^oX{HJeEREI0gowYZ4}4x`!%;PbvKWb{*+
zT=V*@_xd~@!&9BQu=xEL!aG@>dYek%Gc-xU+&j9Pf)A9}B^@b8t)Y;ua`rddWH;`-
z=coLlTd|sMMow2-Ss}C*U|kr<JhG*2yJBw|AX+=|rk7#sqmhz0%Qro%8tY=3^POlN
zRgi852d8KwE5Ao857QGX6*vog8$d=Efh_20R+arwM?0f|X3%0dC@11F0mf)(dD^wW
z6~r3Fyih?}yeL*}=z|?jtVs|ga+@%R_d?v|q_t#7-*K$hn_7Y}4ER+~@pVQ3d+@IA
znqhSSzkPThcnWg;{c-!69FzlJ=l^-lw9mEFmIn`>EUXSn%ATO&rr-`S`(n3G=vru!
zBHC1j1ez!A_vf%r$flwUA1=<8v3&|3x>Ly9k|0iT>PqoiDIMpcWaaLYh+M~99VvtY
zy{xtra-Kk;(05qwEL$(%=CzIrU;3***itreKYQ?ux;oUq-o3lgg!c(Di(ODi<3Y>i
z1ZZ0bMT_a-P2Z!NYBKAEHt7A_v81%y`vn$WJ3&G@kB^D2af1ge?e5wl+Q0mK{BwWJ
zruu7=J^ir%CUSrf%fDrA`1mu5u*=~4IR{Qv<#Y6>@nGRDab?F05C6XO9zs)V?Y64<
zZE2<SM9?zz?A!ykedh%CS*jH2*nVHTr0$=2DY3~Po>Y~Q=l&6&u-shYOl1*<G_3C9
z^?FX8oqMmlZ=X{<{YcCg#9Jf!a0{~^gJLst@hrQc7mr)-ZdcA%yS<%#$}S+8e0%Nd
z?3;0fvj`HY$-xu^G~4n*?gLNSiQZ3oIhO`OcL84vUtZN~W}Vkgprg>6IkMu)>ILq0
zz8gA8A#J~n&_AFUxNqfuBS?oGNT&fKyI7THB14K{F$SgwW?2yUgXBCLx0I+0ImM@y
zfq+8a#OAY|Qq!u{3sIz4Axu#E*Mji*3>(3^0<wwguMh~P<f5058=+?D`Adbak`FNR
z+bz6Vtk&Scv(f|UhbCTsABw~3)7;!p3l0eDp2@aGZ!Ln9+=Ni(;1$?$|BO2nol}FS
zu)s6<u1%y>ABb}sb#QAp4Mt-9pnf;wei=LrwLv4;wOOz1I7pQ*ZJD-a-Yh9^`!Fgp
z+`=eU2m2d#2V~PAiW6MCR#{qQlbGAw`)lpOp|*mHjXQ{!$c_h%^z}?8B-xTm$8l)J
zjq*y>z9DthzJF=!Cy1QB-X*U*7|$aK`W5OkqDs+6c)w#oM^5wui0JNp*!XJx{Rq+v
z#r1Mbyh<4i!#B}dF!`?}2{D4U$H~pMnw(dHhi^w*Pl@pZoYjf38;JIm4yIj6-+CL<
z`7d3+FTp$^v@QR2K_$~>;?B9R$H`H@A?xqy1rl!Jrpo=c4JU#Z-hmgMa%+*b`&+>Z
z`7C6%5xs1}N@srDE7UCeXKH<6`q@W?&;SHY$F2le2Z{vE2!&@ZcpvO@fVUG^Cz{!`
zCz=;jCz`iU%{nQbyr7E+^FGs^;SaLx9JMB{u~=?Pc`bs}RX_}PwC-HEs-O$IQy3K0
zJUIdP&=Mt$9OA<tCN>KWc^pGRS(`fJ-OK$U{<9-*;Ji20lg|*dCE3@52r;lL<gLj3
z2;v9hvV)=G!1Hp1!f>ZF1oPaZGQEZ3kPwMTvzOzwSaB~$ST=8ohopL`@x9WZYjD%A
zMTo}La|kTg4lg{)@JSu4Z!BeI8<RzpQi1raN_Kfu5}L-ekK>$VI4F9Km_~jo#&R|n
z5KcTy$YI#e_c}r7w6=b>w*Dc>K0(|DuW?nf)YMN9F0?aTA6;OLU<-J|9=U6-MwdFU
zn%otbOd4$xwKF!y4@0n1YPUrozHMD#*o;~Az9@Zd((Zn<Ylfs9gDEZhkVBwfI8`!D
z87+xPFlHg;)x8%Iy*M?B&>Joq<vaHVPS`Ctrgn*p@I`wd<1?6;fYVrd%h2-XVU5ho
z7&HBRPWMhA<iW_nKQa4ob6j>sIa`+-lJ_z436`)-_6bMdvV9xJrK0u=#|&{9ehe73
z@g4_7t@g-Hf7){d`&yLXS)f8Gs&g3J2fk_a$liyjatsi(ZiRKHZq`#VT-7A_?HAe$
z^A2Nm9`2L-iYMLqXmp5IrzA6p#!cWE+<w}j4~wq2g5R_ZvIgT?2RQ@P_G(AFz|(ah
zFFWg3qMqHi40V1kmPVRT5*1t>yY<k9pwi_%!6Ad<0w!Aw?NkkqX7G~Cg18VcE@1nh
zoPm}%AX%b^-GuK>I2Lt5tS`!(nuw-3*Vv!YgfeC46iVko#SH3{gXZ(-vm|87>t?~7
z*(Ol<^&kE?|9@pe4EO(*4TB&1Z(8Cj+1v?E`Yn!-CdYPQ@m$P=&O@YN=6{vV+{qAI
z@<DR~ub^CrQ85`52UR++cacXmOS#MzZMv6*A$2XRz%!9xI-w+n|L_aoF2ZY-ruNTu
zJcz`YVKvMk%s^w!-aqOlhk+GW*#wx=B|U<EJn*){=s9Qt98*cBLSEmES(o-BN-bF@
zE#ugtTXRbLpsXA2iY0-l@>*5)^$CtlWlJ1D13S)1G&SXe2`|H@3f`=G!UW-;WooF8
z<GeyWmNn+pzI+>mS-GO@k*_OkJ68i(1n=b*ApvkwD^asbs{m(R#kLd1%CLRxE1MHu
zy5dIO)E&w7Lr8@&E7bOB`2kZ;sI0F*njv~RfHQg$+p3=fODRjK#a4)gbO@$lEwp3k
zV_0W1h6Ri0XJk`4=d5s4fU@)!FwNW!%nkaip94VLbPC}vs1YqYJ3fpUDTzw1f+D)F
zPuXYOdIaQoN3M*8ey-Th5A{`>iYwJa%Uxkj4`PB7gnu*NNqYxIBA+LAjl_nazUz7n
z*3z+3bAX<gM$fRK^oQj;h*&}4z`OE-wX*wPWeqdA=;#hg@_kL-l^jjsron!}B<A_?
zi?%Cmyt*njll&4TUa?@#ILcktg|#nTsJ{n>^KVFALz=saXz=OM54Ek3+^g>H^et!s
zAB!98Hm0!PYYpeX6}4IR9y>d0NsJ3NjFT}aUay{Ae+|3+jp3J%klkKOd8+E&lr6C4
zxQ*TA!Y=a*n(>hF$vGn)YgLPR-FMkUamytg*o{ZIwXcRU%(uI5oQcCi`Tc7fny(zs
z*?3!&|I~gue&LLr%V@XyI;q9mfUFv;(vD_4`_KpY&Co*`9Vx)qgf43vm{jaTKPhz0
zz{nNb^06fN;hn6j5x{TTz0#A_72(*`#Ewzif8GDlLtQM=WhEy5Q<dj^To~FKG%Res
za2N+PygwM$*6zYm#;g3zQK~@@D~DNL=CC3WY<r0k^~RzWRpc@EB&nKwSSY{FD|A^H
z>$)+d^7HX5FG9Cy5glFGLx%1&c9K@dX9Q73BD|(4hPW5NpzmSHRX5?O7D4&d<h#p^
z!IC6GxVC?prD5=X0dvx(9LaCAxU*o+D-gR$<f(1z+rnA!vb<2)=wir_f`I8}i`Dbb
zlh=7_gA-G;5HfTfY->u}6AR~SJaHrU2f-1A=H>rjVD|rrff?C2|2qR$YqrO*aKPR?
zqWS>KkzQl~N6~?h0xy8A(M!bFua+wweP>GWl1i~O@*#fx4z$oJqQ2kb=KlO$PaOZf
zq7wYE1+4l$l<Gb1?q;s$^2zc4AOlupA~mkgAAK5J9*DALjHzf#XEzBj3<EgGGrlaM
zflZ@wqwVALR=e1Jzuw<B&w1O2vuE_lA#%nI)?G@ggSYxe*WZ(R>(#oM^}<v%o?8(p
zc@&en$Gw8`%y{oUgLg3Uzvz5xwk9K_AIh&ts4g_(XDA(-9ibWY&EtKy8CFL<f%LME
zqasUYD?>}scZgfNCoJ|MXcSQNKB|hc-#0~gCR(YO(Qt@y_ODF0tVN-DA1!aE<Zrs?
z2)5?D$hEd)`y+=@y!yQUF%hTx4^e`Q;^0JzN;h6*jaHJ-EzpV_uEaKWhcO$Av#rC2
zo+io9cFeoyBx}r&;Fke;rS?pO!?G4dSrG!KYK<ScNejJm#c|b;R`=Cn!*F4gd(QmD
zM7=s3L3+DM#-@vFzu&=k5lP+Gni8K`)nI&!WeKzRmVjQi_x-sl^rs`zhXQtDRsT9N
zvA^^i`d|yR)tInWUGcVhtwjHcv?2j4b>7xcdh0VUc1^t}=$E2a?=4YJyJ*gw(jRNv
zQRmG~Oi(h(f(Xhi`)o(=5_2^DRPWdB7)kSV!gQ>xYqg$!NN+fQn-JDE1?ei1+3wf8
zD~oeko>Rrui{63%`<{VE!#+JjoPDRCGtUPH)OHQF%8RtV&=C^z2}^+T@et%*2QyEO
zcvi+t((Ct{x#T-W`b@U3!@M*_Z|N<tE6PhLx~0MGpKl3~M6i0OIX;e{t2owHk*V!b
zWb2Va5=o>IMeUn+ALvWWo{w-radkEuqs2=pFOmk#%f_+mc{8vmAK?V^_r!1%ayvYj
z7*jP>PlF&|BiREhgFKGFr4}a-sS$NfRvaOu=x<Xikw7y+n}kgrUkq6{@!Bu<3^nxG
zKM`e6<}_dM{Mk)q%p8N?P8VDJX#U4vdy_7aU|jAf^3F!f8BGL_@2-->SwiguK~d6Y
z6qK8U!`iKSx1W+w36|oMtnxHAA+N93TyN9dA3g!QY;2c6=!(o292S}naPfd*N+!`M
zcSv~n!+s3qeXGSCFO{;$vM8}eT{keR0Eohg>0Bl*5??0f)u9x`raMatl>oof{X(*a
zR@{Zmx?4!r35K|qF7iM%t#O_pPus$=6FIC45+rGQ7|Wn!F4**bE=HfXR6Ae+KMfMy
zEZ7gPkz}Q+cygqv%;8cvU#-yzK(Sx)H;j#R(^RtV$F{$zPU7A*eK{~qh;AksTQ<H$
zk@8Xx_s?C(iWI7wL`AnBwe*lVKN%<IQIvucw@XC?bH%e6@<!}|=MG&+7lCLKyC&JK
zQ9XJ8c2?UFoy3W#+L4(DPgvf#Jk%2Fqg+-x*-$t7+yUq2e$lk&mUkv<XM@HyVA^X)
zb>!U>ra7n}<}ik@o}ptjOs-1>Rpz3GXNZ5J6A<MQ#n=T_7H>x=yA8pVE!GiM&Bx$5
zYd*0Y<L2S6U@|E&keE0v-RBrY9sDBx$|9g#rY-sNGS>VrJ_`H2p@Jp*)%$a9H;FT;
zZa^7<P_{FsfYkmH+LCyV1fDs{ONj<Rnw$pN@$<k<!<1}GSlz64fQ`Uq4eF?(CaL7x
z+-Q+qGRt)~+^H)Imn(v`FxXUZ$u?@wE(`RC6SJsv!!xr&*5MFr(cSqc?%#v_nz{<7
zL`vk{Z_vwzZGA-UGfgTRkU?JRS4Cl!&oYDwRcX^`YuKjL-d{gQx*L_9+O)aI4q>a)
zF|5zwR#w_2RHkWfy~d(%_A{E2>Oek<YV}P8x&j`(mj?)zQg8WC<A5jl61M%%xD?f(
zg1`A~E+=`JS=_khI!m&(VdT)qoSYumwT<ce^|yN}O8EO|AB1G@3g9Huo~_nfD407j
zgt^s=niBHequ2Ia#6tNSx4SqUXyCLqk|-O4y6H(CIE^iX{bj5*%+zop5W0hq!6C(i
zTR-=9OMrFucc<Huv@5`jnm06TMTc~z9izU<hHdruRWbfwv;7=%fIG!mi8Ml~I%a2S
zPxnr#ZBemolXm=Lj!NjC?e2>cd)N@?n@vq+nrf{!D+1GS?AVF9!3+Q51ma28!(mvg
zPAsXp30YWr8t15gr^3^;p0Uwa4Xc!EP3fTv{bH~1R;cOx8a}8bhy8?j4Oa{Iqt2_s
zYPU5Z!g_Tc0@kPXB?3&X1CyM>;{`YI?4}Lz7HTTF;;Jf3;PA`KvvPwc3e*^q-a>AO
z>n3cbdK}*S#Ev-pyjbQ)C^s9voh`wW&TY@UuRL;lr-lhDNA2m<pzOmU-thLy!X-Z`
z9a^h{m~DJ|B5%WTCLtUZVL1<OV)O6e3-|W!oe13XU8rF%3j>aNUC$`~uSRj<)iUF`
zbix5}iEKB`%%sN_Ri#6aEbu=uc1X5#Evpo)GnZ~I0`1Fiioy8_^j0I{>J=^iKJt2p
zF`jW~okWu*Ht`Demur&!;rM!9Ks-v>{yl?%y-i!xuPOJ$rjglktV{ZpKTslazf$ix
zk81Ryx>@kZiriAK&dLZ<17=L7k&lp`a#YVc&%DkEYz%K=%u3n=JU#hTvQ2b72k*M3
zYoKMVl}aua{YT+POkXc0pYEeu{BtJF*!I%ff=S{7nLR3pUSCi`hHHmDOIsXfj_j`<
z?FJEX<hR9_kw0O>xBOoa3bN<T{|8U}N6ArUM)v=~6Wtm-u}AFx#S=6q2vKqcy6lW;
z!~*mJ9YC94R5O>^m5N8d9PyO#1xD`po}q*qQyS=05w<>j-<}H;Xupf4K=;1R9={ZP
z-}t{h1V29?E*}re*-aVf&1Z|7*MD4~8+o!96SM%fn|c_<JA==+t^9!A?rkF0M^r+m
zAXS><eGm4LA&S(TmbX$fFdM1!*S3ZtJ<Vq+Dp330>fe_*-)om(JEDj$%R>)&wKN8E
zxdV`6R+Kc;EmNB({NnmmmV}~cH)Yi68M@6UdVCEDkfXs%qNW711Tz+VQCk#@QjI@j
zH0N1P_lUPAJE0jmMJCyN+0i*ETr?_|ucIq>an(d;bC_j_emj_qtl%}8l;k4RooExm
zJHK`Hc}(b6xMaP)<LXmI4NcjclqHB9)xZlIBU)i3PbZ^j>g!KML(OCL3w%m=MCr1_
zh)ju%xWsYIQbCfG$h6hQwifEC+vgu;WO1vrvo<4xGXOcn#eS?Qqo#Zk9TNiHQ7I-}
z2UTU3D$xKOje-j3hF|aZ3Y^r;!pd~69R`AiM{;p{kjv$Ar!&nd$Y=O$sz<JArv7D;
zmV82=hn?;Cz?;-34B4OtBNA21G-pi1kD^1m>_8{LSE+Lv^);)O+Kgk__s3<g&a8_@
z0!k9gp6Yh2w%lVUWj=!UzyR8tnau+uM4cBnIS}EyJOS5_&_Oq>p>KVv1yamudyuj>
z%oiyOXs@`=&W2s$zckJQoC4INY4cPlwy{Ev+`kL@f*MIZ?<ZDcz^g`33|r8!nVoTV
z79*uj-VVYJ-=y>-Y&Qa+)8}#y`k?z#5yXlGQ%qcxH~^!IDM^**11+{GRBJ0#S+ss8
zzeS{#;>)xGh$Q{-3&48h3TN&9OIl1eO+tQ`JV<i0*c9DEc}#rFsZlnpZTDD&6N9-F
zJLgT3Mmu^iHu`zD#wM-aK%>N>(FI#)M0Wk#jOVI!f_%d8QwX;@bZ(Q>%6(le!?TfZ
zxeDbYwx$(^iY}ZKQb)d87T#-$P4xUjIUons*e1Ew*5!o4+nn@Xc`icXp<<eXf?)zx
zTPiZCsi!x$XNj;OkiHN4kX(sNBF6N~`6NeVo{LfisvLKF8E@Xs=O(g2x}?c+#_mkn
zt5V(hp+}3#QSb<AaH3tQ{J!LzFUN9k`)jiL>44(zpsB}s$bwg%8R}HAQ=_$>MLief
zO3O=d`-=BoPphOxG0IHFRMxS^mQb2lT^7?zwag}Af;9godLTRs<zx6rTmDcCB?hCS
zEyn#sEPeG!5B%N);Fvn8uFOWmsj!WTxxvYL6yneRqtP%bni-BLKHxa$Qs|^<+_00H
z$TEf0t-_dVZb)6;MlKhcAZ#8;pC5^jj?8Q9pB4W^dS>0MO-2&ihJY5!YoOjGFvDA;
z7I~iP1DkJ3lJiogifyWUTAO|IyrlZgxsfV!glT-*>V^0j)>wKX>H=FeaSs89&sR#s
zQNOiW+!+r<4uq*Ul0u{$>gdsS+7&wHw2$ZZkycWGP=okRfkhlyjPp>see&ONPU~Jw
zrpR=YYrRNJJSRCUr`)4`VxCSzE3izoGO|Pq|DLD`=;_HV!$3^-))pf+xyY-#3@Kq>
zExpi<o97ugKCFJR(SLJ6tHf)Vn+h%4G^`1dQ$)LMZ)hv=CjhqHbtx5`!mL-J<*%Qj
zQy_@)&xm#frHT6*v1zaYv=3n7HzVnDORc6@z<w`hFr$-N$i8-BVs{B=%uBTwUCOfe
zW`6}-lqaH5?OFX~5BigRRC*P3E@dL!aoc3k%uShF%m@XS)%x?gJWgk=f1qU8ZiuZl
zFmYCWa^jI8#T|%e0LB1s+4w*yqK4$UAvY5g>tn`>cl**sJxr>O7^yz2Yju%sa}Q`F
zyP1unjW=|r6=Zm!23TA@6e$x}mkaYAn_QyDT9T1_F0^;MRsixAmL(mMTk~VA;Q7s*
z=WsN^?9@6uGq~m~xf3`_julmuyM+&bpZ)&tki9u{>3L_;KQ*li>|;vEgD%6RXP>9&
zIo)bgnE`&_2RJFtsTCKTe_v$(2<LF&_CN`o<MKl}>zhp?;8uVERw=o`C=lLkVYQ=r
z-sa>(rvC+r51G*#6H1bEmgf`0US@1)ZAmfhqe?2XtUOxVrQcl-kaW|XQUS=PNL}%}
zuilzcEG}wARshBVN9rYqKkSvf0QRyp!Tgc#T^)Pct?&LIlCLXM5>38|A5mbsjNt2V
zm6p+vbDFHL5}|I$01P8PXx*Tm1R7s+7XJPN-a6E_fFIG)@sWhb2O+j_uFj1RDb^Ua
zaOSp}e6rNCkC-f8X#rtizV+s650D%(M3d0sD^G}VoKB7q+YAKHso17rD5Gl{m6?62
z;LsVHGL#ODv);s|uWR1Zi~;Z^Bg{<+AZoO7TB8Y%p9b+h7Q2p2Go;Bi;L;g>uq<wd
zN@Jgc+5zMhMbYlIVt;BJVrIM<oX9j#Z%|}Y`dGgAvB)s{k|p65&YQL9gSL-4QyEV7
z5sRs=FhjKs!KWKOpvV{atZUQguA_W9`Ly^J=tdyyIszM(YGtQ&3jM!WYDH#{Qj{NI
zFbWg5ElWto8TPk~KW4d99vHM<@cNW?f7s&=KdWyG)dRKc(Z%&>WM?jp*<&4_6=K^$
zC2mX(w?4xkeR1#X`CKGnO?pAznvx9rPT?zlrx;CL*IIE$M%rG1AB8#HIefS0(<Px;
zV_xwGjOb#!Pr`<Cd%qy+;J!WnH(78p|0kCUCT4c_|9+{+Rv(YS;Xv&Er1^jlNgS@m
zL3Dydgczgqv++l`F`uL$c=%1Nt57$pUrwMk6q~avzh0h5|H<4knvBh4PSWG?{-Uky
zoj4sGyydT1JY|?Xs?xYRD7mzbu;JckreAdae6`B{Z1d{=`TOmT7hXUvrO$j6Klfp~
z0$#_y31g(4+B@jN)sH+u&271;%7^Z1unt9Yld`OhZdduov0bqzAJGHmn3V1~2oQ{T
z+kwDGwXw1dON-AH)DD%N&ae}jd6hsMP4GY@n)W$?Ivx=;;kw8%msNMaTl6^MaVX1m
zi7e4k`(H6GbY4Ixd4ZimCr+Y&JQ;in7zw7m&owh7`K&#6uo-dKB;SLj5PxGWgwR`!
zm$(_)a`&sL7?A8C8kT%L(leG$7jS2ven#5^{G+kkOWR5&U=eA8#y8C{7A3qo>&OK;
zrV(CaUaGTb0(uI`yzh0afRS$|y;DSbeCQ3wz2wY_^1-_&OUQ-iNhoC0oNV*}Q3iZx
zy;Nyi=h()uOT|9&gv<{miDpoQN<I5DGfP25c}I;q<{{^8{-hsFGZJ59fUK&Eglg=A
zD_NAUGD`#DNl<)EamFk3T?J9m|G>{zdGsTh2{0-pU+qN^nhisKygRn<Kj#RK;?fS$
z18pB|CdVY^%xEpK>pF3$PRdBmgAmTQGw*XtB_;X+m>eCCtP#Y>$5$r5k(#WfXndR}
z)$ZA4XCotHo$%4^(G}AQeZ=qb#<*f6qS5`Aa3=C}*CVWjnOndjKazmrc9@MJO;Xt}
ziWyQsjb6Pi2@+65$T*bS+XlS6o<2Ma_COs39ATsO<29A+3$<*<m2{Tkw`E=KAa+Vu
z;?^GSe=VPGq!@9HoXH{OiR&Y-D9pS*;Hl`Y`7d@wSBnjipn+VpkR)9G!|RM3ca@AI
zS@A#^gw%c}NRd-6xYynsT?#ss7@y{*A@60^hb&I_R3To?jIk~2o?XS=TvdZ0CGfxE
zks-?c2zf;1PENufsX$?+T+Z3cvRK{{y6VeIEz31cW9HHv1y-_oEI2ApdEtiFA6_@B
zH62qG%+xP9kk)?nQh#KZNfC-qO30f^+Iq_~8WvS&;$T!#J#oxRH~enceD1ew1EZ1>
z&K1n*J@eN+iKfb)9Gkg{fvUq&1R7m-lPI5r<~s2}sYRUvRr3)Tt@ROyRQLIsFiw7$
z_1&-`>EWuUI<zhr(0iw<H&$A#7`z8;T5zWj9Gq&g1>2tq<6J>2UZ<Mi1^gwZ#i#Xz
z7h4X{T6#8IFNF&UFH{Z`zL<_z4ujw6PJb>AmUWmHZw`%4&LHuTAnu)3l>{0hYocUb
zCOJBB6(!`7+$=T<dv0v>iP~9DxS|-dKU{JRk{Fw`ly7dktIH9-|4qayPX|-W1da&P
zJW_x<uDv6I!OAHbLk(M}h{+Bt^{to$;?!<wxR-R-ip@$0Ud4hcx}iTejG`NOo%5;u
zrI;Q6i1G6ZRgtZNltYd@S028$mtYH|K+tofhZ0;f-v&?ix&ei*>g2WXa|lN=L6!%8
zAsXWm1d-BZ?4m)K%2U$)H5F=3hnK@CC4EMQ#m$_LjmXijwD9X=Eg?dC#C!}qAOs~-
z#W{Z%q)ZK+Cs~*)D=pPE)`Z2MqV1U?K3|`DIFdca6W0x}5{esDc>Av(8Gr5%#JwAB
z-v2Q-+5VHc$->C-KeF`KTC%e^tw=quYFF)kW(k9G0&WVZX0S&m0|E$w@XM8Be>p`H
z@jqUr9XOBTCX=7I!4rJe(2I`g$KP{ILoTmNWv!XNRWeu4bGLMTWz=pLPZ#%J3HWVp
zdlWKL2Dq$SV_RjZ{#9)Q@I~V4yt{l{Qx<e|0puf3lLIhgPu04`tZG!xaK1d>4j`us
zc!jz>zi-zsrLoqD08F}?03_-TnSD7e_Zr?dNnob6YdtOe5nshI4;^3cGFL#G**7(f
zx0}smC(H56^~?6_`DF%quUxKNq-gWXKt`P)sv<BHw)>eh-mD(tbN)~D*SFYuNKsy!
zIfKl>k8iZ~Y0#h7<#jQ1xe39BinO1g`-4$yo~~E-E{<*P?e<p=RC{7scX{_juk&m>
zX70>f%2hu58rcI8&M}!c!Xg*<cJ6w(E}Kjy!mQXn{Ld`$Xhs0dOBIu9k+t?2P90G}
zew9RF)2=C>gz_^T^L%!cSF&n;`+EapNaF*U&j;Jz4^7giRO?Sq4%zEsX+71EF2|*n
zq3cs4(A%H;^Ow-o-U`<5MgCugl~IFbA@fY!2+8metBrYS>u}-IWE}+fq*W%WfJnp%
zzZLuizj@Vne-~WIBtLoTvY)wAnUH72VRjLt`2m(=68>nw2%?%d&ZCgV?S{?yhUBqf
zVHsT1M(O;7!+sqcJJH;QxBlFhP)T_3=I!{5BP>axSm2MX(rR_5Q_@D}S2ishjsxs?
zbebFm4!+1;Zq>g74`{Vs4-XYCc`E=6q))hplG7s=c7_3yq@b@)FXmVJoRtRCL>Xrm
zSp-au3ZiM0W{D=BQl)u{%tBHg%}#QdZ}f<*1SA#^vk<^l8{3{K|4_O^^*kJAMuyUT
zBeka&-s{7<f}O6qt5Yq8w#YUJAszQpbf&e;U+q`j7BNV!glT#SyIJuG&0$;U14OSf
zUAot@E#-0Qt-#x3rIT0sR4?PE2+bzA!gcqp|G`LToNwK%xG%$aIfz9Z-YdYoM)oRE
zb<>Qj3A)z{qm;$dowy+bYckPWb1sBpD;V`8aVGi~IT()Rbw&)D1)l29G}=NMozr4t
zO~sf>=@h(1O)X~#AbmtHl{)BYGo75|8+4as+NBLT9f20iTBQQbTJNZ1gBr|kG%26j
zeECQHDlORb4=ILWq}mLDdNc-+(@4|>y3&w^s^@uJS3Al(c_k*ud1jSC+PSW{P^7N&
zs>E>`ZSa7N{Q_=;9)MffkP0sn9oQksr6Jmk)r&d1i#2_Q?;y6s)kwxX1G4WxuunbF
zbtSd9%lYR$Xn)OK;oELsAzsgnl{<94O|$nT!BF@;LgN-R*^FQ(PRDGzD)B4OQ;-?y
zaAw;K_5(j!)wT%(mRP=8u<&!WwBfA(v=X<hf%(BPw4dVkJkJOX+PVq(I6Wa5B>F-s
zHTBEg(*)^I@j(&p*a^eB72@pxk;i7fgKHJr<7Y5AZ_NuYxlm1c!ZM9M$JzR^!t|I|
zR4k$)&wVSp@{8V^^)~S|MH|0kcX=*z9y&}rZPks)6P=1UiSo$qMvH?Jacdww@jfSO
zs>t&hnYAI$rl#`G={rrVnEMjLpPXDup;y%4j_WF9`LXO$2FV*Py0rem#VtqK=wN+I
z3&tsjwQyx*2y{e@CrnL8d&0#TUW+q-X5Z8<?G~(nOGR?jQG`G%J8?f6ha5Rg_x<X0
zS-%42Ds^pv&|prT7_T3N6X|;D@NLe&L71t?=?~TMF-#j47G<4x$jk1c2QX!hWR0vV
z;!pRSf$Y!*sQF;+=E<mUhH#c23;p1$vGcIv$wgS|Wfr<eAK8LR&Y^gGED8IK_~4Yj
zqc&8}6-t={InAd?1;WAS`Tb90AWXW>T33Q#?Lzz<WRRVV;6GBo!Ra%05Nc#b3XcJo
zWziB$*=sHBSM%M7Izfs$u-Ec%+<(a+@6kV7_PIU*Xoi(UN!$YLaLVElzidlHYYVta
zcr@tX!vpTR>2CQ|8rgJU`^tC%GwUEtL??sNevkD)3t}+rQL0h;UL&fIuo*Xr*L!G8
zaMmH^!+%A+ykb(no<vO0PUVwD5Bx1)0kfZRc9#`A@JBe^Ei+~%>tfWfXS^8BvQ(=O
z^y#88+T^?A@lH;s%PRfaZfG5PKtvU1>K8Or><g5}b3fX`Z1b{Gl_VXWg#Qo+hsJ2U
z@vfu9C$N7)V+<+Z?`QgbqC+4G`Rg9g0~pUBg0MeJ!7DVu6kaV|6{bDY-N3^s@#k*}
zfzg7=uM`U5j1dMD%WEk2ZL-51mrFeqG@+67nG{kGZ^rD$wL{xDMkwfbgX;C`?M%i7
zp1kVIAS<c-lX)r9#=hCE{6GAJs<cg*CV;}O8ve~w-T+w4tKqjR@0C%=gI#tu>OC@d
znd|zu#4Pw_FeDF!gjPk6lgT(<rT5CRAcg;?+e5>iaooz4*F30$G{sZr=eqgzNzS}u
zqxk1sjpsr!oEa9LyZbU?iyWo-u+qehA;Z!vdQ4n&zU&PsP}=t2B~N(E1~=Zgv^{`j
zO39RFi1@!YyA1D1k&&+g`Bbbt(?_;UEJaP#U6`@Q9;v2qVA5}MH&CS*c@U*)reF!0
zL9x*D39=G*6l&`<z^RKljMH*5qiu6aMPcWG#CuX2-zXk&vL($M7Mt|(QVNPw!$&j>
zWkYp)gLvR^h1E2lRiRL+x~|JnHK%)%ju<&RBO|z`)6ZZzP7CpZ_tS!`Vx@VjCx?w<
zmmONIA`To~7neOvg-ji>W1e(?#(>d*4cWBfDj~nF`&CR!qnjXjxI5+){w?tu#l?aF
zPrDPw`<E9+dDX`LYMlx0`V{*!ab93F7o>fHxgxq>ZCCpLF!qjJngH9fZrSQmmu;)d
zwr$(C*=5^y)myf0+qP|;-gn#&XN|KztpAWBXUxoqCpZqVyeC;2-&SJ?)9V;}HltL+
zW-=Yda4O66C{u{D`V_3V;2hx#SB6p3&9aklH;y)rEdWA5YuDpIFJNV-54Gy{W`U>I
zl&~j&)UZsxG)Y;;+}tVfo$pnJ8#uk5vD+m9i4wQo%%h&R#X+OG;5KwPg9s<iL8NTi
zp?${e0(otSDXoP<>T{Kms$ei%0r?J!8ElYg`PAyh<C3jpgGPNND^3UlwW`sQ9gX1S
zNh%ut6AQF;!ftggSU}We@`AoII=H?U3{eFQVbCW)6R1&;7IGSwl4bm=6~9IWq#R;}
z!_k1`N+yFE*73Kf;daDB#mAUPX|buUWlV;ycMB1*dybg;#6#O=By)_TU02uOR3Fbj
z=@i!CR+}p^ybAw9tv76Y1FAPn_Nbo`oGWAmlP}uoJG>rKDl3^3L|8)XBBg3=m+b?i
zWFh6k{L-%EmDLxEFej{ejfW&kRueU7w0SFym$&6*w8R4F(YsUVu7(nTHrf1(+(}9z
z`y{5>*!odlNezlfchsiy8#4&JQLjZ-pUd1_U1DtL4art%I{O$&_xiDc&UMh=>AJgb
zP9t-DK7ws9#GK|}@ue@mFetL`=(srmuCh5G>cz9Df(@<~(df{-LP53e+Tdqp%fc&_
zqDI<>%T(IT`>AA7(>P#(`b)zL&ub_6_XR$P0&P%OiCQb&WOj|oReFTl6ik_l-}e2$
zYI;5z<uWYnOJ#lC9%uG;^idNE;bZkub^{Z42vvbfq2tpfUn-%qQQH*&YAz<5lWDyF
z%fwr*m}A_Z;3ns&iC|bx`8W9NudeU$3qIF<2l=L}*m8f6$ydV}m+WoyKgg4RkY9&H
z*)xFSWB*A3FW#IH-9c||yK!iBsm<3sJ&0um@B>HGLi=m`N1*TMagl^;3O5z33S))5
zp839pppGh7Ukd-rzT%GGe7L3|K_PY~9;C($-XN~;{r<#k%HL$dU0C&2m}_jFTW{4r
z3!QtfrRxXDFL0~BiWxhntTq#nx7l4+?vk7D`*VuOL!(UGD*@g+?+!|l1QRQz?Jmw9
zP0W91Gq{|s?6>P}ybO$@3vaqc>JX*e9yYR-#<c@j*7{GoFOT47Pu|*imiKvp`ae5+
zICozPc~KcYkvA?P!NX*t4=*-*uv`{iA<)gm;t!ReT<{W8s-`F}uDcSN+(YF;??Dd6
zl7C)AYMAuHxV;-L+<qV`Dqjcw-$jDszslq?F*C6I-w!ZNno_X`tZ@GpiC0A7rZP69
z$$WmTycXJH)kk?b*XKo{mmhpd9twr}tZ*~ax=e}vQv=1rk=UZtAM`fBs~jD|?N58>
zXXK9W$V$uB2mQ>%Oi#K<H4#97Zl)$ONf5h1d!G~~<zz!|#ifb<HPB`0&P7YDiRbI<
z6H?a2yFxR#31Vd`F-lkMErGn(>f1VB`tn&>lcMrMxRpmI3FPx|7aFIVI*+<`uD~K+
zFZU)4M3X(XVE2C4SmSf3i$}pDpC1v0^xAsmlc;WSc?%mFbKk48qPmFreYyHXfn93P
zOk3)M$*cI+cs{bpwt}6F%>jO@4%gmZ(IvtrgTkH;d$t?-+kwQYd~urztU}xkm(=3L
zu6n_%SLgQQVT9;@jl&c>arXdqG*Gh5fX2Mv=FVv;?5h=K=TY&2VeL{lwoOVbP0XoX
z0ga2`lq$^8cD@Pk3}E0Yv7`av^x2DN%7#uO9N;R<yP#pni73v?nuYA)S%19(IC8!x
zPu_2YV(J{YX%C;fAxaulYlPyy!F=|&A6J8#qaOl0FdiaHH$YyMCs*m{ig$?>RiLd}
zu&Y1Ce%X90$9Qm#U%0b4X)?#nu+YR1EAp}^`E+TH6%2^xaZ}xfwfW+rY0Wf8-E+BH
zo!+6YsIfskYm13MKWnQ2bz3upmGCkM!PhqXqP&{T4^3<}{(L(XhrVC%Vj4K6u#pOq
z1>gdEb-}nH3ezEj<~7d_=|S~V<pJS<$J&brsB!W_<M=8s#Z_60@sp_#+qGn}3POw#
z-&lKeqAcut+Bvtjn+PyM4vxt#=jX4vM#}GZHmS*?>?fOJdjgrSaxz|LkX0a!<ilK1
z;pA67$?@jW*cw<P5KLmQhQywoOoK%kSr@HaMsW`}V(|5mwqY3rzLO{#yA@H`^`OPk
z?Pm8oBKL2>Se#XtY;2`*#R+>r?R9w;%gmGL$qLquHm1C09;4DOy2q>7l(bLgZ9bPP
z&|Vd<N>*byi1c8mYv3K!;8M4Xqs6tgzY1XJU;<`7Slp&6Xxy$iv<QF4(kB6ruc18e
z45W<*mNXLt-46GRpl3nlbIb_LhKkP8z#2R+pDK0SO&>YFlK-w0Qv?*o3iCv!4R+h4
zRd}uw1hU@MDBRT~PvrK<(fR(k8Xo#d!3nyy0a>o*jW>oPA))sY6hGd7UEH^Ob2R)Z
zmWa=8;<IpfJM!woXOqg8xBY9sKZ}KC!!LH>J7$)f^nhH093o76Vz>Eok0z_NweH@J
z@l*da53rn&zk>Cv({U9rDwMmvVic0os@f`~GAg7IbG&rp$TNkTWAqq0803T6S2()7
z@bNKfjqg6k#?sS&WnF{aAETD=np-*3HCGqCd2T-#!;hmDXTj&XcIkY^<TyMJPW2^&
zBI<8_wHV<*7|(M!Xvgn!l)8g5rR*$2usl%jXIe@;(5mspBf^ntVV-Pp=25zjB{*}q
zg*>z$_Z7YM^T-+t0zGujXy%??E6Tik^L^JLdmF~pYb3je)vK)cCLT%lw&1IG;QW$i
z85Z`7@;d`VqlT-+!D^=hH^P2qHEnJ5{#0qZR@GPIzJ(uxa*4g~aZ1N<C&o$eko}y=
z(qsEFsJ3+_Fe5j^yeY{(+CT$vC=f0u%N15PJ2nq#tmjnVWcRPZfd3^RSR}c~ZD_wP
zc}OBfQ+<?f5tpzwM&#NWj~<XClF_PDH2)Lcjj#xCF6HqmBAq|aCubr>aCc=S^A+tw
zgGiC9Wn?}MT7ZKIl5(eM@#(1W=J$zhkip6SXn(*nHAfl>Q7%x&28wnlqqkiIgS=<F
zdn7i}mFsv)%W)an_t~FMzDhSjCRNt*)0I(hsIH)*)G#xJOw|u|^Bt{c7c1U}s=eJ-
zoAm^CEw@CgtWm@}7~K736Pm7~LCep^ciBJN`OL;_NL=&)>7l{pm6J1!Dk3zFpjg+i
zM6Dzbvk5fUt1XG4`yq_FsodLZH$}N8utT}d4esPKsGy*5vHlr*>eJl-b^eBehq<Lk
zOPPnQEM?^lNFPqCKTO_VI@i{GV5Sr@9+b5Ivypc(`3*4-S;eX@N~QZw5l|-1#8?Y(
zK)~_%fCTyF8TK3KIgfymj|a#=L+2Xolu(d45&)EYp{lIlVcDxf%{CSrRf?zbzWDM<
zrobD`8O1#8RKt>kS#^vImt!$xx%uXJ&~=+oY4$#TX=5duE2aJ|GaHshh?(tYg46I^
zSyH;+AvzGhl$O>!QKWcE!@L&ns7v7$)>?(U{Njlfl!2L{5I8hCLJ>7Sl<d=yg8ZdZ
z*)SNNvf$FU((w8lFP{xj9z!>7X9SA}deky=sN7>`C^$$~Yj;nHd0SKrS1sj;Z5y&}
z2QMzoB(s_)&!~9frXBQcYnP1k??>;QDfE{3rl{8D`m*ZgqJe<<@-tt6ig>WgK!w<v
z5@!~{SbtzUq(FW{aa^_mU2uOZTrMydU?LzSJThgUN+mx57vg+UQT`BDPxOZy_4h)h
z$z650j)ui*!~ARk`b2)>wV|dj6R+7fh^RVS%F2lMmY$Ob-!=bt6)h|m8a)D$4}?&a
zi$F01T<qYhBH8N5t5Y%Rl?qit_Kp4v^U*NAf;)RtW^WTb(O=V|FoF~}8uKwwKcVsN
z`ez}LRSv?ISq(36?)sv6z6vPU<MO0khNQL^issBW*`e(!S#Bidij6mot8-rZR9WKl
z@)$Wj`9DzocXUJ?#36=F8H9u@2_xTMeISLrRToW(sZP5scw<DJ+kDlI{>_@<D(^2~
z(cNgQ^KFWqc)19D+%gSV{Wu*;3TE<mvDfODhe_iNG07<N6^PD&>1SY=T!wY%m5ig0
z@BR)>gS6oyPlcZLdHgHgr1|Mux~D~Cv<xie<DlJ_c@a%|=LAyN5&FpvW?N6h7DZM{
z*}+_GiC5<j`xDWRbj7`AOu->BGK8XnQfFQP5V)8$`5yx4!0Dm2E->Ql)M_)ZtvEgW
zRQR}(SjVB@tI%Z87%Y6uzg{t(cud=#WEj0C)ukft^Xqrp^F=7>J3XI|e5ekw#{Y|o
z`maJ~jLgjcVUU^9kc!1-`yUlGiC;^kun5cWET0EGs}<3O#^bzvk>xo0{UaoyFyCqH
z_7%n^K1^*z5kd5JM~KJ=!EF9+76SCBhe*G3w(;Au`|D<BCpT0scR;^Uk~4kpjUA(K
zw#{Hfi4J}ywC6=L^sx~Xaa3q_eLhIR3Zuz2WSDq{=j-8<oN)`Y5@$JCwxp|=jp+b|
ze!PJzLpR|go^_sb4k<=6^LIWQy&M-L-Gh-uy>P>ow#Kwo8n1hS@GsPRP4sLLaH;)e
zHew|+UO#R`XI<ydGa5fn=Fg{M=C|i7ka2t=<<qZPDcLt92xrl`6i{~)Bdl%R(1Y8j
zgzU<<B>09{>FzX-iwsr@6ob{^BIjBW6L-KlV__MXs6s3~;=NN|TOF2w^g|=_N0Ub&
zdSRX0tI*NHHo9%+Fdp^Ed-L?V=#9)?UU0L0C4^Ns0IfCwKw<m*1i(V3K$ORgRqt@W
z2fCo8Z(02a5SuoT{zVPSKQVA{xf(;mzu&gvWS;b5Z$AB_na}2TFrMk8kHW=#%4CvJ
za|JxTPgyqC=?AqbJ!^cR2WC60@R#UTFP2RpWYs_r5-UHb5P-OPIot}3A548<0ptq~
z@T^F0L<B>#DeLUZNQ!8QOo0t#T}LhQC@Z57m)_qaoSIW9XKI(H`0Q~iQjUm{rfC-L
zQx_O2ow23kI%2IvTc`R{tNa~K=D;^*AryZlAE+8Xfz{R6by+(r%a2CWIO*LlOkD>c
zG<t0=d(RLTsVi(iG)FsVJdFCNdVv`qDfZ8jS=Ti=ghgSK70A4Y`C9<2OD>SDw%TP5
zLw$@q(>|qPKSXNfl_mUJA`M%;LUZ4js61nG25!1PO=cL5M15t-$)6N>Y?meiU94ii
zV?XB)+nvxfl0oiNb|vLOHpqz@sfuc%38yUF{_~N%mT&O<Z*rT^K*uuqMp!YjD@&#s
zR+(eFrF={0gMpgXNo_;}JQVC$iC0c$i!Pf;a5x5zp+<>vZnGU(p&;vmEQx=dI@G_-
zB_VKHoAqR-%YK0S!B7(6FkNsyQsIbMWiP#4BzhV6KX6XEuKC3wHZZMZb0D|&Q(OC0
z&{GBVcq`s(Bdf6N<xj*Kv~$-^?WmrLdE1UJj4uJ{c9<_!`BnRS@A@rjK%5ogE-MiZ
z;c_cul5L=68f&BLn!Q?w#oFjlwJ%A(tCR(()$r|7(2Qm#QjcD}A^??0qDLs4oqU7-
zL_#;pxR)5mK^l_3ym%b~Ig$~V?Yv8ic-&ewJR^{99$%=7#CD!OgPc{};<h((6mCd(
zmQrvBOwUF-#O1EM$iw>T$2$M$iBtwYo82$XSZUC_C_$U4Xt!YqZ5ckjH`AsH3;v0W
z!>*{?I!<nNp8KN-&m_G^Ikz^Voxg@LW<G0)0cxD_`ieCyS}G0IqwEz)Ms-v9CfoE+
z!cjo>OdZK1P;Er!-xXNpu6RBX!(Si2pFDL<U4O!DgaEa}3v{#ud1UWcpg;k&0oP}H
z0a^UctDUIQtPt65*D7~QSMt+nFJj*+naXT|MEgjKBJ%cgZ;DL<_5Oh0LoU)*Dr_Y<
zb8Ne~B8`YuB&K`YE)^t9!Ig1HFdi9jos*w+YUQaRJPMc!d69VYK3U<AxEL6LhHCR`
z|6=JAe|u7r6)NvJkh`w^d<(pC%3T0bw|G=7m3W~tjYFX@nT(|{#lbjIqAhBk-hxSB
z9+KIK-&VS{hHrjTaMb=L@NgnsT!_-j;DSNr2{s$_Fxs#}Ke}1j`3BwNQXKzZ?%)3^
z@W9Bz@E_k{L;q|9#B6X~C)DTv&{8B#z#)jh3BZn-d3FK_SI_RU9Fw0vghkEkhqfJ+
z?LlV_YgFN$+K<AHuZ(E|4}8q-yL>#IpA$XZw?8)*r4hzQ3kBYs|KIKR`VgPa7m_#H
zwx{3e=s;kVbX*F2<bvVri(NgiBF1VP*93w&!tHjSX!iBY^7$T$4@bW+2Pe1Ehas}e
z1fz(sb?f~0QPu=nWiy-cD)GB&uj0?Wn_Q`1&Nq&)pJ%Lz?dmftNyIoLMcgP&K7;T?
z4`#{Nuo3To3+I3vW9-0@b1nbKr_}bSCHuoo_@F~c6|)DAu2{M~53aNaqywkc@`Uxw
z0*%R=xJSt)@Tj8sW(!e+t;M7<%mTAWEsRasHiy~GVrlR@cimLMB!dSR%!7?cI^g-t
ze;U6s6a{J9^BTe?$%t)PCsLXb0*#sTv_iiFm@Gb8dFySma_IF0<!@oyyR$#kNEAoD
zBRSGvsC!ZA8^R7SW>dT&mW-2dUFb~g1N51NCa|R{k)5`7uyK!t$KuqexWRFXYuZZF
z^?U_jZ7pM6NifT|oB#=J@qeLx9P+pZ%YsIB@nzGdU3Ss)&EO~63A%Hxv<j`06%XB9
z0B!4GGzCld6xqdu^mX(?`f27^hoTZYs?&r8Dt3`R7x@6=OnkxV8!VMnod)0}s?7QJ
z<?r@9ZqclPmN{rHRKmbbKc%q<`~9!+x~ZOu@v~apb#a_R8CLX$Betcn1M%!ku~NIg
zNL1FGu~r-z<8YWF7$#69&Lqe+VJCXqyvF>}$>BqV_1@-@@8KBRy3qoJvyM$1YD!xX
zbp`yRmcZz{f2?oT+JW85qVh2Zc!0c{J;8L_29x#acq#inA-o|GD|WLTalHQ}tsqs>
zs_;~9Qv=DSXZVX-0E73umC9_$zCunwHNC)m3IZLvN8Y>V-umI|R0X<#^lhrLBg!&#
z{24`3#vFrcIuvjs8CMBQUC((k;+nbMC|>@C7}vvlQS){&tStX@{gNVuuIG3Qd?Y5^
z=FZrzeud9B4}5>6fVO6<GL3>z-~0I8NzwKW65f&{x>i|Yd|^3NaFi6sU~81BP^~^i
zr{N}7x*|)0GnMX_s}dnQt0*lM!|#17hofJumj}?Gwv-u<5X|=b2YogBC!K3>r(OYT
z%mZ8Ml%p@j;yqg?tiNTv3|(Z$R*H45Oaa@E`>wj<n@Trb<gflW8Hjtp`hjN_OB}nR
zhw_5y26B+^{Sq&-MO}vzGrFvWE!}Qmo_7xjk97A<5Im2H@z?&mtvO0=g7`kEd-S9$
zYf*U7Ul@m@Ok;|_-&}qlX0bo2lRs<1+{nVRKU*v#wkM-|YyUuYs<7^=Q{eHJzPD*N
zdn!muLf8RHotv6E%>P_$9=@h$X}*Y;mP%7Jb|BB4z1k<MzDp+yD-~FKmG@ooB63<h
zuCihCOoYf){8khayU($$O4;D?rE#5YG&BoR!<X|8XD%D%lx5Om(BjOwnFy^IDpXi*
zq&sNxoXfOs@n&4^=Y4xrtRHu^k(Em3-hXO8Q9NGWF2XGCZ|a^BS)yQj!8xhtN_F;G
zkX$=nU7y>$nzo$Muvzmm6+!aS>27jNyJ^V9!|^_|&7BB+Er++=N8#Tyg?7j!7jFmm
zce@8;-isg~rPm~$meV4xsS~NW`N)sz^DOgcF^K}Y`!R&86nLu*XPA`AT)DAWG}791
zz@I{`Pm^$uvTc^1f_rh7Cg(DdSm5|5a-3oeK~W6Tkz9{VVW*WmTJx^KwFsvdij{i%
zFfO4xv^0wL!RG_ZoVWykeqC#{q%DK`{_ea}6>Zh(f02B^5bO@cNyLiJb-vzupk>ta
zdqdRj^56PjuJHfLW6sFV{2$zgE{%y8EjGBV7wT(7_4qP2eRqX_3R)*(4NYh8z(G}q
z<fn&%G{Q6bI_k<I(%4#0C%k|n;v{a}*V;1iRn7+Qwr4ZvXSkI9^~LAq-&g3>f>{$K
zWkHmsSG%nww9%ETxD2bUTq<9zVtYdpYoi_PLCc3LXBtLbDQ7Oiy2od6b`r!+<|FSu
z^Y<{BWyh}574(jLM1g9nVk`@hkJ86kP3ca{PL62Pm84A-7?{pt^E=qyYRNK%Hjhz9
zpIPsj0A8fy%3`F}WICCvM*Lz$4B!>|(?MJQ`&zj=QfZ7}c|NO=J>`gwg)Dk0Cnqr<
zaN#mL+t_gKJQ`^sm=LkPVuI=*A^jfmAXv<e5P><b^)z|VfK{*F`8@P8_MFT6vAw>|
zX)rrM@)3&lk}9nzittg?1$C;*J<H#Nk~h}AUH7yqyG4{R8x$jIUNtMzR2#CzLN6+m
zVDB+<*T|a?zU|t1xa}d@hRY8FUm`uUoelPIJOB=^m01#s(rV;DNgX?NHLs^gLqA8Q
zx(-5{+uVBXqFQiC&haZ&(hfkm<sRHwzST!rpk$RG8N?N<XH7RsV1G%R8JW57j2l)$
zt<VRaQETg_O6*l;U0Inq)Ne$;DFr;+C~3+(k28@Y$jS+?R9M5gcNAUCDP0zH+pQ(T
zVZ&mvUU_M;R#Cf6?YQKB>}>0(@{cBm+A|vC>9J6&Nnz(X;K+|UxB6(|^6qT;aWGME
zck;sJ`Mny*pkW{{h~0!)X%FrI%KeDdoJ+sq^5HqN2*)Y-aZT)ouj!jIdcERr{I@cH
zOCPmS-_?PvtBDQI!Tosq0%P3Hqegl+#krfACFvWdF>#Sa>i%ioX=bIe#GB$ROQ|xJ
z`I&GKR(yHM`0o17=A+ynHy{>x@y+ZF@k){R-84r;Pglx~upx=2<x^LZMHLLqG#u7z
z^CpxUxv@EY2}C{|-LcoCR0^0j^jj*rz>#y0BVz*RJ0Ws82;l*00(6=U!CXoEM)6cq
z_87NM-u2duS2Pc{?2w@uMi5eY$t(n|^W;jt6bQ~4^B$`i^>Ykr=~dPy9EAj_tqmT8
zS<3y#{KZKj3t?m!G|&8O>a~QC8|xqf-2*=1;~0H7&M8rHqj_-2oH6U&4_xi{K1v--
zRqUCCSvZGR6wUeYD0icM1_<t&Cp`nJR+<zkE11{z?in_ZxBfa-%#u{a5V=;8Zio+M
zL$gAJuQ@#`L0ao8MnLpjQ-IFmG{hJTmpN_4y!QTT`r8%FA%ft$UJ#$D0?3#axSt6F
zNd}_-Pf#s5FAVt=^{OCfupj;~;J1I4UB(kJ!*QHQU@oaI&T^N=8sxW{`yvdn=1?G9
zEO^g8udV{38GbLtf)ce>X*w(@6(vShuz*@@Ox2~Vz(97#W<I>=_Es^%?fl8q-}x-p
zC1+gQ3KjhxcxGs7Z$K1{d|hCwtz?=FfO#Y)?f?uzs8nW*#RpjbVv5M$iTbHBf4-Ql
z{X%Ze9FvAtzaAG4Dg|Ojbf8LvNw4vOn6RmH+-9LSzplnkpY@N1LCnMhH)?2=nXcSs
z*2faNHd8}m$J(7GVhBk}ZT*IT2-2#-^PSt4xrrp)0BiOdT}!jV6e^9qu1>k4f4H?t
zp6h4Ha@@U=&PbXdbvf9o7ec=y`016T8?<+TdrsTuxlK=niHhaQMbA7ZdqCzV)F7lm
z(|YJ@f&EB4NRaOpxrdNG#QQAD-#*R4_i$vWV4K1hjHie$x)dN_#GFjbgM60QVj3kl
z%QE&?CUnSh6)PCdVe^WaCjA7laU&^j5739cwenOl5(cLy7feqgGJRY#gd&}B)lm-D
zane~EeZ^6*XZCweW@Y)aGaD6o6tfLroX9c~jOnSSRb(sp?BA@c25a&DDJrlYj!`c|
zkF&B&WKpP38H|x0P5~X%G8ZCeSk=L0)Y|HBiJ5ox^`fcMz6l)H*8bX8%q31`{TAe*
zR7pH-wncnpKG+!&E-qWZ3qn4PzmCz0I*C>)wWWi#C*JLam3TYP%xDG16rLfL04Up)
zkSJ}ZcF*N>vF<NSqmsrzj=9`-Hb^U83(?csSDrpM4MD7FWE&rS$7I7Mz&<=>bZHFO
zWv}#KlTeP47HOI_6aeS!nSDztKPMNQ)L*9-I(N1WbV7M6VVTE;)fuM)Kv1El_h>^C
zsOc!>V@GcRnkmJyi;5vIt3x#PJq`yBpk0;6mv*aVP4`^wTkg0X=7QZ)jP-d~WDk8)
z{9}v^W8?9c+R7cxtxz*J9|$lngxSEU*PS?0p<5^{PT^VK(S=RK)2y2<XX8N>w!XyE
z`_+Fqb+L%sO|C0E;?jnrN?#DBM&@R`fLko4<4bjOQ(m@6Pt~t5)LoMuF_|l!<1_w2
zsONv+sR_;`Cf{~@VU4_70ywY3-`*$qrg|F0|KC~5$nam;u9=wG{=;@XrTIVm67oOW
z^*yAplO9k$0)#cF(?hH6Fiw$TIsJjqi;1rv5eA&CVFk&`DxPyC31gcucegsm;<JlV
z=3hTcSgh}ft1GwHXXeiC%kH1scAuZbjU-eFvZgLwHXD&JTQ2=Xsf~-HmcpcOlHy4E
zAJ4Cm=YxyvKC+0s0hZO*)G`NT=tK(2tG6S4xaKmpPvhOhZo!U_7v@K)M~;^+eR?eH
zaqd{Ce$C#F#CULt84E^)?ox2sw=X$^G?K7g5P&?=UqaCZdu2MmWs}|3cC_J4&RQsM
zaf!4d0Se+MrlWkGcn0>$Ihr_*g-<BFns9=3ae4?vJ$Eoc+iGq|+pv{Y#1r?q{KsC7
zz^Y0x-45IRbW+MpRaT}6hhtr<R^<pmPqn4x8yf^~w(bSui<bUrj(kBtqPk4PX^Y1~
z=oCIUw4g{Yhh)AxthL6ApzxF<p}+yLqafc(H1!vfSLs$AVNuN@*XlQ=Va6GR)f?<o
zc-O<b@0iJ-vckVE=F{Wh1hfrz((^MnvJW2<eI>$;Y>p*eFV>xSZTWJ8c78`G_JrXR
zbX!f$RQY#;maJ@<(fCCS&mr)u5vzHPgmbXJ8gy}C$>|5B&e;rSoa(g%rj__|!!Aa>
zHl19>6R(o)T0z;38u+xsPYQI7>|~DdDhq-yT;HT?Itz;aFa=pBrvAZPfxRDUGfG@)
zxI&SOnB3}4a+r$P81H@?3$jP}YWp=^&xaVXDdvhUi^ml=o6kOUUZ}WB=gi&w2k2m)
z^nu(D>orl!lOuWoe&#$fYk$b?GdxwW<R^fSv9Cp9Qc4v<f<JIM`XBx4n(hTdo4TB9
z&LM;H#g5>JL4hBGu^Nn*ZABj<4Wj^Jl|*6NunHhPK2OJm;FkY}>)mIs=%efy&<W1`
zTs~A&{GbidO`vG0UkIjAHNi;>6oLnss-prN+6xRCLvq-EU0$~n1lxRf(F7ofBuKQw
zhQ}pG)8-+>@W>v}Em6v~<0dWjQzDv688nucC<mh2dB!C|7NW--3OGrL9IqR4dllhb
z2gJF!HV8{|(0hx$kT=u8P(LBLG0Qy!9&^ejF2wlv1v`M}FD?Bpfka?Ck_ZSiQ|8GH
z>O6V?pdKnwH49HVf3y`O?>K?cu`*4~Wqmobawu}bF*0LkgsYlQ?s*D<<~oiZM;v(B
zNrMT+6rMEO83*OB>Q8L>qnL2Fz+I=+bF86Gf9TaiDRU1J-bmRD)U&oNooCv4=3uWW
zw#dv>mkm+NW_)lg^J+tGw!i+u=lJ*(!s8_iv-X^BW;FOU#`$>x_x)t~aWWG*Y^RrV
z`sM=4b$1E|_-id~vs`{j^M@om?!nJ%r+R~ahDK*WgOa5g`+URat6ADnYPxtYj9AHi
zn&q7ZtKaB_Jd&f4M(xGB8%wRFMdIB_(_lQN{Db|*DdtC2C|GJ8fJnK@2AFI5#kT|H
zsKJi#19e#`{-9CY$kq$&MO^fAIhd@4G}HBzySv<=dh3GnEBq;!ENDfrz3~e{Ln3fN
z#8T#G+ZS9(3+Fo#s*k^C_b<z3anM0l>O*yEP{LTsrAtif7whkyLcp(em%gPqt3w(D
zM10bg$*sLC{39E;L29q{1i}UeQuNW~O2Cw1yOq-vH--);_wYg%Y!qMKDN-lGP#M27
zSDt#tvphfuC2oSb4Fph1NKJ3XW^{UJAr3bQwb%wcHjGsf*;0~roxa%EtuDqvbDp*U
z8U+@DNKk>p-^xDso2(W-RwD`?v{FXG`w2rDlRBv@D@DQA?jaoWj(K+jV6g^KJnhX3
zq!2ZXY440TWOn12P{r&xEMJ0+sPE3%gGdaLeDK*c1F~6e-DRuc!aFVxN0-Osc9kxy
z+BmNVY^nOA+$f0_g1P7lA;2Ha=Xe8BMk;;j)ko&n14#jB09*XD>71ND2OF75`F3A<
z6#f;@kOQL1u)A;#ifRF3s*UGO6c;uC>#t4w<NJ3em!Eyo-An%6u{PQz98#l1h7N%c
zPMgUv26YMl&(`3Py`gGO9~!^S@HxW5WIt$5nE#KQbc0AP^Tpp$o<5d}Mm9b(MY|L?
zAFadR1juE1D}OAmwpNpZOyv86uK|2KIYwu%?ur(kFek1T2iprlQvx$v?x!GGRnDe`
z6S156?AnIrfai+rbeK+Ro~d$&LFX+~pGdBwtvslP6K+@cnc}@+r+uFLpCH<$CCC~5
z*^lVoXA?PXG=h-aTM5(+h~o{LxpV)Bwd|LiYzl&aXAWJNNyL#96yp_pOTy@lNNC)M
zrYZ#x8a{q#G@NWgd;qhHVMpnHMP7pyv&W=cHGhSukEtk|3RfJuHq51v6oa7qzmvA_
z3oIGk7xrZ;a45w2RNb(w+K$as^V``n*htILzfBe;R;P)!>2T}3!(2t}MwA$=D2J{0
zSc~0z3Zk_Dz3!cOaMDZ9qyQB9V%3t3Oifdh7A7dJ%6$KLVX1$e>#k({T9vg3J>w;4
z3W0&Jsd3m@AXK`RYgsx}$O<QmOvMkdSHd-drH=UyJiUFlwmg#XirQw)^mH8aCD#UA
zYjJa427fu;Q|Va(*N^$L770(EVBzI2r5dQUfxn<p;h8UjwOQ2$k|kR)lcKFKm}2hy
zqSZB2_fP3q%xiSEoSm0T*m5=0=sc55ywtuOUw)VPmnP)hXF+i1v8N?{4s?|5HpuGO
zcu_=*6Y89xQ%SNNO!>HQK8wIzW?o!YkGFWi>!>+OHEZ6Mlx&EyEy|;FT4Y<9C2yya
z_WiwyXhu}kH}wrLUgm3xWA^DPS++EV?`2CnA>XdNWH)57j=-YkiY%5gdHSArw@P{N
zr<4T13giC>nsiAbt-HX49HIL+>R4Wl{ng?3Gg@??&%a=F8`$lBinoH&6Fcl!*^Pae
zvT=KomMfh|#DcpkS2Vj`vF-YtBF*7z#&@fgImyMSb?bFtgj1Z#kZ!YEDkH;>|6?__
zp%cWuN)Yv@<#*3lEKlRXzmSDIzp=CH@Yf9T`~8fx!8!c0B7M8Na`&#Hfmx5mRntv*
z0#Dry3&=0B@aJcp7Wu?+DMxg5*FO$3SU43qVfsHP6x}_S_J!2yDFq+F{1zHawoeC5
zTs{7vY=<<$BsD>`tdDKG*DO8WFM3^M6)*pr9Q&`*9E=<s|Iy4eq$y>G^Z$Pzs*4nC
z`|tfvGlHFk54C4)*S2<skmK17eR&H@M)V4^L;UJ?J`1W|!K*@tx7J|)U9LLKu3tB|
z-%zRC>x0R|O%38iXsqF{ERXA<dwY$)`jQt%!X#Izp$~d)S()V1O<F%oak)2g<6aqW
zQGDVmk50$h`(Z5TVuMcKMb<c_9>XhluMpZy;CS&J{8Ux`#OL9rsB|-Dxc_LgLSixN
zn?GN-ANLzVHAUA+hm#&HSw;H0#)|V1UXX49>8)w40LRuW5~}c$A)eWJbf#qVW*9N$
zEV=#tO7T+6ge3RzB#P?0AcuY$76j<8y~3-(B)n_^-Du=~sUrcu;_%K&OypEqjjHt8
zYKFQou0dhlh_uucmy!g|`DVF8$N_3nY!b{-aA4Vf>X5-Buq=sD2)b|X6^wkBF_uA;
z&h`mM5tP6cV`HrY0<1QTCPq^CwN?^r(hkv*Fd<AiNf^zsXzDd57W0@%anj%W8RYhE
z8oM+!MY|Jqih3A6c&RhY$KMc$lNDRvs+0TETla3LS>8AzXKq%_DwVs&h_ZkABup?#
z5ylw&2AeEmk6ZXn<sgNm!PK(usN5n**GDF)WqO*5c0_6Xyfct`{MrnTTZR}-;36VH
zFbIEdn!(vL`WxxK9(_zWYVhvVJC6affagrIHn@G|%15W~Y1{Ff*C<mlo{mX_Ri{#f
zY=wrK-_VLKC>BJTO!SXx%ao~)+0G4d8uTHX8-K*{Imvx-W*K9Hv@R^P*|!2i&K@@N
z#^+8HU{))$dVNfaFnL_I3CkIyc%O0ZXtt=!(I%nYii%`qL58`nQx>CrLGVd<EaYX5
zi><fJ@)CqxZ@}e`ORXVh8O~Y5Ed^+l<LF^Fky&5Y*XX$PCYo8g)$qr@24xRxT!x;O
zNhn%PV|qwow=+t5XeZ;*esuh$j&ZWV)Zsm;Q)*x_hW^SYKhE5f<3U_-A_KvS%iT}~
zSGFzHx#3$ugpZVWX=VGB0gvZPJgFjZhco<fb|jfE!8y_)R@l{U)}k>0LoD?k_v_@#
zjn5!2YD^?6(|lXOjE$b9KJbV<u^@LUvJR&?Z7qgTFr3_=k=II)m{Rf(G^Gv}4}mgx
z)GS6bvsPXvVdJ!QGog)Ms|FN;_$piID*aJWAg^GaT-8M1Qdcx!57U%q#jsNK-KRV3
zl5w2Nx{^Mh3&>HBejK$nA>NQgn9G;#heVCnjXiQ|hSew!Qm+D)n>W;#Xo-+RMm>S?
zZ5c-vN285^mP^^O%C?E;mKP**q?7|DExMhT8@rXaAVfN#!I!IeO}aS4frmNwd|WHR
z>gd)YB2hdR;CsOIROe{IXL9ExAx0t0si(Z}4lF%QL0X;@Kf%KFSW$7B#8r?kKR*Fb
zi7KcExT~lcp9HzV!FJ5OVb78p{?la9t6t(81KVz(xCz9w0|U1|5V*Uj%Od;P3SvFy
z4z-0RAFP{oC|<@<3}N;7-WWK{mPd6DztBwjV1pJ<GQ1B7NlBRcTD7bcEPZ`iX1;+O
zO-sJwV0y*Mo|!KZBb0uzH}HW2WKJ%DpV@MtA(cMl>{n(6v=!IG=3-^R72nQyIlw$5
z054<$_VAupFPNrv>E$uu+@$)Zbn~ZAOFM*`hRIwK0wV=d{KETtI(@~p{+@d=iFp`q
zIY0?3t<XB8Hbf+`p1@s^9l=Ixw^a6+yBTd=-Z!=8XxI}{&JyIVL^csR+e?ev^_l96
z>VIR}3;sGT4kpmUzo6}4)goxm`n2uBF86`hgKJj)MJEMYu}BqH=)l)YoI@ypxlVpD
zj(y9K&hQ$OipT2o5Tse#N{okOmc(konWnngSlM(p$S-Gfp$zBRK0%P8c>KeHK~k6r
zRVUO32<>R&SCJbqQOiqlIw+rpg6==WJWO@Q#`rWE5D(3RDg9GBQ;5An-p>dCAOby2
zt9I(NLo)=w#_6CBb!$6mIH<Lnk*G&C>$vdP?xNJi7sGR0qnZ>147j98aH48I8lkG1
zw(K@;n#<Oh449`dq%IMDWnJ)?p@;`C?fr0WEnHUG`wH!>%Ja&e*kHmG9G=lBAFclN
zbPy+4B8`J#VjeFDWO?WeA+~HUoEI_LP1>{dR+M<U(`DhR1mD}5s!%qHp-2E<1yp!g
z40W5taq=6&J-vRPPydlvuNELpcDH>eO65+Ft$kEwXq9AZY6}nqoEDJ}JW8hDwR6z9
zcD>?q6*c8E{GBEdntOqF)w_Yw?mU~%ewa_nJS<+$A$940){TUS7N|R~9sYu&4NWIL
zPX#@XX&w8O*?;$4y<^SdP`$yeoJ0`Y^v?AZ-Z-aRcg*^$pUvj-qa~b$Z8CDLNjkSO
z)&}LN5^sg<{H?oO#uy<Wk;;&s24QYvR==jR+Cp>mgE2*AEOX2AR-6BakYFux6<Ev4
zMDc)6E2-JpEvV1Pa<#_dECs#-Z-Z9Ls>}n0zMR}g{zQ5;T|;T*cvOE7QQMi8U!#r~
zr$iol*tYAU?{%F{AG$B5#n~ZIs=`M1`2|(^at$8l@+|=zV9Xk;VEW`3Hu;vx7&Q4^
z1`%0e=bzrcg16Qw&@COth9l5|pO9EHiqP^+_rC3KBDpr7$q)Rfx%2w+K>q`bzAt9}
zzv+Shs?vp#osH@LHf1mUGi4K#BmHAo-$F{~{cC^2CnBXjY98Axz!^SB?=nX0Nd5d$
zR+xp~Vt-)Bp;&)vjm|Ht*+xa*`HK$oWAO{<hx+anjnAilC3WkAjnK%S;2WKj>MZIv
zq{ZEh8Ze{yh0WV%>Z^`7I^R|#zMq32b-MEW{<p>{s&Tz6PGh_(_CHeHfh^@g?62D`
zYVYjidjFfV*ORZBey;L_p)QXSX6{JSUT8JJoTmpKhhu;ftr@3;UEWbul=fkDH46c)
z<Cs^7Gq-s%4r5t3qp1KN9^vfDU<3!=JtQbNcz58;1vk8yF|HoO%6jQ!{Wz07tBP^$
z<-YP3uvsBH9Ow`(^3@)GTAGh$7~^-9DULV_=T_3M;hK7~+ZyJ_6|1|A(!Sjndb_kY
z8R5-v;~V0LCFqMr;rQ^w;ul$OKjay^4NpdX(tu(385`bx0APH!Tv4h%L<kI1F`1FO
zkN{NjHaxcy4NXgkl5QhED}yh+!`8U992Pln&D!!Z<`ugxk3yn>N5c#gR0D*&t}f1E
zzT++$ID3^UyCVhOsF;vgPz4LSQv9IFxN>&()kHdf{>dxZoXDsFM4kAmSKX1T{kk*4
z4E_&`FD*h<RM7}++z2LrV+7MVyWqk|5msz-zBx=k62<T}QcfvBl*M0L{97{uVDXxz
z<X8?4Q=}sgY2+=VynKPfo)A0d6dV{<@6deo?Taw~wzcivUtI0@dtp3r95H1!cLBH=
z4(mCAqtpmp*uqXY^rwccUcxO7ypvO}pIBd=>u=7z{nK_5G1SFw4>n8UPe`Vusy3a{
zV`}YZmJO7D;#?=)6#%)SD;wHbJzcGyR!?jcwl0dug_e3-53`Y>h<Q-?Up8|1{)AYG
zf)o0<o_C+XK#H{J&pkZ;{vvXSbtnRuRAO-jJ2Wsn^^Cn4Mo-Xw``Ilw2vnU1eI<jE
ze<~=JEU1EFArB-_GY;UcS1?_o=7n3zGQf09B+jR2YMTxNV5oPX&jgwnbk3cK(6Ixl
zAn$_e;-1`TsEU56Bw^C5yf@NafJVrQU(B#5El6`hpIRcie1SB%>A^8$^+{#jGOfe&
zq7+B?mwvi1-r?TB^qbfrYP%xWXaJw|XP+=bN5{APp;jE0M<TpAf*!X{;D4S`DpBn=
z@nESG{Wr;Y$ofOhQe&lwAKlZYF!Klxi88XtjafgA3*u`XWolHoXfhKz5y>npv{%`Q
z>qI#Jh-?^>%3d5}o8rA7>=D@p;(i$}+zeits0-zpO!V6LFv`1W4w%Y|okUO~nVaTL
z1*N-07o<Z_X5?y$tSn^-q<JzHGG+3nGbppwM@8x#OlVykO9PfcD#f!KO;d_gKOa4U
z<<qN)@vvwqpU>{63f5e&Wx;Xtg60T_dxymVbi;SrLPJm}gW6c-OS%pJQc#l;7^T)?
z@zU&QC}hJG2##fruD>f3=Wt75GYYSl`Bh-OV59TGHq@6p{Ge4vP2|<IYK5xKlf%m6
z!_vqX06YnRawQZaxnv%eZ7i(@MyD*vA-FD0{*}=Zx--QK5|=dnERI`}c?fRh9ety5
z(Rb~!Y9#al>{_&_MSZ=2CE(~H9Knt-aP4>6h|6gCJxn7~Jy=-je^od9QnL<6#qy$E
z@DxTzHN@6anU0UN8=1@cIU_il8=2;Y0t0AQQ*KY#R&@cvu*Y$vH2T_({2>PTk$+06
zO^58Z6q)V2dWofERb7fa1+``~{{%H%r2J_*G;BxRv%FH=P~=E-LtSUrC}VM`kGecK
z{3{eSG;67Yp>?-}yXV<>;nvnoYK@z_=GAT^=YH9@2#LpPQ*$O^o5tRdv6;0D$*GCJ
z`bCzgiNAcf>i{gkt0Qf`?QSc!1twrKrptfJP;5{b2i?+OC|(8G5???mTK!C5&#>du
zn@Lze=?l!OQ(u9Db;2@-yg6MF#gq!5dO<IF4F=|0?85;gvyZ(438eH5SURBqO3<6M
zs@Fh8VdAb1K0Ye7O$~o5FZ|FuD$NOJ{!P^Ipwu#U`N<;8z{R%((wC4s3`KTQiq{8u
zTsn5$a9oNvclg=3Fh+a701vR7k`n@JcvzrCqIt83(s%S-e;Xp;>w25yH1|F54Sybp
z)&cZf!(`m3-NOemXPW+M^;~}d|Kx1v@quV!W&3PvP8`-jHyr9Joj@*X_UUP8uD04q
z5QySZjVtQtHVD?h#5&IGmbH-*xE_dJSNxosm*T0CDHpAM!pKdj3=$%XBZYOrI@(_!
zv;J6-9^Fp%Ds^wcyV$Upc57*8yBg7Nm3Wo^U|b(V<^5hUWi@Pf`rhK3v&2Sn%5v^X
zF66q;W4Pq9DK6pS2rV1c@z|X&CP^cK|6(5zh@)ajP3Y*Dae+08YrJ5k6#Ctwv8+ko
zq`4kZ(UE>Q+<*I>K<vkc!l#?{Hap|Js%KP<1MYmD#>rw*)-&9Rg9%JzMiVP&?Q1Ns
zj;9R!`TZ8^2jmnZB>KOMWk$yT2D-q=%Jv@?g(3B+f3TW=E?>%HaDe0@pZ=?S9{jA<
z`ahHJ>V*sa6k*%rlT<{Js8KBLjc2018#gnS1PPzdzqI#EVkXUZ8zt!X#@QQ6w@>dy
z?nFm9;k@1BW9H`LNNDmfea+dM2NhWni%l;Uz5&b}X6E@}!JWtZJyUi`Y|XDtm1c;t
zEvKD5G_S9Fmak8(92|s(B^kMYeF`XsS*#SS5Y`;uO--!8y7bF|Ev)F?)$VSa$IRPR
zP1kGd_PuVG*u=UPFE0x>3pH|f0y3iBInrZsr9Wi$Yp)rlGWKL0XA59+8OB|#pIl$z
zw=7Qk<_NEr)_t~&Y03$!iIwLe$V6*g;^HivF+@d26>zxeJQa$l%!4HTwg=YHS^)?d
z>XE0Os9K>pXSJu{HELehsXQ-1lqdQenbDOdjUt)Vm<M4l{En67)0MmR)V@-Y-5c(R
z8y@8nq&qohuup`JuM71ikm>rNxTrb7&b&stV`RsHtdZhuuuudu1fajEKCCTeeDsO;
zf6Z~Yya|uhZm{gJAmSLy9@@&LMm($-KfykccSG)f$44WIeM$C<J}0uD>W!Uts<1<G
zW)Sw-jEXZSi~klRL#nqWS-^jf;&)}q)}+sfWf=$l<8l3Qo9X$FJUvK%-fYM+-H&*y
zMTvc}=pX{JJ17gQi-8J0QtC1SP8~B5e;OyjYsJe7I6nxwqs-$S$|&<CM^*~sdd4a(
zn+bkZ6I95S;LQ#f#j++E>`PDFviDZgvSMI<Yy{uySmTW7ZbbVm3{2AV|7I3(8I9ZF
znr(~vAde$JJoVQqtArMVmr?U^15cduhyQCXIVbL%>EOiD)~22c?6k}Ra{bgetDI47
zxjs_jPqy@wCIOe67Op&ea(xhL-X1SUt2q1=x8D3^kOk$p$&l*Z$-CmqvGSdvXtn3g
z+Fa0}-Mff|K~gLTI`M0#7B*_}p>-zWMje;r_X1Z1hGnt)Aq$Wrz<+?q6G2!9{)dJ-
z0C?pq#iWGa5bTsv0(thHf1)l@i*eIVJGK$|OBRrLzK~`6@0`-xBSVsU3Rd%^xp^>X
ziGDfG(oc<b5Dt=GpUZ}$?b{YXRLtZrUKh1g^jX;C&cB>BTF7K_>?f%66^U4jU|uz_
zJ>r&ji5)n{4%>jjUf=cJ(9R|=fh~|vJqWLfdW3k!B%!K|ah)o9c;%e(!*3YmLx*KF
zXFP}b{K+Zi-K=jP{bwRMdKe!~wyp;Ulm2vZYA&jtJj0K+%^Nk9(D`0@_}fH++7%S;
zJ1zJzE?&Z0JsGigMijf~+b}1AjJ0he=#UnG)h2#bKaycIK-#}vltcT{$sg3hK6PA)
zYB13<O$ZuNm1Q+USPm8-W~o<^b&|X6Gv~-W4@nb%QU(i0K2C{M`SO5FA#Wr(ogR9@
zF^cP*kfSNdCR;rvoPf)<;*2F0Jbmr4s0}{VhBS9l52U%^S47?dxcb+#VLE(kK8%)!
zm3r{?@k)g41q-Xlh}tz%94c1TpVf!Pp6dos617#(n$Sa3Jp9GA?{#=dhw9laf7tp6
zbd_@*pc4U5m<y!@8Y716Z%aURs&;T3j>LT9weDr|vRP9-y)C&PbNba#kNQ!=bvj~z
zz*<EWw`~IpNh7@*Py5L)pyHrnailn0JeuYUS>zkY#HLfFn3o2^lHytg>*<NXA#o1e
z`@B!!iO{z>Nv?<b%q(<9gdU6FnZUmlIrxgc78?~cJzmO{^lb4y5V?J*Koe2QA%3x&
z;;S`{&LrlSC-jSV3A^w|ZR{WNgEFJZF!&7JTyo**JSkKZl5B|qy|lpJvwJhPFYq@X
zg^95EzGaqiGO1R5qG0-o=4iv43XvW0hJko9_Q55SbCB{VOldW^it`m1LdqDRU&;`6
zN5UDVi|Q!=L+L~E0W*gN^~klGmNMG5urZGK;)0=Yv6yqKfPvIr)72eIj`%>gEU)^G
zA;*CeSaF2|M;-rYAr`bgz4JGkCEFLy=o?TH|0Db$r*dBaJQTg5xR)Mq-A&*Nd7dAv
zt&GT4X;)ZSg9{6f0<pvE%=YecH?-6qbdr|MZBD*H^LF5oR-zRIB{zNDEJL0c7}1-o
zXn>q-6nW5@B5zpVi>*w6l*W>27>Lm+InPe8%7<^p6CD7?a7cibuv52>DlkM};pXU~
z^^Ptv#41$A|L)IxpL(D*NQpQyTK>&ivIXz=BOh#!Qs@6R%>JuFV@8hu4F3MxG41}5
z*ZzkfgpVXOeG3i6iE0k=n6lhb07>2KWPvbN?AOEWO`lp%B88wic=6=;mJz!H7rJBm
z)?6ks&)3ABhu`M?Eh&e8_FmuSr}fuuH^mPf4NUPXd)7R)CURL<{r2tc<|y`P;eKM^
z{sFRqf-(@!(!*T?)qO8OlM+>P@Ba4jL|4)b0q-n^p!l7pI5{*sp-(=(546>XvV<C^
z*9pbz^<u9@1d|*9lA(DXUin~Ecsj5AB_VmGRTI`5eFSV>Z2}sLJ+h$vm{4Mn|EGlU
z&Bc0ezm}_3RzBN2bdE3<A=ZLK20nmuKJMD#k>%g+{uE%qvYv(@DxBYW9xzEto<9lS
z^o#J+u!mkPPz)kpMyRxF3s{}Uf?>bS_evfKtaRHFY5iTv&h1nH;|5}qg)9rh{K_LZ
z4Z68n+V_K{VFb^DwmfBTh{++|{qBy@AsE|e#l10F?*XH8kn;(hp1C3U<o6r$n82$+
z0TKzZ2UZ;l-iG{>S$F-OCQNbv;O#u&Ou|_NJvflRC_XnVf4dscE(aUuJrc``y1R54
zD%0?GtdcPjbIFJ?9AAULXA}$E>M2|`Eka+wWl5Atz~B5ZKOt%{zB_!S%@Yp7{%e%2
z(T1;N<nP@z4<l6f@!>OSdCF>?eGq+9ToU_)6ItNB<e^O?A}!`hP~-l1D9KS;??B`a
zugj;Vyaabe`7(fkFFq_AR%G>lxa*qdBu;p|9GP!YSmmCIIT2i%$Git}pJUf=5o?!r
zqP<5B`u@@MMlp8rzMe^L2S`WSr?$lcUK<13oDdP7P|B<ra+9`-mA{KvQta*k?;f~d
zjB)Rf88>@TvGe8_14vc=(b<yqE8ODK!(+l=MC}>>+tYDgKtkl5Z<y+pny&z9tzFER
zQ*2{Yak4M(mQgMAC%RFlVl42<3xXsxPQ${-@v;TW=1a#JyW%;|bDL*GBx148rjYLc
zVeB2EL<yI0%d&0Twr$(CZR3<}+f}D*+qP}n?(@2P@a|f7a3{HPk~z$X{A0)dB1KEw
z*7FW!Ts#LG1=uae`+mRrpWh0a20|3nQF65nj=49`Y@X{cO`D;_5R+_M4e{K-Fx{Fg
z2@}iGAWP3%<T&G1`-n{ly#qH_3Ed^&F1zrRQ~V4afobger031S^n8^22Osw+O)1~4
z{TlaWvC3^gTi|}#l2N~7a$X%TQ4}WKl-xnr6ML`D5GOz&We6<=awp!4z3RJB#cCHd
z(-zj#0Z(-zwz5xV0d+uvzBd0Jzs4mE-0IhqzuVp?7p#XQ@k2@Y%?}A=4i-`_i*)<=
z>*-PG=rFqQ;z|JO#8%k7N;Dh2VPX()d~R0=i~`islL^Jf4Kg|Me)1TTFSA#7y+H@T
zkMiNxx+w@;`-wKHlR8`TKsmHAiraUl)qJ9M>ZeR~!fQG7;diw5919^!*XSTBG*vJ5
z+hPo@eF}gefc$d0)KXSqW6bKh$_i_9^Ek;S<uHznU4>S-pk+9HcPW;TgZozULA7j<
zLbc>>D#LJ>s7`{~ohrOQ#3!o|*xl_fkKpLh*qC=x!K&vYd%3jG!hXV*(&}7myPeVW
zUOHym9I!hz7zvF>-#geQw^4A}sLS6cyXaIldHDAG<Qj}hvaPYjZ$m{kk0*r!lE-@4
zqU@Tb=Hp&3QG1r5<V?|c(mU$RCn5sYCW(bQPl682d6taYrr<e;ECiu!#o#WKF*hu!
z>;uZ{G*CzUdtlLnAOJ$nef%V3)VpIcO1=ja)79ou<wXnp8<OQZ9}>t`I(k|v!2K^j
zy4f^AUWpeY!31<iuI&Wi?G$B2cI1R)g!f;fx%!;a)6?PCk(%sT<0`+ul)J_!8WDn{
z5-DG5rX*4PcUv~%ON$a>S@>DWDYp0tIKfz*w@cB{W(gh#0{8E76lASnD0(ePGt)3h
z#B>^t5kevq!|xQi2Rw8Az?|8=f1>QQWK)3gvc628D>HXao8PTjD;xHOqyTg5{Qyd^
zTtwT$sl?{Lo>XTt_Nkg8dDHdqa{A1FlB&F-Z&Wl(vRG7DGH7me#;B(Lbzu4!UbEgY
zszqY_>AsC8^woE0w|_7468FL?dV}8l#g_47x;v}<sUvpp8~Z>TdO8(X^2nvtA#Q=O
zZoee=fOL1a1y^qsDf@3^H$Ic8Zyzl8qO1H%u)76Udual`5Z-^AYWPEcxS>C>n(sDV
z$wQS~9)|KkrUNcC$)ktIXCPGXO(8PPHeC)$G}zuEYpt}cUAi5(wfV3JY?@53L{^+|
ztabQlt8!N|4I7hQyII20!<*abT{6hF+v(#jqDB_dYL;!g6GNTjMrWwr425b4{UP8g
z<D&vOU4r7hlRQd*J;}?ZhbuFpy}=Qq&I5({HJNM%cBw_iieN>?oHWP=yu`GTwxmCp
z79u`8Z~QCcxJR|dET+4U?hAWry?PtD<Ti627@`^Hw{|+F1Wc)P+Gmi%+BAW2ZfmF3
zH72a`C+{PB)RW*@PqRW?Q<1mH^J@1hz+fq2bCL|Y`C1308f*1I4RpO*#Bxl{z7qz>
zbG00VtXIF`!?LSnI^Lfadxstkc>Y`2X8)i5LD^aVlibt%zst5$XdEaEE>shsm-N2&
ze2}Ro=W+bkuP`SL96oi8(Rzg<NorH)QP=yl_|1bYW0c(Q6q3zHZQ5z=`GxYwr_=NI
z=HbI7z8#}hwHNE;p(&$Sf%9abUAwC%&+m6WD^~Tl7Y~6|N5lEVLW-pN3Fmf%i@3G<
z2cw6S`<+MKeIQ;5VdhXW<!KQte7A<z0whNo=f6pX>HEb1(ny9&D|T69RTbf!t_J>^
zOr~W42B?}%Z*^bp8U|D3SFxf-&$p+wiDPY?2$nH@6@7km5x3~y_BTCzZH1}TQKL)O
z{D$O{sr$T9eq}9quw>zJ+;#DfaX9w_>xMy5C}>HDP*$S|Fw2I@-TLjC*lMSmS-*sf
z>gfD*Ns@`2nT0|FyKI@g^Wq*X5>@AuhY2dyS@IAzN?_Yboets(B2EV+PR{O}T&vkq
zyQ@fbEl%9^jJr7*gJp(fW26JoCk%N1ZYQ(x%O;X@08_)GjA36WIR5j&<q@gv!X8a%
z(avQk8no-Xg)L)Xn$Z&Gh?{s|18?HjhYtI*>aNIKP0oj}Z>O$voDwdyG!Xa=ugizb
zWobEW4g+Am;SBb4N-ihE3)>#u{$1_<>e!zjj)6{17%BmKa1ZuMC<VqpcQIF<6G#i$
zbMg&@-@zpHD92HI#Qs6%S=y?R$$An1DPQG6Q|AysX7BP1u)M`iV76L$7{-<&#un0l
zcvRzjsgCiqNg+*I6@{OVxp!FR%0g2V>pkjYPP#O?s*NCqS<5_AgokW>MPBEco3-R0
zM4}PU8|SUBxaamVr#6lL)ONI?9a90~nv=okRpl2Bem-&!4RE5?L1IF2f(u3BMNw}_
zWLbWx%!O>|>t*U~_2aWNvc%)SZQ)R#3-Gf6sEM17(EeF2nB~KzshOxwFkBmdpnyfs
z#z*FYB-1#ytuhSQP#$$#S{st1LF@?D83~5iSzujl&Nq%VZ&5l(C-yZXmXMQY^B|Ej
ze!#6UPe<Zy2z`@miyXt#P4HOu(@G?II2F}>$a$8@+$K3;L#?Za&ELwX&)1j2)b8Lo
z`O7)`=aySAx;(<NfN9<~BZcxLPm3$~Rqc!j52NwZPeMXYNDppk(1}Cq+*vqUD9(D_
zbY+x~evf=^{R}P!0vnBJ{IDG<_HOC55tj6nsAFDjoq5*~X4Y{Htyg3yR||21ITye6
zDMy-Vg0AQ_oCv&N#8~=12fyEUqU^;W`F;53#~@Ga%{aKDcio)oyrP%w1Jx_TUt*U&
zBfFqY)HJ9Uc)0yker>`;QAC_S>+W;|XE`#K4|lGNeNsP<jQt-wV0_d{O7+Aix=|3h
zLwgo26^nq#XzA(auSqv~>aDVBTdNj~4CP_t{@(rc%5Zs$R@fk7tQT<}BJ0X<t$!lA
zzm;lgVLC<vV}kCzw41(Z`Mn}BAOL=-RII1PP^<1?uh6Cb<XjYgv7~twnHQg*`eHd!
zo|ri2YhoV8tqfcR3W`^|@MrbF^^C9KZGT3Gr?`;Wk$PtoY3y++i95(bSD`<&vg+O4
zTwIEcHp5~nhqMzIOjzbt-zAB;tbKZ(+@yKCVDZ^Wa&=tpbpQao<$nAs%`TrjCXB78
zW-LFk7zF7%iENSWMAVM%NM`BRU28&S0<siJPdryj{@yd26!Qd4&($xvWP9p&s6jKS
zOkAwI*nw#yiI??5M_$xz`dWT?@5x!Xp4j_BCb?Hv|FY$E<lF@R&f0rN4{lRb3dsPN
zC^2mOYL4xDK;)9F3<si%Y2RKRjE5D9=HzF}q?fqu7D_%2s*|tAb*0}?80-C^#2AjW
zIbfJx*{8q0Hrmg|-NE%GIxCvlxDi!un=Ozeo`eEi-A_ydz9LHaAQC+P1j(-9`CAw8
zi^VP1FNn>(@ey15C}PoiZ0IaVldDj&(^y}#qn_&Q?Vbh~IfcoAUiw!sm_Pi(pl*V=
zEAd0d9f_V7Jgw($kU0Kw=g5QHu0yyBvK&xcR-pR&%2Z|U8@fxoFWp-$f$<iZ4#q(>
zw+l7f4M4bH1PHwzPsv?;n5_1DE-*~9^|aGdMlA4#qdh0=7}6<P5p0)7mc?adZ`Yg2
z8mZ7-2%@2Cy=R=!@G<dkn>+FfPl|sR_VNhC^*XLPXnlbuuk(?}l5ndeNz`?%hka{O
z@_u@$5nza{XrF9Sa^~J**Sj{U-?HgCfc6aV@$>pKcCk7p+#Ggp?MwgFU`OC!d3Ibi
zcH7f2Uk^41h^f|L@9ES@2NQoeGzoNaOG;aN!WoOptDT=p-D~c|MskwLUjJr3g7E7G
zeU-Nn-|qu`dz-<*e<_hn|C`c^@juf_{tw)KGzR+*Zhr#Cj18#=4B>)d!0T(RzchPO
z&|K$4pDp-2*k#9r86l$lCq&#Fk!fKPh5~zUQ*QS8KheMZjUrLMm&b?hU(e8fex07*
z=eF;U`cp;%oDgoFopd7<cYd6h)eW<go5%R{T49YVe3sV_myk}Ss70)MP#V?O8MO}m
z<TJJ8=m$|%T|bZ4wJst!vtw$U<_UnMcD)w1eDP){mC$dxkM05+Gf*iB65&*2yWt>y
zXQ!>2Y`yUWTv>{2byBAq>_E8()0MJsyjn*)>*y!Lx*_yhu0FeoHZxYvqG&}YzBSjx
zGIw;hi>Sy0XH+Z_MD}lVw?(R6I~}Xagz9$s6a6$E*~Q`cJ`<z+S#@_}o*4VWLTMw$
zDL|5FoWh5TdYX+Sp4lX2+)ZJ8cz;Pk!tG4fNhZV&&<yqaWoHMQ!lI){?g<D~xt8B7
z$d`;IA@U-d$gP7O*bdOEvq2G=$2leV|M~Nm1X&`|Fd%&O)dTs9GN5OkvYJ5BS|%AU
znl5G<!3?emj!hVtv7%A+j8mR;`e7P^ZtBj*DsWqQrR)1EO{UFhhbtL0r0!o-AlI$1
zX%s$D|6WKM)IXcOrj?c_#kBy}BULC-Pq?g5;NpsrhN)$NXSu2}HY)w41@Ap<6wUEy
zd33BhC2*k&QsILybBV$ipmte^>RW9mU!=nm0CzDO<|?%D%IAe~Q!AUbhWCL-OKO*w
zX_8RKFg<@0o@bPDIpRe}q>8E0aYL&LP!Hi<nG2^-Bv40lnOs!eWHUh((y{CmTrHf2
z2yN?jTHn6+Gzhg$4s?EXh`=8r<0lO@=Cg8wa50b8om0`@>rg=kL96AI#G4hfVmI=-
zdui+#i3hJiMD!1ql>WNRO~on#*3tGI*PWO4Rf~IJ%B4q8Bs)UYCI$jj1>k-}W<{^3
z<)}_<q1Fx{s26>3iy;_h<6u$^cz{3<Nx_woycI)i45|@!XW>nc944)V2_0QOx$;K6
z-U8M)cd*t>G`dEq(^7OiF*j}=U`3rFt~z2Ya`JPH%Wfcjv2!%mWJ0Ghwj&O*cz+vs
zy&65_ni8VimIJfquvH$uBIesUM^cN;%28G`x1pOV@nCt}aWbcN(n8v-ZZe``b$BeB
z%+)kG7HTcWeXQlOA-lj6^Lsix`(68}(YkcDlGJ+lP@qk)s`fmc@~AEF-ao0?o*Vfi
z?^G4e6GR?q{oGLL=OZx&GqLu@D<sGL8j`&kN<7fK(2h}=6QxsOr<H(R-!q9qn!?=T
zgfea2p!|g}rhUH1(<2_Pl$h};W%Yb&`c#y7>oQx8#LS`8UKUw&lAFDc-x=<@Cj95y
z$I-;7LwN%)${dY_tLChKGYbv#^~$Q5`#H88<I|O$Tr*@@srJSzcAJ)hF|dS?q{`+l
z;8i0orj2dUV=th1(QbD_W}y!dj{$tIx#7+)KE$z6ew!c8IUzc+>h?j9EVLVKw#C!E
zwxD11#V>P~0~yt#6?5)xSsQbS!<qW=7S@(cRUmxRVosb3SUX-7FBFM=+8t@c6ZO#c
zGAB-8$n`7xoru-N3ItxkoAEXk{yhS$KhW=-x5%Z#_GD4W5)avbU06ZNJ<4n(L=Upg
zQu*V!Q*>v^6LsS?s;jGPr=j-w`gzC@h53%x$*nSiiqPNd2eYT73?UhN*2jGYcxz9Q
zonWW4`uVCz%YMupv?=wE-KxEKVp4w{j?o(-D$a_=8WmPKtT;5lIjbWaYAAl%R}ezt
zi#dh6$mCL4=`Cf%B3yAT`6JUn$1V<V>Yzh89v&4A`YQ*FAm}RhG2i<Zn?4ibg-L7M
z{5QslBVIkSA-Zra%~Rc|&P|9+u4w8X`YSC76}FCUEPYcT7~!%a{~*num&uuf)?GNB
zcUMU$Aq}|z#iczgkI2$BeeaaRhwDivT|ZtYCvVh(loHp`SvdaQYtmV^q1D`u;!IEW
zePg=xR(tTf0FE!^wrn*wcz9Ol*|5RTH^GcLTc+`vF(n0Bw)kT3TQ|fW70yY6#48i(
zyaMC`iNS*y=+8N!!dq)Tx=lxIh*^V~E_ok4KIjx!xMz54yg{{}e{T`a0h8W2>RdE9
zHLI(7_p5!Ud$jF2tn*-5C<9)>-x=68O31ydTpOiE>FArGY}=8vRrh5iy3bQ5Es0IG
z7PFY;$>8EQRDea6Cnzfeo~RD!W*v&3@Ln%0`tVIl!eO)@2u*sjgltxRaut1xyUVDJ
zl0rfF-8PIC)Ql$VEvg_lwb6fHeQ;-a&XJ?4P#KcLEHa4yJ2QzQ3}wv%n^OR%?p>>3
zeSXPeL*5U=Vd_gS(sfBnIjg^+)5~L*BjxqUVd=xXuxi^>_^HfvR%`QdImfazeT3uD
z*~MT(Ob#-S>;@dJK@<>*IMm?;EwX;@IzXl$s+<t_=!&(E;~p8C=Io14!XcG-e$2oT
z0Z2m%f{Eg2Z=lSwESb{;WZS|F6FKZX5g_Vr0kX;@qStLk`T>M`pZg~D1x|rW*MC|E
z_TWY#p`4ekSX@7onwC&;Bh{=<#`q|3ucObR=2WRJ|AH6|q5^5YYMJ_~$EuGlf>bR(
zECZ@4gFZ9m#CzTgXodLOEtP@|W390H6|Zum<B?ECo!^(<mli4e-VJPly^{TU@AAvs
zNHe8%RYmZ^&eQMC86nP;-gnPyB=USuClCP{KAbXr3xl+I#~THG8;9@#h$ik2+4v0{
zwlB+$e_x!Ti7qo7Xi^r3A(`^6xjW6YW4uU(;v<Rz_0RU=!cBPBow4^DS1pKoMkCZb
z^_yKiek4znGg)K|S7DY?%iGMt2~#1a#<6_$GrX4F%NV$re}Ga~4jO(a;Z(+Tcv<WJ
z0dMOh8}Z-Tm;VU{XJY<O7`$6+GS;{qcKh`IUxc5#BNAW|a7$XE8!ObMn<Z;J+c|nA
zj!YKOy-b}{4a(m%)mDe+i-nUM-;A5K>G)#S4t~(LukB5<?@eB{cfa-bT>trE@BP=Y
z%$Rw%+m2A2e!C5j<+Y|=_V!rfMz6q4Tn^kyT0d%Su=>XCXWN{EuRe}z^~s}O1j=7R
zi|aPGq&@cP|LCE`IL(`+$hAm_O!im1L~DIAF_`3rr#<JAJp__x7Q??WK1CFR>|_(B
zv=|}c=8t36Tw_nfMWy(CO{eD0D^goUHWug+PX3^UTr;~&3S76&EwANwP3nrd>ry7B
z;9Bh+Sl@RGO4AN$(p&{O$zi<5keUK-GBk<sze<v|cTo<&kNf=1`T1x_p_@6>x4*Y%
z*yQ)qWcm5Jj`+7IP^<&7InIq5Ij*DGJ=Q6xGBWt`XxnMq%h%{6+}oh|Rk2-`n%BjA
zU}e5m-Zym8z4?CBPpCD;sKxV!t5t3qhGy4X5jS^qaN=TRE2lq=#do9WqE!Z54FGF8
z?s0J0S$d~6e1Ojsa*P{!Tg-8-g|ezEIsP2mgDf7RLRsY%%1;kEUVnw$icaFI$*&7h
z;gfx8I*|e5i{{18mO?ai-J1n$YP2E8Sbnf~{kpKH3Uo&MyZ)m&=Q}&6NS$`*CM9`%
zq|tH~5jg)gG<7Ppj|m90yS}4tq}IgU!ye9n1B2psXJoBSls)nYnkOP)5`v%-{!_!w
zwaI<3j7W;5E9x6M*6ndlR??er=SqENu!VHYXtXhE_Gu&-w}*{3r56ZhDQL&pV1RAm
zqO|c=3RDwa*h!~C!4R8)|Gts!xVaIim&Wz!R-)BL+==!OIiU2yy^h?uK5uI;?-Q9s
zigqzTzd=*Kw>XL@jI^2T31mYGG|LUATAsAGfWg0er%KKx=r)1gloPG$XAfn4D<gQD
zM7c3h4*RjQlPL)RwxzL(404-ZOjCw};Y964WqSrV&GoV%Xh0j~M#y`|eeq}4cBI1j
z2;qFgYGuUUWW)@%N$4A<D2Gxw2~%fhy#V7f5LY2b%!T$cz%DF)1~Pq?x=ryMs1ay^
zrf!!FZY_c3S>!K;u|QGEUvmu*p%VqMbVI;MtH>#0B+R*qSFXzf$~x@JF9alBLMs5l
zF?}o;FoVBIiNdcPV^rFq!pFe8L}Ie+f@^~!<RX>v2%p1BKg$R|{nJbq0sY5tY?C>b
zJUmP>zC|Lj3S5uW1)yzdp0?c+7luc(hE<LNBmfxM;M*pNLu`0&JM%w`NEKgcYlV^;
zZFa={6P;~lLP~txl9SaD9-e;%VNOui)2if((et|(T0+{O+`%XzUHCYKbdFpq0Y<SB
zA~|HUDvmW+Sp~Vn-t0!$$m#APp)GaBq8T>+0xPcHb;bBoFdx!%m_!Q+JKz;1j1`4_
z?>ERZ$5u8S5Fg7pv#J|5ZAVU#-989g5l-0dSyuN|56KdzM1_<^vh5DBRi)b;YOzV}
z##)!IE3p*G2v1pO8JqW(f-{)2nE}v=9j5#ll8a#}M{ECsmMyyof^~BxzaXHZUnd8t
za?EA!0k2LXt7hV*Rc~=N)k*`~D8<(e9*GMB;6}lfXGAL|<W-B*RHMd)uTMsWKc%8t
zl<R;<i4Ae6wzIanqli))OO<B*i6(k2TLj-7a|*=xWcL}ldNiI7DD}gqjMKS1`)`Zh
z*48mhVjOGE($u$jWvn^N%39{%iX(h6m-H^koaB*7vm)AwN_CcO82BdqJmLTnZqj_B
zV*It56@s&U3$keW>-9+rdkF<H^Ik;^NxGQe%?5nDMiAb7Vfe3?0{iQQ)+m~gARqV2
zOq)U<PbGNgLHVIqg>La1S@Y#WtAU;RLS0jiG8Tzhb11YnHRfN~Jn|~JxbB$)Sq4ZQ
zL*TRch)As7!!tjnV|N!6w7XT12h@6i+{0u3gK*0#?R7L7dq{8W5_HWzeiu$WpJT-}
zJh5<u+)=NEi5obau;1^T&M)uF)w1pY41y!_XOX45^vYn^^|v_;W*iw9s*L`VrWC5p
z8b*T#Pbd%x%L%}%yO*$lz*+2n^6brEOe4afT!PZnUjs5VU-FCbi#Y>yP4H)3GuuZ)
zWV#D}{M^fPk0tJo*8ZjJXf3Tj3bW~zI`G7V?n&bFs?(f8&3;T=ij#<VmZ^g>5R}~$
zXvLt{wsS2A$8v4W@FsG&Yv?XE5_aq(6-O^JWCQDvMq1@^)wd+B)lpl$2(RbN&;34)
zVx(@!&zHpXgONHZj$T2$riISzzmW>A>;7asLG4N!Z3)6^ZuY_TT*;!^M-F9Y-W5+_
zRT;Nc8L3fE4KgMm5V0pt6zjpUeyz*X$7>t5xQ^q(X!>jHD34;V(Vq7YV5J%ha>Q?A
z(wV?|_-RgiDl#6`2s*B;vR_#EaZMFkChQA39UBDJHHgfTbLF!;Q9QWQ7KR-Qo;1$U
zR3N{Y8D$CF8H?FryrhaFI;YA=vczE`vY8{|xap+Pq0s=UD}92Hb~#-VHU)C2tE?0p
z<IpRd_4Fs$DQw0iQ#<zOM;}jP<4u2e!wR`xgU`Vm+IZWQ|3!4Qxf4T{y;KS{W2ozB
zj&$`<xiU_x_t5rmb|&9494wdR#UmFe^%VO~Jl1EW`A!^K2Qo6Y*_9*}HyzgPXFvQ|
z!P}j3efdyHG;>iv-1_}gTYFc^A9AF%kt(K0et5Uum*4r*al!a{#CjIae4Ntb0BWUD
zXGjlfpF+PC*iyOdsn@n6ZRLQaUOOYHv+m%~n<)jG_>%P58h3?x^?D4wW1$8l@bdwC
z`#{cSy=5S{pQNy(6MAqxM=bOi64-bs0DcSdM*ua;q?OUtkW7Je-ioyse-*U3^zIO&
z$-i?98L>-t;g7vmg`{sca<6{CdvMyw^@*Evh_G)a94qA$zFeueJY&tIHv(G4E*H&9
z8H4^UoGxeGz3Fj`{Usew8(mjTge}cIVWj?3x*{2;$7|d8vMoiN$9u6Rh^Z&SI5&!X
zluDBudg4a4GNz?npxu!&^e-A74&lou@@5i3$8NBr<M`+%`J?QQ(nSV7RmQ;SN~AFO
zP%H0`E#P%*`SC53!_q_7NUHBGUM?srsHu&PHyer@TG)_0*Gi4i$>8o8V6hjK6BI&<
zv!YIX$mBdr@6Wlvt8psrf9ucwS2+JajOoW((@y^%1^5Cw6u<WyEfzMzl5tL3ZJ&cj
zGkH<MNs`v%2Z;2wt~(K1)y$hALnM9RB)A6*;j?G;!Bru7z|ZR0_v_^K_Gg!G|1$5n
zGkj!0zw*3Rc@aMkENHhT<J}c%fP?)yfUeJ^3Ta_jQWNp}>DrM?KCf1@?Jo`JT-%Iu
zXD!F&YUlZ&I6q~VtQhNd4tYs%z1zlq!^+;+d2M$xRxt}<@1SC#)*CLrcE~OHmt3B3
zuCOr+I8Zm7|L!;6x7#Y=sn8$J^Xa^>ND=xbW@%9tIx{t)+Ga&CL=}y((8b9V)iahm
zFT#037_P0VYPEr&T_x?J5U9F%i@-Wja=x9a`Xu08K^*I9iR60{`pO;n=wt6Vr!+w;
zMuh4aK#O@e_X)rXyt_u8D;kaLW7AwgLYaLV`Bp9HmAEhD)l|J+_tV=n_sZq+L!+dt
zzCgp?i+JBln$P$2QI{2^!UwFBxXZp_8WDv_xt7@X?NOR&V6#!>)54DOfhn{@K7Ufo
zCaDgatVDDaCiwNZlQGG&z^{y|&W%HiARo{f&!tWu|0Ef8%Knlgw8qG)jj*_u*FL$k
z@J~J9n_nn>4iMRnia|N?=2=Lm91+djOh^_z34E$O6UX|>Qe9<|7#5~-sbH!;(noj%
z2q+=!NF~TQ<bDC-x>>7|Y&?&7<H=i)tOPnq&H#DU0*S)Uh9;u%oXC08U>s2aa`tTL
z>odSYRoI}#o1*8a&qQPN=F!kWxLYz`Jmxl&`Wmdyf)R8arJ9CVm^(U<s(!zANwK~Y
zQ=fJzgw%PYjC@D(;F`Z32P5k%aBa=Tn;w1`zKFWlnU%&176dS;;HR5IpQj<yg~XV1
z1p~xsho;ID$#4S|8mdJyx3)dhx6hfQ=wz1kg`t;#9TllGE)Yzpn^ahb%NTpbYIb?U
z-!RuWkDPF>b3)ol!1HKDa+psIzR}zar4&;9?axhkHr<J@PxUL8sQwQ?#Wyk+6}u3?
z4sDKDU|?M8vy1q?A{TSBGKwBHim51}Fux%v7QyPY$&&Qf&{&NOGZ14m@iZ%^z=Qgy
z#7fC16mV7NK&e24(B+QVTb@+d<eZ&#0joBcDs=<IR=3;C2IbZ$9@2{r!h`w2i*^+u
zajg%X8{tz&MDiY-zo}YtqahMA6Im>5&bqCJ+s&gHkgah+CO+QKhSOtN#7p`HlGpNT
zsXRGP(-h~sHq;p7L!Ne*V7No8k{}ndKUvvG0euAEuR?$_`eY=|1K_)%KRG``E(uRr
zrpj^4=x1s$048^)#_PfXzPIi&NlZv04!eusH8iJUyBwCv*ibFfi(Ke6NTTU~nA@E^
zxhxQmygo?XkFTyxXHKV0K~;xFlr}Ev`k6{n@(c%s)9NZ(FC-k*o#6xxr5{V$izWt_
zfGUiI%jQ(|FB9fv;$k)34>`1*wnO)jFU@+aW80S{EQ)2QPgOWk<)Jp2!)S^?z4YFp
zL&QmSS2<Ec6F%6W2Y+C~^6J;_MhYi3+rqlddtFWOwx`umH}#FkpM`8oTI=}N{btol
za+_OwmFf=He7^1A<h6tt(!mXpJen=6v~P92Jj|IpX%<gQxB1OCs6ASmKBXt(OG7(`
z+&hq)h@U8u$8}~$(NF66rEyFq_CONH_%M$Wq}%i72&(I#KA{Md2c+<=*$!UT+UiO_
zd9-E;@=>!<D9rgr<LfN!V=l4vLIDPPB%Z5b4_K8bu=q~nNfGFC<pDA)lJj08&X8}F
zjM)nhC!klk)*Tl$Sku6*E7y30o!xWH6{IunlBBP&GJl3hLA+QlbIR7Yw?;o};%2E$
zpTH|&yojn$06E_t;`cm}bf8deZ;&3JYIL2&`ChPur0XHQ=5;e&Aeyb5^PBzKds^ZT
z<@|l%5IglEG1sJE4ZF2o+)cNYx$PxS0n7Z*UvG}ytJG5;%w$oRga{ddU1U*8M_O+S
zn_>otaJ_fwtZIhcbeD8)$o^f9LUosfR^9Br>R7pJdq&0Z^i^DJ1eA8f=umN|xCr;L
zfPr9YrDncekG6V)v(Z_l9py2*a{bxuPF7iZ0xXIV*<3Il`kY-i4RQ(xzw$zctS=e6
zI>liN5RoT#^82qh8;K{FjuT`(pOQ%M-W?K$zqfMwkyPMg!~<3!=N_)20%=WH_*<p7
zykO7Z=dD=4?nLtT8Ev(HNdyA%p`3<FvTif#@u{tQ5ghqNM<2Sq(-No)Qb{z#mY#;4
zbfaJ%2!lczCX0BS7!#xri8=-i>eabWz$=xasFtts(dj4-5<zCpt;Iuo^OoF@7LnIw
zxar+_hYz;`SzfETL)eMSQahlFc5<?{7&zv)KRWZngvyYJA+vBUsFLIrPpSCstM1Su
zEr5LW=vw9ly*YFBv>$jpH;>S1B~HMgY>aU&lGdL$IvD?br3wk0wHxawdJf=SPgrnY
z?IY#D^)QCYzUR!A>W*G#d%xhtCrb+dOJQdI-|&3S|D5~$E6jFVZ2yQx$|s=8#6f*P
zXnZJ^e`LhvKQf~E<zxXTQCh#3`6yaKN@c~mHU>?wAyq_i(EcZk7*-#gm*T4|4B$;4
zwv6868PPwFeYAEE12}j;PY@e}{4{LPA_l()W~5C~b8^)m-XA6}RR1O{kH1Z@(orc1
z?`AgW#VdF(G>ENe*{sd~>#<zL!5#6=LV(g&X`-?-NG)lY&|^&a1#x!PBiKh~k<9Dp
zruK6e%yt?gT#QlFeP)U0`%V$t(kt`hlGky+%9$123#&UY6CQ8<SR{9-s9BC9;|4CD
zOdP?%(%4}gGfvsaV!)6W-K=YZ0(c8In$cr5a|&z99pP-l951`HEZz;~BYnM~U`Q`D
zK#IxL4GFT3l%xp_k?~Z9o7e%KhS4DVP2tW-otaKCFb5fcNRk>f9=tRCYircRjygx0
z0*|i119<$(T1IBnMdp-n@(MTPu<*-aeec-{qOa49!c%{)NVrx_o5<yp;B^%(5`gv_
zjWPjmV5n86C@z?DK_25pOGsdF9!p020Ue;8bSdD$(U?FaDb@XHNizU2nZxuYu$sjY
zFxj^Q1S(f#-6k-BfMy|*b0l$}ggO`U1(rlCbb^9Ts;XtV2}tvvMv3adr-Eu5DlJI5
zO$JHp1>=b{TwGF+h-XjpgQT&+ejSv#BZQq>F1K--%lyJXyvR7o&clLz_YBbz4ufc*
zJUT@K%{f`Boh~G}GpLyr*^?wBE-72_NQwi$@f_)fWwwG?yobO!>0fefXXv3;k2DeV
zsMmJ!fO7%8TKXw6sQNqYa54iaVxvTouTZYwtWmJ68#Km%O@1?yYH7B@J1f{e{4_<S
zjOlQLWyzxm{t6y33Jzv7{njMSSm^s>n8M{qp%Y8;o%v=aX$8<*zgPu$6uJp^wRXg-
znfHVTaNU-n5vGc|vKyTX^-91Pm|3cH?x+(fCc5v0ZgQgY@<mgqrJAc<ga*@qR%s+{
zTye39G#t&#Fqcb9!{0x)^O`jGl+{Tdh4aZ<Fr-Y1rbjTR>+z{g2Kj72H8`syNBP86
zVl<YPkc*g3^55M!R0RNyj^ej_3~<SHU@5+5E0@a_KrGB9PY8mZBj`&?u(fK99$c!;
zjGCOq9<Ee78rsmo#pBM%SdJ_;EV-wWlnW~xF%;ZFi+kes(|@3Hr4;4GBf&*9ugYgL
z8;hcTIv)a^84ss~m=s9`iRpzybb6%KwOgY2p*Ow3vQF7UBe~<q`qSB_ar;DB^6XGN
zsut()yqo8pT57+d#JLm$lkR)$$CJ6H%qhliZJq--<oC)2+uDAVlbgkW6PsY9rl(8N
zOZyHh`x+q^ui8U-S1(z~PJygRpk>9rl$7Trj!4pPBN&_%l0T889#tO<l%tjY;4AM*
zdD}j@N}1xs$eNCK3@}r3)~>fwdy?T;qfm!kwPj?C6-!kiZbwe6SSn0VdDgIwqjOc*
z5!9&~m<B6b;20Ma^y<O)`d`8LefkVf)e7TOm-)80q$eL5;Ht_k=JT$|`n|odWY_m~
z7@e1Z7K-INCY`FKaZsb$7^>DO#_b!Z;B*I>Px|NZ--(l|AZG4i`pWobfn?8iN|Z8S
z*{@0rG!=NzhD}7fbP!FkE=1*9sc12ErWOaO8xKQ(^lzb5&bPZ+OMbjBYsj8u%v9EG
zNStC<!Pk!bt9aPG{anWi*Gf6_%zCmajHiU>FuizZ^r%9sY`Nuu8tm|vSIs_v9roe|
zytq2EkOAkOB#ut)yPn85g|~ohi0&BnL^mefTb#-+B3pB4m(N=mPigFnDfNrFH8}2!
z6uZ)}1lQK!FX`3~W}Tl_dX9}t&VP>VHv{}!6REqQtd^`J(?(+0l)`qY_(L%!=JYCw
z2$=H4X-f{+Z62~(^o32`HmE*%aJy;#UO(}s91p0mfr;8~wt_|3P`rt5kA;T4m^AWS
zFpkK#c-iLf{xk!o*jE5#I43|W*-OEy+k;e7)hdeUs6ek~K~%IL7NcJ!c&9qwXm{8(
zc3Mq!?`}rC8t~Wu^y$b-v(9-V7w-PZj-ld^rz6mU4KCQ<$+gAv*<Vba%2Lm6_vp;u
z{x}^kIW^v#-y_W~k)=Ov1i@symEhMK<}Fl4$||e#Y$%;adT&u-jLo@wbyUnWvKcI)
zBW@7T4*tBP9WI$k>pk|V0hNGLQBttBnBNFzOK-6{%UXAHnz6FrLOK`tj$r(awU-ya
zZNhF!Pc95;z;^L)xb4MmS~_9h=dZ)IN!W5=Uqk8{x2q%d9NgZ6t)KY6?i@m%-8%bG
zSKQb=I$W!%W<u7jitRb7qMrCdYhMfL4MYgU9n$+8?B7dGt=ej2VCgB9K~H8{>7`SU
zxbphL0a)$a$ke0a#py~I%nd+L{nNcx+5#$gZ@M!_h=6#|5zi~qDG^GJfx|o@;lT-8
zze7*O|0b>qRrkaT1ZI*b)QIUO+p{{ErkW)6Zm&TtedGVN`_BH$Z4m3a-w70%5ul;t
z^%gj}>PcznPID7Rv72|<NyEw5EYe>uVw*$9ok1a!PHBuQ;Yk9%@a&$Fa|Ob<%7@4B
zyQw5k^1FL<?(_AJh`f=$pZafQ|9^77|8p7s$5!6-|1~d3CQ`KTD;Etg3AiGw(2W;u
z*JaI`D)eUV<u9hVaIL*OzK|>WH!n%0=n?sc&wO@d$R6@HiuV0_eLiseeS+%u>iYg}
z4!*4Vr%z*~bcbE<XYg^|wsIFaQrN?%{bo18nOFNRY?%4M$Gy7KnSTvq`sg}<_}2&2
zGWUYV9KHcnHoyPb4IJHn|CtF5r>3omj#Xc<$pkh3xp641P2PvTE(z=2%dnic%9J#I
zp>ZL;v)Dg-|LKMQB|$u-Aoi%0c`64)ixZ&=MzV)KZMeFHZ_ND?lbT<T_G*ySycCrW
zjX+>bG(DIZWW70%;IKH(_Kj%`!G@kFnL`t817858rAUP^0X*o>UPB8xYEPnLTlnGx
z%e0iADq$DbDXsdW+2)fV4Di80)7JZ#`BEou3Ll<w>+*MH`J34hERC3NE|Ia{b^|Ky
zCa;Q=BO=5?#mAy>UqBNd8@Ar%Rkj%UJlMniwt3B{?&s_fFm^3kZkXc?gM4#sZLw$r
zD}tMcgsMFne2t3UPjbcd#-aV0{6$W`JLQPJ$D!h3)8WFr;WBV!qt-Q<vbG4#1pl74
z?$v!d+jOxd;nlaGd_E+BWJ0sIz}juJhat&`tI*0A5~FI0=UpEFRrUf*IxIIZmXV_C
z0mdBB+%YA{*G6UL<JD&HqT&m95&k8fEfkD*E>zv}k@GD81FjY7TvuE5Hf@c(@U8Ek
zjB&H{T*dIsg{rgf=HekAiHX(}`F_Ue0D3eyk$Eg|qxFC&K5ph3r?qQ=vYTHIAiX6#
zyUM|pb3$W4l@qh#BHxic2bfRb8K%`iT=`IYkOh(TWGgs~@jP4}Qo1edmDoDXj;sv=
zR?+}aWPY*MVSC9mb=kV_{Gv@o6Bv6py}W8B>R#J|t5IxXy}VOOAalvqFgkW6H#Hv=
zDgNqA%N7LqX*=0cWMA}+rme(-vA(*Mdv4+n@@Sl^<;saB5-s@p_!=yHlXCex`mGj6
zE%<YWZDSAu4!!o3HY944?qAzS4CAQDi_+B&JE$qz3>eR}Sz5zTiyP!S3&aKvNg|;e
zQ$gTg8n;^L(sbBI#>|rKvSf~-@AxdWttxPEUd*W7ak#5rqp6%n*VAhgEiw?tHoC%`
z7$+3hXemPo0(BDnJpoc^d0%U<)&g=fxJdE)iL-p7kFqOuW}<yfn3mihFKPdTGXHNU
zhPUfh_o=TA(kWDw0beDpGFV<Q!clCJp>Vs;mnL5O-X3#nN~PqO!8|5ktar6QPadF?
z5i^oaI7%=g_#4>?{e7AqiY+rZ2fQ&z-uKZ%>mH?3Q_W)*U#c6c&Q7syPKf0%o;->K
z<5!6J%VI5F7*QxRe<+E#R99{vUrl8^`G6LCx0#|QNv@6iBB(!eHtiqp@k!C11Z^ov
z>Gr7#+M@XA1I@{A2$droFzDRXo^2WGGE@N${>QGh!LRtmMSp+SP??w#3L!-2Pq%Qp
zIBCWVom#j_&@;9bzZMm31_GoVsHFN__5U88BFZCJQG`8vQo%Vc)o>O}Z5{_ReIP|2
z`7kJ%#Iuz!8(y_3u|tsQ!rfB-0bY6W6Z%0V#f=9qnhN0Bg;AYWV3xBe8*5qB4PeY$
zD!!cpSjj;dv3We-O#UGCe)%{Eu`L5i1tbKi1u7;br{_)50w8v%(T${LE&b9-*bfY?
z?_=v>hqvm|WXVj4bI#fI27&#n_p(-zTwhnK?G<J!gt&vZOlR>+T3f`{;ab9Ke1)c(
zk03>x;FL@Y26%2CjmHBF+7}#?;hiqC>~Rmo$y`^9T@#*sRj~r#7q%7Y(W!hv{`IXC
zHWW6Ty~@&(J(n*8a|@`alVbMJ+f4P1fg#KwQamz}=3H|ByoM_(1wUVBfg)10l6^u4
zX)NNb)ho%JV%_QMY7%Q*uj)ug^ykX;0bKNTB3gF5K7nK_19yb|b5EgiLOoNmj{0^=
zqb}DQXp{U;0r#}_eJxH(m-0-9uQV;p^DP9BH>hzK8I6oAi?>EfigKcMg=ZNK5Fi~p
zC_*%3hR)#m+?pT~rrWc|6^{l6ddeM&X#z`3)I~#v7+8rJ^T}jG;$FpB5%au|wkDx?
zRY)()V7YB&jT=My=pbC^)xB2_`uVq(xOtnFc<o1m>yx!(dc$kJlcqrr4lXU*`I(f9
z^_&;HwYuHRP0ijBVd__S$BYtTnp5Rv^eDT(u<mO=7pP+p)A+Vd*_K*mQ>KyGDKZp5
zjtY|{=@;ejgbY(Qf3?QDh#uk9n@?AUyfs7IFmB$vm|l*k)g7)+Ux|}!%i*gyT44H?
zqvM5;A<)63o_4|zv-ryfl;@R%A`-3W+r|LLYbnI=A=cUx63{wv4n4U5esRa^QtmTZ
zbi_19tX)lS7K<H?)o5bmO<l%$>r=E>S_MRI1fX0)PAW;=0*<>eijVX>t$WS+Gq*Zr
z9r)ddJC0ijj6n^XTO9Q3U?RXCivXJBY?qh+vF7RQD(v0HH<@y0mBAr}wsy?j_cr=e
zGJ~ynPtm`1R>5vI?i+syEF+h-8;nwKCGQ_YioW5hrYL?%_f^H{i5KV2P8TrzGCKO)
zBn@aIz%&*y=JV}U1R>HYPFIaF=MbqSVRA^SkP`AM|AySUs9>Bu@-xWUY#$?e4>F#u
z1Rnq-wWAh`Yd1a6UfQl5s75~BGN492#j+=Y;Xv}8nM#A!kX88r4Sn_$30QxdehLPN
zI7YW*aW=nQobB<FwXmPoZ|uX9pZ<n$M^p<+BB-p)7@tmm+xg+MFE$B965{rL_!x?R
z2R|p$U^A%j4#Hyrs*<;5&TX4vTz0((0pZ4nU4%wUG34HG9gLbGlFX)inR**cUS5+h
z?jpruNPLi98h#q{4-S5SB2JAZK@w&@fQcFl;>w@;3mjOvWf^&iR`TD9Dt>r3FZADl
z_~3`Q&W217w-LJ$zk6D&^+wVIhxF22K${z(9Y8jh#)zsvpj#7i{6arOpT;Rvt(gY;
zlsJ+0zxH7CIzmnpu+{H-q7WwuccORAc^aoT)JbWepKxv|LZ-53&ybMo2Qecc*b?q7
z2b5k37&j3(UJxMG@ggRYab2+m`EZU595lLVWzxvx69DOKIykx7E#5FnyZ+ykd0~U4
zo&T*7`=1gVm{{2VBZOxgYdqGt^**=OgP$Oi<|be+3?Kq<H~WcptYCTjfs}7b=i#%0
zNYmt=wmTXn&UUK2WOTITC8pU&^B;7Zr%ANu-_7$IDbIg!nl}CVFU$@9=LWq<b!D9<
zZgm*rxJzG-<>>L@?V+}DrQhNj$xpz#ZOQ(%u(_KjyK3h2pJOgBns3#8=c!CYz6*$-
zMg6tawzh$O28O;#88_|&@E}8Nj<aIc@9p(a9>OCVz+KZb4WSyU(f;n?+`+Pv%!QW1
z7Kon7OpL<X85Xp@W2tIY=;>QPh`NJV1PX~8fTPF<4(K8*sWA|M0>zjL5ey=>MP0BL
z$Rb#(hzU3@(3%%*Ld!k%(t|xy+yK>1=kg;yV<eT+DWz<4O#Y<(7PwJ|1x0?Z+bOkp
zj7VN1GBmoFj`&(937!NHs|Phz<qlV+{HdThaZQ%#)nv#D6pxRRI9{dB8ZAXw8PqgH
z!+*k@@a_AXz-)(soV^fj$<|l8Pt&5e;9KvuC5(otAIjHZi1Wne8`n*AK`h1Q1{yLK
z1FD{oHQbVM+^Y@(T*F8j!AN5b3A-`9kB%{P8{&wHZY79`t7a%fb7S4UAV*Ios##b1
zJwm>c<ycWD8zk3&Y~F}VC<y3XQo#a6yPAe0b!DvTi1^GyAUH5(2#rat%UHSMZzzv%
zbv7N#PD<+xEDbnX4C8e~b)@@&fml&uY0+KlC}{f`&-Zic4_M>Z;b=~OZLg2fNg637
z`he4fCTR}(Y0SW3lpaQ_kFRdc<ZK>iMo#=cT8DD6ETMK<aF`c7B|7qLJAD|8a2muY
zwoUA~@J@IAKIww|#EOA8zW=FDK9}T%iI;a@IhD9+r}qHwXWs-X2nya67oT}@aj_~C
zE|`lg)lS`$`=wa3IPS9%f_e8SlA*fN15MJ>ozw@(Fv&CY(%G^#KMO?a+^^z6(>z0(
zH?BF_tgf^Gu0i9a4H%Xo;!pJfA>OWuo0xKGjzbf^5z7^$H*g|U#gMe<&&I8<LDN5r
zW+>T7R>G1bX_DIKz$9#ZA!(3>I=5FFrV_+!FcR)`YUjQabMg#T(q3-7m%2~@YOy@K
zFxH)}gS7;?u}jhrStl{Ld;D7Rt%R<Max$>HyCo>@4Gp-#K`zb~O+A2{Je*zNQU`99
zQ|Hj1MU29C-iU3f<uc+w^ifiX2M@cX7@%OFs~BPRVY+_0I8Mx^9HBprU&w>8wqV$d
zG=N%A7J401pJ5<L&SK`(&Wd&JyiS7ARZt!YU~5=#@U1#|j0kj#2_=&DW%%!>X!KTy
z^s$Wz<q}x(BTDfjTBtsm5{sd+5{qda`8vUd@Zo4ZqI@eW>7y(ATiHBGWnmz^BCe^r
zexN;I?N@P>HZdsZ{npOgX;}T}PAI?C;Pu`ifkF{zON{Llgo*2BrdohZ3|AF?$Y1@g
z#D(e=pm4oG_0|O{lDB$ZRQF35<V>nZ?BF-B{%CkYEYV4R&|lCu^01X#vWr;$I6K3;
ze(bU64211Osl1O*(V`&<g-?6h5e3t_gfCBcM!(=A9jBPsvBHx}OL1=m?ERsMqD@u7
ze8HjKq!DN<2DTK;3xZkWSWN}Q)&c#j1Chld%Ao0Xsz`7%y*Z^!S9IZ6y3$_aMtTbE
zH!0*yB_3vU!(F<efFJAV$sa4pCh!m>ywpua=?n`tKcHzNjVi-S*~b&AiiWjwf1W0-
zRrr)Vg9-l9bk_h9U6%bju_3Gk>He#vNVBe9DHc%09Gxj5+FCe9f!^Lbwsg);Nfy99
zfw5Z&IdYiRTabAdQ$d<fKa_J5uf?~UZepOLEK~_u$PIFt4I}qC@JM@Zs&VZWrZR>l
zie?LXtQ#~DO(h<R_(z?wu%ZdkKmOT<I4l)O5`%>>rr*@%-WxPU8E36tP(EGJnS{&s
z3?i?GMO=hCf&<~F&2djLAKX7x;FcmWXjh+PweN|DCWzlfqea}ivxr`vx9w-A37;$e
zEy!UQNoRskV3Qplbr2=y;lRoH`D5sI^+Iit4n`#dddNJ|aFUw;-n#?iFJUx=Y*f|`
zE5nOr{9>%-Ex>ZIERbq1yU<vx90~Fv9;89Kqc_Y}sP4V3+w?!qf9~d)H~+j#vx(D<
z9z}Lp6xDnIi1+qI^UG1zBWQtD{u865gy;?ya~GD&@zY(vvZsLB-RXV`{qQg}v9_Hb
zuAKq~N5D?sG?~}?GJ$En%8waBwOMx*svmX*ANnDAufEoet#VJW!xPVox*s~7s53rA
z_UeSabtN~3Lf;+D@;Dg2__=u9(izrkKW5=WsMF?p)2(H<bOsDlcs_|*aq+~i_hwD(
z{h>m-E$;HFHac9#o?JT!L3Qk%Il^3FJo+!lc1Q$|rSgJ0=O#8cOgur)3zExUbZ|$^
zmkN_Vd=Vz>eFThGEn_4KGad2<eopBwStf8;oY|p|RrOVY#N5?zoii}9=(aerG;-Pr
z-z}a(uj8Tx(NPvz+%VZ}l`6eA$C>xE<l|-~zK(sn24Ch$?v*Ssq05I}<uev%^KFU>
z3ov9=9lC38_fT@r)Iy5<9`s5-1=2FX%{xoT7JT~C4TSd7D9yoQ<6+v&t&Ko!QU@2j
z$zytCj*~pXLW+$0y2Y~P&ZezMvuV1f#%RqGSAu=s@<0lw%^nka;&5i-jiZ!U{sv>V
zmz>fA8CR8wtV@0XdFa@8g~6<WcC(G1M|0(btTc4+lB|R&e_QHpMXPO^+ebV@<S*A)
zBOBt=NXcW1HLYk~6IGExsy!?I9(A0LV(-IMing38YF@GvEa0b-3C#j&Uu*epG}q4m
zH8^pQjx2#40Md=^xRJ6>z5^69LKUzuL4%bzwvD<hEzOHO?|2{VmLORdXDaL-xv0J~
zlEu*~LcQIH3c@>ip$zpnQ(v|jgL>7>x}H44Kr&3A;Ov3)v=xuMbUG+6YN*H6&2sw1
z7_op)XS44l>DC|JW<CkfvK-*0uHTl?*Az9m#jK~YTZtZMrQztD9K(l#URd&X1F~0@
z^IHx*`RBcryycSMcpZ2?n~};}>l`cgX`Fhdo68a7evzROj&;7}e7RYCWaxeJ*0$Xe
ztK3r|dGgJl9G|=MkL{#3H_o;?chGw;=$qj-95jv6737GV>5fv^ly>iPUFFej2>l}-
z2fI)+MLGXhClY|EkZx+36*Q^G?Z|Z$9mLt@dXXF=k4232M;n5_`irdEJMHarNbL0F
zFuyp+J%Uy>wJ{AZ5N83$uJ9eZX>_g^<y-h%ExfyG)t<|}<^7%h7nuD_kpI7Qd@TP{
zj0htK%YS$(k2NLZ{$+OkbBJ{D8>kXB0|Ddzzq`oX{~RLTIH&(-;`Zw&8KJdvP@PdM
z7&-K4V@1q=<Fz<CE|d9_K?(4^x;P2`@f^x`OV8);mFxF4EHhGmgd;O+{$rJs<tBzq
zDLY%npWE~zUah-?rR;m-&PIwA2&@>r@*>h`fg*TmFzN1P!GWIH_=%fY_7FtA8rTpI
z=DVl3nC7izr)P1Z*b?N2(!~Irsiwia8>g<ljvnW_3lNg2$#eVb^OJH6SG0%Fy%0f2
z!vs7INh$yR?g^Kkg@K!^1F(o!iYpd!Mr8n_bRsbWb%-Po;`Ug4yfdVfcPdB_b=(dX
zD!@oX_iHpn2z7ueojVhx_o#w5T`r)jaX0R>dS6r(P*^4eO7j_##<}tB0pm(HYn=KH
zJVn&757HZ^&_4P3!TtX*b`C+Bg<G4gO53(=+qP}ncBLzA+x*hDZQHgh-Pzp{9sNh#
z!JVJcnY<g%UTfw=l|TirnmG-eFUT#W>1$EY_}#&==YcX}>2V9KQWLRi`jF`LH`PjG
zh6vVv7ol_(kx)uvPd-IOp%SW^cmtjbrXgJV_dX;jB43CjRY(016A>G=4g>d!qMr1L
z8P$YtS%B=*(=63~R=*Td3ivKGXiyc>5-0HpO)#-~=NYkqYB-8YpfVY#;DX@t=+w}q
zh5>ryR2|gC5OI~qpeW=Mg)ne!U=FI{V#XeH(8)h;&T6CKvcRW?RnMNZh9TWaDx;?$
zTEtBCK|9T774h_p14_6*gz~-$JcWXSR`<AgiT2%I`6I~-5@@gPfsoooGN3pGoYz<y
z!KX-Q*ponvKW4z)=1?}N7ZAHr7Z}?D5KT$$hxEs#jqW4Io5_VO&Lv&Ra%>yX%B)Z~
zj1ggL=HPrWBire2F;<)exM>R3XSh9~w8^{pCDRV58jLi}qIo56kN&mYq5VQ0+(n|n
zMxGu_n2)qX6Fo?<GHZt0FUbJp2P0!EP-#dY_az|FUrt8o+D|4@aWM@9vLjM)no3N;
zrA$5N_*$d-;^z+Mh81C<SUt{2iyMj#GWrh+OjVn=z=>J?tJH}Xs$&*%w*Yja50RZn
zWX3XD_jx_g+QL0G-7*v0Z`V=(u5>@|A7IPl*PnF!(z2=-6nYsV){HSOz}>tFP5Fvk
z?zZg7*%h&PONBPI0ar@fz>K_+oZ&=PK>y#^J-b>?CfaD#1-LfeQJL|VDP>+#0*DFa
zfeI8ql?;QHBF$9z7iX*{CPcM=K5V6PcPpr+7ryw-0kMe@FxNY}Eh%J%8GLccqNaJu
zUm1Sn)Eg25ilXBf+zw?4<$qaPeL?DClnk#am&mAjwf<6)ifd4YRpLj?U`9e^-N=RV
z;vC&3XhBRYP-cpC<>-0ALl)IB6En)aXgax>E@XQ*mql`B%`t$Rqf>o=6c}HEA@FJf
zts{!$>j2eN!w9@ZY>mEhkS|dhjqz!Wk}kR6I3vP0WlUP4SWjpbHTp@Uk^|%d;|bEb
zI8s@a8co#k)*CbWISx8f?x0yV{h}@9n8bo2JY$c>KD;v<NC(2`D8TE~$s8?eB;W*g
zaXno1P)Wb*(=1o-D0CBSQa4C4wM_k?#lWb@vmP`?+kz~*(O5<@80t)3VXRnn#b#a-
zyTQsdKY}EZv0$VXydwt#jKEl)ghKzA%3N~yk$rcAQDiqjQhb@arMH1rklSL=QRtv2
zd74Dt(aFP>jRw^ap-g}+9p3K?3zlQtsRqNfAiM#Qnd=|dF2d;8@vI}duVd!12Lew_
z=UR~xy?0G#TB)nqP~Yr=C}!53$GgPG#7X6#^dm@87mLhq3~_UHH%72WxHq4g-gR3!
zvO~Q@W*cney9ItWGxGg3RYh!!ZTTK2K^oq#Qq`t4n#zrU<28ik7uXHfuZzX!jn%64
z8hTAe?TR#{WSeRuGHrqHCu%ckmdxG!2+s~HHlHk5AG19-5}j)26P{M&6$@kE;l`P2
zmFN<qxGY;oj4VB21Yj4hURp`J)TA0BT+e+l;2IL$`r;W)=@W-4FHXYFP?mt_i8H9G
zo+9e7)JP|AHuNK7!7r?OC8F`_d!^;ab=xFoDh{h98Zgl?r){RZ-VC|+MIeQ{0^rJl
zcpR)SKByJnB=5#pC;hHiEmv_^?D0{!Nf>NG-To5VCrgjYp({k6m8<yeQ<Gi)#j(@q
zVc_n*Vd5SB?FIKslk;}%fSWFDjdLXS&X-xQ345_rwMX}=DJbZ+<zj2~z9(U$;HWVP
zpj$h+aYlBGqkfNE9(=vf!`ItpS<~2h%+HFu_2FYe_6AyQeHE6Wcf#M&)}2FCc<pu$
zY0V~@AMJXFNz$3vc8a11{1~DXGs)hIEy6a{N7XKNB6;NEoiyWxDfLP5w5>xwYr5|`
zT_F9`h3*bg@&=BVg*Pg)N}3ezm8>QCr>>RekgbztZ6mYjB0u<4dP$NH+bvgpA7AKr
z>LAM#LJI4F*?j52)z#xG`0roW8N(3&>EZqFc3w=3|09F?BaDdMWc%L_??3pc0`MmW
zhP3}{jCfIdtZismkoK0K`+P^0R4lN$F>8TG85?A7Cg~oFbxEO*)VBFNNV&Yw@8J1V
z^!KgE-Emu?kEC2XIhr9AOFU@Lf(dT?s0(-)4zlj?*Z0%oqu=4D!RH$u(rj2?qJ@7c
z4ybFRAxDR4t>xMD<J8VPC=T|5-PU?Bv8_){Y_P6s`5@j2)c*9VQJ+!QYTi$osDbCF
zgA2T4RD*jR#GvELJz~-Ex&x&o)w>R&WV=ccSLatqRku<AV<z<2v>BlieGdaykqVab
zqZq0t1Fcz_zwRu;Si|W29p0~=%oZ%=c?Bh@{z0kU-nG1e5J!K=@~BVa)mm?)7&JEF
zt|sh8W_D^7u!(|0N3MhpFnxkm4MdN`sjRQdGU`%8B{R?)keZP9izcfD7SUkOEci~z
z+Dktq;Wn8OL!JK6r3tCrOsuNt{ORRg6+)zcTLzDm6ll^$i^fw_O+rcu<M8ggo4(2N
zh}a9|5EX10E=Uu^LvvgKO=G$gD36he{zO{%(T;`m7Y>d<ijdr^jmS|@r>Knz*5*Pa
z=~SkZb%Ac;z4axxo0YS0Y4LR$cw7j{a}E$^rbUf|lw(BH?k>4Kd|-K@oMxoHZW%9}
zg;YJqbx*qOZmqRBkgHtAH6(I0{xN?9R!?@v+1*2z6SEV`DU8GTpyU2gaVU0~Q;Qq7
z(*<&sYJGvJjUNhGN<t8m*xXJSaoCFQrBvKL&ERY#eiLC&(X<9C{~iwbCTsb4Jlj29
z+1akUpHPA+Qn`Yet|FyH$S#js8PvXlpIA9Lis}AzoA0X9IJooMZ8|?$IktbD-4SAR
zdqOJk<KW(iWu;jb=6~e2ZyqM39F>UWTw;eiD>Y(RXMfzWG@KgnK7zjv|AR)I=y1b6
z<l`&)YRO7a#GDwj_K#<CQ8$c?WN6t(SJ}|!Nzw?`+4;PApJ)zl0}av(qIsNGO0Cib
zBRXyR-^ahzz(P{tqM*46`FQp^m{9rsAbFpA85Z4d?K7_o{}23N=<n_`9X7xvjr!q0
zr->YvH;jP6ZwtlpK8?*HsM~~#kn}^bpF#0%Y4dBE07PS%=)KwsP&@)yC^r&N6g@wX
z7GcPO1o%Lb5O_}P>A#cslp>E;Ir3z%RxPvG+R_GLSy~`?(4Ss8973Obk;vhIK3_8F
z6J}^t1ZD`%aCIUdPJZAIWhuX_a3|r!8y;1-a3GL~Qp;;++1|P84e^TjtR$_lGZ_Ds
zGepYySYG9{;wN8vZD@qI^HrokL6^&i0-|U_&i?W(<fyxk)NK_pmYr3Mf;a$m9hN3G
zpYRqpBR-Meh(RDk&)7H|RYU9$QYR=}MAe1;fyg2FU(-M?&lNRnu{mJwI!6qoVN<zs
zu5L<IB~f*Qbe;i5`ef>j2S;Zel}RCe+RAaVAE$gyy%w(08yd+qY3Qw=j<GT$&^@KP
zMNSl0DxunWMp1DCR2lKG1no679?si?m##!zfXFdqZ9&vle_dFQ-EbF8cg1dwxC*<v
z9Py5A7f;|RV_)pjO1;^!z-!nR*G%8DA|Z7L(i4|j1Lq1*p}HklZd0$!(A9!CIPeEz
z`(R~lf2?O?-*KbzwK660Q+avH3#tvCbXDGm$UYltR!(;j{6`uIX5F=l>+S`&=NoXy
z`Y%X|s;c9;QGy$5fK+2zX;D&2Ku#}1Y2yA}bG)+4?5Nf0mw^$)yN(yibRUVr0%Y0*
zID2`RrX#D~D=X%#vs64qya@<Ga{jM*PZiuc;8UJ6(-{NNXISc{0E==NdHRZvsqv|{
zwu`GQ64jMCLywFl&P48(RBzHr#I{zoZqmC@x-A;(rpD7e7&*c*=d-rtoMnJpJx2^)
z+q<UNjx&dOfW}77{6-FU?qxBGWW9BqnbIE3Y0Fmi?xLA^f{Jl@ZJYGoZcTxwH(t5Y
zN**8v?Q>VxJS#^*anR$0oGD?oIH9fxkNG%`op8HJ#=0Fzg-$@t2{AMqtMx6#kMZc<
zGSM7v7*2|@2Hh*cZH(%u3O-Mc?0~)pKVKy~!*v0<3(1*D(yC3?c>+1(57*n{@(iv>
z=C39h4w8!tb}ck1UoaE#;An_75*NKQQI$ExQoivoGa}aYmN_<70!!Ij@Ua_^v21Vb
zMPB?hEJCMLB<in%ONouo2MDwX>-I<r&YG@;Rn&PUMW~N1lE`8aa!ptp5EU><_QA>J
zxM<PSdMB>NcH;rn=PFSo3hAlYZ1W-^{f^hXIMjsc?9A(>M`_QdRpRIdjj3mzpUbi7
zT%BpvXiH}F+kvQcC+(%+`fBq0qLl+B`$dbtn~7{ULM25HQH^`;yni<R^xQXE`?JC}
ztmcSw*}(NjxHt0aV28iD&h>cND$j%xthV%!Et7olahb`!O|oIOG$&IGF^_Er4dcM3
zNm^_x+&@)(+H%)}`U=d~7<0u#2_c~C%~FRjxWHM3tbif-js)(U{O~l(xkGYyp!clV
z`iNvK7aS<3I~o{pnhUY!#@r5XuWgV^iFdW_?NR+#Y}J!`*7hLm$DQ2R(w!}~QPwjH
z@ud3yi18mXHYLU^B62PHm;1G9YQSAR%iJcATIkvch_}b^1|~9p^oBc`KW;c#<CoqS
zEg`LO700^&saC6OP-f<i=0>1qTf6){?vX?6oJE=*T~LCv7DeXXXTRA8X^}<-V#gE+
zU2$~nObeRy4<#G+FJp_V`QnBLQ?W(CZ=eN%uDXqK)zeR4YKy>f=*>^#fhebI$eC*n
zq!x36BG#1?UnTxcxJL^#5?7oIN4m6oJNc$H?N>ojad8F4<Ip@4l+-OUL0S5L!6d>{
zFTbS0wgW}!h>tDg*+=`NB|rVq*^;ZS!0Pzr9IR5-x|F@ji|_E_wXQ6YVu%SV$+~5S
z;A37tw)Fq}QbGDp#m;}XSK{FKAIP&S>@ho>wx^t$GUs1&hX-&FLI?!L26k{ThYV>!
z+SP7wIRtKSub-Xb_m0-h&2*k-39Bg`k)qwcHS_=5Ryx>Y^$_rV==Ke**ENzmgU<i`
z;pqJmv@QU3(rbq=pQ+TZ(Xr)08@RYJav<NL)GqJNPA2wY_LQCSul%~0MVxXksfW9@
zV{Up6x9~P|T;K2O-@$WgEUI>4TwU2|a7>28XM3@)<pG%^>+01GHtmVO(x{Vew=ade
z9n<W6Jb|wV-nh8@_|?c&Y3|)Yc-YRt%n7K%FNEdbDUCg0gTLl@SY;C@=pw!p{?PtC
zip{J*k(q2jq__Md&9VIjuGdp;W_Mzo(Q2r7@)-1fYt4}_-BB+k+U&8L@7`#P2_>Cs
z!NGKeDC1(~7UFF&t%Um_3xgsm{aznh@XI0Zw#;JCCxzF|zWJ)eQNT-Atfw4IT<BPV
zhLj6&1ou=2@ALFbs<5DlTcdf@!TsiEOpGb=bEaRGE1ge#lBf0?&#`71yTt?W)Wn7{
z2C|#o`LLbuCnpQJ*Zh<`U$6S#=obq{p!vN8!mdjDr0BsS{J)Q9Jxy04fsagOBX$em
zEPwY}>o6E3<6F#7OZ-KX0$pPBC1k1+S8@G2X4K1kM9iN&9h0y3w1t(S)QE~}rJxxC
z!yxHusOGOn%R`QKVU#Qcx>MuQt}lU_&hZ&fn_Yl`?aFrc%@&fKp)3x$Jxjh$mF@&{
zx|OY7hzd{i&-WtjHAiT<CdUXBG;&H?B}f~s7HCQ2C|{B-i0bX)eQ2MZ&K7x)qVU{W
zyMzO^MQWr?PFCF3A8FA=3X8rtROw?}2L^jI_bq_5c3Fk)05^=9&Zyj{*E)n7?v*5E
z5?SwSvo!e4wgOF%`UdYp7HytgLl>D7ZNg^Jak;n4U(22gBDRDvJ6K*6d4&76MUz|8
z-5tTMVVH%L1<Rskn%Yu)ly;`Aq={a3F8_+9%QtS=c=!Z&;JMcwp`Y^Z;ToKOwdz60
zNQbIOyWz6yzAxT2mNlma92a3bW+V;X8^mIOnJ2(?w;;emuP|t@NDY&HPVk;kYgAZ4
zOtc`mOT?1id_9-<uln7WkQ*bEI4gAJXFhm%o{n&KwiBs%BhHa<;sN8t{U%U_KYnI(
zt?8YY5b8gWzPTZ_Q|1T$9FKTApl}1d;>^7wURJMgIA4pqsjz))sckk%5?Z`W4{tb~
zE!kxNv<;F^XyG`=pW0dZ?!=zl0b>m?jQaD&gz4A)nm;dWVSAr0SWu+SD0vTK!ls?3
zGnba8<p|j_)=ir<$)lB+OxfnIYr@g=MYs`VS_;65oBhnU8A6j=viGZ0tUI?W7R(w(
z$1OcxIX3Fc&Bk(Xy|Rm8=!1TtkWj%5v!**ZZ}pqekiIzdm}m-M!=>TSqR0Z?pSF=N
zRj)Y83X9#rcuGhNdC0h#lZL2OvIr{W-8>q`7L8W~<grO!CelPEDe0;?ZFj2j`bI%1
ziE5BZm9M2Zr&BaF2-T`!d(C&(yF9z5I>rHV!_EiBPA;zK1}N?v^r;ahk~kOvoeuMI
z+qc1ug|*(nFRMo@bSg9qf&F&vwr&-k#eecEw1+e;il)nHr_^v+lua%UddFifR;!Y|
z&F1!m%?Fgw8Vu5Wq3#p1i-MOirlpgBj3FZbdey7CNhSv2-&{$-^C#g&6*7<5z^+4L
zE}Fm|&psvwrtAsugEgSR<PWG#aBS1Agovfs<4Z{Ik9xbJM?V?HG~vBj*{>n0?5!|o
zQ)xX7RG5fMLX{&l>Zg~cXbH^L(4y%!%n0K{NafJ9?TKNN_KL%dtvdc*feCG37BI(S
zl@99Wt#S4mkP`yu9<(Z#14t05jLxDY7omA)iMR|8p=vN&ZL^Di`Ggv_z(uPkN@gLE
zSbP7-dI)XcP?wFHF7!(y5iXsf-J@zK_t$Y88$4Cj692f#iffSuRjTQVCV-aPYyTAs
zB(LuXq{93qLh~1x#>f@P^q%Yaw5rnuT#AT}+lg{hD)yMjd9a+6uVc9GcFZ&d@CuOk
zv2(%*y=EdUBsN=PjJ}+oHPtGqW-guYKSDhoY2~|*qiNHXG~LNRDHm0Y8RU&^JkQ+7
zOfkvBu%PlaoH{Awqp5mI1a8UVZOiUHb;Cg{ElFt_k8#EW$sN7e4R)fPax%-GxrFpp
z>Nyls-eCjxl=B(0(O!yt%{G&mn|EO3N*<AZ*l(GkUww6j?&oOPS``SQ>cFf7+2867
zs-3pm!D~id8k`x?4KrMK|1Q27fQs$=s3=$-hc34I5G!mnkl-|o+F}zmz4po@`BCze
z8oXh?SntBcaW{IoQw7{poy;$qW_!4@m4bx~sC6)npoL?Y4ZU{0)!z655^G9I&rj~3
zDpK=qI%>jl@Kah(=H&sea)$j$zxtvF@+$>}+~oK&kEETZsht6KtJdX<s5wV~<2JLS
zfu_TS#xY&LgJk3h4%jP8%l1sp1Aw}I?XMh!NtCC0X{4#&UsVgqr=^dLPze<s6C+PD
z1D>iU{l(uT85c<e0Ege6jcQSm^r@{3MjFnc7x5YUP~8Pcavhi}rmOUO!ea!1P}E{l
zm`!0qwU763-LXPqIwMGM(0nc()Sgg_Im4JUdgHT!-E?WSX6&XOAs}Tpg;BrJ-O;l$
zJ@Sl%FSyoO0MGi~ceqgy*YCAkg;KkO&SQ7^-tD#E=7<;RH$}5}$?(-zrO*9~W3Njw
z3LMM^A<276L;q$s7WtY27ns$2uRV$Q&*U7KcKr+?S29t>pEa-&G?=O>J+oV#Uq^)B
zC3BQ`h~fV^0S~DDb=EZ<=I!#9>(je^k`=W)-VFJKv33nTJ+B_Xb8mpa4H;A`k2Y0?
z^|83Z(;TvhX8wHFka`p{X5>_CjBQ%1;sI(I2|?yj?y?8aH7%!t?wR1bHT7U|1nVHk
z_FkYE)mX6i_u!015~u913b1pQd_FgYMwm-<yu4%3SSUwXp=e)RjJFzH3Oyq8?q^(m
zO@`Q=FRpw!tFOJ#xK?=ANqfXU<zdtxaFHjOGSc9E=o<=BM#J3dtA8ZDZ)qYaO0|mG
znCQlmi`5rcOT*SOFgMDNLDL=29g$RDpGlpI0^|r-B4*@x39yDdS&<wto~LatG9YSq
zKTsiu0_eK=k)GpV`7!qgnl`Zy?kAv;6Dq4`R%@9Od}(GqIwHV}QbiAaEy?Zzw~;y-
z`Jm`+zvTou{5guHo71X$Vi9><3VoAsm*;(DElrCr{02yPiyyg7a}sLAVb*o3xzaa|
zoX1yeCF9#~t~<`YYOc%A)Uif!#7mT}le|4B^A?o|vJfuK#kCeXI<^v}rzPzbLmR@P
zHC`wObUiVxgR@og?=|#r$365+Hww@(EonVz)-tAZS1PNeRy+i6gj*zx-UzQPNzY8v
ze3Bc3CjWR8>|4nnBc4E@_v2|DirEJ1HgUWNtyoLFCs#Z}!aoWrXYd2s%7Nc5+HSjp
z|F-NB(Qw|n`H)+N8K@VYVLK>dS2)W}elCviUaC>_K#~grK4Llc)El<yywhGBeDi6f
zEpXfZcEI9QDcjGlEoBUp=PPOTRJ^uZ)%9(+@RrYY^tHsAp7L6~putklXXB-4DBCPQ
zt;LC<t*l(}5Z7+I*e~)tbcJ1rM`po-U#^(1z4=&zWZ^$oZ@@4`ut<jT7?K5*8v*3q
zUXwBTRC8i(7I*}75W6aFi*CLqdO{a#cn}A{Z&7+LA{AETIZr+Hpxg_2ReyIUlm15I
zhrR}|7jwy_|Kjh!(;ZGp?QwW`tf4Y|NQZC@_%nJ-u{F1W0*}5^{XO9S3)y;>>^~Ia
ztpC-@?`QDH{{O4#y8fS<?hzjYXh^%>Cp@VtX@kr;(g`DWq>UtOiqxN96$R7<yT*O^
z*=l8Biv{KB-}&#UdsD{9VSlr~0pCyeZ}5D+{X6<6>dD!qJ=^m;1}QsyvRL1~@-y_(
zN_4?Tkb&cC^wZeI!g{}w*z8_kY&mIjcbJ_IG^z94CVa!hFP|13?hoi4898Lk8+dZj
zjFTSl))>Y!J9+TGS1n=HtRKc#FdE&&{oKH-X)SPXPms5B|Fu01dEeZjKl}52w|{(m
zAU-W2>ZARjd5(I9Gz6aVGIUh1z&{!^E>NB3wZ8QH#6?m2KBO3Gk{2j6XQhBu#sd5F
z&0@~148KiWo}W-5k##MhR#86r`T!FcE*DpN;>nkDQR@lEdJ4cSBk_&RVG_X&79dCW
zMOT6V1e8`q8oO4C<fuqZOBGycROf?83<hwY$#w_4Q#P#5CyHS218dwk$vE`*Xq)K3
zL7Bi{;FsodhMH7z<9JWO@UYk!iye(Zx}}Tw#S`Uh*3Q|ov#Pz@JI%dnEwL49&F?`p
zqPFO;;lBJR9FE)m-U(k6TlfK9lyHb+3zb{bigc(;*pgv9&}kOyKDt1Z3~A#Q5KRsb
zN@dqgyU)4Rs=yG$w)w$TRDC)Own)eE_Fu-MjF7^5Zn8}{$`G0{v}(TPwSVV^errbq
z=Jf_8-pR4|cl!frknDJkurtZ<mVt;24wG8%@bt1AxntthJ<54KalSjt!>h;~OE?Y`
zbD)lN-h5qi<h(D%T_{Q>Fs{Wlh+=GPe4j|=aH=@z-!_X-DtY@sgE~&Ht4Flk*BJ!j
z2FR5)*ZROG!<rEd-BE=K6@=E822F^$U2YT?x5$NRF_LZ9TiIM)P`=%C<3*V9E*>Ba
z&7|Y_b-;s8T3?H7njy$!dI{#ZihS!ktc0f#M&zniMb*8J`V{3CGlfvf^R-Lo5L6s6
zxFeE_kF?Y5Ak47T5u<E_LG9BLE4cPXai3+|2`moSqaI6{WC>AC=FN7VRT?e1fHVZ>
z3)5sqgQ0%!$2m-ANvjXj!ItwhSyH`?8Q9dIGOTwp*J4i&aI&Yp9gh^%U;^s4rMtOD
z47MR%E5;eXSmlMr<IGi}M~p@qW2zM<VCkwz>v=qx+k54(BjDHsqLF>Tn<-sb6wXx<
zUVEY{G-$Usoh${}aY(6@LF!N)6&MZWlf%xNg%qpAf#R|)^qh|Qc9z!es?m5(%asZh
zHH<FuNl;3iXY2Pw#@G}wX%9qbFs((ayGXA4oi@kvs-icd_)>(z)R5|+&8VXH^T;41
zhkMiIWrAfjKHpYDWL3>aq#e;2Jm8h|)QFEqcD(~i%IMOo#Bwm7f=PuiHbZm}sEmOU
z=uTSx#J}qW0tY(~V$_*&RxW;JJWZqeR>kx^dbf=~Y10ybNB#p|NM#teCt-Lg#gZMY
zADPB<Tsuq=5$THohj%<5+kG1uq)j7nE+ur<Mh=~{mF>h@WOxabY$0=q(zP?T(nhh=
z_?(nPiIs0kF#d9ZHyAR}YK5<iu)OT4)@Z$HcG&$&fCXi+Rpl;0mh8|qH4*=@1LeJJ
z!^^0yRD6OZ+786IQ;~YaT7#Ji%j0ep7y{FnU0Tm+jw5H*-xJy@phQ=B$E)eBAU7e+
zX(cIGxjJRVtYC#rWHJ^+W}DJZsd(V>g-WY+Ve3>lGlgy`{YAr?vZKWsvD;;Hz0)zg
z)CE;c4|WHqqG%fYC#gBpWvp-0&UO)!z$u<g;6p<$TB|LCvcaX3b_BBl!MH!zZ&xb;
z8>w?>SIKwRk90a6sm)GlXS;@kxS9mngsovw-qXm&VXcXxOT|$=2OP9Ikkv17HlI+Y
zY}Z%lpmE9dt2IF0eNsYGuGyaYcZw~VTO)6xS@GjMQmk=0eRaJ-O(C69>X8<%=^&4?
z4XJ`zz-U)NTU8N$8|Qg#r`vSX)?7d=-&QSmMeWDAztoHBg!+p_^$e95F(8!URsq4a
z%#cnYa_6qZvSl1B9s_;1>8Waurnzn(^#i2Fl-=gdP9!<Zfv_6#?E*uxiNKqmnDu^r
z+x}R%A>B9H4Q@H@m_6`}t6pr70`ld_rsH1__bQuKl<+aG_UfMPFnbI0icin+tB?1)
zaGKNK>lPbr_XaMYZs=>`Hw}8d3#W%oKB}Vovmyzto6;W-6&KSwEw!uj3m9hKK)R3k
zo!C9bsC&KA5E_`@(fUdJ_3I<5z%$u2Z-n}GrzEq-`#J9#!MUpS6iX#c+Au`jbJ;zl
zF}t>~8p{9%?`ECinWnH&^wIJfR-|{8^mu%!qj{z}6EXVBy<=FhjMyme`Uv&&0%wE^
z&KC+wwbt>baj|^mHtc(1;5QoTkOY3}w2Mn;A`GRyq`t=8&i)G7G>R)d<}ZteX`W>`
zQa0Z3Z-Y75P4`;i(DZ_9Qt;(k=CbV-I5hPMWYaBKFl<hL{&h6AVDY!6=(9SvyhTpM
z#jbzuV6B^;jksCfY5W}UKi{vx&CQ^=vSTVKj1`S+^evRe{MA44Tyme7Lsm&6|4Rel
zYM{++7X$_GI=kOPR$vsllqiXY=l3xx@LSnKj-Mo_*?o|zUw3)^6%iFJ<_R0i@uwf(
z0gxr&d8!#_m2{>VcjJsQ@H{~9Nim!b_W_HOHdUgYK!nvHvIQ52GtQFOz_9G+bMJ7D
z+J@_9j(b~D&zMi|GM*kcCYb~!5<9zOIp|>924PsORPv{flEJR|ME6;AkHN>0#=Ah>
zExq^$eAV(ie(X+aNoF!a3|n8W1BnM-(3#Eq-k8To2}jP*y;sSSM8dnay^$5dqfRcc
z4@4@U0s!wwJ?21W%Ju(;zrQnQ^q(q~|Bj=`^gqK%U0Ra%G^_~S57ck)gR7>g=#=BX
zA>&$q--L3QFk#X;c<B6lS83~XjU^{J!+YE|Y2VVb((gVyx-deM{qZCOd|ezJ(YL?H
z^ZD!eS02WF7aa9$)AW3BV1B$4GxyLba^9qZGe~9DaunI;q8%hR`@O!qw$bqWA0CP|
zsP!JG9mBP-Ty)S+wD1QH%`#<A-XGOt6yogP8z|%##y{A{Y6UH=caFN>YIQVhb|fyN
zH9miM7GDS$`&3V8BsdmbC;(nDvD)b`80Is6uy*f)hcgQ|`hHs7-%Q~;VSDn&UaU;!
zWFY%S6Vb6D{mjb#uJhoaVl;7sn`%ZU#vH%q!FBE3TDnL1BVgcn`_KLs!5skYb#p=3
z5fu-V#p-F^TmyiuuSxx({fr7n&U@Qg;^z%<JgN)+zN`q!xIdbeJ`KvnE(HN|$1fV<
zXs94uZawXGb`^?u1R!hkYQR&<k+`COmnA|WTm!%x<4IhHM8~su2nco@P2&KsZx-eE
zu8Q%VZ|009rf6fKxD?n9uhw;FN$#^^UpjupP817~l~J*If#hujH@{RH#H<igVEq$y
z@S@~2@EjqLb@1+4P;M#v3t>)B+o#;<jrSfzhO}mB{+O5RuR3kMLIT-uk_h<_uBZU(
zZ&Sb!Ycn|{R<_67XGJ$VpehwcLNbuI%W^4SzcQtXQ+DZ4_uU5$M)9a`w-ykKjk=_r
zCQddh1^ifjRYklI56&LI`>hcbDZlHn=!mGu@+uBUa^u8+bSl8QgG@8xm&Q>{aC3@x
zlYml6)~bB<j&dIqnW1>D^8zM*MwAcbmnBMa3rTs(yq`(2>G$^h{_Q=F`<pq38K%4S
z=?g3ecXcc05J8`IpYs}2tvpd^I$?I}3@^+)GvG(U7)F4uN4mi5aWlF>c}-DKgH$=X
z9IGU>rLmvzUqeRvgFHfH*<O9ND(bG0FA>llciD-0d=oQ?$|FI5oZFcB?YfQ8COM-o
z3h=m{$$oaT^H%hfyo{r$FeYv?iPIk<aF!uQK(Q(XU~aU<H9b}=mfHIPa|!myvLte{
zDx41cPyLvkkl?rq&#Fz6W=s?Op>C8Pjs=2z`?vv=iw?@27x%ZFP58J*xC#nPWCppu
zS=cXfOdR;Oc%l|?(IZ<8+`+DD4Yeb#jsD$f)|7E&NSB}-5v8T!`ry^8!-%o+yVd2q
zB6Au{WEBR>!@tJXvbJjuA3vnI77r0(+?`s)1bU8(209WAI4(f*IrYc~i5(B=#(DXw
z?s1i=A_bZ{NpjcF?l|#<W{^I^9(-J_3ZXGW)ro3Re$HSw+#GL&JK!<T6jev+EvDH*
z@K_zEz)P=?co~zYpLy`GLftjjcxzl{&$IJlhUzH28;Sf-@~$$SQrnH6Dl-Ehws{!Z
zVsT&F+`Gv_sW6wp#z@Ry*<9!-5@?NFxj*!b1>H`;iF)j!s*Em%Y!1s}V}4WszSuNd
z;T>-JGA@{ekw-nC7qO;rkdw7zcB`Tcm!3J*cdMg3^~=1kU7&uM&uu&-J+-TLNgBnG
zrWMU5hslxFPQybUZcMxhg4$g<f4P)3??{I%SdY-<U~}9ckt@pzm!Tw~-Gpd^`T#~H
z%?+7onEZI)mmoXdX+l8iGVdm`R+CLn0Ic?tNL(~`t*Vu1D8J{M)uC)K>TLO{7M1&+
z+jufe6R4th!_iEaLIUD5S(_KNPqNw-?jCd>{4x23l~hHJQiHT@Npq6J@4@$}&bDdX
zF3$JWX|<-YCFO~Ar$O0x6qEJvZ`*XNz@v)N&!m1=6cIDgbk`2d5{*Q}(53G1n}G{+
zjE=nnonz57Z17_i5$?i09=2tl9_+npj(_J_nCG{cu)j6>g4nP!tj>^?tWMvOlUCQ@
z<KVyqgO=algDzXR&{PfSN-6_bpB*@BI}xjzb(dls=G=;wpBz!E#%mPTMwBay*->0F
zwl(?i5i-i!RWq2T-~CmCTG>M(wZej8io{YR7#rewTXD;hI2N>27}ulV2~_g|@LOWn
zqhT!2V~VYVF7Bt(*6)O;fcnrug>dTS@mbq{0Kk*rkjeF*oe&fIefR1|(beC2U2c<u
zDRgK&!%*wI4;7pyZt|-LgxkTe*cx{}QF&LEt#k_FjGa*%hJ5G#BecXt)|*a28>ql8
z2%L(r&Dvty0#{ClPTLg7l>&G3*d=u@0zXvwl~nGfIn_;6pHWxE<!PV6>e;mXqrips
z_p^7K^;ylJOqf?)ji+gQk%4F!9I9Af$E(m~nH{UyT0uk1&L~n>S&@Xku?LNpSfDAP
zz`I5`I#kE%Uu0|c9EL<G;C34f-|L)M7jztw@Cpg&wS|wU(^1hj%-DO4TrPI06R{@P
zR=gC<rw;zlRj=PY4<{(leMM0h9y0dTR!Ed50%81Fe|}>k{b`MHZ7L&sFq6u;noZv1
z70!7yQ2iDED=EkkJ8RG+&&X2`UP2dK(m(`fnIHmJ(OrXhMRb|DW>E>TQ@`-3YDTjx
z-#YSZJYHI^Jd0JwNUWhyjPRM3jr8NWSAY>&ER{m*mg>BAC_+yhcH0SPSFQfaL%_Ww
z#NtOJ4|f33AMMwh_TdSO><X<(tafaAJ}B9S2*Q-z+IL76tXQ-U!xos%#^UXP9;MMs
zvk%VxQT3X(F@*D0DQ`<<-^$r`Y&5uD^59LZeM-SguF=IRq50|WZ;eo11<{@i39w$y
z9%+ADpjWjRQr~dC4JXT<_Yt#X^Uh`GS2}0icjaYb%iwUKzX%o{_LgzRn~btKw_^!5
zM#yR0;yG=5M?pav9>&#wVXy5R@rxsIw?sbp+rbXFDXC_^=Ery@>Dd9M5w(z``o03f
zcdNd)TlYH1-`emF`0ISa+biJnc`44^ykig2VKC-Ac_|x;hP1g&pvYKl=~phl0!Qhw
z`k8&dP5}0|+W&7+J?TL%UZ4}8>*J26+pK=;_{9DT6c-hJ`9Bpx{}r&1iG_{v{~y^L
zX-mfvw;*<(s6XN>gwb^WHiQGi0dC_=*Nz)_l=wN!yVSdXQT~a{uAb-2MX@vk8>?5M
zWzsB1;#Wp&o^2G7hxk9D{Q9mqds6>+LiY1(d;8k+e7o4$ELzG^nO}G?o%d><mIb$R
zvh?EnyeLcR*cIm&95gQ~<Ke;W?I7meBd09Zztg^J7-I8Q8mC#Dz@OMq@mJ(8Kx1l>
zq9j?%93Cic#werBExtzo=-eG;j*0rX%r3%TOmud2J9n%|I`b_|WP0-F|Ni+cMf(Jy
zYZkFqrrEC=EKcJGo`ZQ-4$h0!-xRJ#!4$Wb-II27G}v>fZVEJ@PowrKb4U`r_19un
zfgOT5L33uyyK|_Mmo~1T9PUlCEq6ScX8vo)OO_;i8C7(AxK(rg4S|nUNw!E8w0{|z
zLV3B@-`HMwSvSo6tF=gW5Et$1JnrqabjaB&A!MnPL<>Q^D;T_D`fM|KUz^rCG@vu-
zu{j_Ij`6t1&%w}=>b>I>)ObcF&tqqhnWRGdhwM-FYfAk;8t49froumdunnzwJr;%U
zB2Aji;X1636$BaH+?<>-eSXBJV@H%@mTfuc-#vKuHP?pNvQ0CFo<}xUr36xklc=KR
zW(`-Q=cp~TQr9<-QL!OVrl_*nB$ADWThEh=Wm;K*N0q|TOG&%tMwLX`kjm`pFPYkC
zMsA)@UoIW;m2eQz^l!|3#JHp@N<1Ye>Bi_h@Z1Wb=+&qi1^y$yFtJ!uiBKdfoG3%>
zl_ca5Iup}>ojlXS7o?r~-JfCCnF|odZ=r4nfnS1iv*bSRa`tRGioX8cjTEVm#>IjM
zaAkf^BhI!NzVGa^L9+3XX!S2H<p2g+AAgWQlF#)%Q}4ZJ&_3wFsU5b&gVG>AlkHuH
zoBLuRFf&-jkcrChA_(6zyNJJDM{*AekZrhglYQ|caJCzu?130HGMd$)4dBO%<DA9T
zt54kAEJqDP8_nbNIvnVuZRH%Q0dH~42n*bhcyn`T@aJ;CW_beLZLS|2=(R0+=WxJ2
z^<!+UM(f4L*aVYvXZjNVvvC^#zWe<5(4}y(88QHC!$zjSZn19Q%PxI$K@gum9M$#s
zVmwt#H69T1;ak9uc5fHwqwes+*mm`uy4ix-t$-S5R*VgTshCI261H!*+oD~}j%_CJ
zv*=XY!fa8<X{od~WTS*#YSBS~sax7VtkDV6UM<ksx&$58ae~{MLNbhMQ0y9p4jr3!
zzooIF&q8Yw>(8g%?#fkM>e}?seBfVvZv_n<x3QcWnn_g>)~O&llfu_A+OCtr{0)|C
zL`T~U{tN=_jb-{xWvca!BD<pkZ?GQ)hPBu4r2As<0MaOLMoUM-G>dJ%U2WmL3Fou2
z(_PRs5;x#-LxrarQt^<Wwb`pFDi_`{E2-PCodUqMD@S#`&}25DhgRJ%U8G&#rcxaV
zn0aG{9zKRBqolpS+GadntxRdr1i|JGjyrI)cICOdm?|DQ$XqC5u||KcZO)(n4Xn6F
z_B0#3lcsu=t$mJ_ht@BH6uh&FDy*6t4zT%_M&F^?5^DS>30YPJ>t_|h7uz}-;d>xa
z<zz>wZ}q9-zFLu^sSE>s`h|g<yq@Y8;gBR154V=ANSOU`B}IrGgT}BbbDt+38kQMm
zfVbkwFHEVR<*~1-moiY?VWl8Cv{i&!l7g35&xpNK(INC)?r|ip@B8sPtz@ul<2B4o
z;CpI@AHulW34b+7j2rE;(~{X+#H-Y{=!ErvbAe6(?UMMO7Z=DJ^e0p|Qq;$#H)cR_
zSRbo^L@~3r(3C*I*P+k(D>QMh$!V3BYSApU)gkmXoacOlMVyQB^`;2cz(U|6+|B8t
zRG-|KAzrPS{nPx7oUS<98dlCUhY^Vp2yD!E{VBxhvQpJa{7kd$ubf#>W!_p}@ndsM
zrNBgG)FeG_y6C1xQeXk6R-6(Gh=TbOftKYuYIU?M19nuz#+jIDOzSMl19|e=%Ol49
z9k;`=;Et)lcA@^8n#2Z5y@3><-*a5e?qK%;IpYDt=#CT=Jq*N>J5h&^pE^s_uW;l7
zm898imP2FRa}E`pK31_&)8wO%+s}~)D>-p5RTgd%_h(|fR=R;3gG}u67XluFvfSx5
zq4a#ZLoaoB4;XB^-_v>l@Q^|~CX!eKh9X0W2p-(!)31T}GFmBUY@k=4zT6SZ&XmFC
zAX+bi%c&8xq?<tqhm}zHA+}9j{@V?DCQn`u^SVX93PQDQ1r}3u%~Fzze1L7cMtq;R
zkXV@Y(MS{ok?5}TY08hFDFjNP{sZqyZE3ttQ?z+qGqmVtqeX|jUX3KeJKkyN4J#-T
zV;zFDMisnt9BEBRWQ05&q1BW>x|LQIPdqjqHM7E@ul!K#!!|3Oa4YxZDO>~K%<Y}0
z>=L5rxBH3izCe)i%wEog_Dh`y;>+n$!>OdIr27>6*V~HT1cUTOsqddzz(C&=d-K|`
zXqNA65J>TvFC>kTTGd8X_o1at8g2N5Pino5ZduD_v)#$-F+QsPI$3Q6eOf3OS))D<
zJKp$arMH(|B)yyd?n}RIle^!oow#<v<K<`i<JndEqh*?8joCc3xV%HRZSw<nLw4Aj
z3?0wYTHxN(;!%*{k<y~p17u*X7kw=euW63qD3A89y&Ww^#%a0Cz8$FrKu<Ym2?uVL
zT*J9y_H{hl`;d1>O7Q2tHT&<{*Iuv*okrZMBtV<%cVqtZzgfJnc+s}awJC!bU-pXL
zwZdztIW>{%t}+HS=k~OG0<&&5uLPQoWFs12MmtZ#E--f0XAySmmc?S(@~1oH>ixs<
zSiF>;=A$y5;YeXxsl~3U!4HRI6wJB^ukmKolC`DJErJM}r`bQ4)yZjQOE%Hn-z=Jy
zd{r6}4rhoXTG#Hv1=KS(Meb0AV+T;tKoW=3+vf=z<dA|oJAOApcUIb57+I?!t@jvF
z3GLl-O+KI_SIk*m0wy#^YlRTRDy8=MF=usZb5t;b%1e&gYElskMj@C+)lBPd#O)|A
z(q|j1E|>qb9*$zTP5*YB3$LAePS)<)qR@&eOfM>3?VN{ySU<S=_-<Tgjo(jH+tzWh
zf-F6Ky0%q5v}>(S0ylc~FMs1ngx@!V+f~+2wOd5QLJrm?glA;fq~8!$C8NW@NT@bZ
zq=Q<JBNT*NSyRc3%sl~@?oSCw7_Dr>Trgd^#&d?BHf~w>bi38Rf2;l)Xm*l@6b8c9
zQp%AA<~H&Bn)v>8Q+G1_A8I_d|B`*l@IPw2s~?*;&i}c@o5a^pE!YmI3j>l3*q(n=
zd)$5U^8UXz?;?_OR%DLp>2*pilIO`&(TER`c>Q`Gtwo}{SS_Ai{Wc!I!J3zU4<~Pw
z1$B=bR&Q5}_ZRQc!!z`lua=NM(FYs>$np;(8a`c}BxI$IqlX12O}<VMrzK6OJh$u-
zw_J|%()XhgcRxiAS+S-~eYD~qC^aVqbyZ)=!;QOAV2Tp&ajCmfhVvI2IVG#a*)4cr
z(z4&x>H+>s4-Nm0JDF-x@?DYEw#rUzb;S>HI@hI%Vy2vC0{cyG%&S}y=b4jvg9PxB
z=leo!Yh<yew?&PplBTv2>gQIc6poEHZwEgS;35Q?w&MP-0hWXgSH}+k09LRH@>V1-
z)Q9LqR_A{od1ji%>!=ul(_1=tl-P&pSMzqsS7t^p=}I87RcmjzsIxd8baFoaiT!YH
zlI4N8^$O9chvs8UIg@?>)?wmnj{BSs_^?F$Q?R^)(IYSz{*NtSxoJYYu^82&WBq>R
z9vkels0(+xQPf2;YJM5Y_782a;>=KBmc%+fyp)*t3i#mS;WdQ$$S-%^<#UUN)qyXM
zU*xQW$G>R>n5JErVs<U}&LKBbi!%#1QkDDP{IuKlB0Kgyw;^y{)==Lvo`^sfA^8hs
zGPu2-B5=Yo8RTCz$wbyig}KG?#Dikn1^$X%_#}}Q2tccJ1^nvP&GQ=vW6kH8G2z9I
zP<Rn&@X9As^YHIb@t}%{Ka!m8F#(@zP7bN)E6>SE27`ac(8_Ihmq0L_oTD*METe^e
zL<I~ZLQa#g8lnqAvDzHe{)%VykSM^iJ9#K;>{Ev3b!t0{Ts>+W+si)U74I9FCM*k9
z8-r&QPxX;2PiA?D!wrS1j5K~wthw=8n+mlfAKh3a*IN^|qy3eKJG~Yl7$gnVO>0Ji
zJjT<IMm^JLtRg3vP7Xw*4a^x#CtB%&je>&%Gj3aE7^naMsD8SxA;EZP8!YbjmEcr%
z8e88RN-Mq%qD2lVt=mJkXi+S=DIrBjR>+ngd9|$l&Mb-U&ulI?+zm$!PWXEJv`L4z
zZ&^)h&{it=wN}KyWMPY}f#ux|2ItlMaolVQhsUNqfdgT|<1L#0VB5x?yIwX&>hn8o
z;?AHCAx#?3KnkHQ4lpv?*U^mDnM{9=+tgc(&+JXuvK*(%G|8sNJC7|Yr@jw5<#KY#
zS#5T6r4o-)8SvN-(ojGCwY00Yl)|)V6s81QSA5r4#tkr3Qd7H91%{0E&4;_V>{uCC
zY+=Oq&7QoQXn`~6hCuBG4cE%t(@NK_uZ!Vi4d0Yj7mqm3$S<D=Ng(Q=>7#n;FDA_d
zS?UB5tcy0BEy+vNT0TC>IeRn0%{vBQ=Of(Cv&}Wva-+5IcPl@bA~k-t6WC^B)s(eI
z`#>=?L4PK1UiRyrCB3nUtW-O}&1x|y9=!J)9}JNqFYj)`uyLcyE!8zr%J2mR7!1R#
zxTE{Y$vW&GTm*k2FkGLqm$v+<wCBFL|5YolVI%1zsy>^w4j;Lfv@VOSrypd1T+03s
zjaoYDbP~7ig`KOroP~2P*cbpJE3F@NGApfz(PaS4Ui*Gm%fF^b73)jOn~yXb#lM3`
z_Mf<mJ6O;d5jSg_<{xQ}ieZPn9@dl8P4&J`I=?QmQsV;<Nnl7^EWKhLm{<gvJ@RJ-
zlL1CLNsW&NK<fB9okmv*pJqb24-Y@r4xXz5mGm+W?$s<a`YIuZ?8o^Wpz@_0i`z;^
ziy%25ih5gAn~eg8kh*$Pfx`IACm|2$-AB=5#E(AEQ?{AKdOJ@g_xTCFAqW;$DqZQ?
zqq^182FT3df{xLi#elesc#W{!hj|@bmP~X&Y}Ki2Ig9d=@uSXs5!$o@XDb`2$DjhG
zqIwfX64wYrOTxs=(qJ;WcUf}Xj9t`^z-nCG;sI$yi(Qnq3K{oPrAm#s=-!jz7rN%8
zY|{3$u_;?>J2H{eQ`=cneAK=b7MGBebyswj`oUY3cr+vYegQq!q;S7>yl<$~Y^za|
z7=RCTaPlb_?6RLKopH0Y5K$ZN2rF^gT7X#LJlWMQT)~|<SKn+%^Pa87f`h9qzez_#
z)*OyPW>z`t0C<fANhX42>p5-3zue5HyIGCA+F9dzx-gw}9mvBFwBunRZILhbh^W*F
zaCGSH?mDK^Yf_9<S1_ih+m!5Y%Bf)r3iR}TOkOosd{IV&>TWF61uZVf`el-w4aL1k
zzY=|L|9*$uG^~#e)h-hDy=4wQ-TyX;BMbDhPop!LG<q0YIft)WhwO;{W=jzndan2v
zyTA*fk-sAB$o|iHa{glZ4BLw!OBKjfs9Be38Sb2o!0PTc##A8^yT}89g+B}Y#17CD
zwJ<45uC$*MZ$k8h%O;5hJ<G~0|C=E{i+0$uk2OoI)F#4IP~PVp4~;)GOAYMN#y86<
z^+rH4L5pRTy=*<>jzgcD^-e-#POkMnGy%eE2M&&hp-k}=KGg)f4HrNE$1Oa#Gw<tv
zdb3&nJC!%f|2X2i(j1GyW=H5cp?(8jB&%!%>c;^Z1aop`Y9R=VH+@CIzm)dlSEW%)
z+}fwfn2Q1?sby7iE{|@ydwR63Pt5msi}>kc9?z(Gee-5g8*c0uvWN!HZpI4I=LRj=
zxnUMoAQ`6#jeWnY-+bRVK7F{myl=>@k8SF+?c@_-J)ciYvxn9+v+QF1FQXw-_|`Dq
zCA$&r+?GxBOA(^}0$@O~BEHD_^g<`#8mioKO-6Cih&q9<qwXdTB$P+6!(}*jK0Mzq
z9w%ro4zpjn<k)6@=dV=6Y*waTi=<^gRHT-|M+OeQF#kP>OrnY5oi%0?jqT+xEY8LA
z$hU!V7yX*V7HD*p<a<Vz<(z0_KxLJwD|6T6<jz3~+;bo_FL*_n<~XFm(e#<iO*uQ`
z`SY%es@~cmfnNfi>>TLOGc5z+yu|zPP@MHyn5EA3u4ih5)qul#42_At;}J2wU%de_
z$${Owt$i`twQXhY_AeWhUtHxq-U0H3RVhlOKtu*VeIL9I5MmsEvGu;X057sb#-!X7
zTd61+ysPq8aI5tP<2S=u#a2(UEj5{78{wD+fkwP_iLh3SbK744fZ<XWQ%=k|d%|Mu
zvM@mhoF*@IUZ{|)3a&$28%~@Xt2m!Q;Ftt!2215(JWx1~C!E~XUiM4*?I~Lnr5sAs
zwX@;Ppc={P>6oNGWUW#MbONWqWQxEC&w2iyPUC7QJq{wexUF&kvk99lQLsNlMK#{M
z#Hn5B@Unt4*ntU|kYLozSCBs};x2}0e4Osi2P0Z?pUaS&Va)}Xa~9p+^w{Z`9KH+5
ztN7!H$VER~O-w8m9k@pCR((M^4?YsOJq3UUuMWu%6)fi9$jmMTpGK<WAswo3_tf#O
zL>r=N@S+HhHfb8Ck<ZFzXvab(jk?b8fv8l{ehH>(;%CV$8(=B#tN{hrg8BU*3s?x`
zCkYDeC?VEbN?4s;<25Be$uU%QVGeDc3llY<z9u+s{k|Pi_NAzfxQbruP+&dJuj!m9
zBZJD;QX(#U9{M(rv>+uHxKBcvFEOYOz_AF~F1MUHW2l}t^f$9Zp!8aol<&Ay;-Af1
zu3EY$=XYdiE`3i-diqmfSjXpM*EhC<u}GToZ0``fJ;TOEGz4Tb-+EIysrIRXoDZ=|
z?tjH^I*6<FB!ZC)@>Olur8}pJVe^_L#rId9mh|&!)ITWO@0|hT<Lf9ed8dS>17Vc4
ztRdu(Ox#cqN=^XQ>we*7X5p__7_<gGJE*YhpRc^CD?CfpGtvDrbi!!!+w%;q{M1R<
zNXDd@sJeIML9J+*HqHp(a~ZbH*=)rg1!#Qp@YZ7JGaai56P<X);A`;E#sN%Se;n6i
zo-ZZds{HAAKRZ-TJz+#^+?__T^;KbM5}l)(yuZ>P@5wBXB}svQ$h<&lId^AGztF8g
z$R=HIJ#eFY=a+sDC=@OwA5#4<#@;D9v#9IVja3!fw)MuYI2GHrZKq=AjcwbuRk3Z`
zIJN(CF7|iYck$n?``K3ObM`U%)6-v^=<gyCwNYUgIjdcO43^2q3<gQ+)fmN++|}&g
zTjWW{>;ukK)&%U=O?fy}S3#8{N*(6*um9ebo0-^$cbc_dzB{v}Z!ftmKnZ$?QJ>U_
zw>gPE#ig0+uaqnO)ZKo3H@S_xPk?Ua@RE|hr!}H2o6`Yy4aXea)>KM<^NiZ}@sY??
zqTQUrO%u6jhcg;rvhaJ|4ejJEYE>@@W{br@9Y%{-k6O#TX-)kAdsX<kQ*{_CR|{+4
zXPlS2bSQyn8nc3vReuk<X>mg;ek;(@<wPNOHBI>@<vaf98)U9?=@nXdDyBWtSnb-&
z`2@5!O<jh^u5^$z6FkBB(j^u=j5Kw1YROqp7P{qaAse%oYGUOGARq{fG6&=Yl;#CY
zs4OA;*(D?o!o%$xic6zY_7_<?S>z|cy`pBd_FHv8xMt{3$h*&u+~$aCy1TfT6`87k
zA~r`+M7*a@h!$-0U${KN6iJ+_vk4vKv@t5jWwJcVtSC(bkqOM8lBzt1Y;(x-<ERBq
zD|d$XQDADBimg=Zdxox5+r|?_T-r9`8{hof??fcwD}*wm-QD&w5U0{-J;CThSrD+h
zurUHf`C!MMp68O18+!hXWEZTVK&hz9M4yVD#(IqDoI2B=&^Yrjt*BPyhUuoM>AFtR
z-H9-MW_9N)h2zXm^|%e?A8~6k1oGoN{e5pD^vF#Lc=zgi3C1!{ItBE#+<31fZCFdt
z&4X9*`uj=5^J0Mc!2Ye)ookmgRe|NvOiUZoOtHnX9EqKapMEwb3S@*(6Ds;S<>j`W
zrUM$TxMDT1BMw4Z@e46&ejFP*tbr7l8cM;lo3-ljeP8Yyq#Z8(>c7b%$Nx$eIa&UL
z=ln0*?({$XN@^E`OwwT9)8^hMG8t+A-m*)lef5>v=^~D&+l+!JWY32Z$q6y^7Ac6l
z{Qg8?o2L`T6u<pU;RL@uJzr(q2v6=$GkSV>e+ztLP!y=ljmgLzk71c)We~KE6`h_w
zEDN2-5fBQN{7N}#0x)W>mo`DShmQ2*_);1oLIE3C2Kt&<KW_W6Whr>|CctV`2f7yw
z#0m1*J9+szYqj_&uN)S@%}CN<*bH|sI2oTwn$qv;m{~s`El6ss_U%GHE~g$wLZgRk
za;mXjO(MoU<#2@Lai)y36v$Q~6he}UYii~_-rV7>90)=TUd9K^==HW;D@$RBKws$m
zNkCDo17hMPcKYi!v;t?d%_kM~4?2*25$6W>Z?!#ra14$e+|exOP+ww9GXQRqu(&o)
z$&>Vpy4_22=dwfe8)a!t^c+?G@q>X^_U`~y{n72AU5(HvIE-UWBSD|rIR{#7ph3KK
zvjOwjN-aI*OHmwH|L6^Zzx&y}YY5D0?@&fKbU}W&^q%g|Dmzo8dAQ;gY-71aAa<Cz
z>$lStK{FVpvVW~v&AJUl-`!(G04C3vW%*Vb`~Fvx>#|rOV`4<*dQYMd8R%*<fQD>C
zKrT%6HLUA2=Tt7jO9Pa{jirFMUVI+X6INmCr>PV<9#)q2rJ+yY)bH$paIYx)6H7<;
z(t_iO!1S!cUg#MUj++v^WTJyv(%d-97^A+@bi{E{9;GV4W%<&P7>hn!KF)~NNP;n_
z28syr5?PkYjW@Q;*0f~v^4-LkKXr$>E1ptkN)rnsJha~=&%<zcwEEMPRw_$7UerA_
z#Pr5gl*pQ-RJnHZ>VeLN$-m)EG1i$mbcc2t(w>br<VinzeYGtQ&@&skHM1bdO1}Dt
zUbbD^Pk-z^kT6R*JtA>hQJxjMV%8JOP2gYB>ZU-k?jRg6A^4VC4U6gLnJhoYtl3|w
z7tM8%^V48fi*)smhfQ{Ba^p%T+vzkO_m7`0TKEYGEZVA$vNRs-gwmRQ1-x_v8^bhJ
z5u_TdShUm$)TeNUyrV4V@g(k7uqyoF3KyhdWmkswXzwbJRv<KJTGsozdS*-l6;7VY
zFAujad5o=QWHhlq^$W5<C+mCb=D6Kz>&8$ps8c324A*WddDp@)cxYWt6kWo}UTNJ>
z+|CJlR{k>Gmgnn;&qXgI?>dIXDK|kq3Y(ZNLK8P|YO)FCrc=}Y-RTAO{=<XON_un=
zu;f2fA9wFc+DCkhRFZu!nLK_oW__Y<W^V*6IEZp$@(4Y5ijb`1*6E?u9L<7cR!U}b
zZaDZPiFn_kTRkhNx616mlM#9_Hr~rSmeq(!faRZs8u|MNz#YeaU<4TxGXFHI6nBBW
zhJTj+*Y@TRgvE3HhlzL4uM_JR6vBT0gSM%Z69^6`35>qVWD5+g4)!Q|oj#5#ZPR7E
zg>et+Cuh^L#!XI_Mdsgskj<y<$Wbqd#yt@KC`ly>_gk}O(Vw0L!6wZ^_VAvFa7k;P
zWV09SPvYi<s9};9v-da!OS-b-ky?~apQ}z#wM@op&y7zqS<kRY_e>bMepWy1A%(Dp
z5Jg&5J*axK%0jNCW$<K0ntF#hmvDgWbvGX7@E@@bPYPt^Q1j3bt;eij$8OeRRXLg}
z+?6SN8f%CbULKk$ye=Fhbn4`mqX)x>FqI~?3zL7q?7P~}Pv9dntfZJCw4ufX`8wBg
z4#Kr6`ZnLp61*YT8`}w2wK*~fu39c|3al--cM9Wd>oN=E$C;c4!_J<mClM4MeAjSe
z^od{Wm&XiA67l@v0V%EvG}a`xAAv4PRu&m*p;1T>o}yLj#F;cGoR!@iaoDJ5aSqjt
z$Q60*Y}lO}Up&ti(+a=mxhys+yPFgh@oE@PvJmX8aOu`VX9!Nvn}&Sh2XYeqIHs8q
zUhh!e1F21VJsP}L3*RR_!BB3Iw*5>-buQ^n3lP`Tpf!J@G3O8kSS7XCqOVTYl}t{U
zH>Z?ZkEF@=WidoUvFB%<Q|~{xc5New>%_xOd(FTx#8xa1FLVqk9Vba%g^nbr&(go>
z**2vO*$(v&<9HtF7xJ|A@EWBi_6$G~&tO)w?YU&^dErOWTVJBbH0g}$t@n<6sB;(S
z)o_qY=JoR@LfFZPve9&FBXwWj{|SZ*6LB0586A?9QZTYxsT!GQk1sSb#mnLJsiB15
zVZRcvFmKp8^#24E?d$*hg=S7^tu8S@fZ>93gZfjT)Bfg4^VLZp?bhO_aKC2Vw23=6
z0w|f%7W9gj+iut7ZPW7lLFJFFAyt-R4ITg1cbY*j$es2Cw6RPJTy>rd9O&PvMm`M%
zF#DHVS{To@5CoxC=Dx>=bx{?J&dU1sU2o6jM<8_v&e__dPldN0JYh-Ou>zmaYE*wV
z|BJ+O{O{aiPPYF{RR7;@vFJayc=!LM$N12C-nhFt{eNz8=`rt;j@NptXk4Y67^#AH
z_yNbp=|mw#`1isA==a3wDeIO`?@Y<!bBZJcqVJnigl4ZZl32&-ePI_e@%AV4C$~?g
zuXpNJS4(07$#`jT=zZbMTG?rCBa@UI;>h+@p);I-g4E;SHqO;QYczw<B5p2&?ZAF?
z{T;-OH&b<#d!6?-E-ej)v&;dDps2BN1ep;3x({`CMHT;D<>e%JIiTh=Et^%#?Bmb-
zHlc5}uO|_?x{-}aU_`%#x#j4ySHzAePB1f|LWm<d%!qy8CP`9RJVkf6h`d<#<I+Ru
z09%q;)>I?Tj_NLs8+@>HjqgqsBp!x)UXm?U1seILSt{xJ`8TZuA#{yAbDRl_v4Ef7
z>{{HZKTxiDH@;AB2QhPk%3__SUHS>O%c{2T{w(bu8ZIl(<7fO`YdmeF2DS-k2g;07
zFWGN)Ck=4c_a8Qy-lo%Ve972WLgrJgn78x6xtlKxeDj^zuWYOK+)gvX0BEu`(iBn2
zH*Mp#Nv|4s9nRlqiMNQt;#mkq?95uzA{1H8Lio6=HtDjMv2jv5ezmEcW<8$IThFq4
zRkh;=XuH29#L1Y6TAo^KULWX81A~^^h(^t5h0xHgu{cd2{S~s(fAdo^@CZ9*c52jE
zCdWU@TNqy-n4OhHVd_2AlDEw%{MzKCkB{bLk(WFB6SfwPl|HRVmT2Qe(Ffh*fqs&D
zJa=mq6+2w8xO5XrHT&UcqaQXpCKo5U`#Gob6j%gL-k8gTb#zm+_<+gU%SZ@->hW#=
zhy106*~hyx?5aHhAEpWLl7k8s+v?6PW`!!JZDz2LjY~VrVe`T2Yoq>nt-2}cC9Bt9
zcXy;KR0k%`vdC!E{+KUBc1f?9l4(6Eo5e*$8UF6TfLn_>81m@8dO8A*_!eHAIo4vg
zF$6HqOeqY&Ka}UV_0d)RFiB=?qb2m!ak8NmECi`fHKlcJNwEnmn;1_>lu%s@?dEc%
zZ<J}Hs(iwTXl5CMUZH*qnEG_G*SxU%hYQ45?$pGjn0=JOcA!6r+}Pe_HA_Bd@?hUq
zmxDm>&O)w}MR9(ms4O)>>jizusWptawu)tU{Jj+tjES=A-Sr#AO1qL@?W|*Sx0#5k
zUwao5&^SjlRitflyT4?po57nb+IXkV4!yn`$a_O49C7lD@TG@D4TJ3&mUP7^Le?9P
zB+dU=(<_k_Al;TEMMfz35BFk?k3-=pLn2Y_WbL$?vfrSjs(M1BI1+L;nL3$y_Qn15
zzRW!_#b^d1OAoK5GV!L#xJO++IoVlHHDJqn?~W^t#;Hhif8kP{t1_V#ZSFEQ$q_j1
zipUL4LBHS80&1fFypWiPI-CquP{g=ZJ<cTtLV1W{D%FY`VCYx-N}Y$=y$1P5=5WPc
zJ|s;MNM)~9F;8#2&qQfpq5vwjvTq5~@B?0bArS#65zPiEjkI$Isk*Pg{sAS(9I6q4
zM;uLi!z;2+CJEIUWUBnU2XgczoU7dH(`oLNl-_b_eFRmkz3BUwBNLk+)ZAdN-|ZQh
z$69nN_~G#;;TPkst&e2BxO%#{rib3$ZcpHRqg%g$lpikVZ(LI2pjz~j)%z!pc1Rjr
zCd~P}Pi}q-5BjPOh44aHVk7t04)Qshh_OK5;Z40*n81U;JI%7}SQ)RH9NQvfd0oy+
z+Zq%&I#?fi=RI3Ef3dx7ED(A!pZ1VK&DG!3pVRME%hExmTmkDLY`&;boevL2mw8cs
zP9WiN2pKG%$U*s*u#3ISq==VG(*Bg;f&O_yxLYtXYtBjRc;yMWKVil@bnjT4VF~Xv
zd6St3uX|5;nBEvc3XWP7;LiJZ?mbT0mhy+#poJJcBau?*xx#!}nD@y6Ms#vkn4twC
zWpJ$pqf05B#R@WA+3sai!*W)U6dI9ywDXmX7rkAcYr?8T#7$b3Zs!ZaT9$`x)7(y>
zGh)V~@ERPAqgdIMDoX<s6y_e(ay4fS61ONs4+`qoP`nb@h3u)C7<q(v_6!-C7`PpJ
z1pCBb10lCcZLU}AJx&e35XeLX9K$b`+AadOEkbvczje&dR{I>i;v21Gyj88-p$b)1
ztTsfdE;r#j4B>v3(-WO&><z`ub~JnJ2c=HC#mP91c5kgs6^WQsPJZqvqCV(1#23x?
zsd<$IQ3L1WTl6wxhSAOeO8RIzC+Fj~_}sDhlM4AuQM^=>HGRD-=EpD17f#GDb{=_;
z)>eLa<1-)+<R))M|L%twH40QY8LjnZa2<ys1Fk_>Rz)ia?z@$E8p(Ort}RY;x`d4_
zypL02o-AJrpjU5&%14#Jo{zpj20Lx{mXN8mtCs>8DgngN>{Qn&3@L<8+pCLgBY(l7
zWoLVLQyKaYYO5yYCbIk6&>j%T;!BhNCcghW+n0;w|0lj&PFfsDSNF7AghWyAsefxn
zWiHa3Wfx2oPZSK(TWd2uJ}(UGI0=NL(Wuu$M)D>0Kv&-1Di81TF<`$JP}n|34{u<*
zef*aNO0G#XLVL3Mwsq<Kyi@6X+l-Ho$>GjF>l=iy8q`aIA1vxLu`-ew<t7|n-C=jf
z%V9TbI(^gwx_Y)4ueU-)`wY?+9R0MDP?p+EN-ANd8J}bQHYF`$-?Qd1_)jURyOQRp
z-8Hmb+#aR`_E2@}Zl=tsgQ~sshoCg4<kVJjc0R*q+*5Q<0l24P9ecLEmi@jZS2)nF
zhm_ulWe;&mF1eI1w!B#bGw!q(AMan!hb`~Z!;0q0g~W%hdOhVd_#yGtrBb*g0oQ$r
zrO{-y_EJwOu6GI$_<+IaF4bbHkcc<Kv|c=YCZCHeaNR3q)sO|7<fvblm`9dRx;rEB
zC1x9^Qtaln^xj)%dE6vYgo46eB9WHoAqYnviQU4XYp3B~M}4Xn9!&_*Z2hY?-kg3F
zwGC3g%ov>&#*s~~9j@~Ej~wIJwfN<*CF82QHkl0f7ViSK>U$8MWglD}L|;0?!X)>5
zM6u}=0~5e421i=GHKQEB7F5)}biRVi6Wg4?-4J-;E88Na+-FoD%gNX9LgM}aWvY3{
zfxSoMh|+zR1>IJEdg~Qj*9YSA+}5Onj(p5Tp~eFcxDFe{1Q|jZ{*Ivsh5dbS1Ogiz
zZzXd{y!Xa26;0qh<mK&^6Vg0l3Bi*|L%B}Ew<ZFD>v?P4PZEiwC8#3xEZlC<V9AK(
zExk{cQQ73k3B{%(O9e51D17^uc;?UQqP<tulthF8){BjO$NP;*(X_a9xYX~*sG$*C
z6xfym-Zab@4O#}2woDXR5hl@#|KP6{SOqE6Ta~@=l$M2axsMj6pWBKkdO*7LK6Xz?
zn`NbBG#l?A*sdW=5vZ52g(}PF4E#c#sF<xb=>Q&`Y<jWJ!fLJ*3ONm#I$kS>8)=a}
zldqD9HaL<>yg$@!a3Am-6K!dCJ%qq7h=C)lsjNCA%Rg0BW<AscLo$^N{|YA*Wre6Z
z^;?02hTnqe&ajI$>gxGYBqk{QS}bjA-Cn&A?^dp#^F_-$YoQC~RyK%?8#QtLqYmH6
zx&@oHL4kHRJ(7>YII&5E{`A3>$+gFI?xxX(huy5XX$J}yn&t@%P8%tusJrYB&vLQ!
zLk&)Ls1?914x7*}i)pYXT^+}8Ol$MGI4SG{?Il|SKyzXU6!1QbBDZXV?(%q=I;UCv
zv#?S4nu|P!c7!zI7bl<ALUt(T`eetV`14SXE5SG8^_rNoE!H$k_YC3&f~_)L%mQan
z_vNRA#~=pLYR^Oj7%1|4t4)2#MzRhGa()GuwK{fQ=`@&Cv!PZuhGMthmox;x?^nCv
zy2w0U3$-@KAJVedj4mJJCWJp|Sdv^lAB*dp`xrH4ZvR2#v7IsqpSiU}`1hMUFK)UV
zIv#YjNENj^V$gGsN%AFWFMpgXUu0^bnG0BUjnQXvS_aJOY(=rIr;=6PGBP71O<;8=
zKsa_9Z{_N8MmJzQ?52BJSB!#Dgj%1QsBgavI;$jzjv*IV@E0}|mR|ZkKzmN3Cn(a?
zg?6D_E}vtKlWQ1We<$B0f)=Tt2x9q1EW~+Jf=G#9cwE4OHC6e*a~Lk$iAeN-pYMh-
z0~`MusGHXZvf)pwxC!UJ!Pz13(Frz{?<tCK8dBN5rW2{@4fV3zIAFd1)V892Gi_C^
zN9s8W1qpCpBJfB*-?My;rde4l_2&@v!x?8s>Vp3$2prEk_~m0432I?e?0V0ksClbg
z0F=<oI*91DIrUm|ihq`|@dR-ERFaxTrRRuxjqs0}JH^*JVxmp4aChTaLWxQQ{DX0C
z<Z@buLk~5yXN>GcI;PXFojnxb3T*IVaJyRjV1d}$&o+6?tdQv^e|+`s^^U>^4DD`l
zfMNW$$L_k2|EcSVp~;3^OjqEmZ2gxE3Fd88x3T_#t{p}MGm805t01!K{VVw<|2>@H
z%l?E!#<jm+VuOp3G5+3B#*9*x6AL#IVf~IY6*RN!&oTJFFkIc##hb{)Bqu#eFVq11
z@9@yyrj+bB8b2-Xuzrvn1G{Cjh0NP0UHD6QDuUro9kr?Z>JV=BS)L?NT||4FO)Q|x
zD+@sU3dk0RQLbul@MMp9@#kz+rEN71u#OrF^1+?G+*K87mE<D0vTE*4_n%jU@&DF4
zYPv}TTomm(f!_&bu0{Bw;pNe0M%O72J!R8{(MkL}Xw+p32ojm;fKMz_lxEHi)!nao
z*5;r+7Pw)X9qu5g^DKi85s3V$Ft`Y@_wpce96}2qZf51kv@HbEQ`eC1af6?-bKsqK
z$>}g+i~6c9{+4q&sp{>dp8Z@Mi%oo_F-4f}{Pl23$)dQz%7eeMtMyfzOTdUTVm}*E
z5kTFF*eUZGHz`qVB?(eu-zRonTRHN_=4ZkU&Z(n2^GAaM_E<e^T};97WAEh)CVi(=
zQ=o3cYR^OzDO)+|=QFQ6X5sg2k(1qw&i!r5H|V?8WyF6I^Zyl_jG2S!Kg{Z>|7(Uj
z7&p`eD)g`PCSU_^l77^Hjc=S9`u!WR%&@MtQ4>d!6&u=B3nk-UbH-alcK2`7xt9?c
z<eQpo-LF19y_?tfi~E$4)8p+A<Hqzy>*A7m<0!{1IUbz5`-jGlwq+dMCf8h-Ug(&Y
zwwr&@^Nn3QFWw7%S<dy&9f|zo+6K-2uxL7w`}&Vb$E_Q6U@rSH_^+gJp``+iTWqzw
zmUMyLUv_5wrsp3$*}fzDgS(t#RQ3dj6O^~r7h)2!AAExGcxVO%aI+Aw0MM}!2|f^R
z8C@18q#r>f7-?n=`R*}P{;{O@l35;0b$A%=rhKge7nzXUm0V<4PZ5R@`R-e+VApEs
z+CZEin*2(ty$CXj)cKcHce2(wpqW_yRJ|yI%KlAt8AAH*gW>fn*(S=$5_TqkXwRZr
zdDDwMlUGv7x9@V~-E5ny>Sqri1hPU*kDQcOfl~HtN%J1_H5mBs$h*@{E<NJ_uw<db
z5}$^WbL&lBk--;xYi!7|staNB`ECJJSYZNcWChtPCEbJN5?TX9*`Z(q!YCH*BzoPw
z;vFP?KpBh!`H5~sm&9>%<P>wipirt+aCAfiSK|cBP))<Cs9oe_`xPDwZO2~!pNc<7
z=XrB>OY+V%`hlH#B0;%wLo?C{B<dKp;_(S!pD+<Z^73)*hV6&}f5k+v3H+I)-UicF
zo*s*^((wF;yGAHC0;b$entUMEiKySksy(a~zL6+;56*UxWrD~IBHD`{GGis(YAQ&Y
z?5TpqYq{lRGsJ5V68PEaxX5DRuQyXW#l`NBiiH%d*9>!9TFT~;kKtAk;z%HZp;S**
z8I`L3;Ce&I^HFRHi{JeX8~VI0@_y|u$`13UhvGG^G`<{!q&4F-usSv=wgym4a8wy+
z%i|pR_ORc_ZRkX1{Y=Ar#dz#{|17n8lf9k3C2x{>(QQ&M+p@n<BlrPUr^2PRKCcv$
zacbc{{X<qQ&x@PrsZCxA{_oMMQWO9Re%Qr=ffsX`Hb-}3U{H4@pH|2v_J_+u`9J;%
zGfH$<&XeKnikMg0BkAQNZ}-gn!=IN#EgY?Z(Q7Q!ZxlG1TQRf+go6dw>4En!Y37EF
zgU6Fl(6;jKNC$lqcmSJhEW`d}dOyp>B#pE5=PD^6X3sKcpnxTTz0xFlX%0=)RXNof
zHCdXN`iuh?qUl1%JbS)>FH0EHsQsj6EhQvve^wJ_JKHC+#A_~2jej@WzYS1WZG#8K
z%xHTFZy{zhHju<!9s0NB2Nyl(I(r`4tka4#+-cipy)XT%U5A!T>MZHTsj`HT*>>jH
zZ|-!Upj{!Kv9nQsrN7Uzb!#_sddHD5tsqje+l^`wGG|bceM;@qS5@MSCTOFfD$4jY
zSJmFn3g4oMW-S-w^@nN(C{|a=OlLsTbrO6tegnBVyV7=SbKQfTJ|aKvFS~A^qZVpv
z%-S_g7#eOKE;}?Dn||#d4H?}%vL&bId|DGeQT282lyZb(-Fm+t8<dL0!bPrccAhR8
z9QB087K8L4p<*9aW5pe}sIwW#G99(F`ovyEudQxvo6BkOT}=g!6gbD$Plixmg#*NG
z@;2-*#7`pxw;;NviBmJs;!LXw%ir$HuPS3`4B?ZD+ee(jm2)mX;~r}XHw5)Jz2uU4
zeROKpwW#%)=?Z>3o&#;O+^RuE;<Wi0X>$oz2E%{kfo<TF>T%vaWxO4BNr6tH!lF)U
z(h?d=3vz?~&Bk?_&yA&`U6CHgF**@RVjr<F@ku(Z%5GT@EeSZj$9VdrthXIz*|lZ*
zF0crOQ*ULAwkOq>)9L5YIg2EuqSjLTTwn1~uD(`sj1`_O^Oc7&Eb@<&mLj(E^pVsq
zyqHYTXqRkTu2Af|FY!8j`ssXy=$?1}jx4N}eJsR+=Owuf3pd)_ON4biMZe4it6Ml}
z+eX)fQN)}5uaG^^?)6tQ^QGgD-G({-pq|z+`Vv-P&n$f6tHQ&Ohw&^$=3h*w11)Ug
zz|ZK<k@+P02$U~OG)VeCs;G#rj^SB2n!8I$Jhsz(Iq627P}W^mq|kWv-pKvPX{hk4
zOh7lg7(b~(_j0_I1Lt@Yhc`qxbmNE3N9P~t&y!-YR}I2O#@Ca#T12x_kIBZ^iCG^g
zB}H2Ce<ErUzt;Wlrd=`5=ySKGGG06_y1wexj<U{qW*V)vzy0tYBx&KB9tdcWv7GI1
z_XrnH@jr9OkOabgAX`$BU*G0?l)#Wj{)^Ocvi|SpvVi}Px*?6JnEzppQ-6RJNG;R^
z4B`Dx*+)l9eyEEZWy(>U_S+jdxk5hQU9}m&B7Sl$S@bsNjY>|Bg4N=~tQh7+PtMP0
zxCHU#z0vFQ)Zy(GlNGzb^xD9)bGGW<mm51;<o@C1V<c#4SJEnH(1q*!^@TQGOwy`q
z&i@=EpBK5Y8MA6i@8#l#AXR>jOMWdxOd@f!VaXob5wyfvM$H=U%g~a}*H@c1Tsl|G
z6QC%Wk<|1R)~TC7s`0B{$3v~tpUh8bgC4rEP?i=!=y;4WDMI|{ZQg{d*8N+1m<|ay
z-6pK8FP<}jK?CS)9Tiws=rYzmnGN4h4>-}@DWVlr!-X5^9IZD)wM)WOKuM>s@5a<k
zaAEkds8E`00bmQPj!uod6pot;8|KR)PF_9Qo2KNMv5L$lnxbhB<1zvsn+HZNAde+@
zl?G0_IOst9O5D}@mZyukI7>vUi4k<;42P2T@x7{eb>@GiBjHssQT!Bgh}RKgV1Z3y
zKUIISCGCTr|5SvG4@6!Eu?{vwP>nyD-D8kc$@3Ic@1arxB8}Ht)J!g#TYNeG`E|Z_
zPmP#NWwv)Fiy=KPK^(&eE(@Yr#EB{1@yh)mw^S1>H>sW48ycE#&#FAtP)$=azt?BC
zXK)~Jp2T`R&0K@`fJbY<ZCVl-;C1##380Q_I#6B+wxP)^<dN464rr-C?lonwg+t5?
z`#{TSvDFq$%0>E{`Z86gPTQSQL`t!?3_u1J5HFt36_7fN#|dH>2dhtn1FvJ0;mn=e
zZ0S_o>+AW=!0jK^@6EQRyh94uR0+6D6L_17^fb=6KOv+kqfl}i1aeA?{Ya6YSX)CX
z#jY((`Wyxw+N%CUfMPmn6p!*qx<ObdoM|og_YK>4h##+pFM}%>6iv9BRj?Ma-oe<2
z+oH?zl~o^_58IozY7US}bIh~{-&%?VBj1m)cStln)YnztBq%xeuiK(~zJ|9tl?4?^
z2;RAhSJj^beQpoDHK`{}g0?21r^4nU3|Tb4B?QrYwTI8<=LWDXIoE%5MY}9QxgHU0
zho}aUvDn2!3=5hOIkjNbj0)8^tx7$$snu0O7wb!2F*(a)Hel7h#Upj4{}1&_?-zcL
z57tlLPv?P2#@6*#B>6w3z!nQf7&e6)SkuGAobGO!l+%6s%C-?jK*aw9z0a+x!iih0
z=rA!K>O-TH8A#nl?OL={@!N*&AK~BaVjZK1q|z>_@-Ik30+rnCL?h(Iy7??Jc)P{?
z=&5!?TEMoTR67BzdQ~e1>nMgfmHytQk%UA0=en>2M&PXp3$6jx%xJ!IEG8{0Lw^;s
z*9)u`#t==!j>a8`;^XPLDHLB?9SJ40Cx(lN8Z1m2uhU$1z%(}>D+jvgKJ7H1k<go+
zw#m*RbbZu@(X}bH*0Lc{pqPj*E9Nn{rjuQC*}vYNF5XnrAQ8N1E4y3FmcIIC+@{L0
z(9Ex%s6!m3_<)Ufy%qr8D4gt8jZVp>EBrP-d|pRzP;Hi0q!JM>?T=C-)4GqFsLAP4
zbLnuLe)*fnIcB@f+1uz}^?1_=Z|Wk=f(@HT-aj-EnTA`7L}(jW;>z=)c1o)N7wV*d
z(ff}rs8wpdA3^WwKkn4?NgCFil@(g}(7O(`p%@M5`gC+Dx7rX0y%nN86RWdr$PN`o
z&Se{W&rr1a?YCiYGcU5m#h!CXR@{at@y%0&Ssqd9W0WI{269i5S6<1y6L$;B;0ZhD
zszy0Yuzbm+L8gEo=yoUJ3O2y?>7OfJGwpmp^Jr(g3awq8vpfZ!ZQyUeEj$`dLf3^k
z1?iFl*KF!m;<}rhJll-Qen9o*HwBf<klV$#+m!%73@D$w{*?0`arv(*D@{29sl<<B
zA7-dET(%O(eE;B452Fbd%>VHGz_Vr>N5x#mH2+J)BnlY)mANC7nVf>!6I}cEaigeN
zqdDS{skHnLm}h+fT3n1c(yAor`E0d+G{!S~(A$$WPAxw+pBYkPklC1!1HmVYMQg0{
zLY=L2H8Zo@Xp$|X$<WU-rQIY2uupG|#jbyCdSHL8Nb<^l8Pb;K((*wwLYm(MO|V@?
zQLIHsu%IBP8*gR59)&~+b>hFZ(2<aS!MnaxgKc7_jVJdtE;sLp&5|95;Gal2b{?f#
zLIalJWk<V7S?IhdD)D+X@$@^JRzZiGWeJ(4CsRbC!h@@PBbWZwf<YBLc+n!NpO<Lu
zZT(Qg92D;CiWhX}s&q%FDl!|uWl1t@sQQ!LO{;&1HuNXdH4@&Iv(d@x;#B8A(<r&w
zXt|-|WdV`8rhA^PRx1uAy7m0>nFx!a!RXRr3HJ>~fJw~t5k05src4VO{WU`d&o4a-
zIPWIX82wvBzHjZkh6#RRG-$ag?9ob3oE_Z2!Gmt&+1JH!y+*d8*#&bKnQ1ud6^*Gj
zGcsRbpuMYMa)j^;GAy3n;J-=n|8hl&`9IP=Q~#v+e^#WZk02|h&>o?&_|eS4ACg_|
zL=n#)+y6f)rdF7X8p+_43?RXti4sHk9*bQ&+~32H{@zIN|5`sh1n=r9IImgnpvHRP
zaQ}+7eZAbA-YF3`_0_KL!%6|?G}6&zn&nF#5;gMC=I>%yKKvw2;+a_jiGAmG^DNR3
z;G-A#O281Guy&Z3cX623hneVuM2!<;@WZQuw5#$edq%4olJ*&CXd<YLb{69Qe0?~-
zyPq$l7)fGcZW}-0t(E3CO(e1zg(kt&AqU27+ez?InMe+cZ%ApFpUXU-lc7sWfN2HO
z@WqA-s&xXN9Of&ppQDjG15kj!4XNV*dqp@T$@8EjL_T+9Lix0YJ~7sWjG3A!ONq5b
zm-!VMwf5E51jd#KlOR>*tTQa0<^vfvQYI8TTZ)8sDNvuu<))$qz+VzjRBuoQ?b+c&
zYU#jpr%Go8o3nImZ;cM}&P)U$G*&M}ZFe@jiaZSv*Hiy{oUd`ix-o^GOwncBhRDBo
zTIInY6)?hfwOY|>h#nh0o8e2v9(B*d2=Jp|Si;PSsoQtL29(y`VZVr76WF<4n;VP_
zcARhWX0-xQ3kx_wqK&c3s{0n0&Uuf9f~NP8zos|paL7&Re8QhrRQ2AZzI?OP&UBp+
zusf7lU$J5zf3w+_Q5X&EXgnKa-9+tB{dA0s?Iu2Hki|5;oRl!pTkSSkXmQS^HL)e1
z(gn8DOplwYm`0S#m}&wKbh(R;lu9F7sjdx`gD~6zt33B4$xNngjasE5N6U>UcLfu@
z4P2B-4Q8s;FH>t3&dcpS^0J~JR4~KJBn#g4SxvMrp}Vn5wWL~U1|FoMpX0l5RQ#5F
z`W;*$f#Qjc7t5SRvWa{l-TAld>%tF5XSM-Og0{?UQvKbv@cn9#<on^8vB?VI{kC02
z3CfB!?m{|Q%0T78i7*V8`ZGnZJ#T(iG%~^<dJFU-oIjaO6tj`tl9tN0>8vc2Sm&A!
zUN=s`$0}epUK`P8nqvSKOZclkx(4;%DDuFObV$paN3MDrY86hot6Xm#o<%mivOC31
zvl)8-2%Li}^c(IG&XjJ+LF7eTRHV@#SR)jf_e2EZy{g?f(9j7X2_9>OkgoTfZ636T
z(ANgZ+wUz0DK#oz^L_Y~_@gO4_?+jk3p=GNwg=Z^nmmDCWFSZ4GSMfbtMzp!u&}7U
z;L3}FE>%e%4uWi^>W#h@`IriO2o=m}61{hQL|f?<^0_jj=F5E*L8|-$`@`^{mF9)k
z!gy?rNLD(E2bdECK@eOhQOb+A=rK}NhYr(Z8u554o+<gk$u-)Mu0ke(WwmOs$DSJE
zo*`Ws^-mX0AY_NOKeli`ysF>ZfCm#@Aku=qfCmLjsjB!oJHN-5rahMjY4-F#V(f_D
zCBKd8C=?nBbV%iKRmM4-qlZgQ#fxjiwl46Axe_bEd^)G8yybR<=B>RVYO6obJ<@Yg
zy{#};UJsSGa1$9VTnV9%V%K-}h266hmjoigr5ci1^4;{U8782|bIh$JjZUr)-Rd6@
zx^rW=jZqRTvD?H_SstVC)w`yXYtMkjVYJe4B|k^7p`KUIvm@ul4efu-I3>2jc`L$&
zW2oOZm~Sa?4FSz<PO8m)Y_$F=@-(_4ucNn8U;Sh?i#bcD#juPV2N`YhWwn6zNrnvk
z&VlB~>~dD-QXcL<mTbozfaHHt$E}9n1XgpE%xtv=W?-mAjF|*twH4G{pi3^$Eu*l}
zIBM?uOA{)%UzJE!(RWsN_=Do?*ybx+*K8*GW53Srm#VSZY*e#`vQ83eL0xDg>^>q1
zO9^cg1?#X~*Msu-`vcnME_0rxV0zDFjLcO-;=t27!I-~Yy2Yh#`UbwqwhQPfR$lbG
zOZ?MV-gIeer=AN679yCnjg?~pMrq;}n~gN*5!i+8V1o?_+#$6(SeIbfvJtqpG}qg>
z{A%Drk|aiZy0t>ut7Ms_Q)rUyX5R5ut?MVWlD)rN6%^JkriR%|n;phSro2^`|9&lx
z33Hl=CtvF~Cp{S>`%butLJ_A=9{-X!;Zide<lmRV6M2UFsqR=kiAtJ^2OQ&RB5<?n
zij7@(o3^G4*65E|1vt0hJT;|RtKK=6(?D<L@x7<36}MNS^9k0RP~8@kI4k~r_dpY`
zae~B&lQ8*y_~8AERw+~wID4StXgEd5Qj=AjTYg@u<?SGF?tS>65wcn|l2PtW7d85^
zaj2Z`Jv3`kZ_v2EzzPteCq71Q=%_Da@Il>EZ4S$lZ3PtQLBWBX5ygrKS@HcD^Y-lD
zHqcr@pLjRuKKkQJ5_#NR{@G^)Ke*rn29{UN*^!N)vb_FTFbRctfU|*|Af&va@%`kO
z!FBfeiTDj>R`i4AzbGr${|;}<#Q7hMmP49jwz%T|CzEpo&3Wnr3WE<u2IVN7uN4<W
zme4i`eVni@N8crfNFHAg?^S9b=jNi~LSJLq>aB4=vXi6T8Tf7J@%nR{zwhz+=^7_`
zNUq{`e(dmBF0s#VoArJIMRk9}an|!ufqr;grM0!R7An<Vmtn&0dbPE-+~;0sz5_Y+
zeSZHR+txR}R{d8SuPz3)n$e|Woatll{Ql`o0n*W(eeHN}Ru>Ghp8f$@aG)3M?iY47
zQLr25L_b~09G$x%yuc!jz#{WDF_2e|R$J}J{e^<%Qy5cK%G=Z8)MKO~J^|H)VfLX;
z_e}X{Ks%^I^xtIsM{&Zds3pxU@KwZDN4(-JADDFn^%cpceQ^Zcc?ZK!No}x@l>m^d
zVz7rlC8eMbKewuYBKY$BaCv>Lt23;lVMCufn)mLq{HY(VX=)_TO)cJV))ERc)30@G
zqpnTvXgn&mYQ7%8l`#&_tGP0<zC>q#Ve7)_el%Gc+X~#Jn7K#!;QP7I)MwQZ^aHIS
z%(Xp73Em-hg=e^nTS1@HzUMFO3C{&2SZhm*bYUh`1)iMHHe+~X#ZSwmgCvn{U;mfX
z`{nVegY?X<n<;38Yq6t+rku>gA9R>dvEg{v3%O9=E1I<~);}m9MSrT7azr3A7Vc))
z^o`c;U7GJcOBp6*O9*esc7ArHy-w6a)qLD-ll)fC0?TM{1-ia=nq&6~3KP7Ty@ERm
z+?w&!#CR@(Sr3J%fRP`~tcT{t_^>3A<lm;J0A3Pc{#H%n>i<Jv4vLF-96aRm9<P(p
z)mk&7v(b4qSkB*Oin*pu(*{AW3Ih-)QvwE1wmK-e1&zHkhAlYrd9&doI5DVj9cZGp
zn_NVxMjVdfMi3Q)@ai^kPSTya^oMA*CXQ8ws6i?1b5SdIly#{2&<oJi-0cC|J;Omi
zyyv)jR5?Y;IjL-@j8{?i=DS_RowtsgZ2pRk)+)XM%GKw^?&U<^t@#Uvq-}^c-j;mt
zkZ|RnFj&aK)yXs~xTDU9xzWx?@Trdrd(!J5D<3ZnK~{y)0S@_?=qYX9VaE~GE2MLM
zig*3FfIk7@U8GUslB5vS_DeX9sJ<poZ)6a@@E;iT<3C^P>rsCY_5v_?@qVP>Kzf1F
znf_vx@(;#(56TOH5Mli=PSx%Tnj}{>6OGx*=QUyb)jYKY$xC5GNnp<iu_M;LPvv(A
z0ooLQq>gC?Tu$;J8v>UuLOqRYi~hANIJb5jl7&!DKvfW-$wHPii<;Y7*r<)4<mn?b
zdaFe)TPvX;i+7%u0LYQv`ctBg;c=_KPEx?zgvRn}Jhy?yB;H81L32TSl!D<p0+}5-
z+S-mTCEYRZs>Yp?@1tt9r*jK?;2#4eh7MN!c$8|S{d8*kT-y7qeA$1il5@IKf4rT7
zgPw(BxKGM2(Lwojmh(lc`MtT*B;gYFy(RNT#u64wC<Di_1=N7z3Y4lwC>jv@19??*
z9wu3u5`oLUkQ;zJNfu9}k3V8p8K&8g4{Lsh<rrry&9*<d$W$|c3<%)OXNVp#)AFvS
zZYkV4?#$;C+L}Lz>!nz@QGXsQk{q)$(Jiabp)I1B!McIc8^c4xf6+OfM>@?{CfxHu
z)A^a&e5Z~JKBqz+Z2DA%12l0#8O`tj4>gOs4K=!S5=0|=^>I`O0gINt7Y4G8;U@~8
z0q3i%TB4rdLwLDe-P{}Xs!RcW6`KQtZxc9+<p^%$zO&pc0*8ZY?pYd`d}ET#9_LVm
z=?t@EdUQhUc&sNAyX0))%WQKuA4>u(p}gFdiPU`x_haq6c8p!kzNMM#zvgb9Byid#
z&fG{XR-y}?0zR;g`wt3HOUf7RNyi55`tnpETJkOUA0JgM_-zawG}m%ob+zQI7WYE~
zkZILUoqq?_0Cr4yL6O(V(Ba<2N>J(#?3`h%D2Eqf0r$U@@X4bFSx#w3L&zD*LXMKT
zB6igXvi8!5xPcqEipcf8iyR>R)g*uJ-~_?&=C5MhKw1FaMujw&eE8e3CkO4lSF_iC
zLwQ%HM{rr5;$5}3*>^O+>=X(nohO=Mt(b=I4nO~ut9kyE;l!(%RI{jRI^3lyj)mBN
z#GTY?N-@mSTlx0Zjo7lH*fQB>k-2g!vK;kQjkL==eX^33>@||I(89;c<9N|bXGRKd
z1;%mh-3i{sL4}HSs{_SY&(ID1oilQdY%>hCZ9#=Rv{hyee2*%=rAir9OEa6h&nLK>
zR&G1DHQKVadrvPD-M^g`(ft<?rFWH<@^rgFL{Oz=-gLQC0hsY;=D_2bh7fqGu&ZR_
zU9|$sWNc!pYYUo}s<;UEDmx4@nFRSd5|VdvUnLrGhYM+Ir*sOjbE3K741}}CVPw~b
zLYVzDpTyyKWDxz2VcoU4pqYX)!#jDcjKJwJ4VU1~A}F)NZo5di1ryppNpgm4=ONp|
zy*Tm5pSlSDw!q$s$=$1jn1r#$Ns9Pt?YPkoPo3D`BDUHUW60WKj-}$&x(~C}ZzVZ)
zRzWuvr1hbtr+oo&*%vsSEFZ-O1%0<If+4D)*ZOnYxagWis+jw3A|an&df4a){li)b
ztINOK{n=qf7oK!n>Vl!@dW@Tn2`XnBoZc;QdrU@Vvfv_Gjxj7|TbykEHcx3gn|W+h
z!aSaxy65;V=bLsMlpLKYB@MK+X%w#3bt)Ir$i^N%LNM>n(47pib<40`GP)HXw|}pJ
zX)pHQ5@dqO=zG7q2!pnvvh;l32xxN(eEqkJ#{aItla=W|w!o(TtzaLt{vRmY31TX-
zhPQ-Z0U~Guq~rQv3lVh7`ZT#$YS+Pa2?1TV=AH9;!>WEUeK<+vqhVclezIMp7TuSV
z^wY~WLru@lyxhzC^6sPD%mm^09>(z`MuA@T_9<Ynm6t2>_xhdp=g8RFgQ1OfhZX1d
z{c8;y+p`g9)T4wNl!JJzTBurN54@k<l4++~%@UNSUlWG+DdufT>P=3LIKsa0#mdwp
zUcV(szO1PU%C|1eo=>k;E-b@w3CQiQd5mr+IVMxoe%03}yMDr3X*CJq7>{nGS7GBF
z8jAfEiq4)SP_?Y}f!DDbN&>xf3D1N~tUq)!28%5VB<=IbI~ih<UgL*Vxxbi0^POmC
zLZ0VH*PYOS7wTXhqXwkhr=4#~GvX(u6=H@+I15*jI|s5X9G!?xx{;K#yjq7YCO-UJ
z&=k<29QyfdK<u7u4F?*Tn{k>1`@CA{wCo6=G|ywq)dlNsU9TD0G3%alErsH_@~?xT
zVtM7?mqBZ^gaw#1_>Q(JVX0L)jAeV}yCF`BHH!W$q}s|=StO#>(M9y1V?<dOLyyis
z8QCvjhad+foiFs;rK+Afel{fDR;tsR_k!H*nfF|qc}>KVAbPVzHQopX+}H^KGxXfR
zVabfB6AH~|>s-32o=AV!-;G{$vM^5J-<J(R>jYR=pZhRRdRgha%rDSPo44<sbP|vo
z#@XuF+54`!@cT9pK4n5Sn7(*!{GbL{N#?F(Fr-%NIT~eNRdW0W$+)!|ArGTHE+kMb
z^nxRZTE9C8zu?YGMH#0l#=dW=@?OzqZv3Ol&WVeb#l@AqAjw(i0-BMv*Qtm+@UKjx
z5~Bv(YaJH*iFTWjw@&ZW3io^sby)>j(&8bqIXdH0;w_n|#fYM|@1W{5gKuwtr{x&^
zZ>4KSr=jz2gI{VHwgJ4GO)I&-sF9CW8nS1Ve)mrrHGX8}d4<0JYPki!vO38ZwQWX9
zL1~ywCOg|;GlXdGIc_l-QUOZj8f%aLs5T0EQ~$7Jvix{!?qn1YU}-4!fpUBf?Lef*
zp}g1aKhy>wX#bV!bwTx^vT74Gv&?!%vIsByNSS-4fzrp-Ya022TWGoOR@aP2bmQK_
z#pP(+IFJOZq>HeiJnskC;twZc2)QM^z0_rcY&ulkN@b>3bA`{+=b!PvxEIqs*s6bJ
z1`J3&qaGvKmhmJAFwqllaa_#DU_BH6ZWOQ&slhQAcsabc4mtbfHr&8?zCc>udT1n9
z0&w$7eVeV9;{$!uOf4&!*7M%1>&g8c%=V9La!!7$p<{WmeJu`ib<6Z<(>Dm=@|-i|
z5!*sL9czn*g!fS|7zUN0HQ$rcW5l!}d94VD$3v{?tJ2x~Yi5g<ow;e4l6cVjJKS}u
z6t}y$r^(G7U$KC)MN|q|tY%3@!6h(3Gy=KH7~4JIApuw{GIq9t-oO|l6@I7O2qJGx
zG-l4nej3K?M$AtyiKcr4(2|uMecYz9Ff*0|2V4<X<ja|JGCl+<{?JL6Et!5d7t|{u
z%KRH_k`K)pnR6H=27cl6l)o{`hv*T^`j)qlb7*bU7UL|oX-?9ffMk;Y&Pf^)+EQb$
z>i>#tR^CA}2%Z@-b5=RFL|@9K{1O-aXw{S3cxo>M%vwK22j?!$t*IwxA}dInZ^N)h
z>I4>Q1`&~hAYh=QR&K8Fui^<`{Gry_f@<yPxbA6sDBWf*8DAw^5z~^uVbR#V$HI6s
z@AYlNIii|oCy9y?F8g&L6dKVa>K4_KX>3~s=^eV*+SFfylU+ts6jD07%lqfJ0%Vv)
zm3Wt1NLY$VTK4fEQ80Dv*(>VNV4TM89gdLo`gmOTl*7c&$3oI`qcvR)u>&XHC>Xs5
zSW|_|kneqN_0@WJ242Dyy9^N+fX2;L%D-poKfPlNa-y=VGEy;^It{n&^b?LIVTRx(
zWP1sGc13H^=^`=@xX2c%NQBA|l3Wm2{E#CZ#-gSt43R-$mu3aWa@5LD!uM9MpZ1w+
zzt&1bFTKrkcOj(2eYF*6^>_OkdWzV3c=h2Mbjrc05cq&@%zxCtM<bw~f}d;1i=S?V
z!g-kavXH!nSMJ(-PI(J}kV*LjcVDj&09!3q0oh{u44~+tDT53!C@5V&mV*9fg^4oo
z6y0HW{2U;%ugx@yTA0^-u>T~!Q8Rcl-`~dix+0jn^77sK`9d(sG#LTb0Aa~2a8?1;
zw%C7F<e&?X*xGJ9hnF=(t7o5sBuM&tYA}W@LBnz_!@8?5#s*+8i4?-ZdV%7x((@$*
zKZ`__jsmZoz-<VbV83`|rWN{oEEl>x=FbYQ>-(u|9XhM_4Of3sUxduor>vJ36TBM1
zq0iYL5H48*Qi@sqa_>b~t#^MO_Ch|m?^0;|E|Wmgp|9QWDJ0x9m1kO<ja+NTs||4l
z)H*$MCF&JNN%Qdeo5Y~Va_jd>6bA<q6x-Lc>tl$uC)JL147NH*0c^G;4+~xLy)FJ~
zqE>riJ#5A9KB#632jL5IWUcLzQ4Vj&b@t#P6y3w6OWY$1l+nO{((d83hK^hLT5(1_
zdz}<w=sGiST|J-JAQh`9$lg8AAZFQ7%uZ@>Fe=RB>kIMA!<29_FCn5IEvRV<2O-ly
zb}R7R1#C>1=TyI_dD1+QS4|+Ba!rQl_JF<&{BRlh&DHu!<F7@ly?eB2p>w%W-0D>N
ze1>{|YPQ?PlZw{;X5{#!z?D9f>2c4K8V+;77J^iU3$&E?!zvXL>}LO){fs5(Nq{Z5
z1%M8nf61D%U($RBJTHIwaH(r@8Lu+1)x6Qm;&V*Gote5w1|@UQAifP_wk#}MyQ*$Q
zG8n;ac{VL7dDQ6$D^)nWXYAp1_4>^eNu}JCA%J)z?X;?cPa*KFp2IJQ9G!T<5w=$~
zeS<|fFu$~YC~Fq)Xq#1)K&ZZk&WFwJvUu2D=0R5ErS~2ZAbY(<1>=L*;#HKxxQ-XJ
z)7A%6aBixZUMA*Qn#dC><rFTW55%K=>SEh5&qM3AR3@ZT%H=FkGaL%v9)?ZM_`NW;
zE46g~my6W@6=hTQus30pGqhB4wqcYdVqs!p6ti%2awcNtWas?%Y3*#{$S7uQ;B4~C
z#K_Lrgi*%C*38+Qh>eBwKUNktwXI_DI9xxo^%MlVTQQL`4h~t>VKmn3NR5%{=%6J?
zU?P`F=@Ch$WIQ#k-nWnOR8=_67g?WNV-LLJ%G)Kf-@8*PNk&e@IK<MEa8Yq8l#C2X
zF;W&dF>w=d2}y9$<8+LEC)!)tB>pumV&>i}vx*w)t|O2bX2ZK21Yo3YNt5OxCD;yv
zsGt(m1|EZHU*ixn*+U=!j>USz8uF0iZnoGGaBvMR$v6P{n*l*GU$cd`vl@cXo1DbQ
zttcqYnb2gt__<)~LfjO*lxW6J?uDR7^ttZnf{?t={!-Pq@iaHTnf#d+K#1%iD;NT7
ze|gE4flAsn+M)c>gaLx(=3CT*qAfrUz3wO_k`jsd&oL40mi?WB`0a86LWA%&*9M#H
z6J--v8w(0fpvfM`39&NJ3r9Q$m{pMY$Js6}_>&5y{ug4681PpZY8*Wau~7n*k4J=_
zdCt^7EW9x{EVZvI04gEC1s;lwwo&hodLg=XA|9K_!$BTcDp~@Cb4<HrV`TVAA}dH<
zqcz)`peT0pApD@)EHYm1Sa!h;qf!Qx_7TKps<N^OW1wPm^K8gix@O?e&&L0Uv2O|%
zWLessg;}<3+qP}n#w^>mZQHhO+qSJc=k4G3?*GP#=<eu;?w88y%Fe70;KT#0yPS`l
z<-jtgj({J*2hdUCQE|+x@EnV`B4(H_yE_&<i0vtVQR|&s@jwT?Nz@$AeluVQrzXL*
zhw~cG5pV-2F0!-D#1$lhZ^<;a_9B#7So**gw_K^=j(fec6lV%WDpZEU_b^tP>(D;{
zK`_5!N;V*?B#mSf&Cs-&9Hlx5bqsp=EP?`jz4OUwiF&n#{s15XoT0NMcLUH^7pCMA
z3WmAJH5Hu=;R}S1gt~Zwj1l*qP)XzYeU-X~U5YwM66laLS)qjoyYL~eubGQ5JcKns
zalJBX(cQw3g;D}jK0)OO@Sd;zJ_bHt6K-v#>*}R5YqBbeNE|$5z72AJ=Ae)GHMGDD
zEMx0Ah8JBm2_V4jvAI9JP~#`JIVQR)$n`-?0%fscS_r6L3+#$~or(m_Uc~xaf-Ev+
zchtd1<3UOw)Cmz#zVrkxXvS0AJ&ZiW1${K^i-8I+a-cL%Ja2)}DD6lBm>(oB8vqc4
zI2Eh$;B;utcpDu=t<5mdPfJjIFH=hG@g%i3sleGVIEF)Uf11INp^lLOyMT-SPz#(*
z^SYNmKTt+OtG`4`d>!Ynj&}5SBaR{W@6)k+)c9Xqb+e(5sEhEMeJR#?D3VroLI&2g
zgOXBfj~|JrB|#}t6$}f7lVW*KiZGtTb?gfwP>xgMyXpc=`+R8R>Vhu)Vq;R#{sR7-
zkIC^gc%;{<0#u!HslQ_reMP^FAtl3T%!MD+sfNO^=)S-n{`QK@AvGmXu`s;(Fklvc
zUPqo(TW)M!Xm40lHUDN6&zA4wXOozdo!noIJ#ijx51()Ev>h82DH~rEPrBXTCSPCA
zCtvSFAyXY!s#ix7&-eRJ4<|prd~bZ(HmZLd9UMAzdp=)HW^{eJyWeu2Qd&A%Hnu32
zZNA*UYA#SOYIM?`M{?*ckKQ*nZfsX{ee9kNj%|9jzWCRW#e7=2)_WxKQ-{5##~JR7
zem~T|lBwND8Qt)ozCRzsO28QL!)yoFpD0TWi6;iH1+YN0-E{6#FvhX?LU9MFs*cx6
z^ku1P8B_Fkb<&ipmHXd^qT&kWVPr;JkFX-2g|m%^jf-Wbev+XONl73@__?U#BWeeC
zX2rK?*!laem#N9hbtc)R<k2Xeb5IPBlUPr$Wj2kQI-uX%2y7e6^Tc_|p%af^R5mu4
zy0CLPvnNUw6-{;}ia0s1QKnp_30lR=-OAQoM$D()>t$C?rY(fkFTC1M6T~Fu=c$op
z#*7pDIQJ`3ZxlkQ3XPSI1_1$!*0J@ttof~i-UxJ08z+H~#!yXb=u_CC-!F^~V*z&`
zvGWcmIY1vOhNa;1LR<SSmMPf{sRt~G*^*~%ohF<U!;2g<G2tb*{RvtT9y2AqBnb>q
ziEglW)#jWLBAH5&Yss)<nOsyFze++}*HiwJg3sf`%ztHIWEfx7ir3Grea&!asx{RM
zNXPW(|AuRlJf1@v1{)@8307Q`+N^h<o`+6TSLydNw)Qm@^EJg#-^w6Prjt5jhz<JV
zU|NmOP>rwFzHia`OR2q6%)XMuG+DLS7`VbJX=0tHG}I|SDzxRn_yK579K8<40o0ut
zYvMP}6}$y`cGfLXl6nNvc$j&yejn(&mVp5Ukkd=FwS2du`o-LCv?aAv!h`XstV8$`
z9j)$i?+l=BXRfDu8{C_@47t2=eVes)UYs1QkXO1ARCuZpM3g$?4n|%mx+#s|w(OV(
z8y?n{KK^K!rjW?gGsEIv5UT{5?g3VyDD^`1Oet*50sDaU&FlS@BGs8F!EjipykY^A
z`IZn8R2v^ohLjv2gviHIE;X9G!xkpa{KZ1KA}bknm(<VQ7UcKG{>az&^>@zlMav6_
z`kwQP&DX$i`;&ZC>i&IDrf4)7?eQxJP=ZVhvDf`Et1C=$@mWjgJ1y@`k5}8yWs7Hv
zbYVzXelQ4Yv27vvUO&|2+|>~e1}3%_qO{8fgBN=-1@z;4TPOMPppQgej1uJ?>7$Rw
zXVwIH3=MrjNeP|oQ39xlVZyv3`*@u9%!1-<dcxEFqio`W-<L-=PuLf4*lW)ELe6|o
z4$~2Dk^hPRIr+l{Q{u_~#RBP4eF{Gh|8maLkgSpwjqGz>w7fKA^z!bBhFkkzS%SCs
z$i$~H6e^dDjFt=!r<aM1DQ`s-8e7|%>y-o-3!bu3*@JCz8;RPu8-y$N`Hd4s)6XA`
zo@{%C*Tkm#2Jzk=NS`*nakCsQ%CrOT9=8YYj%{n7)$3+f)s3g)>vr6GW)RPY4bRo`
zmW~b1r-Sc-55asp8cN0HmC$`>S=)qr&#-CQ?U0z>9zjv8NeLd#1>_9uC?~H6=Z}Y3
zx=*wlgSE)<nuen)P8a$<v2hb08x)`SGg9Ge1^t`vf~4>+pUq3>4BhOn+q>dU!A>6#
zw`{M~YoAUp4_$h!BvAsFKC**1H@=F&ns@qAy-(BnV>gbBY0%y0Zwr?%6V68F9{fK(
zS->SsJx0V8R&PdGNxYo^-yg^PK0eIvgXJANo~<6d3R*palSE0aCA54oeaTgd23tWo
zRi48SBkIWAo7dGXFXy%yFSso}UF~144L!JRId}$bW8oHuEII{kYvo&h&l%mzIZ-b$
ztSdhsc1Dh4dMO<}eK;;k9bnFG-+h+GusH$K3YQ_2+dD~16}@d+S3eq+yv-dl5+C*g
z{Or`5EY(>3q`)?{OsE>(Um90iT_1ZkFW1l<w$C3|*Ct<2&$cV78#mow_p5t3H7p|L
zo4VE*K!8^T*M2-aa(P~b{SPNsyS%zSt=l_2@B0@U6{fNFExKNJ20dT7ljl$GJ9%CF
z31h<L-JmTB2PYT!3LB*!nGmJ6dws!#k$tuup@tq<=m%<%4#?5FExLnt+%jkfY>^Sj
z(Ykkdb9XLkcT^)tF8TBXKO0XQAF5o9e&0u<A|B9JOQ*u$1|bF`mqW-eUbw4%iz3N#
zg+O+MaHYeqgdjvL`rrdDXolSU)Wr&rjRq)HJCF&YXt6^o#j=z(*}R{Vl$J;QzmEcv
zH+m^Xw8od5HCk*y4r|jkE6<~jK)=hKH-^o(rq){{)%mCKP<pk15M&?0xl-?7z;mPf
z3=v)K5GybG2sIT8o8@2FkX5}RkahduNR@iV^ga0^L{FEoSenjJ7qmGa#59a<@k%in
z!Pv8^(flVk8bS{|GTDaxRyfN3>^4s;_w2<@)9x4Ju*TT!wbQ7u-D<axm0amn{@wkW
z>W-i9r`lHP(MPexUDWZjw%)a>a9AP6O8J{X7r?C|4LLA1cGhY~>>?O&0u$?E6YK41
z9BX-K_FHjAV(fN-cvRVHt!E?H@<z}<fHhpRuS0=w!6NvLJaAJ(f1`paL#em&l@10b
z;`5YJvzKnV>>+Y2h0u8R=WB}N?l3%4Hm<6%qj0RYqVd@4nP3H*)zv}Z`pNyhK<xq)
z5^wTQ5l7nTx2pxg{(XkZ^wMrvKNJNgjeEbBqznQNs#oD&{|nnv;u4U|832iML^c9u
z{-a`n@HjU^=?!$<P0AX)NVe1_vtrI*W9%?5K-vwwMD<PWK+d%q3CQb2xa;v8#}adV
zI_WO&LTe0E`Q$b>J~~`Rdv5ygv86;lGcsxOVAIm}QO7MO7Y#YZg;i?9(SOY2Aq5(~
z9FtFJ*#3;)4rs+G*wR=nG$DZLW)FLBl;UbH$+Z?;Qp>keB{Z{^%Ynkm*6V<$=oIVR
z&&8%ma&_oJrxNK_*%U$)0W01SNk;0tVVNN?w5sUl0unYdu}*grZ*v`Iq>gxGHnE#H
zrG{J-;>dW@UN9-sbJ2hq@PNeFI%~&@S;IMgnb^5a!MiHT6L6tAKQ((1ZEyvyWut&&
zRg<|}AJVvR-`8wY=lux9uzIVO)zYY;dx`=uPYqb8EuOfr!f1BT5VCOKD~dksRg^I$
z8$5bh=xx7f>;7&NhJv&x{Y)xo<h;(y?#9dw#VlHJMY$EO#~?(+B_*k{us|o-NT!-T
zZyyxKwepK3^SdedGR+LTP%~Mqg$n)*%fwloo?V@h`<j6k>qDYtKNSl8L}tNa22(2L
z*W{eVhXm(B4h%dhZZUDiS@Z|7Mk3|RoWGV1uhc|MaYs*z89t;NrzmCR;DnZ-R+vlA
zax6DuRX}TXcq`4z$FzQ@ZZGz4Iome*SE#?5Ze-@Ff{+12C8Dz~#O@}z6AWL@iNM^F
zJ57G5lLnNY1e40a_teeOd?6ba?w(f3&Pj?d@w>A4%dreV;*)HHg;3_Np^+ye8BTn4
zPsz^28sE(#9@eN(2v34bmLQcLP6S)`+Mci`GG+bBYThEqV3Rg?DozQfGWx*~jMI7q
zzcz~Gx1<fYg3>4^xdPID#fGH15sT;aHj0kE7yXsBUpL;l1IMC-PV)1M-y}r#^kgNd
zn?S5%)HuHv;y7w)-gh0gre?=!r`BRBLJUQA(1!rqXrZhaKuqn{1i%Rq=Rxke6T_D#
z@4a+G>#Q~8DGJy;7_(yWopPx1SJ<}4;PFE@<>ioi+JrZ^PHs25Qc0VyR+`u;Qtywa
zSQ*_#wphAu#J)FGm6;%yDx=$iDz4P($Smt%$ClB5hhUu4drw**<ObmyFQGFGN;9Q9
z7)NIulyYTK5FI9Ts|<&w1=Z@frT*Ky(Ap?6d@JCaP)j<h%C?7^NTu6_>B<Z%fup=O
zu?jLVz5j)<+~9r-Jlt>$95wFDSR8Ov33aQ-<{<%@v}H00Qn8kYpvS}+$+0?FJaYDC
zR_9Ew@lB`b@wCOvOVOty7yrJ>lr_g$+IL>=VY*(le=Qm7XnT{1#q?c1RetgFS@UBv
zZW1>9Ru~In!_)2a<6gby7IfdSN|j3A*4-xUqTC=WlE*{E0{Xobb!38zBw@ajDKbUE
zmIPaw)(o>UK;2SH4SO<N=7_ePTvg89@9-hwRc^-+?;~?K+9HnFR<AgRz46e>ZDE|8
zK}{o?klK7c`M^?_l3GYtp)ntJ%XO2t*63E8Eaid2q^l%ZOU6E8;v!LWATs%$_%!ky
zR`FX35GHzkx&gJ2M|h<OG0NJ$I!r{qJ>~T07axi@#{b(IVPgCrjE(=bH^R!s`2XpR
zFw*~%&M~E-8FR!2?|q{B3a>(7oif2{&O9HE%;h_4kp`N}4BJp5J0MnYz2pe%?=z!X
z=de%Y9FGnlP>_9CsMS(KQ~io{5imdgUP`qWpJ-|vpgeZaKMn`hM|l8P&7YR~M>>3z
z46}*Av@gigv2{PKj{{ab(kZYf)KrC%#TBK>VA$Pk-}fmlX<_!S2?vTNJsD|mFK~^%
z64B96Ia(5GL%fR4rG&_DKpz6+zoI$FwZkMO1b(!?k+EO(90Fx58zq8~)k_cpX3&y$
z5!GLdnl^jsqkck}ZS(-^`lKbs3ri#YfPe?0a`~W?fI<Ap2-)BQw0-fS0aJk}^iavb
zOwjuL^-AFBzzCo)shne{WBGk&=xT{~O)`fKV6|aLVqN^XP&{fqsCfi~P;04Hx%Y=a
z3UdJ(&~SZ;6E=O9!lwYt=qj1wekGydY7ZjD68vh>$YhEY#3KfkZP*BfM-v-RiqMM<
zE|aQNkUV7~XV4%5q5{$b4<EymAR>Sg5E!K*7&I3W`h^D^4JH8|M`+ngaUtRv9~v7d
z;OobO0s@d#M;8fanD+}GT=2e6y%w}j110)4OdcP?GdF??c2$h;#WyNH7GB~aP%(bd
zmz$_9&WWgu-~!7YI#e!_PYN*8NFNCl&Vp+=YSDMmA4T!E7j!K+iW>E@IXr%`#AIYD
zL~SfQU}0i<YI%{6$Z9WfUb8tBMlOYYp{JT;TW+=5;cDQnL?4};aom6mN<c(`5#Z#X
zS{EvokibN)fEGPsa+@+~A@nC=_d>lQ4q|HmxFLmoF*p{50|h*RaE*M@CGxW0M%G9k
z!|uO_BMJQ5=mLtyyAs((3sAvu&b>Zm>jE4i3x$s$!7UK}nD7O}jw9A&Dv=e0W(qgc
zRXS3&g-6=UU>TXijUtJ7wGp}R7LpRm&N2>?Im1i=iVwp1RdDfV-~k|p1I18aVT6?O
zK?ncBLuW=K5a<<)U?XAS3Pa!)kr6ewgR(c8i>?gE31ui8@vSs!j7)8;<hPvr6(*l1
zUapHJHZLb^XD`O|xGev&Y6QUSpOlZJ+AA&KS;$I4&gYu;Cjiv20Ajyu6A!US*^CfG
zGGTdNCw80I3E0_@kyK7nH$g#Ed6y*Iw$-ke10qAz^f2x?;1t<_53Ar-cu@d>S>Bx=
z=?pwlPEQX=Dsj4Wj})pe3%*9U6QA0$NKyh4j*h=^o~LP39EUHT9*~SjQnRUkeIn-;
zf=t9Br9f_=Rd=+3EM3gCz>_473OlQy(STgoe5n<3-nmaw!TkVNT$~|x06VrFm007;
z_2s1J6L}B25S9_v_x$W(B<9B3j@BaC5tc*su{NL65Y+PB(Q@n8DhUUa_B_zKb4qBJ
zy%^`@A6vfj&C_Q7m4-V$qoYh`APMLEf<~3;-@JH#wA)uz*<<c?#$1?QGdzt>Q8a&T
z6Bc+ulRQ<4KCR5NPOEdeUSq}_VrZpc5-U^g{6VBKan`mi>|pEN$Mk}Zim=<AE!j8(
z<qXjY$?9B#%US|@87sv1D9&)wc!LYk`*4ib|HJ8cIX@7UsYOWs8Z5O+hl%kBovOAc
zP_WaBjJYVZZA7(D$q}r5Ec9X2A{*Ud)PYLdFwrg+OyaduBg~iX=)v~_`q(H-%JG+q
zXbXGU0{Xo1HA@xVCeGWN1AEBXKu(4vWU-$D36T{oor7z572Db)u5XX=Nws5FklS=~
zgXm;$lUg*!xpET-dF)it7s`B^VLV*}&Dgz-&3c(y9CFxEH5lBUq!+pR<S`Jf8jSzg
zhCUu(zVtC{+Y@lgUw^$4z9FmJqFd&z>$+OgP`mR>kZUVFCcIFbmrTHAR_K!-@eb7P
z4pe#;m#Oa$9xv7?Z?A1aG!b`hlXbE_XaY_X%dkR-k}Rf)Vu_jD+!LmnHe?3*tcGHY
z!W=f6_b)4sb!=8>hy$5T^KNn2>6=-4Qj8A4mtWp7*OReQJwEOyA>0hXMz}7g{?%75
z1eAi!=EY8FcV#wxm>lr1by?5G`wUOdwRsarGgtLw*BSV&JldBob?PX_5n=&FCeFsM
zPL+xtf+HUK);}gUPOC(pFy5DC!#;+*Ywy&?ab3o0$8HANL_WcwYr<tS*PafP>Z(U3
zCt2n@-X1SsPe)I}V|mahU2cRi+up8Uu3yi0@2{oI6K>?&H{90&3-)TccXplcp}Z-)
z4OPp#{I$qe8fKX}zdw$zIZxjfwr;X_cy_#gCQ>ero(3KkSOdP6GFV-BJAWL#+_7iU
z(n;E4hh8DS!!>^JW>gGleSCf%E}j-xfx=dIyk8&hIdBZYF??Kgy<VptOvyf*(v(l6
z-VUB}Y7YFAQPbz9a_Td-4=WhagD)-YIFUJPELV7clsa)EKQ({FQc&98u~xcH0$?<y
z=AUW!(#|kg>oPJk{oJ0t$K0jXFcc(^P8&CQhtn%hXQVApX3^3uJWnw-r9Jc79;dp*
zq?t}~Z?h(S6hDVs0|?DoNG6xWKds!m0p2K>b<YlEC@pJYD9fj*B?*Ju(?mpWE1__4
z!dr&69SkbPudId2N#yB*uofh{p;0a}{8fP@KKR`vr;#*BCuMfIq<aPrNhMJUfud!|
ze}N(|^}tM5o#3GuEnjz~kS}dIp8HE^0;SKXV1HKL>cl8#-fSb_<gh3zS<X`YBp$WK
zN4+3z{h?09!i<_&u_SxpBW<@Nbi={ITG#p=K@5IGk}{c_?)d3q+hIFlEvh};FsTo{
ziag+o!zH}H354_E2_L75*3t$!?YJ^0<X6?zM{tWk1aiD0C%LuJqQjP`ZKMoU^LZ9d
zE6f*Q9LJe<jUlR~ZFaiy419$^UH#ma;OIqhmq_-U)3%F<+van8b%pj%eacZM)!F6j
zp>|D@?r}7;wAP~>PlnrQhw&9WhOy>q#0N$bjX(;)%(aI!bd7^=R@GnC%8ZFqi&V&;
zACPcI9GH!e086&dyJH**#gP^Nka16KX-cl0kRN(3n1(iw)sVoC*w(CTpE8bz_W2IR
z*EMT9mYVZ(Vtq-~mn(GZxdAP1#Exy(+!OY~rIzFxTWv}0mW1c@5>4i&vS|BW&VY4;
zj0a}C2p9Gh^hFdyAujqp`y?f0gJ@^n@+%XJ(`l$IL^J251j~cYZ8!WA3x-qzW^~4<
z^AH5)9i5gmHk{)zH}@R09m3_c*{zrk8HItdc=RXC>Kke774?KdDX}m2W=knAZGi3v
z6*1#%wP`5M4x6&K+iqoeNy}1wY3J<~&DxW0^KOi^;mvZ9@;NDUXVBc$ZuBRX(=7mj
zBFiW+?dgh>?sxZ%J8#jhoC+Hb9lMwZc)8N%)VhdFx{0T$a@|VLReH<yBO=`LgdE0m
zFI_M0=nq%8#E~|)ju93GQ+RN%1c4v1BbKk%w<TvQk?Qlnl(qy3L-dTWnqO8{Kb+D-
zDj$4hg`KcQjm2JgjhHbtGmW0_v^J3yo4OkM-6n>cYgm?YT3+Gu(Z?;M91*P9<*y|L
zu|qJLgcELCF)Jx2GdVOXsLI}Mx6it~y7=F=D;d#zL04zUIl9-Pirao)JU?jsM>Uy=
z;BN>I##+T<ClO<)<0+G(nY1*z47kSKpPYckjJiBqDsL0Ee{Y_(jZu|(AXMD=<lex<
zjuh#WVo;QMnibz1rH%sdllT?gkmTQr<d0r%TqJ!r)qU^t2L2)ova_>~tauhTmIuES
z_UUrOg0!l7er|8=b$yF47u`S<-2$~RkKKds=4(I0<<MD(C%tgGRqQ1{*pf3U>f$x6
zfs$GsRkSiUZ2(L%e2>J{kIFRM%84dXkc6Qj`{(_!>ZpC#CT?E1%tE+)3To`7Sjr7q
z-}WV(EFLxzKI@>hA5Gu3Qb1`Z<la8`lX`yLh|{^F<e9=3ft47g3oxv;+>t)nbDk@=
zELeN<OxVg63#4a_?c7x?!U&%m>%VzBsa$1zu0~Enh+zXf7yc?ZGh$KNKG}IMReFy5
z%<v6{?~06UWa)PzDqKKV7dIMTX(lB?dpP1t#6>K>FW^`9##*H-XaNxFU<u$v*f$5y
zqxPFr2QTaa3^!j)HGxiW&ImMT4O2Vzn>Uw8CBej$adMcf$~r$pD_TI<ZxfOC#!b{G
z2U31hKUV3wA}Q4^Ysq40*lP@w>CpGm5a38bhXflhRP#nJ8>bZ$9_<0xQ*&kde`^<J
zy8jA@&&2i*c${{kv~2+$THwtm1a3z;1yAIaQh03q>|eI##?t(=Oz#*0GYGo<Xpin~
zq`O+7kbAA}jH}M2s|y)yb%xOA#*4HusolBO#nq~=m*LP{HYaLPnpuYlLD0{!0<3(e
zM^%XK(@^+po9DOZTj$T4#*&RxLWuRx5|3x+jUu&%NB`u@hMuqpPvVkw=H=0@OqW^>
zA^tw^L;t~{?Y_;zv*?GR+sm=$1*Z#&3vLHRXIb^YtugJgG(lK60aZ%B#zKoT*7@-J
zdX{yg%y9|a#n&fNoYR%hfkjaLLD`$;hp~HmRtc$iHj1CK9}`(ZE>vTm6u3YZNuG=i
zpK<P+aW3iNQ7-p6AHz^8pfMVud8B!4ADa1Z?rBe8J82F^yz?r+Bk;^5ymDUuQW^jD
zZU5YCLs9lc=CHOu(&Y)UlHb4rH0gm_M2|?BM;>sQ<_MYMj>37A4*a=XvH0YdupP>)
zf+D|Lr*o@!HSDBYS%{2^XI-F8gMm#UyjK30h}{yzbq1q`MVpsWK8h6>1_RT^SM){{
z;vguUHj4NM3+2esJ&Nbcy3#+28<>cV;SmQULiG?Iny=DF-5Bu5aj{R#X<P@~T;#U7
z^Wx6_F%K;0$()~FyYVnS4Jo4d{05k?fo}P?x$-~i-2Z)>pOKCAfBM^MC&<S5)4>hh
zc!uL_SwZ;(svrvHmxf_FvF3Y-qNyQ}7yjk7_sp`c4Y2qfuB3IF>z3Hm?_4@<LB32h
zx=D1AS!$!XH_9d?w8|@6j=&1ZpKvF9ok%aU+t^RGD=x?Wp-mY$JNWqe!_^{P{H5n!
zeC{?g`RKm(rhueG@Ns`G20Zy8{qFv_c<Hnjel!o?kDa^}v)wspq}<5rj(Nf(&0oBn
zl&Y1mI9)hX-JvMhj+%`)qB1@5eBYcansQ{spdHun7z`hAWP?^G*#3%|6Qt%$`H(Xi
zdFIVf=#l++5a-{kfaa@`i*6PrRZMMwZx(`P27-+4ha~2&rs$`Z5T<;bEP$H^31`V5
z99qSXKu@v=i8zZzPg30tuy?tK(#TIjCg9WtG({zhL)KWBT6+POEe=ahQYv&SwGS0;
z4&ZN!u!PK|SP3|TRMAU3L?QKuz@HXErZlL_v-_wHdieXxa_7^0a#pH&%sL|)TiNp6
z15|q>s^anmGMjda|K9@nUr8gf(Eq~_M>}cGW}OdCc;^j*x44|3c4hlFI6ge0(t2^3
zz&*gQ4w*tNH4yCE$GS(gm@-l9w7coa_SzlYG;4*lSEtayj<%xB7x6moMft<Y@p=-^
z`rAMq&XBkg_Cy5PXL3nCcGN>j{+Dv5C)4-0;X|g+$NR%s5j(OISDVjW$c4w;R!>*8
zA*QnT%=JplvS^rV!@74S?RR6@i!@VCOupG>2=+|MHDSA^%G9(E`f_&1xXZ{p+*a4o
zMs0mp^Hm4$+dG1^NQ5vOjfl>g()T7x(M|aKuIPjKkGjx<(~o+jr}o#2CkLTb3+)fm
zRxP*pX^Sk0c_&yRXnnqN?w~-7U%jXq_9(x2KRLJ&n{Z+sV@UEP6Wm%==%oobdB^@}
zb}`%<wUI%#F`Pyv7_|vR9&ukz-QeB~+rE(EzT-HQ0*~9DSgz1Q#kWF42~s0neg*D;
zLXE)lM2W}Z0Y-S7c~CG|mB5h1^di?<f-)87G8Fl@#0{ykPUOAOT&e-V_TXDRVOKgO
z)&W6WI51e5LXTV;bQ}cZUO|B)MlK?=vD;X3Ae>CGEkbG~o&r$n@+`0=bZt}lE1`4L
zb8~s?R?P?t!4S1FlAI)qPjw~J$A}`2OfXoHw_CkJC|LAu>X%(1_n$=B@7euBSt6fO
z=X=umDmk|jP53?9101aHOfb=C97lKDKNrdF4mP$i6F=&0PPv+1)#r;NGsw?}g4hZA
zxsOOAilYLse)~w{d2%DJ*11>`dB{e2>S$r<UITxyir=kEQ&y@kM6J-i^j%>cp4C1!
zdIUEb1(jaEe~%QIcKzF2W&UsEP?*{OK@`(Y<hMMagA=)VL*{T+m#~_M*8uZlF~_gn
zqRw#66J1fM4<2Tbu|MtEQM)M!fhM}8l4P_MNqe(s*mk@co6H&M-X2a^Ytm*MHuS-{
zFxx)pzA|ysPjBW4o455U4PNtnQiA5K5M+8tnR?jBX}RIe&VH|+X}H+2^Z70vzF0{a
z*~}ohc6~c?2rY)QUEY{EAje_Zs%DKCnoNB&*7V?t$~iu-KHE8HIa{l#3p3ofnp(QB
z$jG*u8Mysh5pt$kHER_g*w<Hlkl=)rM;k6(9azO_^GG(hc6uf^tTO*p?Ep7--JJI<
zv2|td=<3YWGw70N5Z~uJ<@b|PFr30rtg7-Qdl96NRpP;J2?A&cvW8_Y+u&Di!S@Lq
zo(UhCCq>*Vb%H)8%@Tg#Wi%Y)VReFmdH^NCwW&oyoEy+nltm1UM$pxBAQD!bGC;&e
z3YB|;=o{hUp_4PB^B1)XWEXwf;J=04QkJQQ<)G>xo(YD@i*rjxc8ZA*pp&;p{&n+V
zOGI;n7g0&mSDMufnLE-ai0lL-l*GjniB4ya^cTY}kbvp&cl~?fuzx}@IH0i$_mYJ=
zUL;1?V7qMpeMveb&Tz^QNeGSIid%%gP;-PF2XtcU-X5=gg*PPQ=u84`PtS=2MrCe{
zWA}P&{Y=VOx-+*@csza5zaFIwc9EkLmH-PY2{!#V!TWA&06+oWJh$Z5BrZva0fuat
z$}C3|+f=>zs<hy{rO3*OU1#JZ)7S!C_OZ#vP>nwC<3J;&*AD=Rqz>f2&C36ZR=~*4
z{?Amn6&^qb7j)wlu613Hgy<8G5?;Fw5p-o!cLk(|-60SazaG*3Wg&Aq1OcJT;9z3U
z@V;i#uy8f{8E{rX7*%QRWPQ5LD<ym>u%hBYpy#9+6@A%qKHm4x;KlBlf=&OUROn{+
z`nrzlrE1ZKYVK2kdZI`}R8hu%dd3b1iFLy=a^h8JQ<9NgwSr^lO;5ff`e0<6<K&a~
z;&wH%Xr$p~Y<qHPrWzfi-zqQaZnP<hKuJ2QxwPVlJ031oR&!YO_DE!vB`dohSN(Gp
zLO)L<{iK=Bu4SaicA`MU_`6?WkRSgUP!0luA5)SaWSxK(@F)~G2!ISkTu36eKbugM
z-!F4~USUw)7RcVKny=cQP$`z&3|t^5u3}f|4@g@RlAz)-o>}lMaWobAD}o^7AGcYh
z(8N>4K1T2<v}|!R3Q<Zpt@u;nKH?*#-3WWPTj4gH-H3j3<mu{M^mU$~t_|Oa*=YZc
z2RE`~d2ea^Cpr@hYR(&Hvy(Rq<}UBBJltcdk8gl#{At^N3+jI*_rSo+{Ewi@ZCC`-
zA$iWIW{yxB->F>Egw9f+<ZYmAefg$hS?fs)M8bZ1Nhf-p`T-vsnWRd|EgDk?1?`TI
zE$0X6h}ry6XwV14h7pJ-1EERXitAYuV+Ie0T+($E0^`}vs5j5%rH#TU<HE+oI_6{^
z*=Pz^*j=?fyvT>&$6hh+kU|;Jc!sEt`~_SgCH0rK>3UE;K-%)bf)y1Dgk>Xq!FpBs
zge{tgA`pMFO|w2vKV&zbn3reI7aw$S7^{472u%F*l5JI9ZQ8TQ=B!Y4Nhc-SCTM;+
zXIY>35UkU=P;Hl89U+Qr#bP3T4Ef;Wd>1$<TB2cIa(@B~T<a?MZ-dD8->lb+|JNYK
z>skiTAr0+(A-P?m4e?q_gAzD$^wrxGG#l2KcRCA1;Wxp4JuhU=hWv*5jQ6;HI@IB%
zd{Aftdgzg&rNmHMC|{p#>OmL36gp9H(;qxnfr-AP;mqUa-2nf>=P>wovHM)J$=PxF
z=tiV~IzGaqsmjEK6-H}F#{kB?PFFi@oviq9%B@zCo{1kcoZN|Ns|jdpSS!AkePqh=
zN>7)nn6`4Br0`JKYV4L1wb1iRDQ3|Q?Md*GR;4CF&zn9Z?rT*@Mmmt-R(R_9F#Ek$
z7T41+wWrS#49bsHj3^8#2mIF}jPJLZ`CoHd6+D=5ewh(|nU>~8C@Nw0QDZlNDt`1)
zW4k!^)2Vq1VC38)VjSPxgFi?GI3WdSPi$CG#?*cCkq}tXtqXndE*xz8)i_vD_{qC|
z13){gCoVT!%mx^_BcG!g^oE>QiEI36?&}opQ2EzSh4nkQKx&Pm{}!nKN>Y=No$Vj9
zJwZ02|3828Ur6ljRP($nVFKi4%75ft*3R`~n$WlWNr;yNcD(<}Ug`r;e=;PbrL35%
zStVm`IZ}Pr7t@p(o`_INx;)e}*CA?SU=M;TN^iN@-@L0d@vB{yJL_(R235r5d>K4-
zZ(T*QY|umxLpmrQ9Oz?17N16L4m1!ayKYlWoOBgzh~z*|)ce-mcF=m=TqZ;vk7u4*
zuYNR!TNTh+IZ{cqDDtd7OR&ykNBDEO92taGMCE&EE*VjJ<>5uVCpB1Y)o|feeGidh
zjmVt5x6})|YdxOH6YYEE8Uaf1DT;amr28f3{$?P}O)6meT?G#$jQ|G<ZUhl4G?~E5
z>XbM<n(60>EGtI>5xW9tOm34{%_lj?hs8XE5x8*=mdFvG-C6*w!KOrdIz7jI$2_Oq
z&kygno6E-wlLCB=$K59jo&xMB(Mq&S8X|LM*-v~{Ar`9&orS<b>?m=X=)el`odGLI
zKY4GNcoEX{W!C2BBFH(ZT5$Fx+gOY(({=*8J23tFFEOR3`)@uz2G)Pzu(e~QEd%M`
zf^WXV*=@)pbhS4Ez^VwqwwfzDLY`3)=0KRh>2W?^n8PmffWWyJAEu#f)mW4XTm5b&
zCD-%)vLTD@k|T=$u3=ihc7TzJ4GAA-LP~JSrujUhfpE*bJIc!3-8r=O1O(C1w)RF*
z_=F{Ym$7I@y;YAsCuOj)Y3ZfvhQ2cRu0Sr>U;Ps-J}mA*1C$BaJgb`}CZ%m?yMHJ(
zQ_N9|L^9>jLjCjq92ofECqbDClUWdeK;4@~0N%St5b*VVFUjgGJw2wFZD6Npx*!?b
z>643d6GzVvE{x4BM3l_SA6w3pZPd>+d{nBsRGj8NIX5vbzUj-J0N!L%mQ{{-@#0Z?
zPyO4N{tx8)|6cVn{L{llTdwavss2Ao1*^v77LXnY`gPP`mK~bZm&_yu(2L@sce^{b
z@e;6{vAvz0tZugP^&CotSVTK25g^!);e|uuGb(tFY-9#&Fog&<SNqf=HfjpXo0)H+
zv0C0SS5GHj5uCzJ$!2B8*WF$FbiA!w+v|$Y00<u?#oAE)Hdhsb4N@>8;qK6G)4vdC
z6%!gDt$2#AZ>jZAFG?sd^c*NNLYW%qVX@+{3M<L>TQAKOTp<(o0I5p=)U)3y@Oa-S
z(BeN|y35;jHrt>tsU9wwwo2l<_W4l_dK4noG=4lbr6-Z8$of~_BU$*7XK?ceoNoVZ
z?EXi`K+(y-@jt`?L2)4wTN}s!Y?RXp{(rW_nOWHXA*&Rn4z8xS(#!*I?~gKv5Muz7
zjTpkAg?v(`QlUaU4OXfKDs+r4AjVfr7evGfjt_?iHIA371Wc;Y+jib$(PiQ8(R5`h
zc_Fv4p<=n=bb9=>jp%RPrn}=syOVNel+*RB@uB<kz7p;G$C(5e&~M`%+MC}_yun09
z7akYUpy!_CWGsrm8fpX%i*mOxptVkB6U>xrZt1MM!r=zTb2#Dh*)bY18Xt^*k?!N-
zAf<213F{|p`+%d*dyjEN6)cVq&mNopy&~s(g#P6|_O&a|Qb6F~Fz$YFO^4BR+KZ3}
zUl|1*2R~&xo84iW>EnXn41)G-J$Lui)mXu?kco^&sC`+oy-%{8US~`<Dp4jnCgB=7
z3M?EvVK_wmOAx4VOgyii$h?(`haKNMJY|uWfI+-GGDTSO%|+cz%1lndER>0zhDeDd
zNi<MmXLJ9ARvR0aG^IKQ3MNVtB1tBPCW#~{Sc35IK2X(kGL|&NV`!q^H1N(a-eiys
zgm|iUht=z;IO=<0rN+&0Nu)<v=N_qziAskA8axS9c$mlyI`lAt7WgL@T-Jc=4%L8y
zJ}Onl6`nCvebCB)r_NVRjEVpSu?BG>^k@*mfccJOPr8zL8U7*+dQhZ4WL4@F!8?$*
zE@)K(7|s@+GnCH&7GCI*SRho6z(15IKh%sMIFxul445D;7XB|Du@C`WCa~AWjlRwm
z?q@7b4q*n^&wrbLFJK+?Yr;HZ0s5qDIwX@_KmL{-omhj~0%c7Lr0vqNjb4q(^?P?i
z5HKXuE6nX|RI;m@Qmd+(7b*(PeN6hidHU)=pEGz1eHyCg_P#k~rsKxm7A^*^C0dO>
z-(qkkk#~v9{z7bnY)9VbMeX2@mTiAIL9M{IY-^LIDA&}9&{zP(i9KMTt)&0?k*%=s
zBzBywku+;)uS+)QT&hr65&?#QazR3cwE$7&nT-v6k8X`Y8BN|q#d!`@?1F!B)POxu
zo-MhNUucN)Xe3-y^g>(_VIE~dd$Uy|2|C*wj}4qqpWc<j&Q2R?F;tHwyLhMD!Gph(
zwO~}<QYpSOf9hR}MAud!!#p9*r}m~fr_3v-TMqqbKqQplPY{Z%#?$sattL<X=DAT)
zzL~?icySb$2|4e$!AuTWjky?N;;j3nrrwma`*2jpq^7rCfKkydg{yzf)+>NmK|9>5
zL5}c-i}49vEWSHujXf=*NU&*H|LS&)@LrL+^(1)xIUPr}X^Tsya1xUc!7cB=#;p9r
z9MdHh5vQ3ly&OITC9l>BKd&%ja-9vgclizb#Y<<IxD0pvgpy55E!j?D&D^;o1_?iW
zNu)wsX+D8t++#4bGIrnP^}|~8M*IfKM#o9oG~$hFmn^OgjU2WCY#GdTg<`82v`AJQ
zONJB)cgK&Zz8$~5pI;bFM7<Dl8<MaHM*gWdB2tBFeT53CY$jEj0_WYcg~?JDZsN{@
z^~htgO7oI^;rXaHYC)fx8j;-rgVM|HH#dI<H%P~{T+wgrb^GDcCL>fcd1sb{ZrhV>
z;YZiU$M=%rnd~hysR(OhWn&N}F-<7qAopcCE4LXU@-fOy)yc){(5A}#JER)rSLjcR
z7lzdJS5>bG>E<$lnijFmT?l`9xL*apy1itip#eE%9r++xJaOt0B<GG{mkRRvIxD@K
z#F&roASgcjpF7^iB^foZXDwqGKUUR*Qr_tt)Vx!~yxg29;tbTK@#KWCr%y>J&zoNQ
zVaVv^L^j-_@~kaAnzvviy|Q$DWuySz#XQrWB|F&16~?PgR@6}yApXC~#b!NW5b=G7
z5Je2~AYw-1po&|+===jy5iWzW)_8L#yQcgYxG+Q_d=4Sn$*wO@Pa&qJBlYSO7P~z<
z*n@}tz&?7KAor+mQ7F4T%DXBHvY;DGT5fwULLRg&aL2<G8O#~lSR%4RaeN-(-2taV
zFdC4XxK>37@bGTIE4`*Una09AHigxNwe69HcF{Gs<S7I3N|BgV(_|ZsHC!i>YWJAH
z)iL(wI2MOcIFpw+i+A=$U_#o=VJ>X6=x-JtA9l?hY(XSIWp?}%Tp3b;kC5at+V7A=
ztoj{vGlEL?f^=zv)kkR3qCI<;lhdP&5gLwTt5eNsX3reVI9rvhd}oR~%``f3ARBPB
zR%-vmR&tj5qzuWJNL&U8irGynANa*|=kk`Vb`FkWf@T*?bNf|&Rcl|Ni*%{o&iX;}
zT&U3^3B2QaN{3us5s@+Vqjc2R+~$h(MK$)JX%<d(VT#P0xQLE-Z4%~k2t9Fl6{f+1
zA`OwtaZC;9;eJDQs1=6t?d?&QCJ)63?RWAhS{JTv=tuS(?g%G0<u5P)NgM+4^|j(7
zwdwT2BR%>>n0%ZbrGcm&O_kJ1nKdRm`vPYbaJSR3a{?|0m@s&z1w*8;yZ1w#O(RJ$
zDsG@h0vyWm<P-&6>J1u^F?QPcsfVHqe^tG}%#xVvPU+Cuebh_-4&v@LrttXQn#wB4
z17i}wl%CJUp;|FLWy*MXAIcT>*Eto0M2~Co<6bd!hEb0ccl=D2jkkzXD*(S{0IrTz
z6@Zi6BNxq10FE`=N;xTro^mwNk!Z%CuF|EQjuqQnftUfbN8p}Kq4MlwRVdu+UEsDr
z?9wZ|5j1lMKMTn_Ah2y#ecr0v9{%H0e4A?9GN2ESuUQDws=lpd0E{O}goqmvcQ3t-
zTq&<z$5Q_sG8R86dM%q6);Pn(hH_I7bdMd37J_EWn<`uyOc38fTtZ$+8ZaTdhuSHN
zsMuhmiH+oLURs;f>-Q&IWI&oLRX<Zl0MrbhF}fB1UUxW1n7ZvOD*gUPSeB|Bv=_uN
zo|+^3o0$x`rV~<`O#Qk*!?GA^M))LEbe7ngrGQG+JXVM6oa^VawP7jmL#L{cn<0WQ
zsN~$$w29J)FC;mNr#l7VX7;tG*v*=pZvRh`?CVOeVrTrqt?*T?nCE*)Z$gdKdJ_jv
zz#Ko}+ey(7K!MO4YKm<3Mg1rc+U8;CQyA*m39zP>Kf~!C|A|<MHT~h;D<c)Qm~oZA
zdTP%+uXnTGl_GNuD&(${C*X(Q)2skM($6Jfn2EP(wVL47c=kQN5^57?0xN2hbl+=$
z%JIIH7h~SKKL#16Hia#IBFa8Wsf3YCCCpDud6bpBQg!VT4Dnm^Y7tX(CGnNwrywJc
zV*z#ObktNVm{24w63GJAq>792f-+5&sNnlqqs5VdRy40_KeUw0t4d27`^7pJ3ERR+
zQQ9LKm+#HbhPMP|+d?Ej`I%hgiSs$O`m~`~kigm$eK3GtzhU`nX`d(}o$EioIYnX7
zc5XU0X!X4Yws8AuvFRcs0`&KNb%Q^>Hvkn#7OuBO3}8J~;o(>aSq&PaC(XA$vi7-f
z09v?Yt|LUs9t9M%81>xi%Hoi4&l&sFpYrFoZVXEPcBlJBxSo|(3Q*dMaGF#bJhwL+
z7j=KhIt-Y3)g)a8h#UUQySwHe4sRo^%C`>QVb#@^G{A;AV^u%KXdq5|Ca~<F36%in
zm2O!@YN2PPT<3Eh@R=C(OicfTO@^q(WL;AzTQw0r{JbIR>SEg+0S$rcr7FhU-0(~M
z@hxsqA?=sm)ZYUarlMu(0ukxlp{`b;^)KEY=-*8rIQ{jt6p`r~=h8!*^%7C&v2uOc
zx>ZAJ#PCyM`r|Qurv!aq-GbA*4tkA^7nDSoEDKlmiV6cD`c)Y~P`Ozv(qw~)c$m}T
zRc6%H*Rqwe=A2LX#qsr0pqf6Rt{u%I+%RHXz~MxIBQ!FIj4P!Vv4|1S9#gPnCE*y%
zr5o>IbI~#zx_c-H663{ZjK`&aZea9roiq9z3NPEL+~%0cojR8D$K_^ih=_HOhV07V
zw{w;6Q7a(sbDy{CUrP|68h;M5E>H)&(7ptUvNf;}L)=bu{?h_lw=oEwT6Fy#^=E<J
ziylxGen#95vks6-Un2+<n(JZ6+x?=3JFd=LkKdF2>bk3X_yOD#r7N>i<Rr5Lve)^b
zyg+`(RCP1{R#^3KT5Urs32bPD-4jF23RU`ILzVm81TO`Ge&c}FDkur*C>Sj27xC$-
zsHomZNe%mgAu;LUuytKWl0s?E>lQs=Bct;yoDom2cbb|H^lDf8RtQP}7mI>+3=qXK
zZGK&7R-cM20l=vw{_3(kzTi|QqV5&T`rrXuy$}OpXv*E@N!X08ZGg*bm*Xycpnov>
zOge{6EftK|7LxVDKB?bkU<W5a=AK<>2`HiAzo31SAw*n(QN|S`B<oWPDU8aK`Lah9
z+zYF-yo*N!0o^Jl{*>>hI2Pq@*x0~L7e|i9Do<DTbYKMYR{?X}1WXLUrV1qV$&rz(
z<}r~ZNiF3!Dxq}9Xoc&Jz$0)y;=u$Bxl$x3816RYrdLuO2|j;pc6L5E`jhGv>XkwX
z+!>^fU#gnDRZ0*qD3K`!G#aN}en{FL=(no)bD|ia`q+~2!Xn=Swk4vDE*UieDBnXJ
zyg$-(!oYv^fAySQ?g+ch%)N!rT-)Jp3~=}%_Q);xK+KkN7`bPdZxBRQ(_2K(=ENR3
zl{Twcj#iqic#{C%X){vQi{AosH{nFRXpX$@z$cra-bPyyF~-MfJw0Drpj#@b5}Ol|
zNo)GPwf`&w;cWHof_{VDWKDf`&lG!{W@`uW0?lA^33d)4?}j0{c=>|K!f!!6@_(3h
z5<|~ub`~Pc1Vo)|z+l<x-~ELcKPC9P#{P{m2qp10xukUHhH#HRpXVpA|K6^ax?-%t
zRCp0ILt;9y9o{PkEqMDI2R*<Y_As5^(1QCgPVudR8LCdj>pL1$O0P3kgfk;s4AKwV
zuX*h+*9u@#c&b6tK=EY-B}rX;Sf#uHs_gL~c^-7lTRM=KKqEA9f61w8W-bh^S3tba
zb@_3&=pqhb&{%e6Z($Y^XNGo67@A0&(V(v&=;iS4@7LERfnp6?K4{O7QCX_pbMIYJ
z4|MxoW76t?m9X8;+Xiu`$wdwQdUL@o;<1w)OpR^Mgth~w1f8-K<auEd!=SjTR{=9J
z5s-pHwUU%1Mp4!GRKU|U*I+<fjkRXWo_Ow#D#j0;bC0y9bB&@1;tmmbiZmWs#3nuA
ziH?o5dMav)+=r!fN9YV5)zT?pjVPfzuFXPYBvx88OtaUCgbca>mlx&iL7Z*)MlaBZ
zZioFsx@33SXEO_8#7zu&B&ExJTW}g48g{qB*Vic(b$g%$>$e$@X8Q_d<<UeC(F?@0
zEj9n!*A@#y%!Ji~xseB&GA)?0nPXrH=itL2;P<4SmIV4T=3!3`&5VQ^!zOg~?zQ;E
zn0UB`n|*O5;hf(u0;yKCSSY_=fWgS&t~>8>NOgwuaA3<(m_g3ooPV{P1zn6`OEd;d
zAr<8%rele8R`z-Zsuu4zZ@A-A;n!gi21*0O^IST`CfODoRKh>%_G0LiOFNM_=k8mC
z6$os(-3DK+2l#g*45gIV!Rlwy>J}CP>lP_35(8u2v4~vCzJiWe$>>SLJ~bheY7GX2
z`Cz^09+GKq<&IUFE_q>xyRyj#k5jC&$aBw&CNdgyjmM|@)|-1G>?Jsm;Aw%NyL3Fe
zWE#zA)3iIv`WLxNXvs?PZ$IcNa$k1q{={%brpkHwtK7@i;!@e=@SyUAbZNM~w0<ww
zXSwv!sx}tjFw@sgkX>41^BrncfH_+PN<TfDL}gUAt6Bhce_<6Nd4dyWwf1Et%3Ds?
z=);sY39~n9luXQ+Iw*sW@jEKGFM(2(;)Hrz4x8+_=<y8eJLYK>LR_Fuf&PJKuXCEI
zig%GaVlN(dY;*VVk%ILEn}Y@31y1O0nh*!}TO7bvHC>|5>0WR>hzCC2zdN$LL%Shw
zdppJ&Wcm#m(J%=nJ{c^~5cYL@iLE4~OB?1+33L?-Zk(`hyslOyk&?e)rhU&u#w#6v
zt~cW{Dq7Sn+4ZnI8L4B_eLR(Xc>4I;+11>MYFwiv*~qyEqCjtL2WQ~4+u(yy^|6by
z6L{V+cKE)da?ifKltG?&y@pI5;vwHH-cylu@In06HzjC)5BX>$owAZ<KQscBCff%O
zpoN`pR~)|kJQiC@X1n@U>4x!w%RVCVw@Le;9t~r?L5?P<hKzQ}P`Zb0&1NgjqQ?S9
za>+G!|D{#o7U|ek%JfcWtZVV%bvC{;H5d3@kUNEJor}luJvIdEOx;@F7l*B%nZ%~X
zWw5qE^=I!NNL?`dJA6>YDdfFBu1>U}eu2o;a2qa4E=d{1NRO7BB|PRY7rx?l&1TYp
zHxfOb7j7UNI-iH9s_R1Y6Lm9~H@P#MX@dYK{$9O}6Z6^B+>E6n=sSLavEgh;slx{C
zs*TVdXOZOvXQZMBZ<#r@+|)Sar_@HlP{gHf-V+A=+aFqJN_L?&eKBL{B#$!0km8$+
z`ub@)w)=MlXBVZw(3v@is1sGW=|*H(wx<3{XLszEMxJ&IT1d->M@!ea38Rka;U^dM
z<N-k`?m_){mW<`ayp1`P+4c7+Y<aUrO%0_Rv`^8@KlvAFGT0KkE0uUjcVu)C*c%f@
zz=uLd!1vO@?eOUF-GjiaLkF!A=HUe^vEkkP4!0%sW93<GbL&jrYS(Rrv@hBjpt$ah
zrbBs19PyK4e0E@EkZ(>@mtGW56xRD=r$8Mp*v6MJSlV`dn?`3CRiqOvsAJ_TJQvvK
z`nV3h&1)l>6i2oP*$|Lbqk*sUDc7NVUName*?JzpOl4%j+i68>$$j178z%#9`qth$
zTQnTn(TC_(GVXXfIDVkC!74GyR?25O8sf!duf4UrPtkDK6t;YzXC(Cvt@}dcnl3#_
zq-zfDU7~R}oUYDqGAXwTisR_-wniOAl|%jCDBtcj6^N*+lE|n?$4PXqJXS%fdQGzm
z!4T5%8pJ)s9;1s?iP?SSOO_|s2{S<b1tvKXv?V}elSYY|BPBvKkcxGz*-<Uv4-XKF
zZSjX1M#k%7gdhiT8qJs@Tmy)K5|-$=6)s|y(z>YSef&8Nxa7a9HZeY)d-$12a-~Sp
zqz-~4IV$9P!V#CYX+Bl5wm+7#ZMCY0PL!=m5U*|}sOXN-7pbhSvob1XOPSUR3hJM)
zwgp7Ts!Wh+T^ik?tEQKXj!>#tP-@kQQ5%z(pm?DL&m+{;djAh)=hP$$ur2AfZQHhO
zd$(=dwr$(CZQC|?+nzmd=SG}~nEMB+UMec8a($UO0x5eku763)fc-k|J9rqu`~J`b
zHTrn#t?MZE78=Ot{iol81NT5?`j8Q#OaQBxSOH+F%A5KmD)soCIRa~C+T_V`<wy*c
zI(D2pE;l<_TW~E(jyXnbD(yG_SGQGQA}OSa6QHLxrOl)7R^Xb_-S(VYA;^S5^UJ^L
zBv+Xntl0X_A5D7ga~B^D3y1Ujs$cjkXB%P6VvLMH@_vVGDB%=M+EEozS)buF>%vh*
zb0QaYg)pc(oN?+6wq)${<4EvtAt1Rcu<>k>G|`ww#CKlv0nRm-1B@WT<F#MR#7>e`
z$Ic&w4ddmcX#}%h_qBoXXVNW%JMW9HpF*OZUG;K$rb`{2K5FWtzWcoxvZAYbKj8at
zRLcLROaFgCB~1Tg&}*fyACFKk-}~mi*B4{=)9VNbz-9^&^xszhk2&)HR`q6KWc?o`
zONlz9it<_~A0r8PNNK83_38OWgQ^y}LNi?R8e~{uxJ&*jqzOcjz+k*Tg)#=vgd72k
z0ok;@fCv~kinXGZ)`F&%mc_!RYM!o@MN3W3=lqP%Yp(xl@77CA+bXmb=&I@MP+Q;c
zXWuU|(BNz=0tAR$E;d`$pij!9_L;RRh{d3Hk#&_-yX3a<`M5pI03aYa{)jB1BmKI8
zoA?2wco!l2HjgCAGc}ql8AQO1#@6S`S$xnD^p|{c-ceL*NL1_+#HV7gzdgYy5_0&&
zFu=WhfcpO16MPMX!aF4o5Q>ybIM?io$IUkAO=Wm{d3?Tp%eKqS_Is1ft@JT<&dHVc
zxA32ag#toHJrjTLoF?y}rfq4|sk+c{JypsR-$?zvdVvlqh2B5+soKaj;gPA}q7^KN
z3(VOkT0z2vCk>V53Y@>ZQi!E@F{&Wrtdjtu$=bNp@paF;jemN@N>rwJg}+cI%|pCr
zaXNT33*y16RuFCJ=qzR9o2aP9N#pmBuaVdqDK|%4ZD%uMbhXahJ=^PEHXAoJdh}@F
zRYWI%Q7rf3>&?&j6+X8D)2OJn*`xRMlETr$GlppfGwcbqBSeF-@2MK1)dj0bRFSR1
zTZXTOxdxNg1+0l$5ws$Bhjj<j?udoL|6zUqgl-5}MB-z~Q$6K~3bxK`h$8)L0@=Hh
za@L|*C^Lwr>(cPiNSeZ}!;-@=W4ia2p6y<zr^5vuBeK{DXN<GEj-oPR-_o0mJkl%@
zJAN<yzfTRab2X#CiRbIX7|A9z-w&SEO9%4tdnLV8m4V7XX;0av&>fsytb%}EQW(c_
zxdFIdn;F6bd?Q}xq`A9S$*aManT?H^MS=`?I8`@PxB2qDW$EBwlHJ@+8-*oImhV=6
zaUcJtk+F2t!mNKMZK1g2)N<*2;qD6EikVe!wz`IHCD1edQ_=7k855V{Mb)V08CM}0
zeJFb2cVD`tH{iJno)@vH>x{yPLb*Kqz9vVk8tu@whv%5z#7#opEK}JKU|8b=GBn-D
zR3|tiEA$ecW@~N%TE+Dwd0S~mg}~&6$sC#}UqOPhhv8$p4`D6uWh=7QA~9j`$ajn8
zY{0@ru_tcj=ry58(2dpw(N*nF@z8b1agvMNEdZw_SFxNeU~=;Uuhr&?)sAS#6v(+k
zcR3uM7xr}Sr=jAF12aOL8K)}&B&1V?o7i^p*GieWb&+!(HMS1rj-J<3emA4O7l3%s
zJ@Q9h=T%ssB<%fLp&ImZE0CI>2=lUpY{?wsPs;|TQG`vE$eN^%aBpP2I-c`4#;>o6
z%C=@l!Bv8a1<uiRT=PpeHK%oTcTPgZx#dUX+_&AB;~`|tMPlCt9v~Wnh*bT_UY(9^
zp}=|PZ73f`SsVv!VSX;+jtlaJ&;O7JGcSNKtWoS3rZ;(j9(CCj?Gb&1Af~n(9W%tl
z4YTt<y>dWtsSRBGFilKtMy|WsDuF^>*bDLc)T6(|Bq>B_AGoJ#XJu}|w(Cj2B#KHs
z6m>V_0*EJCPw%49V{P@Z0LKk2e`A`f>_sfC8rFx3B<tWz%gi&VNZU8(IdbDhKtg*y
zS{jJ|VK%QkH|LVoGr#9F2Mhtv=aXX_+_j}{F0^Toi}9g&26_f$k1}HrPs_=zT)TLh
zE*xK5>21D!0&50RS0t8nQOn4GE_iKw!=%amCBlm$|KdP~Ob{j~q8b2W5sXwGHrL&~
zegONx=X93}PoQ4}Fz#5Osf<D;5WL;-CG6xsC$WJwbgT89@xlrc|CN0Q?G^kW8FGnE
zWMRz?iE;iWSI~o9S9dJw-G>nPmKZifiXpqr=J8;u6UoyZH^wMbN@jAo7`V(_T*ML!
z%#AWoB%12sq3Khzg8=_dkef{W7-wb3hSLF%MHJW&*`1Yw0=kl<8J#N=>kVahEpXM1
z%98W;zA}^V?u?cEv7*IO^vubTHG=2CpBw7!Mmu}d)P9|axs0kIXzupV!^;78k^<bj
zzTP;EiU#>qCAw|eQz23=QTB2BLOu2cb^VvN-dW)=#fi$UteHEH&`nFg!WU2h2T!Lo
z|ER0i<?JM#PYSB=nv`^SlnmG?ORMO?W$Jc#lW)_=x@RjkM-+zdS-Vo&)7B7C;bq0`
z9r7X-w91j+QmjsGV!~;XYDo511)L`TR{Q7t@ngAlUO2z#8--<Q!?b)3Y?*qh1(VCB
zk!B!KB~#6|*6>b=M+yu48%~5_^7~*D!;{ZjT?Z~Mbp?2J)4Za%V)uB<z7vbU&^-Dn
z#-vNzwC1lb``q%b>KKaJ$xz%ymIMeoz{HeyiVc@(N_S#}^!P8*Go{+>l)D#-H4DJ8
z<Zck`rLatwqnaGVcjRwpJ&3*le`H0#-i25B13T_=P5>;67ue+$fOM^VU=DysLR@Wj
zmwmw-Ej<|d_l6iG-%q;(`3^#1+*lKqqep28sy(c+Rq6?r@<`<KLfxGw#Mv_fZ1SJu
zmNK92>;;OE(o8$|ch=p&4=e&qqId3%M|7cM|E22ylO7dXsWZD~x}j}24(>!xbooZX
zzVy7=Hq&cmNH@V$Iu7{fFhEuV=vReJ44W9$5pyD<Di)WRRje%SF&<E^^Ev*dPyY^T
z6n)rEWu?tsO-&|5Msr7D;l7F7wR$GVkNE^Ufg~)72`OQZNHMg$)WQgZJCAKrAs=Hm
zz^}*yb}{+@DK77cyOZ%cD1te2*bZV$y2gRZ_r$Q3w~}j1nhpv~SK#JE5x8&>Y<nYD
zPuEOI_Jw4F<&r5C!Mpvt2>Ewpm$HK1kh0YXe5N0o%;`dNtr)+X60mj|JP#2Jo=PC~
z(AE+S5se<Rhlh0P+dKwUESqs7VvknhJuE?8QwkYQil~@~Aed8Hwc(NY<uX5ApIo6{
z7#)SZyW)?&c=S1+Fib^B8C%Cd8ahFAqb;>9*sF^pvT}Yn5(9b46S^Yr3bC(5Hbmw1
z9NoM1AowJ4nUJ=0F<r39cZPI0H(b-oz^^$Ch>@X@Gki1Uru;NZ(b4<302m|^mlJvg
zw=IRd)`Hah?J;`+*tQGiBeTH)uOkm(C%?+EDjCoyonfpX13#+%$pZL>#4eh~Qq26!
zQMx`@Okzwxw;4QDPx!j0(A<R7bXfTn;G6aYk&9m(VyW3#sh0V7GABtm0n8wz1c&p?
zw|kr6(#tDv+>I+X`IK#+K_yuBIx&v7kA3JNx_2^_g-Z4U%EY=QpLS`;P#%eYPh3>g
z5{zgptU1NVxV6D%PljbVs$U>@=yppcdeqCuB#wW6GDt|YBEmHA6dNX>8>opv<yXus
z`FzvX*I!d)X4EJn<$we7ENK}}E>No<Ke~dN!_{G^w}`cM^5d6$A0?8Ud*s%!*ru}e
z!2Tc&iRe)n@3`!AllMjac0xz=Cgm2dzCgGq%4^lYaJeC`F=Ly%pi;S0_o0YIw9apJ
zZ2?~MO;}!FlSIp(z%k4Dl7lz<2Ruz@`Ef!ya@=$e>?N4q$FV1ZAN-nkbz+IIpV7E(
zzbAf>*&`o9{suHgjQq_6mX{g~+F<qOv{#)kvM6mTj!fBF$B%a;s_UXrM^h9s(dF#h
z2K^tpxoDYFruSh}{#nT_;Lw+EJCItEqRBWg?PA1tdjQFS#`|@H>%bC&Ng^wnqT1Lx
z^LRr3MW`6i5*XInriQIeF+DFox>n#sdPAyc8ZNbf*#}8yM}DQ}vhB~_L@Dg29@3eB
z_X*APT2=;Zm&tGi&$bs8d8&C`Y3>{cif#)-M?vH7RV1&=e)yHVS6@2p{=%#`QLw&8
zGwVNF>xOoGu@J=8C&XTfTsym&)s^63s0^kte_1g+4C#^e9A$iBe+ti4N&5%3fi41d
zuI}BzwhE9OSZS)KO{3pq>H|x~b_9+Haz{S3A@%yEa8HQw(iZ&6^RU8v4=5~*M22=l
zq|&}Gq5&aCP@+uy$j0}^&=aMiP?fL5n5KCg^N()MJjl$)O_iA8O2x;MS0+kOQAMA<
z<?lK?bbI!vJ(_>M(9c4&fgX~5^KYWfO@X+5pnz!HRfdAwBE9AGl6|~uU!j}Zq3E}>
zhVD8zhlJ1toHzyehBQc-fyqi4Kf6WHT|H553L55TTsCJLd24?1N%KihlG;<3n;=In
zUdonbceRYC_Ox5p&4dT;ai>e&m};>yuVFnjAxtI|(825BF~MC@af&J!(ky)Sj{S<+
zkFl{fcG~%Ix@bWe$6IhxlA$xX6}8I{c!iRmrhA1c-(?h(MPkJZeB5Uz4_{4WQ^;=#
z1Y@1jBP3Z*2dfe5`QeRZcj_c1jVy--9fd5uWa7tGjWM>-VBjj?%5r2lv$T^nu&wm)
z^okWHUc|2d9ipb|fY1pF_Vj!jtvo>H3&iZCP>0Nz(MhJ!Y-m~1l9#T{*?y*v1@5y?
zn~`HLol&AW^|CxVi^}<8s!PN?vN5T>6>HL+lwLrqgB~U@)*?!p+(9pR)M`ZRQ;?a=
zEDQXpxzaj^Bn)VN<<}=Rz4pm8$*tK9HwZCnX^y{|LzuV@B)JbNFjf;Gd{wFR3ptkt
z^J;N^OW@2pfVq;k{(>=|>EoG2l6FfbVFX?n^(!Sd3T$!5;MRgL>}jaUPL_maN2OcV
z8W{jX=cHsmfMZXmcg7k}d6P-$7VZA%_E8dQ*8Zj%I@mOAGe6}v41u{OTVAt?h^i3t
zDqmF;1J;YEiyfS$joSXBMOW{COvdQ3$ff4{^kH6sy#i5_zdOa>tcJ%?)~mw2&LwUW
z-tGblcvw_Rr({+he|u)|lnz61P%s;xJTw|d@zj}d*j4WwgfCc`SUn?|kDvr>4Q<sG
z5pubjJ%DukFWjT&hw<I9S2y6w)9#H<CjyvN%l8d#Fh1-QyE(au^JbaNQqln(kE9l=
zgiF2(Iho^T=Vn`Jdk1{}Y>udApEl?nuehaMA7@}Wqr%l<8BkHhnpqZHzvO%jhJQ0b
zC^I)lL(_Rc;v!x^*$`l98kE2WPsWM!&b7AGNaU#lOkae2IvSxLPD3^+)JUj-$Zj-#
zxSHdVxp2!@{`=r<rAE&K`DeQ;y&Ghy3Y=v%NzLp7T6+0!iGX`lzdH-6+6uDm1FytX
z?jn~m;aw$Jc=hOUV6ezEHtC`?;AR%O1FcUEpNsgEz7X{L4Z*HM=OC77J!x<@PIguk
z4>@;ils;4@czP=(W2%5EAoS7?Zv8I7<VDA(cuGSHbV)SB`jA{&@M*YbpN532jWs_z
zWPK!8Cp}|zhdS0N%Jn6wQ(T*N8C3D<;hH63$ZxY)qbbrG63R<>GERpuSz75pSJwwb
zZVv=yT5#L*$)l@+%tsd}dX)<Jh+Pif0V6`;b6NXwg4C0CiK;gBQN$KV!3~?IM6UMd
zI*E6AT>)qg(4y+p@|!d-B5j?S8*y$rd>983=(hMUp&g+pPjsXaq>$DrO-DCuRXXCp
z;^M9|rr}hJA@7}YZip$1M-&<T@oAtO%Qj&$IWy+w8zPOx_SXHdW6;A<{%@kh{}=Ad
z#QdMM??1_7Ux7iDMMe*K;I01z69B6Kr1-zA&Ga9L<o{Oi;9zI`pMr-bxI401D;}Y=
zQ6?Zf5reR)%q^}EB#5;q{iyS{m!0ECtG00p^+b=_hNFSCwUM<aV-FW$FiEmL5M#V7
z1teq#ajjb)dt!hwyY=pkS1Rq>jrI)h8UHoE8A(444MTu{evj#OX+A(&zlAcn&BI;d
zM^|vBYMO&^2fQGDW)Wj7qCFdLyMd5xJ1EwUxO;w_Xc{gThf1+$j0nDAIzbEm@9vN*
z0Qd*Y*)O|+L0&>>NQaM@!9TM;;41c29PB9HaIT>rdN`<$FaP)|@A!&QNtd{OyZk?9
zXhOMcRvQNe2lw*m1lN|?=W-bnS@zb+<}cY+wWGr$bR^8<V}k>vbDIY1hUv9&mWyD*
zS7qGHdcFX*8oV94pL`a9eAW!!mUXcKUV#CdZh_$9e!WAI4V%|z@P-Ij$j8RrZ>Z;+
zS9`EW`<4Xo4zG~SU=Oc#D)+iws|FehhHca6*bFhl^pNQy33e6(JUsU8-QB*2a%r%1
z4;grfr|kXlYq0G7?Jf%2$Ww>p)N0)pkHyU7i1gY9eGU#Ds_hXbisjJ_;?3a^KHIze
ze6N-|ItteQVcb1G3S076=qQFY2OAJ}NX!_SK5~QPy0JAB8*EnWOuwlCzClw1=eo8v
z-V5Uk<UiFTc*D?j-Ow7c6-6tQc1%^js(xi1%bK<oZp+_hn9bm2-E<moE6`@7)quM`
zXPs^u(rHwiL2Vk=X^e+Kej565)SE$X8vbz%s9t~u0(w-aUV#P%daPI-1T93=h;bc{
z1}<uh4hjsKVnAVlK2Q&|57Hy)fuFk`m+VMWKLJSFzAmi(-#kArxL^<|>Ypf#hKlwo
zLM^&BB0b{r=DZDm+pN8^)LAAkZ&XL#gY4CJvs5>C!w3EudsEezY3)+8_vTys?R!;+
zF91K@nrn`0wj&r#1O?{H!C<K0RV?FZs4$%`jt>Hh$If9j9!W?)@yD2$H4CbYsG<)x
zhy7_YEQ+5;48DYXfmFusv|Dz*-eBkk-VOg}Djbz~Q%o#&lj|~U;h@M#oFC(RD}C1p
z#R$|WZNQV-2uc6IHFXP@lA#mEu;~8TA>)||>>XRQ@Jr>7DGh2>@>mJec+FMVxs9zC
z&a&{=eVz+~TBN$SS9yU{*~Ef*2Jydp3FMHCMY34Y`~-@r9}i^dr@i*xsXk8#*q{|e
za%3K87fr)KDuXXHL^Lk;qUOq0u<eQ+R)hzAgOU^5GR_VrWy%{hY{{Y>+75I^SJt`d
z^QACndE2B*6)br~WhFWJ&q>MZ?J5K8%9ztt`O(>S8FTI%+lkUiCcu;^Ux8MRgb>@U
z#d*pLF?ek1VsMU@X3Laf<(JX`JIu#haqzs1_TQuSp_YT;j8!-e_Mld#R4I-1$zA=D
ze^&A~+v{~d(w)01KwU<Jxvgm5Z3)PzIJHRQCe}^;QG9;Ga41<BSw-rMnIqgZZo3G2
z5umpM<Y8KQy|2Glt`8E{V~H)TSz#T<G`8t-^0@Sl+qg)71!lY3PT$+m;a1rfuIlu{
zdBuEuPPTz*k*RX)w6Cuu{@Kqu_To4fUH6-a-7>ePu(?=Mb$Iu|ARY8t9e1be5xCxJ
zA9$p9`4!ge5n+IxP1JIYmo8f<1(&n$%F6mS*4#f(iuV3s*xTD!C>*Vl$xBn$#&lr=
ze(E3;JE{e5d)#0{S_U&K5@%*mhoscwv*i1B({APu4a^5keC4qw%;p4wlRAtLt>J0`
zwJO>MjF{}oIOO{^V2iE?hmw#>VHzqL8y3@$%??;FB<La#TXOEUzLL1)vyn9hL{yj<
z!6^(A3I9=z%_X#+bewdIf~Kj7-f~B`S{pK5#bUy}`%>;gA2uKcR+Gk?{f2^kJTEI*
ztMirQ%XWl^E$s4qQ;W2-FwvD!BfTj}^brbscM={E;lOz)f3$<Sguj(my-kk^X2Ako
zIrOwSRm6HhM{dhy^KK5Q5W!6()jEqUUI4hK`(w%rT(u9DUGKij<pDZGO}(UN8G`;a
z-?Z}a=W`OS{F)%vk#t@UD8gYb!9C!y_FNsyH?}B&DS`jTLv<3a^vVl(*IffecfIpl
z8tUce1T&ezi3Lf1<wHPxlYek%Er5szw}&cgFumO|pPI0MS{I6?L-c9mlvyKX`Ct?w
zPO5bBPuoOFb0AG*ta}f+5`Y&z!XPGvz=J2AE`Ss<v7idhcbtbiPB;}ca0zI)nx~Y;
z5s9k(3n_ZHnt3+J5eX*&vo6?ige6vtL~BMA$TC;64L%Q~{6NhoouJ^E3QK2n#1fDR
z;2#j@6BwD{D8W*h0szQ~Cs!@SqO(?HWQu0I86oC)X2&4>0t<WG>~9#R`NT1^plN`s
zJQhrlPp<t{av@u=zqAvQAd@61LbZkD;I&eB#jVpE5M~1#ubNwpb>%%+7-}Uv1i3Jj
z5!Dq`)VrS>gQxQI{*(~H-wXX`Mg^oKSNeH4nQJ)Rfr51)@Vbx(rn6E?*s7Qq7-(o1
z>X@opS{fSCMO$con#>0+6hK_vNc}0EgwBf+wV^HT9^&9(!6@MDXlTaA$BUcqf>+tD
z8j~lMErBwUYQ<+e9l#EFea`(@pw$42@UeaV_w>P|HTB9s?1WHq!q9uSX1v4pe8mUq
z?E#p~5RgTyUf20S#OyXWvN1QV<hJ~_FYV}uQ)?yCa!lat#&eninYhxUxh4mgyDjR!
zs#bV?i>`w~RXD?k(n-v5%-i%FicjEmLO<?C`A#XoA)c`KVI<-1Y-o{nc)Mz5`l^S+
zL=+9-U{o3~vMjeS_Q_nzvATaghtlKGPCC#UCA}J67-mv$>-c3^n{OP9Gqy4EBgtx_
zq2C0$#`*LQtaWb-a_qwZ<rvOkgo<FNQ-UKGj_2*Uo5O{KcR|EAh`%gq_r#+CQ-dST
zCceg&mh>mH(i6iEiZ5rvDGgx`2`ErqbiBdU-?{sHQQWv?1vs0Rpe?!dl|HfSBv(tx
zDvl?pJd0mh;w5a{wzg1aL2!VtV@RrzuUzuKI);>405s$<C;F25V#7F^xnM#{rlmMU
z0+B}SwMTu1_%2Q03b#GhRHUq;zhMGbkx$6;AA;kzV9%tnOu~3IFUlX*v;WZmedb)g
zl{wx_-`mTKkJjYkR=8Sj3muTM1)&&IF#%0~#}bEpb?>QBzUS|;dq93@HjaCpde~z=
z_E4{PtJc+IbURl)k4{%=qAnijB8FWTRy&%|^lmux+@7`YB7LDnSQW*AR})O>(fVgb
zB@;jP6XWCe&GkAvtjf&e#FDbbPtF&kSY?<qKg`Zrnc$9OosvVu-*7mZmuep6%*p{{
z84zT*?Y8A2F!zZ4M%84@onhMqnO7b#D6lbC(aG6lLEd3uRQUV-rai1WHX?eF&ovl?
zWumWIb?_N+?CQmx5sg6U0aB40>`%XGdH^(=`8_Ct#f<nRlgz$TOYm(l#fZIoe{r3m
z-I4=Py$3=KbI$t}^LhH~5!-91+7bfv1R0||g`~f_jK<(Dpai7|bMnJu;Yo+0h^nlh
zr>HENJoMwtkh%6<dB5_FF8(oA5IuB@AH$E~vvIk?lH`o_{AU1e()za@^a!m>oU2<=
zp;``ujoP}Zc}n5~zIpt!a|)$p3?lL{6oQqBa*^AJ9f3ri`nFxnQ*MkCT%Z6X4Sv={
z60s)p4m?;S=*E^Vm=?~8wo4aw<;tNu3mP&BWvf2i7qF{g9rHH^xrAMmU9vXlhHrx{
z5;aQ|P8A=9!X_rs1MIWhChWq=@VPENJo3^sem{svWW4Uo2{hy<%+6b|glFJqQtOQW
zsxe`Vhsh{qEl_m+J|MmiEoP7rZ!9AI80t(>&P%nl0-8*5&*L3Rt3xV979?I#HZrN+
z!w|=wh-ECji{}U#VaS|lfHo>cZu0?g(U11Q`4uO5FjYAi2ZR^r|1lR2;%u<1>wDWe
zvM`sy{6_canVma$QirM$#xJ-S2kp3X@dev<ezaW)@rh>n_1B_Hfo+7sG!J7hE74=F
zh|s3qFMSN7j-(<emng3fW$p#~vdUKw+h?N7#HOZ{D|d=>PVDNO2T5G%YCkVtJ~o-+
zb6E7kAWDDZUFh8{_Ui@5maL1rcXB00=ih^=(XZ2!+qDhn?x+c^-DpItE)vQKAPc#d
zj?%vxXHihp76WH(qmZt+t<&pULD@pl9QbQxEkj=r4sT3=e7@W)lRza+VDx|-=_tia
zZQcxGkf`6Xm#e@<$jLJvlL@J-qGELk1q<WwCpGPlqLaTT#Aq;cy||iP#8Be(kr+Mq
zhO4pP5+SaS;1__VzlIF^NYC`3&yM6h3Vh!q0UONkurWm~lHKy@ZXvZs!{Qd2y8>R6
z|7_NM-SA99_~8O2#&4RIZymm&&QKc9*3K`g0vm%Jyno0Y3YGUQTCeTh0Ozsnj6ZL!
zaNO0fY;7z(mX`2<E-Uc$J-Gj~U2)Wr_Y|8_Q_iZ_2$SVoQo8$xc&O4Box3QPxdG8B
zweda!@Y;UgHiy@<RP7KM*2uR(+&C1U|J59{qd^41>fm$YW4ST0E$Hu0sUh4o${={q
zI)Zoa1FTTzHn($%<oA2`$Iau+rP_g;v)!`V<mnP2+0M;fC+i;L)o7WN^5MN*NTAy4
z-Va+{4ue3yRjX3M?zFv7Hb<DX43+j&>f?#RuUt1Cm!fcxR8JfsnBA#wqDq(==-VBw
zmA&Zru8#>T*sh0Di6;OpPJW2WoM`<j?Ytpt^V<brL(U_^W_qDiAxg(I02lmdAEF=F
zVNXV_&Rg>Ji<Y@zyEiAt?Fa&~{K<8VB@7j`VK}K$9tU|SKr8#I+mH9-W1XXgEZY1H
zaR;osG+_InQ#|yzsNNGUy6Nih^~A)UYAZ6oz}z*GTxd}Q8Lq8K*0g>QH`$D44i?;l
z@cCeKW1wXtRVNJv1s9X?)keOPo=)#aIvE&NnAVpDsnNylIQEc7JPy$!94G??nlHSX
zz*cp2Yto*1Xni}=Fg%E|ZkGRSn4Jh*IrCuB`1<hhF$z{okus6{(eFul)IS&Xvp=<B
z2L&-DH(vmZJ$OPX-oIk`Aq|Jn8!041$5pj!y%zR1WL#}D`kFG7W)FsN|0z*R8_UpG
znJx!L@~B?N#y?uM4aXyJ(cpr~YnnA=vFKeYImA)q#79UnhVa6wM07ahSi84#K)8SJ
zXY=$9)#k!&VXa!?$chY66ictt<y5q)R97AZ=?;T<m=d#oO8W=JfE{AGj81urj2(E!
z)P-hHk(IkFwspPnDc%BV%|?dROV(8Or8?-{fl(bE^)w73*8fg-2goQ=S(9hxOIkI_
zZ1dY6etepsKRCR2ZetH^F82>&rN718wcPPmfYTy`0k}9r1qF7}6$0F3OU$8X*+bE~
zk3lB8Gpw^NI`8FjtuF;nNZ2=L9$>L@B>(n=QSkBdQie^gn4FZ}|LtE_E57I?^fkLF
zopVQ8_@Y!`yO;2>Xf2ZYB|Ez70}ewPiz)jhx^^FCfIqT!!lmrenY9Y~N3<Vev;1{q
z()zJOMsWE0rab4DRxX|1!9{1?-p1myaT{}!C%vpVg7<@T1!dNOc6f@UMmiy_U{yr<
z817TmRxedWXF`>V;fnlA_08UodUR2N<&v45wf^jEFVrfQBZ=xitrW@~s}@v5e{pmC
z1)d$g>6e$WH{kfqA6)XXS7B|a6eEA5rp@S2Zl7t;H}J2b;hlK>7xBI@hP>yML?P~O
zuGDT9@%mh*iz~E?hG@b6c2qD*nzrVQ+MFL}ByPQjaa6F2KAkW5kJfZ3s+19M;<j40
z>o=Oz8xk+d2cvSX#OYgfp5UViyDNM9;hYG20P@(x(!RL|vQMF>pD(aW@$OhdIw4I1
zPhT@@m*i4>@g&EX{vo{_eTW$Rn+Q<O0!VL=_P<IrNpmvC6OS=t7F4>Rs(la+V6H`C
zXp(Xe9}cfc5D{N+Xnj1KZ;dfw4nxREHV1@^fGkT}tQXhx^wc^KIGjhQXHno$VnF=5
zL_M<p-1=MjId?-ga_K`*oMO4=qGd{Z?vuYNz9i|8ydZR}i8K4oCxjmo&kGO0%LPG7
zXH=z=nAT4OGup9MhIJ1rbZ^px>|O|0Ve-nSY>e9;-ALv`7b{j~0Q{5q^j!dza*R6O
zF{)%TMc*<T_k<h*xbEh)MyI8geyH7pn(W;m@XquF-_nQdMWEzqJlLPOAMs*!KiiVM
z`~zeIpd5dJ8|-u$h{3OcypyK0`q3Ba3%kxPQHC(}*Wr-q1+>&T6z5<Kj$l^nYKIEp
z3V*XWN8ZlH4FjT*SQ2f=_7?rIGaSiFr#^FtHO}+T-Q2R`%#Io^YT)$xu=QYse9~rH
zT^=c{AWM%X14^TV4LBI@jIZxEla^<snd8IL492q*M;;%A-0@2!oCUCzWr_gjH{orA
zlO)XB@HYp1?E!M~z?-?4lnau`<+NhMVV~HRi2)(alAs+G_n0L_ihR-Wt0xPX7M(Nv
z+8LuyZnvRa61SMv-I!7CV^%*j){rPWgb3Au{#dX)TL0x_0rrSDFCd=-`6RaD;sY#C
zF6NO<NO(MFme9_ZAH?%eaL;p_r@wwixCp?ze1d;oHKW&K`ZDx?q#Ke2J5<SXC}C7c
z%u1$}mXVcASek09gJ>;Et!2&LoJJ8BMfp&KPMa3vRotUL^>KOBCU2$y5GR&n%w3Z!
zW>eD3GhSlCi0Pa<xLp#Fye9ySZ_F;v#<9_~MVq;Zc2pE&+Y5`w)$w*d#Kxn0PxD&P
z+2zR-TVEZ~B33&c^0+&)dOxutw+UO?{-|a2YZrKwoxDZw%94HTF244`HKE*mc<3z9
z@Y9%E!K$9?-Twx~^F*xrXQ3$4D<lCwo=jYxh_Kugyg}NRxrW+tV~r-<WL&Sh*5W{r
zBltz>i?s*ZW3M*EW@@y$hzJ2y?kx+KH|9?pBqYx;@Sf`?0EESE_2;90=57esJiYyk
zm5pDb$OvaLen=KgXu#L}ehMiYY#@IyuR#$dNUYdJGC3wsSkg+0PgzY{XUA9Lwvj&d
z>3<Lt6vsZ78CeV6A=NDU&|03Gbcm-c%6ea`##b7Da(8czfOY50()`tZqF<9MIQ6@K
z?oI8gc8HEk0$X%+_#Nn`=z7IP2<PRudw;UCnxXYp^fgeGN4&o<#*Obc+BK5&pvJ9h
z<9WCvC^OiOxm}j{ui0RpBe+JVH<B!r?x7;QiXkQ)zRRDZGlo}hT}lv8{bm+nwh^{r
zVPWBEa%7S6N<zH%JNfJ+=r2+yVA!g>9gE6>$YSAT<HM*b(uOl?_nhGYkAsOp7GCb<
zEb0D<0CnLq##asr@bT!BfKp_pF41c&T!|}5-WOkNL?5<~i}?5HBB4CBonEKxPx$cb
z0tS}PN0_%TNbeL!47&{LPpF5&9ovzy01mw+C?D*!Fa3UBpf>2XCXe}HvDy^oyY8jy
zeGe9xWCv!ViNWK%Iu@isZadKNg-bJA8CtSpTz&{p%poJrM=MINrQfrE{Q-lmfAMVJ
z>c*^9h!YO1S2`5_WAEVWnZ=-SHpXXn%j1;{t%8+B2^SM#FbvgR5k2GaN=78z9woiW
zfzS&Q^w|o;tnT*{mA2ELamszJiKvuU)3gP10%}dIbKei1_xB6wwu3QGmNCYlR4ad;
zv`O%b5}0k9n^@)L%V3mEucUIe{uUFik+UMqq0{D#9XL}*RB~j#f7Q|(SxQG18hD9E
zSJHGFz3#62gHK0V=P_j|YAZ3RoR`M=#c%p?rt@?>V8zF#mdza*Eb}ERZ3}#V|J2Dr
zy>x%VyzCzon0VSyvR5y6{$M!sqWMOr19$BUNNV-(2J>vT&GJr>PA&4eiT-#r7F3=9
z{!QSU(UZ1HbOa=rLHadD<M;#mFHEw8h*7ejx%%E7)QiISq+xKki=td}ayevqyf3_o
z#P$;P)et>tt9u7+`i1M&1|_FXrHr&U!MR>z(K)8HIeFDGptX2;@nqh>g%k9iIL~*W
zJFD#HghX|$ZLy`29(Q+EW61?ez|7LIMI$3sP=CNui;Hw4IYf47b({W1NLrauP23*d
zcI95uX9AfJ-3Et75Q?!;=_HLRU7>;A5fyW|v+ytVyGJT!Mw=iX=+5vskSw~aa5BB2
zSVBbq{WzjMM;Kp3-a^g<mu%S|6dn#|OeOoJee2%d<RnweVc5EJckh0Y$o%V~d~p%<
zxrprdN{(-F678D~8#5A}h)3PMzI$Vns%>%kTL<9SpA@erQLm;fdM@0oATS~*Nd*Y1
zpj7Ezvv6jGx1qg#ebY>_Mr7-_`@%KwzjCl;t03Am$;=Dl13O3$t~*iUqT>CUsdV=s
zTdwKH?#lhMj`$EA&vsDK*+h(rl0|*rLvqPj@JjDk2|3AH@u^8gMF)GjTM>&M(!hzg
z-8Ip<-Yhjy{#xpSMS!L*gET|^1!7vZStOGz;K7F!Bqs-fO;Au*2OyQjQ00#4j-c@&
zN#4Vs{_O|NSr(U1%p5|v9u~P=9S1{#1ANNjieOMui{>`AtP~~t!9sd0RsAZCCSY$4
zBr>K4nG#oewP9EU76iIOb_RYE9rH8oHvVB}|GLT3LuqgZ3K7XdxtLX|bFuZA<qRlC
zAYZgpsKvf}<;}YlosKMDyKlkvXk)AWdwe^s5&9?O0e-Q<A5YaOI@(TO!W}<!pWo+h
z<6lj)a~M1iK0<mw$~9YM^t=qw*M;%TwjQx7QkfSmAS+`C<z)Kh@J-4$m2z-Or3w;P
zC@)2nQXwNRgb%%Br^X5jrhsy?(NXp8OtF+SzI_`R+i4i4>1Qo2U#SZKG<ki$nmioc
zt}bZX|E}e!Um^GLeWLP^={mv9$J+fW0V`!Ay{eOyRf8x&)gbhFQU)p$`rJQ3BSn_&
zh^k5$bDMO2L*`T4j$2hk);`Fo0=6XfsycLD@I1fmcXz-zTpwLOve%U?m>yFnPWV$r
zAKNn;jJZ)LrFKo@UE|TtTzgOSUMYD}D&D&3KzRlf9USrJwnINN^~<ub@7HlZ_i|u?
z(IWaOhx32nMMhcZV2<+%3}(6Wa#-8S$;jixHr(ywi-}iF!$!V)00(n8AjG`$lF|>E
z-DumgYdJij$UX(^9g0Z5u51Z#<_I3$gX&XdyT2&RoM?Jt$<Z953OlFtKhafucqu{5
z(w7rQ<2M8<9my3i&Q}*s?#bc`5jIFpDPKOs+cRlUs!dolcTxjwIB6zy0~7-`zThy-
z)6_m`j#5WLEZta@^cVRDcy;PV6*4WQysI>@^$_F)7;LwJ%C5BJS%lu95RwOG4d#uF
zKz2Ak3akHd&*#d{wCEH};$r8Clu@EYVe&+o6hf<)Bbj5*QC)$NdRvMYpoDT=G6%-+
z`;yAs=FbZtMnoAgF;{-9_-g)((<}P}usd5z!M8q}_rjGYuRpi0(3;Rf=YcC`?L~X5
z%Gj@mE8v3tpzM-iheD}FmZgHTcM@spcu(Y#NkyEq?S-e3@#kOb&BA1JR=QIyj{6DY
zM@jfaqi7RHhD43B+2w9m+jUj5${Y{a%_UQ0qI2i4ccnm9##|IfnsnG>C)1BbLLJ>d
z6Z}F)Vi4yHN}jBHHi$JLH3j1)RLskcge35al4aw?Zj7amGXW)d<+8gc)g;~&aLKr`
z)zZYJslw<KqYxz&#NW}13JKJ_q2ehgV5TC|g5?2ZgA9t4xgHC<*N6PfTMr`ni!o`d
z7+>U(lB+}yffmf}ci+Gm{-S>k05jdi%tqVDzRHe)Gj{uozFRYDSnQB7y+P{~-c}-9
z*aHOgZ~v^wH>+#cRaY!A9q|g3j$4q<wx@(?x>#~#l`51>SP=_ABmr<lDRivVG1E)v
z_{-_>Pp!;^oZ)HJDE!KqNW;qhtl^?g3Y8R0bo#I6m0nm&&ZE;YcRQKsmq<)nX{i~~
zLkIK7a^e$2H9}<yiI9sJW-T7aE|1saQ(qFW^{XD)p$d-g-u{T#IE5`O2QWkh*Sp`J
zacZit2H09qahYN|mGJ<4BtWg^toPk_!Ll7x)O@MYveEJ>OIGMKZ<5K$z|EM(1_rJf
zp=1vpI*cV0hH9_u(0ps<YxpL)#1pm80xecc@iE-&<wWiWEq|&@BR>X~7Z9V0JCnbJ
zl=QUxE}%cI7z=4Me5<o%q&AVOOCe2OC8|3$YBs07_;@>h1<a$}(HjO(24%&pDI+73
zCyr1Z!Dd8H%t?93qz*!)$){i~!e-zs!MD2%Xb1SG5<^fJ=aIh&gtYEo9cS&okWJ*6
zfpP860r*jMEIZ>>%>ofR&ZTdFdC!J5({{<>emPS$Toh#}GRjp;$mWX@GR+D+6Nto9
zQpHqR0~Y-vPK-+Wv*vJ)x<CrBMY2i+r&N`PYnJU5kVfh)G(LzLsVXUWl(6vk*DqZT
zrKUQZQdqPHX;E}4xGE?QM>YUpwgr0fL$4^0#Ri^B%L;oEiL&GWr9(szPCX-<oMrOx
z@necCotLVIn%=j(okcH_tp^1fGFDz)QcE3D3s7OEO-O@t50_e&v%{_agK_j#!{VJn
z*-71$Z$14af7`um6QEmm>5LnxkJ@Nl2F8vHn=NReFFe5Q#PG`G{B(YX2up7~Kd!lt
zvw0?n>a|-lbKA|7{fSR{2kwkmh`S(iwF&A1U31|Ec1!e3u**MQ&KpW(VtLiuL&=HU
zy2u+ZJOP(mfPY3FA*BE5twpbVpRjUxkt&^(^L)JNnc*~TMA3qWe!k1(%Yp~DMuA%0
zF25g)1ha*@^GLTmu1|Mf_`rq1nv&H_Onl+VRzg)t<|aH6QUr*x-uV!Io^{Wg_n8y|
zeYgTbpwz6aDDzWKQ*J_YF=4+9s?Uj0D3&p*11N7DK$tDdf>`?#%_8e(ok~aX?ol(p
zl`(66-m<}Rm}8Pie+VUek8`6je3)vI1Kcqu&am}#9S83(*lY68Zk0z>7wS<)BxR}&
zZ~OQjNM%7x)q;w#$RrW7FoeX+t|?RduyKS6n-;3~D0Uf!F(2IkJ5!Jk$GId?s#Gfg
zD^x24aBjW6a3gBZ;Ni4)x6(0m#kwkw1sjU({&-u6iZ1LzXKC4x7wvAv`~U1U=f>hs
zM7x<NjPTDC>_t9t9}h3_Lp+f;hY<&ShyNlOB+$2&V`CNiv2)zq0*<MFAhbf{L$yM5
z^f0J8nys|FKdRMa^8apDa=X>)`~&9GZSlN#4)uV8_P9U&x4^!|tyJq?`~QjH-La^>
zu^}2r-~5Ip9QZY-qH+e7RPQ5nAr=dHMS6l^5(DU-?GkpD(SJ$*Fs|q(I7B#d&R|Qz
z`d1RfR8M^!PMUDldF`iUrcz}!Av|m9UAWg56lcE1(gyu}!e`9>yrclsUhr+CcoB49
zxURq3y#7&*Pf8H9YSx4W*yI4cNNaST(c~gL&;eh)XZ>r!_1^c3um|VJ+|{Ssbo%Sv
zm~tWA_{~{4cMi`8lV$R;S=G~`GDk}n8qk61$+$CR=%kRBn=fzIy7s*58MEp<BvYg6
zRw0is97QLbRj_oi$h`RR^o_r@)SU9)Ad~;dlKOw=a54Xnpz{Cg*<o*>|NZjY`_1|N
z{q-6H0F8#RX9xl$j|T$41%QhCZyWuGIp}{&v#_(V{*P?68c#QEm9^CuOoQ2cBC0V)
zj<LVO)s(I4hB1bOf%#(f1%U)T%rMgmp-j#%^Io?)h^VYDfrt5Im@%2@=C(+TnWl+Z
z$2#O2+qbVd1rQw*J$tWX+%U}9KCT*GbuGEi)h-B%qoc_ZB$?)BcK9e5Pp5$$TfE(a
zUpgnDqq1KrKPJ|Z?jrZu;cYl0eTKvG%&VD^<5J4RJrxdnbcMgX=kPUeCXq;_vFLo_
zHQD21S#rofnLV@4p#=sB7c!H^D5Qm>3P%-b<rT|rD2SL5Vtwiplf2_IL!&#y3I|2u
z>Kt|hfg@KzfyBpry1P(QA<$?vnMQBgwjH*)B{f%qeFP@ud2uCH`CTQ~Jkp;Ysak=_
zLRE1mRe}Mjws^a>Ke?%bxv8;uU9>|&yvGHpx)1sF`}1q38eE>A!J1S-$G)k9ZQDb8
zL#)d~J4`h5JHoaVcQ5tcW??}^B`ym2gNw6g`QrNJVJF)isi_5cc&WQkqIZ$+kEjN^
zkAcU!kGvs#1&`n0Tp_dU(OFhKE>TC?+*!}qZ5-CwWeSuuyg|pQH+WEL_`mZWzrM}F
zYg&QFfVDr#cZMNG9vO|rrHV@x8Ot=5Y|m8BSkGL~V60)8(lbS;%63Z76{5?AmXIyU
zo>7`&v}LLa)D?f0EiY{>VOvrg3s)7dDqxdYpW#{}8Vjr|W|DDD<ZTLC|8-irRa_?n
zpGaKiyDD{+?<6C)q-}~{mt|9;Ujm#+btv8>gP%xxDDx%LpNNAh1gIdO%7iF5QY9-X
z7^rZR6sxENpK~v~iUrbztl3(&3094&pgjAD#EFB(ee9Z7Db_FiVuWGiGye$wC9y^3
zFEw#y_^ufiU$ki)C7C@QJx4978kNC7=1s-=Y`U;k_FKvu^N5kgcN?<~(CEhG=QH{G
zhD1Ytkx!Q6vEtk7PRN)%C!fheVYmo%u56b0xG-jUe>#@eh4Q+9j>7#%&8(Gz$aK(0
z=~KFbSLI2`x@3ADp19EG2|CTII)`M<>@>l6njBKoF42_c<j`f|arRh^u4BUKn}oXb
zoxiCi7mBTa;99dDCTSLrOn^3QP%u-%h&LJI=#lbODq4MS^i%vTI2dp5wQSG~SW0Yf
zFD`z=&=3Ho6X#z-b!jj86VcPYsW)7oT$@ApqGb5%&!s)^EtAH+j}}`Ux}#($*awdv
zK9lGi%hg`Q%wHEq!CQ1VrCCDjh;xmVmy_Y&ujgns#y=hn%zWSJe_7tSSo#G=JGo?8
z#T4IKjB(b4ulKaqpAb`F{FTdYER+2VyOqc7>8LeFU|Qohv+-19tqg06s`^!?5-_ww
zjG&BjaT1NJ?$tIlHtVwi$lS!y#DTlLGGLtJk;GR<T~H-!w-wTL>&ofOeB<B^!!Nvv
z6<IXz&7~O&{B>o|iQYZnCV4lTZrO%CIYq|*9oc1N(s>uhPB0p{*)-(w5}+Ms$xTOi
zurp(EK~_0War@0w>UEvTe8u0pzTw)8S}`ei(>vO`_jRx#EQk?S975tmM_HLpvAT5R
zoDf=NTgRoN;D?K*-n<wcVPes9Fn))=*bh<13rF!`_))@x=@i(xI<MfwVUz?`@)VPF
z^YkR8+BAF5jx~pdmeVnQBKGGal|m+6Q6<K!wUlRh7=~z<{qQxQu9=68UpDIa<Q4~t
z60mZskfM#FO(``b3!aF{pogPK@YA=61|R?7d89W}phi{<f@m4mp_dDmym2x;-29J$
zk^>QVp-u26S*&cdq|&64{k{VTG9OY|NbwfPB+L5iJfSy5ALsXXGg$HCeRb!xCDKZI
zz~g%5VWg5=JuAdoK-27(6|czE>t)94o4q>a%56_eA<|AYr%QvltJ@T@VXy>84IH9e
z4_=x>jL)S$mlWN)5-{BXL5?X3LGSLTzZWuBiLEbNT@mI!46?;(620YLpAJh$nakr|
z8%83SVBkW`BYMqMPN%?u0bbmH<<hs$@kQ*1MFV<JN9aFyle%XRe)u4*iL1px_|3NN
z6|WzT=A>|T{LxjH307y4ve?jtw|$_YO}SsAV*g_Kd+_r_-AH%V=yuxOY<3Kd!6vuF
z?02O<KCvVbZC_tTcN@<2tVkNxyLxcj&<UGNxH#<GqXbIwo<MI~q&I2SED<s?BjTDT
z^&^V;T9z6>bIR#?i)+{cp(T0wax=nWRe5I3&73M7FF~TB*Cj+4qlh}5NV>@-UP_0d
z#l1ue%<FhBpx7icP_Puzbo*J0gD6;y!XPyWA^T_1ffEjgQ-+(W_ls(_^@{zi7E={$
zc%W7i6)`Pz$m*3AgZH*pqOo2!O+1<s20emRN+HDK7VFdMqG=LvXr8$%1mJuvK9!7z
zHIc%5#-~|~)ph38-_`b1d1+3XIp4gK{ze=_(D5pTO2uWbtUlWf)c@Qrg^Zj8A|-Q!
zXGc%J`*2Mcz_Qu3pN7L;XO-U{{j_Kt<{|rG1jzpOpc}1t61N{xefvE6F9zQP$!U%b
zWc$gIJBev;&4)QYZo%Blo?VEHJ<rq9R0sZ96fWS9E9wuhIByw7EwKF?NZL1Wb+@V3
z_pIC3=qCz^o{@pLGT3@_Nd?CtiCGIDE)gp)BW6L#@h@s~@wltcl3luZIDI^vb^~UR
zT?Q<P-Yf4(Ym1y~L5DZ^1?xVSAdwC9u(<q<#e^tQQt7(MFs-)l`+0*b9ze?n#)`wv
zrld2rri#w4mm8NmsYPpIS#<a*D?=Y{`v89ubS)r49~fD*9-a(q0C-n@6LEh3jPUjK
z)f&=*TXSzSQljl%ZxiMS#>f<N;L)>U_B(w_P}Dz9yy;6pu9l4$U3BX<DpHm)LOw=9
zb+S;JcxubH7p5rKfJ?UqnRih*#9kfIUIQvBt^djxipW+NPHA%GsbVO!u0JL;4KIk4
z2JtH>+BYp49p@cZ_Zt`Xkd7%N-5xmqw_pHzrU39%<EqABmxP%tbPj!<AEYXQIZya^
z1a?BGb7QUMFMza&-83Q0m~kScyzXz!m57lOvSF*c!Lx&N8eJ7Tzz>hR^kg$P2fdfq
z&?<M&-cGN}=P4(+_>eDw3^*N^)4-?RVqe)_nc2_&5_d^YqLlX0QOr=vc&3UVMmLGW
zkYeD}no6Nr&}-o~f(N9wc`5Ru>mn77>$*O2;MuG6CVOTqn?T9|gyzRG;1Kwr6AQCt
z|4X9t+sD|NLE>yS<mnFh3?UKWpOkRdu<Ln{2CKE)U#7?)XlEDF8vxHocw;8a&rxfp
zTqCaV4f!SkC^WO&<sw)HSt+WEF47$}+a`3cW9Em?BlS?Ym#b;{3*2V~YHtQ7chKsj
z-L~u2O0hiFUbmadzYB}t#x#sRRx6R$Wv|{?f$7{<L+o~1)L!2kL<5b}d3-;3v_VIU
z*DrKe2u|iX-(EWCU9-L)`<J^q+7bTct88#n2u(g2vT3?**Q0Clb(=N^)B0=I;%%bd
zBzAN*uPDvpxl5Mvf3JNY&>il;b(|sEoQz`~y69s?kKwsi)!Nq#`tQ!1CBy9JV1CEd
zs6a{F%|Y7U@GeN(XktcbO~@xn88eKtIYj<tqHhpqc#JW()6^qb(VOaYkX%tS*+Nx8
zLP0@8LsddrSyon9T&~sC9ngMgz$=4(L$#v~kxPa-vpA?zhkY#f5=Xo4GMxVf(o2{6
zt@$W}YGV>V->uh;gCm1dFfRN3p(fr9?W5`GMG~*^_WCt!c4{s53-B}u$dj0>HUJLb
z>Qu=Wsv+da%mU@rX9Ieeo}Gv1>!+n4-RtS8Y?WD0&R<u>rCEr;yCT%N6ZTuD`@Xow
zAIGpu8)je!*&<YA;^{R7V3I5$0ixcdYHWmlP|z|m8)1D}@Vc^Avt9pCoj>iS7Swii
z)wNBj)=)&l!_9Zldx?wDhe6Kc2Q2#0QRMnD5hQ)>^z4j&16k+xpQ}1h`%o~<g@-B>
zPFhM~#8FJ(AI`+cE=_(vC2u7fCrjqVMdfO@T4(8I^vcJB$!FJCqat<0I=*XKukR4$
z;wVAJT@end?+}q-(HCGLG71~`1d)w4%6YjqR;vbtG9B8U`+3j*4h>W|(KZ&7vmVNu
z=j7p>CC6%U$ER^IiMW6nM8Y<Fh0Xvns>?O6s5u<0cNA!<mr_!*3J)eZ<Wkq^al~EK
zhHtms^_DH!s|}O=h_|BraI0fPrr--}i(jqObQ|U@`TQ$BjZw)k+2zR3?KZSo0zT;@
z{RfA*@UW1@0Fdbx$-|e%5Q$u!^T_ScSlV|7C`o^@j#rQ1|4{Z#L7HvrvRz%a)n(hZ
zZQHi(`pf9DZQHhOcG<RZ`@F4vVx1eYU+2R&9_Ab|BQw9u93HPH+WWW?O~l&QyeI95
zlMU;`gw%FMq76SxwQz7CIb~5#PEv?h@t<dmp`5OhyY^k2V1Qm}HcuzYkatngQLS4h
zW-no_^QWnyu{;_jH6;FXwO4NydY&c~)|TY+xL6jMB6qP7?oTLuR{zv{v1TQgT|R1O
zRUv5d`1(S-0d3eB#I*0!FHnqfJM7)nNJy)d1sF{{|C>V$5@j-eVs4_XDy@SJuGAc^
z<W#@lxE8Y6%x#d!<}4M747Kls_=?00BAZ&iRI5;~9xQ2&%D(HcTNte8plv7}C|O(@
zMKdw8c$9+g4gx;($}!}TRFA$X_mG6!3F=eQ0+X7YskRbx6NoroLpD8#mHF-c92~y%
zTy{tVV|!sw*Vg;qDbeZ;0*=8Yj(4N~!Vt?ZCJ^Q=0MUjY1TDP4cgfpkna~g;8LU6C
zZ7<L?0fE#WM$6DzN1x~v5d9GI{9CtG8L1H!vFP3Zob8wA)a5nFj&YWMd<c{EGb{cs
z4yS5v$kruTVy6&#(=(BQUneR=8e)%5Y}qzExi0J?y>4s)k$upa60+ss<J_0;<`3FG
z?{nDRzS<>b&L3NSW5s<10lkvN(HJD8JjR<4^xRzZ&<+05`&Na1A{qgLMQ6fpo_(6J
zO4EE8&gvPv6nKwQ1u3+0sw5XfumR*$TvQ#>swL&|RQ>s%7hBuUM%M!qdPKesk%fHP
z8Hh=;s~)uidktOsxBH?z`x96l;vVM$hApwa0fqE!cC<L*Jc6BZVzqp#wE=aQm~)w|
z$YuxQ=_rT05w)ZIgXYU0{#*t}i1c0IsS=uBT&LTj&_G=yP~hD^pE#X4dbcE$UN8Cz
z?n=h2YLSNl!kfH%567@rTHrFt@f?OPF8tyf20~mbC9b~=T!{iB7lhs#yy%lB@x&wF
z*_e-l=iid(=7r)37#M2fDYa>Wa7|i!CF9*)QVI(l#D5nN9h@k6!Rg%=1BBgzXgpv!
zG1It(D??-(x1-3QRf%yNKFw!k+^=hjk{CQ30(<b#)k|)uXeU|R9jeO7B@@!C5e+|y
z9OWw|7+*SO>+li#QU?D*^)cxgvkA&b%Xb-vHn?%;Bef1VXP;$IrC_?^<QXJks1e^V
zHL3M-P%Qmqj62^0{*IzjA?8ieJ?!%$NNK3dc-fI04G<9v4pNs}$4XP2H~3_u^v?<h
ztTQF4kN!Ho5o0XY7%&nuUW`;OVJeDEzXW#Ep#zEto_b^%B*zG($ko00&UkKGreo+)
zigx4tOXxgUr-vL|<Zp8fB2SQPOW!i+;a^(`#f--<d%k5|2*l9kK%NHvT2WpIoY*+Z
zyAyAqr2~Q-M+Q>qNMg0Vz|->4G4_RGd#Jn+U@_p*5~%=y8}Ve@)-+RA6G>ciSSd+4
z!C>omiR^dLL~MMHi$E(v3G%BP*u%%TxHpVsNjOdpB`*qA7UpC((@%BS+1I_Z7R1pp
za0`ptb176W^pqmDS{jiwF%I4m-Miz2Q*b!~w{Ncp;|H78hn*Zu?-@TJx#HJvpq!sd
z>RZ4#fuaxc&-w#6M`~N}wh{#47^lYw1sW5h?1Fr{5Cycl)YsndagetadOm<9cZ-Ss
zw#ti(Oh*kJVU;j#Ow1j%I)Sipv_LyK5VFQM<g)$WmlLWNA3IxWZtc9BYlZU31jB_>
zJbFz6rm8q_c7H-NS`5k%=$3Yve{8WjgH9slT#DHU0UrybK=9AS;b<aEy_J9r7dy@U
zbjrGIsj`Cy{swmjNh5LnWy>xq7I({zIYB5%SfRy~5y>cznHv86`aFdP9|T+f)4DJu
z-1H%mC3VmBG*98i$Bv*T6nR%>Fncu=JR#vg*oA%-pd&++$-n%n=+#MJ3+@;O4XHOu
z8?TlVb7)AnQ&T<ac@r93qTuFWHAnR1+c8|1NVOiiVjBm0)Ts6-Z^w@&^lH4<c`W#3
z#eJ>97)QT79iTvewsGByt#K@QyjIgxU*Ge6ajw;J<?X!SD&Qw+Q4Gu!piK(B-vUFp
z@UuIUHI_|9(b}5vPQ9H<Hpvtz2{#*!I6;j#Mb-5Pn<w~9l{ywC^sUlBtZ6~O(vMya
zxmfwes%WM%8v&9q;yW=Rz!_s6xEGFeUf=O~jETVLk4Ntt>;qKcm#ClHyk`kQ`T=LE
zT`u$|n4ctkvgh#Lc7^EV{ZS)Q3?FiE@wfT8?So%6A;S^TnYe1dt+lJT6mkP$1c=wy
zh;Qo8;d;E7pWyX13K|Bss%6x4ZIr~Z*!XC~IZ-^Hrti3oSMxrhoXrFslDXFQ!ge4%
zP>I09SAKgwxPSh%HB%)fkx?M$LnAjRaj1(57a50FSvQmILUjBP86hJUn?Q0*e4Mi9
zw~zBSZmt9`e&n}=m%c`9f`09_3(5S!{ZcUxex>7;#l5A|@s>KU<|J10M=aNqwknKP
zErhfjgeE@3&jzJru!MwcT-ih+$)yc7SOemhpPyK!N^D#fRmbXc#zVH*b2d-*-<3el
z<}AMLIUo2qU0%7fe5i<M6_%{CN^=U@Y6t|!Od+3;W&OOS+r_f+;r#q@{S<T+SRs<a
z<C@@D1HRakoDVTMa@&D*!9t>fp*oM?)~KlxsR;*@-*@8LuqpD`4(xR=$|53OUqT6)
z6EA=TMysksck(5JIrD3^Jw=&z)v@8ZGl)vb<ziD(rxNst&l9#JnUsBwDbSBy6AkpQ
z!X4^%MQx?W#7moqMw){=w|zI)(GZw(T|b&~RfKDL2kaYAvM)xSSSL}>+#~&#kV|TY
zY>rTR<9@c9fl_!mw?$Q_!5In0NqSW{Q&s5KvH45ci4?81E#JF`=C6kL>n<Ar%qt5S
z0`-0NR`rbU0#kA)79QPYte?mQ;(cuAp7H*U8oG{-j@FiPqIPWN0LxO&7|-yR_v8#8
zF|{h{Ok5h(Z9jm~4cn=+2>+O#G9{Cu<L%<7CGEL+H#yP7d-E4;TVSZY=%CYw%xRi*
zPA7&cD#mgA7%DQlLnA9wXL!|2HTjC8F(&p)4G!2*fNi&!C!vx8B}R=R#W7=|$e;pt
z(NYLo!_@j2Bh546BO5vrG*(wdx1{)2n%(QT*?hA+HhN7j&?z~=6cZyvPPa4gv4y3A
zbwj?Uj(Pvbo3B_=wbIjJx|lHxA=dY|BlI@7vk5eu<$fxkWxqpe#UvWI@>`z&U2*Ba
zMRfaf4Ai*4pJZ0%wvPWY;987%;r(H;xocn!`RJ@qJf=q<?MC54-9qIe+@ym|Y?UK_
z0O=?J=r^k+J0~A850xnWcsyd%;;8&X_N~mb8$DdG<wVk>wTz0!zJA`q#~zK=Cnk@*
zXN*=9-!(i{AzPR1AR1B2eqUP!m8!COE1E}RPMi+A+Y?+AMb>!^pq~*sp&X3KGV&{m
zlbM4NAE>G0lHAcWd~RJuiY=@8l{*nwqBfPnM)FO&O}+WNw^>C%RwEib&dO*!`~fQA
z?%@H7Z&_YpKP;FSYC_A>QF8rGq1QoYQ3g$#*K?Cg8TV5h9F>!33zSsSk6_-i$NE7w
zj-CEIE8nO-q<Ptnj}8)IOgL^mYIGT>>;YJ?s1$iYz9|w~wa&Q6ux;f-k0__S%?UDR
z=pxa>^Nn`(SpJ3oH)XsMln~f~dzW6+2cwM`;vJ_OMOAokuuV?R;UrZ5s}<)Q#plx3
z3BzdK=&`egB8aTMk9}%{QxXh{4`l{I;=*9W>T9e%qh#@L_vPVX@Dw=~r#@}vf=h<7
zim`FxD2%g-GCamJ#Kp?Td=_ku;CM;L!zAWk^F-{=uF{mK^(LzMDa<}9l5K9!NnF}U
zsp+HmgoFe_<2=;ykhk)?WGCGeJu=2!v&`6^BY@lX<1mk(`FLMI#e$3Kh7CSlRqq^G
zNJA?oi%FxN)j8iUyG1gpqfyTvKCXOlp(LUs#E@LCDNXDQlsIIggpx!RmX1=9P6*y#
z9Zl>l(vkPZ0OC8~Po-V6c}89j;i0G^A7mu&HkWvGmKrJgBDpRrkSFzM@+?T0F+*b?
z>M;Zk5ilh^^2|#(`V`e2OS|od8*$^DZXVsf?r6GYr`!M&B1-iM+&Q}Px(Rgnm08>b
z<+o_~uB$CC_xhF|%47%ROy{GLzi|s_&;1ym0zAm8dN-X7H5<jCE;ttLo*J%pf53$W
zrP;2Uo~qQ;FzKs_%kWu{o0_-!UN1tAyE1|Ey8r|1JqRA@YUyK7iRRekOx7@2#c6@Z
z=&W5GLw&Y=eJ#*4LH28FZ5%3ecdNnMJyi6gDc$aGl{t%rP~FSWjy}2B5{I8$MX&%D
zAr%C|U+HPHKD!<7WHA}^Gq%oI-LGjd(q@0iOpPbY52biA_Qt_`ThtRGWmB>(y83zF
zjKA}vWv|!S9f^ai5v`Eo<Cho*oahIQ2b9toFe%Boe(e|wWBO1c^Jt6WjX!-0_xqS1
zZDvpzeyZ*Y*+5u+YwqK}K487gc4TFN%HV{p9hX!Mqh9En{E4b$MqvmW@}n>$_8y*a
zIYQMJD+c^2(I4^dH-kfkG=(b?x!l|+<T5R>l-UC!7?QG;qgZk7oR+K8hiimB&CR15
zvCfcSn$ay((4SMIeIh3xn6fq^xf(_P^#XN^D0FA8iaQ-M7ydV0lW5gwump~$k)$A$
zp&^`<&@m@$r@Pfcn8M<LzPDu-pI~N?S441mN_BZpDEQ}KAKPBCKz`Z{Jg>Z&E<_|t
zZ7V7o)6C0HV0Db<CQISjT%FMrNG&9{B5+77srEMb%y}niOBSd~gZ(6S>TD^QO|d7E
zjf}#DwbP{VlsVchMeh9erg3}WFCZEAoP~M3N0sn2xz2`jd&CUA;0mbL$;}Cb1eZ-=
zDKic|Qp9y;WDi^5X_Lq^doR{!L_HE(Yi99`I|l99@NxZXw%V1jnIkhvEkOqmLL^Q?
zW%hVY?Xj$a=UC`HXU-ymBWLT9vFNZxK|5C6n=N*MVE{-GIVh%EALwmcz{nd^<zC3J
z8nl%*S(l-Rs_BEnle=kmbzp^GCCykRBJsr5l7OfgNvbfK3WTGZaq^O}!%Cjo=6p@1
zZ!3cxh*v$_g<C*Z(#^`xTC=OWa6l6}sElp^6aqj{n+f~07@oWVZN(95w6Y~wx};o{
z9`&`iiXdN43P1r#q$J+P9%WjtcM>e|Dbjk8Lybb!T2iYtS;$M)Um}Xgx_X=vcgQ3l
zNVW$dn-WCFWsg+pF5U@XP6Lth4^bN$Io*w)%&lA65uLVNPR|*HWdY2`%>h%g6gG@l
zU<m1wAde#53Z$3$&A}CbQ}@bGz90=h$KUSd64V8Gkwg<w3WvnY4$Ehz^EO)Iutg7+
z(N+4J+%74dS%%1&jslm121vA|S|>|=brExlTe2?DW3>-00l?&x+iCQ#^7o(5Cb9J4
z*B&4$4d991<=~pLUk2StMTp<9xZ4$#veY@?k!a4ow>C5_Qbm2y&4%`ssR!;_3=hI2
zV4NQ$BW2n8)?SAgO>KOHgJ<0t*%=83A8-1c_`1Q-f;F%wkDt45#sZMrs@aG+z12$|
zPHzC6kA)IHV_qN}1SqB{VsYRGD22P<GTc?k31Z#|2XE)tDRhsN090|i3?urmGV~yG
z96ZiY3*au2HL!Bm0+z(~(9_`+6^&_!fCWCRRNwEL2iRBwf|gMZhgL=&7Ds(gUv8ZQ
zK!v0U0CU`f2OIeap80@G%d}t07=<DG&o{Hj#LNK+K^E&5qOpEtC3Mk&iWZ~kqoo!G
za7{n;=e?JkU5}{gH(kT!cd!S{H#u8?nT%PNw8A3P0AKeda}3qN3VQ!pf2H8BXa-jp
zMx1Dwk+b2G5nP&yxnH_#DjFQc#g|K%8g1*6HhqUepvC(y=@Q>WpFMMrcjo^lAO9o$
z@&DGT8ULdh@_%&dwXdG9@9XdH=brbk?;pSv{6Bxl;X#Z1+X?@Oa`<lrY9^NdtY`L7
zhg3&iS<l9Z7XVcb$u)H*RYy_KC~xj+vdt|O8H5TW7eEsT#MfFC5N5z&C#b9^uQx&r
zQdUSrv?-!hyKHi4)3Hr?Z+)my{g`Nad>zKkKK_=AUHA0L$>2^SHj|xxo_g=ze$I{x
zs;|u@Mj8Xjaq)%Z8rau!bGwxei)4ncLMsVhh(jfFOdORGUc#6Ypj_A3(NLYIQbilk
zc)4JHJ+naLGFhOIjA!lh?qr7itu=+8LrSX2kq$nsF;#fNkQh{7SV;j|REVp9pC<}%
z7bX=J?!v-E%|S|t=h$BQ<FgwPG&p&XYAzFD+1>FT=y9~aK`Ez}<o43M8suza9Yx8_
zt9W=>u6bO3CnHW)z)-#hd0QSvF5|xGs?zVO!mk`lse+YMsUku~R!C}@rK19rj!{L)
zL%^XbvXxM<m*3x{5LdqVGFob^5<x22<XPb7Z>b{a9WhR3s-@h?DtWk<uV_(_ubiHk
zI4ELkOHnpg4LLSvyD^4crL`F;p~-fCt*u)13~PVu;TD`y)01K)DH>tvC0I|%Ncnf+
zN%s7WvY4(%;ea99F;}<XNRc*?>QHp5WUFv1e=9FpVS)mFJV8^WDsNfwyc9MO50xKO
zp-&kDRaQiv;crS+oMf?LDKn)Kql~0K3B1_&984XkNi2wjZPe>T>LNpqq?)7`jWx}l
zi9r2Az1%_LrruXrwjkU5>ikUo->k^hB_pokx&8K$_oy1&?}DV1C8cxs^J|+<8^PVw
z=$E?bMkW78vA!W=FOXqD;!(^d_iB;3%t%KLJ>YT+RYB@c{X??VHTaDSJ%sfvhr)t}
z+r_ykP9FxfC*P91^v_N%Z%jO)n#KLQF8AX2u?%QrCcbw~c8~IKqvVmi*qpY8yAaF8
z{(Xd8)XBOw+qN-*jdnR;(0i*HOpXja8<%1-QU@50RbBM#0PKKGc1Leg`X1khk0U;m
zrZ)1>h4BXHxo&ITbraWi<j4jFP}y1(Zv!Ohkjq*$ZET16^ESK6?SSdUyI2uC3d-Nd
zgolEi-{4Xj!-4$^n`nC!+<=t*vG0Z-#m`w~r`*#b&fe`k(V*v&?w?SDJ8Sg7$9sQm
z=N)_c7r?6Skj(rDtvVI9yK!}m%Hdc$EF$Kc$vO-do;^Udz(YgOYV9*eK`u9}GniQt
zjZA$ZKpSz;b%1dF5#k6yu1c?RikN%x@zIMj4Y&{U(|AhRX~iLVJRUB}iO{1<DEyKZ
zW6puvgPnJ8;QhjNz;Rtx*Dp|F5l6&Z0*|^%wS!=Qmpgf0M@*&-o_-&gffe1BXyxo<
z7_z5z3;-ukqKW?0C3TP+CBdLF-xYm5K|?uJtM`={)C{C9RcvSRnc=6Gyz|QGBMUcj
zY?@ALv)U_Gn_Hd98rW}(!3rMwImGNYbKKVc46(lY%$9(SRU+7*eL8or)Nz4zLbn!^
zL$Cx6>9sau`O|K!i<r^cyvgq1#U`3(P!FD2j&e)c5rCde&};-6vA`GpScLWB@Ps~z
zw+|%m8h>GKa1?iFwu>?_%NL;H#XTqv>ktllAlIAKvE1JHKLK@GZA*R7^*$QhQr<rr
z4*cF}2P$%|;mXx7%drD|O7JBiZvs7gqkt2U7`!6oE<ip1@Hz*g`{ku=@$vs=n<Hbj
zqudZk&ZzsrwL`%-30U*v*_dDNv&&06#IMu;ZG0pOLTywB`|~`*Y%aJN`J>Ermml1#
zj*PWCJa;Sq94N=Ac9i%Oq$3%x?@X+$HAUZ-9T?RZ70vj(b%(h}-42ZlrEl?`8)h^E
zE|&<WohxJJw)iq2RISc^S5S-_lFBa~*sk|u%gp72Tb|OsyYnSzS9zadBD*>J%oS}I
zZGY?+utEwL<SaG+0z?Q?uZ;g`;KQrdo~8))iSfWUBk&6jki0E7Z;))mC%(YjLZ`om
zIj<OBHO&1E=!xP4&)vY0eMTOnvZH%}2L-NIEd4u^#(UY1a8gJM&_&=>eAI2!94c9n
z9F4uGGJEQMQyMkD-#OKa3;I@xI6c1~NOjdA<O0xY|7If^b(dPx(1-*dYRl^SiiR*&
zaur;fo9#<Xi*`l}Nz-57j*qO5NRZaLW52Plqxj6DQC<<n=D)it6AHnG1Lp(sIV!k_
z#i~|<9Hq4kT}<5zz$0;hlifv_g`JCUAb<V&&1@n&mYl6lt9G4sQ~>i!9nSLR?d)!<
z;B{r$*<sQv{QA8{%xSF<!I*qUXyX1io+>Umhq`JXgKGGC_kC~`H9MTQi;_5RvQrqJ
zXK7vQxW0zEe5+cC@h}PLib-?R(o%~(yKA-~m1cv#5iJQVKihPs0Nd5Jm{s!~K321;
zu$b-O)2gME-gc5zX)>Vh4lXv&<>*bUX9D5i08`Z2U2O2FpR%;rZ_T~m!ge;KRJj@g
zcRa0+@5$eZ&L32(D{3-2U%;{DTT{(woe_>L#?Y3CafgGvEI>-J6*N0Sz}o`OhN#*@
zLzSs8KcUP2uu$;eXH|^7D1mht6Qk&jWo*KHe1*mS7+Gn|rB~ns+0>!5I38i!7x1P{
z52%|pFv<cH*+sBRKJt|IVD`}mZ4An!iW3s6C??Y(lY{tN#VH*0f_Z;`J4;vBpFdqe
z#tr_y7!auX39oxOabMj5mCMv$3%aBE0}mvjjvn(;1%1Basw!F<z5rD5yi?=^1*C~m
zdK=<6jBV2b-k!h_tl9=?n7p)cJ_2JCkaNT!jP|a!{K`C6hz;4YO&@Zdn#~LeYbhCY
zye>0x6B!+mU>&;ZSbrnafq3J4pa(?K>;~rhwH(!K{vTgUb||sv2f;n=YcfV}em=*b
z!Eyju&UU+X?D#<*X*VX(I_S^lx4}F9xk)zn*Xzr}vz*n=6~Cqm3ZGLc*6#_5wXok`
zv7s8mmo;JJvvlO)Ok$sRJz}5mzuILc12IoE<l$TuZ$SpB_)l4bw)_1Ya>7gY!k@Et
zaMZo+AV}?3t0n6Y44{}&1^EAP0j5`69Pk!%EHBLDvc{L0Z=)H=@zo`gN%+r$&QFn6
zVfQ77h&h$R-A+jVE`i6qJn2r`l@UoAEiA#_2?2+^O?=qX9EIb`@d<ree=|815T--}
zgWA*g=@5v8U1C1UQxhRb<MUcd{H<huC%S0mrl(~JJ}3K?r>lrL1dpW~(3@h)eb3xg
z@|<aGFx?}HgUaP@bGKC_ir(z#!7?ge0|Gn6ez1fE)6}#%mJL6VzKVtSZn%N?7^R-o
zf%4@2h{y6xsOMl9W4!2GxQC2gil7=ELwM3VRPP)8J@+_hjD2i`%LPLN()}%MBZqgJ
zqre-uQ%#6`>NMZ_+zfhnX}nU^1EORwyd6xXm#Nd4)++sBCy9?5+)IjOow}A^W1jb7
zZuCxCW0T>d$R0a4iPL!^$NADFQIl)e95^M1Jw6(tChA<=(&EPYWDj!94b<-`(yr#{
zgTRZG7}0{S3^XsY-MZrBZW?N>Rphs#m(+Ew_j!7rhrwNywve3LFWL;6#Cl(wTrHNA
z_WGBpylbt>tM7*0O6sG|ZZW)qxi%t*F7y6QuJ*y7+al{2DrTMla8yYUjPDex)X)sv
z|LWz);nEJ0RMMcCFS=RHnCAC_S3^TjQM32)si*PtDkVzn@<BBg0s+vpPpc=4x~}8)
zfOgn1VD9~tr|?|pV7YdRyR0*jvZQWF@lt~vuYgzhJRaExmTbcY<mofd)QHV*>V+{9
zwxtuxtg*V1xr(^oHHQp_P<M+tX+Iy*N+n#~Z$2kZ{E;sgn$Oz$qirJqw9b;AVNBd|
zXXsoTXY^p>Qoq^_uK>IOR1IMockwaCyYmflBiG^s<=FINAH-C?F*rOTW>MhbOx>m*
z%(*KK;F?OZqp?#{9GTfXnO)TqMOx_-88fQ#tZ3)saI}ZRgx4OUZ_a<GH77O2!q*;<
zXWseb7V>%80{F?3a;8ORe{+(=)M38FR`$K&isiF3LPKzM<D`?$t`yrCeq6MdGH3wW
zPS4Rzp60^Fw)y7j!z&mJ`j^sKU@`<-H%15H$SxgmbbRB4r3$Gs9$R854XNVNx9090
zAVe@}G9fu!(a1P%5le2i3C6wv!u_fp0CL4&WdP>Js5$nbGc3BGp09VBs-t|5yc_*p
zD?T&Ro1_jmVvLs{@7P7n-MJb&RYA89oe_si@tkpNAL-y9rNIPTZY-VZu?51D9Hl;(
zHQ{KFiAy#?Nw>Bz-kgkGN_Cu;Zzlf<qt?R+@%u)4*nKfESy|guZ*@UQV4hevE@FEf
zn#!URBXCT0L|0WyN%afIfrzcEfJ4y6Ww+bXw+9aOYWq8R0>v!XgohZ&iU(Inb~`^@
z=51$eRU$bKH9Am(<r8pAVZrKbDr$i#DBSyjFRl;MoFY<wI9OwR#G1z%o+56aJ7yc~
zD-q;+Y$uElbg7DVLCSSS*e`hBQ&;P|N<gBHmiep0lcb|!R)6xCN-Eu|BWa|Oh5_;x
zGfqHoFo}*%r^`JEpw1wys%6W3PxMzn3x6%PA|1n=&tRPF>V~zY0*l1QJFl&VxOU05
z>0QeO_zcB9BA-4kLHQkY+aVvfPnfO9vaa`>%F^~c3q9QX-?6?G?g?E9JWc`AT!51?
z37)^UUyknDIBkbYCV+&uOm-D08vN=;mDxzOqn1X|sL)s#!&_mSa)WwWJ5mY1R_R|J
z23B#j%@pAeTv9h?(ZvA2yB&!V1?063%Ij{q42?^YbEzn)npBcgR5NO7eDl3ljTHS0
zzGV7GoZtTk!Tv`v_+JFO1A(B1=FLoE)DN7Z0tb`o5BwwP2DJ3w4*16^_kRmund$%I
zTq9$B0|R|yV-&ZE87c>AIhyGi85S2RNtq?s>6tNUAc@zn*jIv$DWYeg-@BpQ`|zN}
zcu<pkC>jU4f4v`{#|Fvw>Ujh+14wsT>Y~*T=)e`!z`z4;zW8IK#4n%NF-T!7;bNe~
zACY270a<Yh{L0H5&6U5VC`S@M3YBLP7dzu8<0XxZgm{#QkU?Q%8&Gnu6v?G%D5oc9
z8Wic5n3$KC=A8d}xv0mbXUG+1#g~=&RU`7Jl!1&Rf3Bj1)%eTS8=LBb%)>~-NJm9c
z{_z{?c>X9|9cVS1c_#8oeGdDSe|I>K`L&VFM<wE??9F#q5}0*;owyyied%}c(yeN~
z^4!$(-hB+Mx7w)G*jQe!tQ*tiEW0GwcI~x>Hl5ZW{{{NqU(QkFNWmAi)*H3`YCSs6
z`l&nfly!P6qOc3z%*)%{T;grF#qDu-B(ts5eCM5ukN!e1RR9LXU?YD*gZ!pKL^z;G
z`{pnolYP2PL^g9}`aZ=O=YtHt;wFI4=@Ain+=2f*p;DoGfAjOl@AA^$|Mt%Ru~q+n
ze^d<rD}NFniv7nA6!RZ_|2FX-M9Y8s6|pn?N4JNKl8!lw8cKHq*Vuts6seV_{r&}u
z`i4JO$FO7*-F(R4a3$g-)Te^OO4oaW^wDsd#(uqd`XH;-l_}R+ECNy@`B}5UoZxKX
zGB}{<EuSz<;Y}XJTOJQY;cE4^4>N){(HDKX?fAwgb7G_oMqi_sUfM-}gmx1rp3TcG
zPhAm;!nI+olt~p?mmWml9Rrv%ibb{{n`Oe|7&P0bVMM!>%Hw9{Jbvj1{pZAGsant8
zc~zv+&dRz=$TvhH#}8o2UdJ1PQs5c?G4`~(XQS@09eT@Xd<`k{GSRu~??%Yy!bD-}
z>ORpPzkN?G+W@@?d#@9I^edGPBzj`89aqFF1Ou+Crgq2|$YcYIAt6PSJ#v`*8Usa<
z2q+^c*{4!iLYQG>%8MaM^uIYN#3+giAf$&7in(ZF_8V8f@vZyn!GObo#Z?g>JPDK$
z107_}UpJ2z;u#RB81xqRN_kK9;?Ejfwvw|h1?+O0%G$aLG#25k=p#@u1T@JB%J%$x
zeAHTuinxe@ptS@rh%=ML(A0a^ZR_;IZW(|Z)lIkwMLf;3IiXNcxsI()3P=pIk}}WR
zZjZr5s;gqC-Oc0Qv1pd<HaF&ykU~xq6wz6*y6H|2Y-4cVm+wvEH&(>fgJfylEV475
zzP;m&X+5?iwAxbqblMz@EdBWDmA=I)8F|m?Fz|8=rs?L5B4r0etgQS}u2Yjrg5vsq
z-x9PWZZk2poTVtC=P0Uf2Z{ytS@R~i$t8S9%plvQN8x=k2+dm<yu9@C56dtfgysZ=
zH*(j_*a%vjyKR3^9y4aQT`dT;yp7YsZ}QdKs2uF*Zgal&Efw@1%+_ul%O>;<;5vb(
zkbWi<tX+&D2Ug2TpLuGy@7~=u*q){LcrADyhkR)mX~cnfT9q0}q<3`-o9fV=P-*IT
z$*fN`i7Pyyda%>X{<I-ahh^?<+fzKP<?Ga)Of;Bwd9L$lUZnQRe3P-~u$|KBIWDW`
z>w_AYs%db=w61?{uREHJnqwBZeOZ+*lkWp#(35=`HylzlA+Qo!X&^H4yYVJqbD?ER
zpNT$sBk#GOkx-K{`nRk24@UC;bGiSQH|GbiC_>)Ok00PkKlc7*DDyvlL;vmlW@2Dw
z{%4YHl{&ODvI$ytEUA1cYF{NIFcYGBb16+O^+|q*s%(;(Rh~MO^(m1>MzM@wJgLP3
zv&6l5y2Ltny4V7%jCp#q#c2jFIZcda=^kx<MWrW-v&&3%MF+0SGoI_}NKjxauFKq?
zF^+_>%-0#e>t~<m4mKfxp&|aSXxEwQKVCsaZGo`o$SqP%Qtq#F8D)cxhM>5iNaVu$
z%z->H?*6isQ3Bf=0yFPwo7|2v*goX6N1m)4^_dDE&sI^W2*Lx`zq4ol0AEFDN$Ai_
zhiTz-F`zyhnfGyrfzbqAg<JuWh5Q1=HDPRaQ{G9Of;=`av8(yV6O#Gj8+|{As{|F=
zQq|OnP5A14KMUZ+W?~w0WDT!Jr;ecyk$7XWsCH`Ii0j<Q>Xd>V&uC+^@KI{-TSeMP
zK&=gcxBwkFI;6W1Bo~5pwbH~I8H3a0dlIXTd8sqS-9wv5w$(us1}Tv2+6-EngC=|(
zc6MOzn0fr;TSF7aP{i7<hJ+b3yN+ujie)Ee=gSfkPzgbM{Vt%3Oz|!xPVf@TA}b`k
z3CZbktyb^LiHltn5{kizI`}9J9NHGNHNx=^F8)0qS(GR#N6Gw)b=aDqJRns7+yGV~
ztz12RIRQDLjohqRTXLLne>g!7dE7yOBmp9ENMS6D;w%M!8F0uBc_Tw?^wSR+F1!6s
z)i=^NYiW<kA4bpxF_@V-yx%8*pU_{36;Yqg1a@<KA|b6d4ud*hFUK`>kt-nKgZP&T
zk<Nq=s&(3&+BK{h6EG*bNrvd~9D$)&IPM7rz#R~RQE#G~mH=Q>RvNt-rt~>P(4O#^
zSZ7CqSNb;71^00*pMrn{p;aKao=Wsn_#i^wN|RnE+|V&IRO)Wq=NZOWp>`*o1Vn@l
zN9+vPXgN5dg1kxX&B_`U{afN^QRdtocGyWjpfFz<GB|+1^7g!Jv4aOAFMJn>Cq^=7
z1#~DDj0<PNvNdZSBxlHaB?FayG_+l2?O79P0+bkXwGm8%M8-%k8=l`28$Q@zAb6jg
z{GF{MmQ>}m#9B;PB(Pl+>x1i0(j)VMs_tb_p)BALuvmr_T;J+2ZQ@l9bOa1{D{67z
zd)k1_3g`S2r(~Jq<)zdqO`P=94{;gLdO2=ZC(aL%caSH?ZR2Z<J=}_^djkzHZt&0~
z+rv3~E&Cl~*>71#hA~35cq^o7n{S-f=RZ9!vo9N`f+#?Lwk7>%wn73_28Xz$d9x}F
zg(*dLH@WsrGon=TrT*N(ZnDRu2h*fVog$IzC$tqW`%eoHLIu*GkWQ-kJM3UFtmS#Q
z*!Qv=K^OrhtMyi1$!c5LZ&Pq?-1~N>lMc#RjK@R5W$>o*Vu3R&!AD1K4V8yMVxqlO
zj|D@1N4TTBeG@wYzFHtfK#03BA?63wdLz|N2EVMNG>AOJ?w2FR@NOSUqcTTUr<E=3
zIf4V=z2aUU9@QUhZL$TLqe?2qsf8OOICH?x>sgwc`uiMH6seQZO=3ph`0&6$ec&XO
zi1%?!8=&oO&u*YDBuv>>2T$DE<(>(q`K#t5lYXfnacD2++du_tdKEy(8w6wt7@8=f
zq1ZvY)%}QG?JIrWU4Fwl%u7B4VKFa}T#N(6G8}j_26*c)gqv-r{=$56r(ZL5NfsbI
zpy5i)iBTg|A!*eLYU1PxFkRKU<Wtnm-#d6t(R<yytD${YAQ>&BBzqi#G1j{@c@{<w
zgU#%n4iX&!i@S%-a7mRIdWndtmTmdl_M?cZtEB;maL#W!4V%2Mf@xdNvQa-jH9%kj
z?nyx8uKl0ZXOK@=j1D1#ILMW4vsA08U)amc%5T71rfxW#KjUo#yn4~JmuJoDnw{xR
zY;inJkr*wfk}r9sX%!ERRJfIzV0bqb*l$CP^sAx+Z+?nr6nBANINO6_8*5xX>GNEa
z4JVPOjU}$^sj#S5^_9~1tH^eOf?`Vdz&<aEpgIsO^?bQNwz|Cyt`+qZCHt|c1js(f
zbLJ~)^j~h_+VQypeFW~FHFAF5XxNtG$B9+5Sn9M+S=F&F7x2Jd`lSkN+7>A1Bc7nD
zpBjNe!l1T@5`}Wuc$9pt0^?SSrPL1yBT~s@QXk$+y_m?<PhVY$v;Fe(0g$>!yJS9%
z+&j-YF@Y5Tv8Bs*rN$}djiP?l&XZiX*&3!=McqlhymkkM2Q1r<MzTJ$>Xrib`_?%c
zx|^BD@0#4MgAS=qt3nm);qYih^yW<78sZv(hk6bS$R0bZu?yvCX;cg&KFXD`vjIa$
zjd>}WA7n)0T(q;~G7-N>o=`l}6|Cs7WNL>s*3K+kUvN$kR^1aEuO&9mAgNO?u+uz1
zF-M-&A|3+QEv>;%KY1g&Wymhtg2J&Nk*~MPD)IPIi%SK+V<cpElaHoBZK93rw7+C^
zW`eOUQM09-`{4*HW3s(W_G$L@KIgC8`V4!2QkBUjGLDW@XidopF@d}{z~g5Ij#?#L
z`fvGwWnAW*{1TRR#rFM;^l^`PbAt_Lq0HvIc@YBc2<7q9Sv2bs@p}aXwpEdCQ2gl8
zS|@yZkb$m3bsws0>ZG?n%LV7ph&1Bh)zBv{P4#-rhK{S4mk;tX_%b~uc3!6vL~eix
zK2YUQ_dMr9lUkNbVs_RlWb8Eik@sy?gPv7J%YHE@R;|+CIz?NPKkEYqO&S;E>H<-l
z<xp8mg%s3ClykC=aa(}zx#p1fjRBn04+&^mKfwf}>NN{p`Jz75CD#Pt^Q)@!(^Dpw
z?a?1nU<unLal5pbe{%})Krc1RD@wyUG)i1sBXcMwDV6d|Sg`$W;pb&j3KlFx^uTyU
zvrJ%Ww}h;5TFX(X=2Kr1vslR2wFsjDi&wfbH^D6e^FtC)`Gpp>2cVpFKdtq<zKx}H
zfhil&ImLFGdxu&EJ~e-19j=@RYpNU7m|NLCM@1dO+L9UF<Bos4PL#s|bC%;QTmfG5
zX(}e>ZImRP$3tTFYJ0}15}>H+mCT^@K;hy1UmPqK;3)!VBmJd0L?}(P2de^r*;3AD
z0f(=0mjc4>r53h(UO3W>)r=W`5?RU3hMVc%1^U%Q`Ri0gRR}`86YIh?1Q7FWdoyZV
z(zM11#(OLiDcLK?z86cBoP7Phr^eOU&NGUUnYKABy1_y)RXc`M!8=@dJ<4=*D@6X*
za6}!t+qf(-<_XGsVvJSeUZ!2X(mNwMfmuiUy4SPECnyV(V%TnY4Pt(gTV59vAytVF
z_5CiymY5D=n}(Rq<Xv7`3c0evWO(^DLTG34o9}&F8@51r2g;g7a;VgG5ynTADpG;#
z(urxtDchgW-zBKe&g_w6T4P%H^nGDjTsD6Gqkuw^abOX;^N0>|+>5-wgLi4(d3%(N
zW!kl%X4bb1f3o80H&Olik%a1DZi>lwog$v>_~H&In&OGT0hgn{5Ll7_gzW_JL=0ZR
zRqUIEo?=9;r0}?SMfq^KPJ3D*y3U2`xt!jcBuv>C6Q-XTvr5VBzhY2gn*Vd2b=D8%
zEtKyx`no?*<7%LT4lXcn0o9@{Q+q07&mhj_11haJr0kKQUxfHsMjn|EIVzH^WOIdh
z%y5CB-p9U#!Rz(240^Ymlv*#+>6XsQi1H87C^>KLZ2s{C9Q)9y+*91MgdIqPR=V}7
z*RB#kNW4TZolXI-l(x6<9Fr@tp2i|fB9Kj0UuQZb7Tz{xtzytngW<T<**o7Xw*vFe
zf~VrbZ*Nx69o6w1S5dOolKfV>*L!AJ3&+!u!2;4{GLZ4w)ha!uEyxi5oSdi4@8Y&w
z@r;$o_!y@IcryZU6=2p)Ll^bhuqkBQKwwEXj`qdkBaA0gxch0}ulJcR?EZW-hdvyT
z?A-UCmm-F+S>oaO<-;<T4Q1tEQ<Qw869Na4VgT&><nr^wFon>J=+psB2p4C6Jb=n`
zPDWbm<_{%d406InFlRZ3B!%!qE1gTIN(mi@#2DgZ;_(WcCfS&wvpNF-GqX}W3!6C$
zfVxQx)-yp8>e8>Gc<-o9@9(WBz?kM=kiPLp`Q*_&mw}trA0+FS12n1K9R=a&h*@vU
zdhN?e1z-pSsU_rXAD#!%2U5PVkXqc@1vtEkVpJG?*cf8p@U~T?FL)s`&?Wip#H_Y$
z3m2VjR$7OvG8!!-2V(G#2>W$cbHJmWV$giozk!s0P+9*s@?rcBF!DcK83KYbiZ=a_
zkbb~KIoJ>EpCGRPHvAu)$$yQ27&-m}ZY8PtXd|n&XCp8ohB=#rRTpMsR=DJe<oaq4
z={BiSX!5-gtZP=01jT{~BE|oJ49vw(Bt|F<lt+pMfgrpq`>EQ3x3R8Mu_9@usU~q*
z-K4d$d}(`$`CQwx&6AL8?{@uFm+(Q#!DKe=v3=|@eV@IH*w+UVGx9!EJeAS(>ymU|
z2@*PIseGZ$>U>RXjYAbtAE<AhI~mgO_-<`fKO-zOIsC;af9G~(*6#ZJ`wDH60Aed!
zto8mC)4u(L;o~|kBmZ?X7+yFAxgY;81V`8%lok}+B)z(SfiKobsFq2v6Hl><qAc)G
z&=%~EZ_>=ts8J-3p3Dyl8mimmi1T3m?V(FKF@J<ruN<YEFwKoOV*T5w+5G-i1r@n!
ziQdAoNI9#|oGBIMwL-dDpqh;ys*6?4EG*neF_98Dp=Qa9;YE#3ZK4RwgEOH*BIO*j
zKyjMbZX>;)yJQI?O@=Z}+bEU^8l5ppfYvNgw7^!xyOTi;v1EyAkI5cSsFQPc3}J?+
z<)#h2xsZCZ(ZFUtxk|!8G$C$m_AJf0O`%*7Ywrtkd5kn5Ml9Szm>E%sTVfFLc93wd
zC(LBf(h&BRx-NTF+?tRTnGR7a9K{f;F3UY>RiY3{kuX{waV;oh7SXd``~Z=ZcNh)t
zKKvDXyiXX>A*02g><|__Ja9a)`j+j^3xFIL-IoJ77}#LUy(Z*Kw@Kc~Y_r_BXfd>K
z6>1y=CA1CKg-#0Z#dJ|jF68XiZu<7!%d!jJIpeWwVK>NSl=$1_DbkCDwV}AQy&Z+W
z?54p+uK={;xT{U`kkyU7{akj<|54p#VQAqEy#h#6DWJc3L{x#~oLAzj>{z?X3`BnB
zWIcrH{jX)LT=y4`pPF@jIwLfYN`n|lQ?jHYBd1r0uOG^EW!~-JP33blTmG~ej?_b6
zKLcgfA7~ascA{M`QWaI>Q4ss^+Lnu2m`b8Dkc8p*Ja$Wm*{=QI!ah@WpwfFCJC^3v
zlgh7vd09x9x7``~c-hQ0_x<GKm9iT60EON6>#VPvd9N`!zzyowyEh%Y<?zczHrt>N
zX9i?$+w-eE?dij+XB%sDyts#j1lVVca9)11`;T7YZ=SclhG7O??i7mdoYA2~ID5B-
z<^0i;TIL1&E4~-=t3+3%wQp6Q9KMm~PQ(<S8wtJTm_<ExRN|qLq-I7Xhav+$a@v^`
z+r&z3zuk)6Cog+28JYJc5&VWGG*@x%t0UX=w+VEo3b#BKt=UWw^S8^_*ueYW-%CLK
zRl2HYho4*ERIT1S?}n|;3{e6NK%QBdy<-w=zojBcwQgLHrr*FA?I}VaKyAbpjsl7*
zAFS@SY7{{B=74Zu9D?{uW+M3Fb{BP<aiIw}RDYmY6L1I&5hI$Do+_GQCrio8OH(5)
zD6^#B+Dy)vy=kp;`>*F$ajG-oW0GWW+4wMf{-Q-w;;AXFl3cI7+*_TJ<L$ngoBfUB
z4<J8)I`HtQH2j&l`H9;0-go|5lXOOMzLL{!SiI{{U$w*u5{%``-w;b~3iJl*c`!1v
zEB$hEdcA&HWFLTmgFnO8#dXIuHu~Nsb!GvBxH;_OvHh+eHnShu*_T{PvNz|SI~<%a
z+B#AcLcz`>z{yod*r<+JW{(9!uy7Il321&&wU=78v`87Ff?D_i)z>0z7u(jH*@xWB
ziY^9;eX}*d=mDoxAMPXeF;-9Mv^Sn57qD0oL@HAxI2SI~6AXqV?!=lL?neuL${le$
z-kf#{!u|swA$APR0QQ`4yj^t)BJu=w$q-&Kuy#2!CO4bo-Qf+jErZ80zWf;8CLe%g
zIoe}`Cn+t#ln(QQ7F}@;{$&1*$tu6Bd&{BBQSw~|Lr(D+TN~sTcM%e4d<*SkRA%*x
z9k_TB&4bZ=aCiuV@q&Ua35YYelef1kRyM{6Y_@)p8)*Z-7+FIH6RnS-WVP65*U1lg
zJV5~vX}|#z-lLZ5^PoKR?vVd5Lhp<U<>$<27?}JliYFNGfIK8bt;-&*kCtk(Zq2mi
z0v^}$vMY=<EQ8ZeER-kyPI6ntE_!S22*HxZnwRh#2>LOs+rE=O6K-Nectz8-Q$BmP
zO3^?06K=#wV8R#1r5IUq8~C4_HS^~#nXoL*Jgw5kOp{AL<IGr7jGnO&D5Ve6d_nAD
zr{T2hp0j^}!sehUnpNZAo!Rj=no;p<8e|VCXQLL~sAKQk^S1=@w^;EA`Ow&bavt)X
zEDpM)3l6iT7@V2#YEA3H5p(hJ(~~t9-+~~K)N6ruc|l*S#lseA0LE_g{T!pDph>m-
zvXnn?Sp$N?_q9Mzqh+N^3QPKUg&Tt5cE3fA^1i^nMEtZ&GQUb6ZO|^_kYs(-UwxZ=
z)+7Hu_rduNfBP^U_u2-p;Bah{6d3yQ2N6fWiY7<#IF=X<{or!L2TfjyNa@Z@%>1}J
ztm%1s*@s4->8hRV5lr#Q+nRV!h`D!UjnSd_x=OQCfZ$J;$il@;Ig*Lnh?1~5?mLVn
zHaJPrYN-qECf(@77!>@pxr+g0xX$m2Uj`%5VL$CNJ-ww`!VE_#^kgc|%||?>`KMpk
zU(~4CkD7msvYVGzxNYWV5)Qi0@20$nVbf!*H5r@w`K|G(u=6Wu#}$;IwV~f%u^rs+
zNM>#x{V_Dtkntr#`)*>xe{@>B<YmVa{Q_dgvb4%na5=O|`$a6mG)I8K*;#4^u71Cj
zLSZZ6CZmP(sh<g_eWUI!3nS#Vt(*<2)?D+}i?5J!`kaRKgjbns(BIjjuz6If4w@c4
zD8(<}a0=wK*sbZKMwV!3#T!Hr>f~<El{pZqr-PI;`aoX9nIySfb;_~k@WJlxzoua~
z*z1Df;WL}!nzcUjlzYG*P&{sY!4U6Rxin7-yx3Y^scw_^htuQU3W+#11{yBifeY-8
zk9%!vU9=#YF;4>^15jdqbZe!S@0_DlCH6IWJ~NBgYu)K^*iE2Hk*)OVs|lv8$=rt$
zecy?{W>65Z4r^_4H@=-tfztB;Wrm^{w!?&x;2DUPQp(z#)klG?%+ThnbydXc=|9UQ
z?D2h$i7f?N<OED?Ze2OL2HYUob)efm_FL#~tySdc*>tYECe2vxP~L(Lm36`5+sLbR
z%(u<IN_lkEpBpcZ-jqS}aU`2t^8fD2o220|aOyB8M`P9EL=BnG&-_a~ZYa<VAyn$t
z5ql87h6IH4aSC|7rW}3$UZ>dTR?V@rQ}I`p6X_|k(2N{%B-V*HWx=o@MoYI&-&z(5
z<q74V-U$^sCZ>P5x3hgkUlyoY#=0#-S9LE#Ut?xh@`j&sG+Fisl@*v4(CMOzFx1w$
z!gBX}_9*C6mpR@jzkmN(r_(RbqUM>{R`f1K<u63pkWR9gV(xOKIMknW*F%*bI^H?d
zQJ^fTV|Z5KQXo3(nfp<z8E?vfaT5F$dxpJy1(wU}Q(Q0fGX?j30Mk!=V0GB<5WuW@
zPi3F{61GGm(}Ho=$2#%*(<A<IIgW^VGPtfk^eEVnkBFmcCoWq5k}_}Gi`yMlPXyHX
z!Q>TPFACNV`X^Qv(BucGwNZ!n>JIc8=Qpbvyu3Y0Da!R#apjC|V`SlUrMgnSM6)~h
z4^~J#)n!P#bCE;i2lHukpU+Uu7+}kkyyl_#NgHo&_kHBwXnsRR4f0_xL6d(w_dM#w
zO(mqT8ky&BxYyXtxdcMF?$m98jScWJO4W&9<tJo}sn5cLc>;?iGKQb=+B-9X1WwZV
zw|45=iN)4!d_pZSKx!a2kq;;1*basq^)91xkybTbvs=ZqlECHZ(<%m-8nv{Y`6xut
z64dO+oO5Y~6f@1H)}$ul*iqL(K8>kp#k)9E)Oq`ivzrymEXz*%O}`M^31`<XK?mZM
zSnPDH^EbLL#bTiEu(YV7;}cxXI<meXbP=7KR%7H6VR5y16^@dKp#ThgeH?+f^K-#s
zGu4bvn5a8Z4H@H`Xm5u}bh@am*1y*a6nN4p8}NQxN3p2EdWw$<ImIFjK_q5c$t^<6
z=h&$A31mfoJ%rBWgT9Ri0<S4x3;x(XIO>x=p|kb(_Zh=-*rQ!~zTVM|_*Gy~kh}XG
z+7TTD)2^lvpQ0SkrIlU7noi8>rSrI<kXX%h9VTiszHo6R<MVul$=<OArw`L{OMnc7
zE$Z#=H)ZCuh4?Lc0#&;7gW0?WAv*{+pkv9>?)R_74M(7Mf$`_dgoTdaP1^gyrAsi`
zQnY-fQ6hSbD!cT2V;eMdeTn*l<s(PY;P>rojc{`yUpz8Z`|BfXVF{j&PF&iWmX!p2
zW_A%OsJe*$&b;p01=@~iF3a>waFP586;>@8+a~OK93&YtEh0a(Z@MWdr}uvYPydjI
z|0`tHS~;0YPiET>+@b>egA^BZ{NINEL-6`<kr@O1e`-^~$~MwkDj3}@crYVH)|UI7
z!Co;DtwT-tOxCm*#uN7R`p_m5jC_Vtc6{b56IWe@R?rXy#;Y6f<|8eM8WH%7RP^Ca
z4$`RsWyXHY3}1qVdw4hdG1(c~NH%}H@(gcZ?lT<M9^08@GfrFRBF2m$A_^uhGB`dO
zW`1SjK7q}clpI-8^ReBfsE)zhxI`d75yh2%Anjt7-4sTxmd2lb4-y*!k?IT?Zw%~N
z+KTE{Ptwc?Auy*VJk5Rf=+6|h)-zJ``QQ#`i#>@WpeW$W;ZuU(_v9<0ypKd4f@#XB
z{37Qv+szzG&(BYho0pLtHe__lZ7n?+-EH&(&7Ae8)Bz;9)~Z6!uEFL?0$VcYCc75q
zquIwc1M`?HuSNN@26~<mnwwIDfRcvT+8V-J@OQ2C{{){>7qB!T$0{<S05)&NA_ucK
zh3fRx)q<xq=K?RMflbUR^8XuKD5cOl=^!%#4c%s%5MnAFJgf|-WxgR}2)*EP7SYi3
zcy>0PP-59s!n~;hhhYJRK`v`nSC{Tr@Oq6AU$1?@QHa42eNse`ub3QQTu6~X05~CV
zR*t8*9cUGNsbiwR7SGS{69+}aRfcQ2rKwz*a1R@nJ+?wy>d3Zd-h&4h8x^CcgonHT
z!pC(HF;A&zsEQ8Lg5^<DHavyib3jCISbp5*>EuGjB%6xky7E~1qi$#&o2icBjW9Sg
z&6enLeWGbiInDSmG*6Sdz$al#k{n8=+(Mdx^)}{Y`0j<<y|MAyD44q52QovOFW(HA
zhSCVqSrDWl#z*V5adKggOjWCMb^iY<`>LomxF}uR3c(3Zpje><cPmbCcMA}txVsc7
z?ohPB-JJlXNC`z+pcE_a#l1i&aC_(JpP7H=uKTth&N@$Le`|fR_c_1$wN6~wIjb5g
zYJTC{7}>e?Rr?XyUo|iOYTJz=&65AzP|Te-XyumR<vrEALG-993PR3H^}Pmj{n;}o
zxwzH1v>00vs`%&%Inv&bjnZCro4(E(<mzp6?}ZaYj|C9uICCse2uU<a?5n3dy;wK)
zq2%-Alf&K-Ia*HcbyIzlpkNk?ypL%hH~YFlRS9N;_EFDfv%mBAB!WyAKLwVhKaj+}
zOji}&+rvJ?6KR+Lrd+gtn)=X}QenqOno*d@toLl1m9skhMu)jy;i_`2%>6++`pqk&
zM@u33onNtky7O<mH|z~)7><<Xj#NsCmV3h1v2zF}ogtWb^tz$z5XwrNpv-;5RCWNu
zkO4j%@OZy=pDsbe!VYvhK<37ZQ{>a#I~&t*hs-X2-(;qC9KocqXxYd+VLI^(UOhLc
z*;Pn$4$63HO2fgVU@F}7nrj+&=&-D@;CE3EJ<c~}I+;ukAs->%$8FZsf?`%bDyn?@
z&=9hG-RC}yoom~lEpwDLJF{RT@h)q*CpQcK_a9Wte&9ujcp}sitK$9vy>HcuZ~_qr
zd%~1=+5Gq~fFt-1GyH!+Gv0ri-v6O9S!r2WIapa~p`hTopc?<%&Hqra{(qrNi1$Bj
zyY$g9S0>Z`8>8vjsWANVnaHG5H-}QR^#x{iR9KgFy>yqUyq>_}@(Pu2esiw)f=a4p
z-?EkOY<g80W;J%u>r#ur^K$x6KV_0gg1OQym==f`^QJpXF5OQg_k#CA_m;gxwl5iz
zw_Y<b>3<JZXX^gJt&_{Z3gPEEaIKpMEVSceAA?#_+=cv)N-cVjogw5w&lYa(jn{zy
zy+{1auqE9DqE5a2gZ3J>+Z?ZRvjLxm2UG?n7Wz-c9NsvX(~yQ_r!A(iRv#6Uf-8u8
zIo=mDrtV?~4gp*)dz0?=>BI(R7~Yr4yu5(b=}N}p{U%-EBMQKYDG%i{ISF)gv;v@#
z&X2#Y5H(aeoPBl#5@;)tfu@~hHkry)Bktkg?!PHdF@rlrLi9X)K!7$-`5;g9bpa8G
zl@lw`F%Yjnm(7uhS{_Z;$KlNwMj*GM4bhw)9x*Jc3JVpE9Z8h>g3g5?x+<4UK$1#D
zgy?zZ>M$jva1tRQ;M1+LrQhVMHl?D@eGN;J;*xZssHcgY!j81(`WAbUbmt(#k-HPu
zMuYG9clCJ^H=d;;A2!<E$P8;1e{Xm92D-HFq<zLRp0Dpp#nXh_xYP~34xD}L_JJL7
zU2?Z*YOV!a-sU_^^xaN=HE0FQiF<5lY@K~MRI`@5%>5E~bHo`m@^0bcYSXOQ*~Jci
zXW6tfVK(%@?qp9K7TqIye>~K+N+o^ZZ73tzB<MHwsO_?Qd@`btCF$SiCm!0!Y;=&|
z=)Xn=hIQ3x<rR*a{PnYAJc{d5gB)O9@3O|#jk^jq;-!<JXZip3djBDj{?C2E`(OIP
z9R&q-=-)zR0wN+H9*~>$Ydi@FZoL3^7`LYNYh7;_ZViyI2)Cl6r<XTKNQmce<?Idf
z<W_Wsdc)*lHg2{sZZ(*zy|)91PgLYTiM{P6OP)(2Bq4>3>r2dnJLKU=AI=>P@nn0?
zeA{C+K4Sm_S%R<LjxrbmSAPuEL{F8UE>TR}(&Gim6mer?C%KO4jLVY!h#CAL``TP2
zfz41kQuSUIk`iRh-Z*^_fv<>dmOkQW#+oen4$n~ms^1@^zYrdJC5qlmbetvo5!@Ri
zL4(I20k6gZlYN6WOfA0|(2>p9qS<`GBM0fdArX$BLLXo*618GI*AsdpL9U3i;LJ;R
z((fNlKM`MnDYSO(J?G{xW+6)PlV{wfNOr5ZQwvZ;nS)xnK}7_@?IbV*p;0I<M$kr4
z#lI?w0i~iOF!~oWPB>6D@=iIRz@oYFpYM@lwD`KI6Q>Dj^}lUlRmMVtv$a~Nb)XSZ
zAZ;2x9j*u9YuT0aOufcI8i|yhqtR)+MKf_h!Dl7YKw&8j-pGukXgk967Iy;S;fQNe
zCPxz+`5ZQBrLTljVZeGl-!WGJSB-xuTJ58xWGJM*nQz9yI9&|4vLcuh7GWi<!<FJ8
zd1Z#9XnZb4YOBiEyJ-ZoLFs8~Qj?7*Lv?!C9$l}4Yr5G3uW2nvZ~}$=Z;mVId+99B
z!&(DdVqfk6H7heP;d|v6+dr!Sgkggp;%=ndZ4n<}iy~p}0=a6y%PyHS{Ar@DJgJc=
zQ#C^;QL(WAQTk^5RTFy;Ls*Yc{XmIpCu?knV6hz9G3P)P0N2+Iw}Np4fbkvmjV4hJ
ze)M!tlyY<W<|h-p5lVQHdWLEC58Ew@O4)4Pn&Zqh@IXxnixFbHRFFTyx!*b+otCGw
zR@nTYy1p;cbncXEpx#ei_QMCKf**$OGV*&^f7125?Xa<VVPoU9G!QZ$m*!|%PD5|E
z{eEq?8W=Q=&!y?|t1Z*Qg}nZT{J5Is$2ImejK~~odR!305xCOan8DNMQs}e@G-#+K
zh?_BR)g^YYBzMfN*E<{N(`goL!tU&JSR&!NFU{XdQ;U&R1N$lnA|z{A*s^;ZAW`L`
z=HJ@JW@aoRCsHFzzRq0I2b-rLhqm_T(|t^~DZy1QulDQc!4<7++1ESeM89Qm5=g1-
z#R1lB7C0>K)}|6MS750GZ#O412?{SRI>2fYaNg$~%)eml(x0~cUgU;p)Gu>e5O#j4
z6IQTwDGncBjCA}0TM=4udT%TGp<{N+#4i)kHcSghb_EvBf31~RXR<U7uQ>V)Gk_<R
zXd264A$J}L<ebwHw6#M&7H7N0oim*h@7w4{#B2(k7SeVuymWtkdrMwa%sbC~mc3rL
zn?#+EdAv95G-jOih3~lXj}&v=W&um6m^s*aI?cnJ%X`Kme`#vaxy|CcL(gPi&pZ5?
zmg|z@OKbIYmS0FgoDBfBoBho6v4UjKmCx19t)2JXj??-4bCygBldg~S(i%Z9iT4Hg
z!0XbCun|KU_9!vclUH4Z(YJRVKMdSl4@Rdk3BkH$;&j|KT>+MwO4sWt0S~*r9+Ge?
z?kA}~5l!VU=<vo}y~~C`uDAMKvApa1?!3Kl3lDs~2Jff?x!ia)$GW;U4mu9ZuR4$g
ze^HF`TaHYMxaPDLzV0?1ih^)2-iTVh;%y{J!V4S(3geO?(m*2<s}s4WWR6vkOaHuO
zTVySPPm0w8lV+e%fCFHbb;IIZElZE-6%qH2#1pSWfm0vqGgdCij#uIq9>(>(qPhw{
zW6f+ASJtCcP|PI`&?eQcqL@;K#<yxfzJ3wgUc%(hz%H{xxv#SH&9R~5FO2@(1e3`T
zHFo>W7_3Cf=kKNtQSQ)|*B4r6nU4W0>Yt#ANOg_LSa3vhaF=RmmM7_FBqwveI)c?@
z;dDSytLc;Dh_aNcRVc>2F*5;lU`QrdEP@S*@hCom$<kN~8!@Zn_BiDEti*s=eM>Ka
z<cx?VR>RKeZ=?jvNuXjfDtv4D$qqkM>+RrhjABK*u!WH!+dZ}^*KDfm`IZ?VX!nvH
zD}@!!WURO;6NAQKnV+49hlc`uKM&=Iqhz6?>*9{s($b~#tG)<sRzG4_HO_^Td(oVd
zXBRf38Pp~(N3a;(U|{BG_#;*LhWXm6+!rfU1~BDcx9M5?l(4>{a>uK6s3YcJDm1_q
zZ~bhjP?MMhHk716f85_BKjaPOPV4OqE9z>>?rNJ9hWiBgP51>oOWnp>Yuib}B`5w>
zz6)}Ep+{{>rLAQ%18D*{irr8Pjd?hG$4k47Qj)&kc%O2E8D{itLXL`3IKgFKkE&3O
z3SarO#QVs9h{20z=J5O07LO4!BLdS{p!Q|kw8yE_amkQG&P`vEDV&Pk#!Pims-0sD
z8{NlwgBil{V#PC4whK4bdx{dKYJ!GZ_$Is~f;cuQ;XUo;SyYaa7E0sYsA6h(WMf?t
z_qvM&irPNxYR-uKLo|*M7J=C|;)rQe)RZxuT%LpL1>z@TiZx-qdYb77#g-`bg~g{{
zXCJ9$e;32HIMpiab&Fr0cKCaP$LaHtMy&@Pj?cteWuzIXh8VlmSqs0jsWcnr<EtA8
z=H#LIIs3S}xMnc>)(=b&0Y9b2&y_-BJwkchr4$1{g(UOL)}V<fJn)Hpd}xcU?!P1r
z-33~^OBBqXA2+gn><hbl%r<PCjLATdVUNrl5)(>330Z!(glmE;n{B(PCxNYQDand6
zn%7$c`HNNXBsRkoc#2k0B5;jfZv4v^pNHr}au0t>!NTvC35&N_EOLL0Mny+QW6)$g
z&KTjC`Iz5#69=aMM8E=|*vsQL*i|`Ldrb!+jH68Lh`V}v%Mgvo<j20>JoH>rHk|wH
zhdBv3=vtK`T7N`yG%a613?uiH<B&k5jM~F)qR5%UjoDr;1ITmG15JE7+vhUYnSclR
zmrnuB=chbDpYIlYG477{Z@ZDjpvyggl?nHmLx)J8NtvX<o)zxz0k=r|jD&rhXS@zq
zEM1Cnlsr2>1PvQbE5g)}l;&GxIz4I&Uo-qpEgl{txJ2_qsWi&OP}p1>V_IX@<6XRl
z*J3#5ymg|@GB`x`35$rgHzyxSHbOY{o!L|;0Pnmv=WXMcY*l^^WP<NP7B^2@qJOvU
z{0)V=!5=$X6eU2WnGVeg)j`cH-Yp6-tfuT(6p#C{UZ)Hb?==2UJ8OGJa>WNWm8*tY
zc9dClK!6W)13Pz1DW}qd1@kkbSJ1_hCFka#X3YIRd0Z;hF3uagP8~SYwh3v&sEkdb
zWFtDtJ?~$-VjIi)Iqbh`93^iZC7)+&aR#nsbBwK&$KL^J3g`;qA6$5D-jGo2n94JH
zG)5^LG;~=*1amjJM#vwj%-qcwe{bN9`{Lv~<I*@YF2-;zMcwSg<N6`2@4a?zf6m^;
zv|8Ri{tUYg{#`Cq+1f27QfQIF5W(N3;u&xg7W?t^bePJXx<K1*l&U=qVKo)cKcF4S
zk318IL5Y%|7hl?AR<U%i&Uo3w>zw*lXvXXyWA{YwoA}y?%Y;iQ*wp#r=;C5}$0MpH
z=(T;PcjM8V4^TGrc|#7RA=yP1(Ixri^UEyoZQh>+HP>oQ&n3n_Vg3$UnT9Z<fUw^q
zh1?bbvSx$ls9hyXi26Q5SEp`7$pe;Q@K=|(r<Q$yA)xFr8^nno&^lrE$?v@4*%+4F
zm0e!#eHnso^Zo)^-P3#i5O8@kJhGNjxFdfsySd>BT+#5nhC>=E71KG*D+mH<AYiyy
zhFKCb@N?I#urZmhE!b0O_uKpZzXN2p<8~#r_src(<u~A>&TVk9w6Vt1{rUEGS(cKd
zS&^fC&#uLyYtzc8>*XPB*dnUU?Wv;2>*q?oPm~V*^eoqYJ0E&LE;<hU_ktlUYjhle
z*>lx;E1-0;hq$ZVN&C~UkC)@M8`csV44L*B^FzaX*lO--_qvUU`AQ2eF@$ZtSvp$G
z^Ut=J75@6E&6`TBgHPc$k+1CdNrgiAHdagmy<$&73)57ko*1%6d(i%kSqS|XCSark
zv*U)yn@R}s@d@!md0<d}J|3tDR1{`o1BD9M@!9Z+K<#*J?WF$SC(OBZ+}ynJ{x7N5
z;fA={xq<lpqttZ_gn<MFg}Dt)c|rUjKJ)*DY4Gy%^8J(U3%)aS&(bGTyy+v7rRGxR
zy~6nBP#jI9!;VVw8U<ZP9-~YZM3g5$T#kXGgYgN?fv1@5Y87n@onLH=C;7K^ZrX;n
z`*&=%)t+CwurI=g1wngHPpvniO7dk5V9;+pu|a?gJbMzINn0msAGK$|qNy@ofC8Fa
zMX?OnS#M0X&J+!Sx~ZYeMP5TGol%CMa+Ijgp=3`}48MlthbR|tgx;!K=`P?S2Y1iN
z7tlJQ>aCn^IT9mXtV|aG9WiuzSGgbElvb})J=rK5Nz#6n;wBoTieGN$^2o7x7EkUE
z7Laa3677cGxD!oi#~}_cNpmgZ81S%b+kVd}Wl+}Z#67L5^X+D;%wq_@$eG~?nd^ZJ
z7if=mZC7yaN<2x^?pANl-Z=;>*6Jg75&OxABEIH1b;1dStQV#$SD(yua_<J!sdwYY
z2EVulLK|u_k9=lmywqVX@%d6YG#vSlzB52CUDy(p@B>e$-q=U4jAX=k4_QAkN6c7A
zn{?@oUh<81#+!g5o$I80)Etvgaq48f>b|Yg+(aooMA|9RKueF_u6uOQ=)t~LqHkRa
z+tPApR9hI4!;@v%)6=ZtP;_yGEgZ>9%rP0}!H+>&eX%yK--H)uKwx^zN=RBt{cy1o
z1FiFWTZ@$PlSW(96Kq&emqK<|qa^DkO<qiECz^yM8K^@%rLo-1g$xAikq;uhK4y%x
zjd{ddrKFVY^aWL7Ro@?+g7+{k97U-3N&BJ$-b+0Did18qeB(BRxUF`lwxhqpF91vq
zdYuvY(;Ey?HDOsqWpCt9!R-ajBAe}lP@Fbi-lmEMY%gy6PW@U<z7?H<_mU=#OtAR9
z?Z{x>+)Hy2Rz^;+5k_{Pmu&+3quq&D13%K(@h*1vVDHkkTzgX6;Vz2Jcl(I+QG$mP
z-`Mbuf8MfUq)p*w)C?!(9Utx3RB$H=#e6xO7~UbqIm%yDKgi)J)fV4QPKB#9Fzs(z
z+MYuzf^!KDz_|nTKARs1I+HS+oOroF@gtxa)io;r%%D)0=QOQy&@t!B_I?w_rPN{{
z63-}p4NbaVUQV1qnpya*FTgcgc!R5pVAU@9xNtw`*c}`Bt6xoxsuzWO;Qbk1FP`6k
z)0tQ=s^5_3V?9AZ;-Xw~cp4Ah6Y=7&TqSpI<Ow;R3vdPdW(fT@aO#AdA!Dd$1q?_Z
zDqi6Qq~#AOPMr|OY_R3nP5E{_-==6{X?uUH>*?eW^uvBz#KC?pxOb(Zum5HET!_->
zTx0_8$mcl^Ri2U2;VCgEs#RBzCG_aXG_D$C3S6KPMhT0MAhNURW8E7ZaA)r$F&M}=
z%RKnb5W-bwd89rsa|o<8s&zR`AaH-)25u7Tq+US#`!R@p?MA)3_%cB~-}t&l*E18J
zMGm6}qc011Cz1EXvvIR;XCr6(q5e@`m6CU~ZTd~uEseIdR+jh763<Tisr{)eVmj|8
z-)`TZ5m&&mHaTw7H6P%#fF+rpbD=j$R?imjg<@QwsteS}>aXHN-7(x<z|9gmMlgiX
zV}FZCH95NLPYRLhxSW}w_@`OJKalR)hJX!3#sQpf(sAI=gjerDGXeY_<5Ck&s^{b-
zS&8jczW24}qvW;3tLq!INproYx{HGH-x6b9B?k#&lZcuy@<0uphdujAIlU+K%YwQ$
zO>FQO$08ZG$rseIT)zq!CQ>9TUl-|j>}d}KPkGI+$CF`xR0N$De10k>o!k5G2=C<$
Z_4M}lgxTTo3h?sr^Wm|uC}=9;{U2YsC*S}8

literal 0
HcmV?d00001

diff --git a/docs/index.html b/docs/index.html
index 70659ad0a..bbf5ac818 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -132,6 +132,18 @@
   <a href="./intro_lec/introduction.html" class="sidebar-item-text sidebar-link">
  <span class="menu-text"><span class="chapter-number">1</span>&nbsp; <span class="chapter-title">Introduction</span></span></a>
   </div>
+</li>
+        <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="./pandas_1/pandas_1.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text"><span class="chapter-number">2</span>&nbsp; <span class="chapter-title">Pandas I</span></span></a>
+  </div>
+</li>
+        <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="./pandas_2/pandas_2.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text"><span class="chapter-number">3</span>&nbsp; <span class="chapter-title">Pandas II</span></span></a>
+  </div>
 </li>
     </ul>
     </div>
diff --git a/docs/pandas_1/pandas_1.html b/docs/pandas_1/pandas_1.html
index 0b7682332..440d6f5ba 100644
--- a/docs/pandas_1/pandas_1.html
+++ b/docs/pandas_1/pandas_1.html
@@ -201,144 +201,6 @@
   <a href="../pandas_2/pandas_2.html" class="sidebar-item-text sidebar-link">
  <span class="menu-text"><span class="chapter-number">3</span>&nbsp; <span class="chapter-title">Pandas II</span></span></a>
   </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../pandas_3/pandas_3.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">4</span>&nbsp; <span class="chapter-title">Pandas III</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../eda/eda.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">5</span>&nbsp; <span class="chapter-title">Data Cleaning and EDA</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../regex/regex.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">6</span>&nbsp; <span class="chapter-title">Regular Expressions</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../visualization_1/visualization_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">7</span>&nbsp; <span class="chapter-title">Visualization I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../visualization_2/visualization_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">8</span>&nbsp; <span class="chapter-title">Visualization II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../sampling/sampling.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">9</span>&nbsp; <span class="chapter-title">Sampling</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../intro_to_modeling/intro_to_modeling.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">10</span>&nbsp; <span class="chapter-title">Introduction to Modeling</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../constant_model_loss_transformations/loss_transformations.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">11</span>&nbsp; <span class="chapter-title">Constant Model, Loss, and Transformations</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../ols/ols.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">12</span>&nbsp; <span class="chapter-title">Ordinary Least Squares</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../gradient_descent/gradient_descent.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">13</span>&nbsp; <span class="chapter-title">sklearn and Gradient Descent</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../feature_engineering/feature_engineering.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">14</span>&nbsp; <span class="chapter-title">Feature Engineering</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../case_study_HCE/case_study_HCE.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">15</span>&nbsp; <span class="chapter-title">Case Study in Human Contexts and Ethics</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../cv_regularization/cv_reg.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">16</span>&nbsp; <span class="chapter-title">Cross Validation and Regularization</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../probability_1/probability_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">17</span>&nbsp; <span class="chapter-title">Random Variables</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../probability_2/probability_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">18</span>&nbsp; <span class="chapter-title">Estimators, Bias, and Variance</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../inference_causality/inference_causality.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">19</span>&nbsp; <span class="chapter-title">Causal Inference and Confounding</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../sql_I/sql_I.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">20</span>&nbsp; <span class="chapter-title">SQL I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../sql_II/sql_II.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">21</span>&nbsp; <span class="chapter-title">SQL II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../logistic_regression_1/logistic_reg_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">22</span>&nbsp; <span class="chapter-title">Logistic Regression I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../logistic_regression_2/logistic_reg_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">23</span>&nbsp; <span class="chapter-title">Logistic Regression II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../pca_1/pca_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">24</span>&nbsp; <span class="chapter-title">PCA I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../pca_2/pca_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">25</span>&nbsp; <span class="chapter-title">PCA II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../clustering/clustering.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">26</span>&nbsp; <span class="chapter-title">Clustering</span></span></a>
-  </div>
 </li>
     </ul>
     </div>
@@ -457,7 +319,7 @@ <h2 data-number="2.1" class="anchored" data-anchor-id="tabular-data"><span class
 <section id="series-dataframes-and-indices" class="level2" data-number="2.2">
 <h2 data-number="2.2" class="anchored" data-anchor-id="series-dataframes-and-indices"><span class="header-section-number">2.2</span> <code>Series</code>, <code>DataFrame</code>s, and Indices</h2>
 <p>To begin our work in <code>pandas</code>, we must first import the library into our Python environment. This will allow us to use <code>pandas</code> data structures and methods in our code.</p>
-<div id="7cccbfb8" class="cell" data-execution_count="1">
+<div id="016bfe75" class="cell" data-execution_count="1">
 <div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="co"># `pd` is the conventional alias for Pandas, as `np` is for NumPy</span></span>
 <span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> pandas <span class="im">as</span> pd</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </div>
@@ -480,7 +342,7 @@ <h3 data-number="2.2.1" class="anchored" data-anchor-id="series"><span class="he
 <li>A sequence of data labels called the <strong>index</strong>.</li>
 </ul>
 <p>In the cell below, we create a <code>Series</code> named <code>s</code>.</p>
-<div id="ea7204a5" class="cell" data-execution_count="2">
+<div id="74408739" class="cell" data-execution_count="2">
 <div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>s <span class="op">=</span> pd.Series([<span class="st">"welcome"</span>, <span class="st">"to"</span>, <span class="st">"data 100"</span>])</span>
 <span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a>s</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="2">
@@ -490,14 +352,14 @@ <h3 data-number="2.2.1" class="anchored" data-anchor-id="series"><span class="he
 dtype: object</code></pre>
 </div>
 </div>
-<div id="9810cc08" class="cell" data-execution_count="3">
+<div id="21908b24" class="cell" data-execution_count="3">
 <div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a> <span class="co"># Accessing data values within the Series</span></span>
 <span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a> s.values</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="3">
 <pre><code>array(['welcome', 'to', 'data 100'], dtype=object)</code></pre>
 </div>
 </div>
-<div id="a0255147" class="cell" data-execution_count="4">
+<div id="4cd01820" class="cell" data-execution_count="4">
 <div class="sourceCode cell-code" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a> <span class="co"># Accessing the Index of the Series</span></span>
 <span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a> s.index</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="4">
@@ -505,7 +367,7 @@ <h3 data-number="2.2.1" class="anchored" data-anchor-id="series"><span class="he
 </div>
 </div>
 <p>By default, the <code>index</code> of a <code>Series</code> is a sequential list of integers beginning from 0. Optionally, a manually specified list of desired indices can be passed to the <code>index</code> argument.</p>
-<div id="6e8b1a94" class="cell" data-execution_count="5">
+<div id="3fddf36f" class="cell" data-execution_count="5">
 <div class="sourceCode cell-code" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>s <span class="op">=</span> pd.Series([<span class="op">-</span><span class="dv">1</span>, <span class="dv">10</span>, <span class="dv">2</span>], index <span class="op">=</span> [<span class="st">"a"</span>, <span class="st">"b"</span>, <span class="st">"c"</span>])</span>
 <span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a>s</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="5">
@@ -515,14 +377,14 @@ <h3 data-number="2.2.1" class="anchored" data-anchor-id="series"><span class="he
 dtype: int64</code></pre>
 </div>
 </div>
-<div id="826d0f8b" class="cell" data-execution_count="6">
+<div id="79f91faf" class="cell" data-execution_count="6">
 <div class="sourceCode cell-code" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>s.index</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="6">
 <pre><code>Index(['a', 'b', 'c'], dtype='object')</code></pre>
 </div>
 </div>
 <p>Indices can also be changed after initialization.</p>
-<div id="0cefb0da" class="cell" data-execution_count="7">
+<div id="117dec32" class="cell" data-execution_count="7">
 <div class="sourceCode cell-code" id="cb12"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a>s.index <span class="op">=</span> [<span class="st">"first"</span>, <span class="st">"second"</span>, <span class="st">"third"</span>]</span>
 <span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a>s</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="7">
@@ -532,7 +394,7 @@ <h3 data-number="2.2.1" class="anchored" data-anchor-id="series"><span class="he
 dtype: int64</code></pre>
 </div>
 </div>
-<div id="a448a579" class="cell" data-execution_count="8">
+<div id="a2d20e5b" class="cell" data-execution_count="8">
 <div class="sourceCode cell-code" id="cb14"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a>s.index</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="8">
 <pre><code>Index(['first', 'second', 'third'], dtype='object')</code></pre>
@@ -547,7 +409,7 @@ <h4 data-number="2.2.1.1" class="anchored" data-anchor-id="selection-in-series">
 <li>A filtering condition.</li>
 </ol>
 <p>To demonstrate this, let’s define the Series <code>ser</code>.</p>
-<div id="775c04ef" class="cell" data-execution_count="9">
+<div id="2aba17d4" class="cell" data-execution_count="9">
 <div class="sourceCode cell-code" id="cb16"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a>ser <span class="op">=</span> pd.Series([<span class="dv">4</span>, <span class="op">-</span><span class="dv">2</span>, <span class="dv">0</span>, <span class="dv">6</span>], index <span class="op">=</span> [<span class="st">"a"</span>, <span class="st">"b"</span>, <span class="st">"c"</span>, <span class="st">"d"</span>])</span>
 <span id="cb16-2"><a href="#cb16-2" aria-hidden="true" tabindex="-1"></a>ser</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="9">
@@ -560,17 +422,17 @@ <h4 data-number="2.2.1.1" class="anchored" data-anchor-id="selection-in-series">
 </div>
 <section id="a-single-label" class="level5" data-number="2.2.1.1.1">
 <h5 data-number="2.2.1.1.1" class="anchored" data-anchor-id="a-single-label"><span class="header-section-number">2.2.1.1.1</span> A Single Label</h5>
-<div id="da3a2fdc" class="cell" data-execution_count="10">
+<div id="21599c31" class="cell" data-execution_count="10">
 <div class="sourceCode cell-code" id="cb18"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb18-1"><a href="#cb18-1" aria-hidden="true" tabindex="-1"></a><span class="co"># We return the value stored at the index label "a"</span></span>
 <span id="cb18-2"><a href="#cb18-2" aria-hidden="true" tabindex="-1"></a>ser[<span class="st">"a"</span>] </span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="10">
-<pre><code>np.int64(4)</code></pre>
+<pre><code>4</code></pre>
 </div>
 </div>
 </section>
 <section id="a-list-of-labels" class="level5" data-number="2.2.1.1.2">
 <h5 data-number="2.2.1.1.2" class="anchored" data-anchor-id="a-list-of-labels"><span class="header-section-number">2.2.1.1.2</span> A List of Labels</h5>
-<div id="c34f8f2a" class="cell" data-execution_count="11">
+<div id="e93db896" class="cell" data-execution_count="11">
 <div class="sourceCode cell-code" id="cb20"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="co"># We return a Series of the values stored at the index labels "a" and "c"</span></span>
 <span id="cb20-2"><a href="#cb20-2" aria-hidden="true" tabindex="-1"></a>ser[[<span class="st">"a"</span>, <span class="st">"c"</span>]] </span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="11">
@@ -584,7 +446,7 @@ <h5 data-number="2.2.1.1.2" class="anchored" data-anchor-id="a-list-of-labels"><
 <h5 data-number="2.2.1.1.3" class="anchored" data-anchor-id="a-filtering-condition"><span class="header-section-number">2.2.1.1.3</span> A Filtering Condition</h5>
 <p>Perhaps the most interesting (and useful) method of selecting data from a <code>Series</code> is by using a filtering condition.</p>
 <p>First, we apply a boolean operation to the <code>Series</code>. This creates <strong>a new <code>Series</code> of boolean values</strong>.</p>
-<div id="440adc90" class="cell" data-execution_count="12">
+<div id="33cd0d31" class="cell" data-execution_count="12">
 <div class="sourceCode cell-code" id="cb22"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb22-1"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Filter condition: select all elements greater than 0</span></span>
 <span id="cb22-2"><a href="#cb22-2" aria-hidden="true" tabindex="-1"></a>ser <span class="op">&gt;</span> <span class="dv">0</span> </span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="12">
@@ -596,7 +458,7 @@ <h5 data-number="2.2.1.1.3" class="anchored" data-anchor-id="a-filtering-conditi
 </div>
 </div>
 <p>We then use this boolean condition to index into our original <code>Series</code>. <code>pandas</code> will select only the entries in the original <code>Series</code> that satisfy the condition.</p>
-<div id="9445c1c9" class="cell" data-execution_count="13">
+<div id="4f08999f" class="cell" data-execution_count="13">
 <div class="sourceCode cell-code" id="cb24"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a>ser[ser <span class="op">&gt;</span> <span class="dv">0</span>] </span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="13">
 <pre><code>a    4
@@ -626,7 +488,7 @@ <h4 data-number="2.2.2.1" class="anchored" data-anchor-id="creating-a-dataframe"
 <h5 data-number="2.2.2.1.1" class="anchored" data-anchor-id="from-a-csv-file"><span class="header-section-number">2.2.2.1.1</span> From a CSV file</h5>
 <p>In Data 100, our data are typically stored in a CSV (comma-separated values) file format. We can import a CSV file into a <code>DataFrame</code> by passing the data path as an argument to the following <code>pandas</code> function. <br>  <code>pd.read_csv("filename.csv")</code></p>
 <p>With our new understanding of <code>pandas</code> in hand, let’s return to the <code>elections</code> dataset from before. Now, we can recognize that it is represented as a <code>pandas</code> <code>DataFrame</code>.</p>
-<div id="a606bbea" class="cell" data-execution_count="14">
+<div id="2f684355" class="cell" data-execution_count="14">
 <div class="sourceCode cell-code" id="cb27"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb27-1"><a href="#cb27-1" aria-hidden="true" tabindex="-1"></a>elections <span class="op">=</span> pd.read_csv(<span class="st">"data/elections.csv"</span>)</span>
 <span id="cb27-2"><a href="#cb27-2" aria-hidden="true" tabindex="-1"></a>elections</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="14">
@@ -758,7 +620,7 @@ <h5 data-number="2.2.2.1.1" class="anchored" data-anchor-id="from-a-csv-file"><s
 <h5 data-number="2.2.2.1.2" class="anchored" data-anchor-id="using-a-list-and-column-names"><span class="header-section-number">2.2.2.1.2</span> Using a List and Column Name(s)</h5>
 <p>We’ll now explore creating a <code>DataFrame</code> with data of our own.</p>
 <p>Consider the following examples. The first code cell creates a <code>DataFrame</code> with a single column <code>Numbers</code>.</p>
-<div id="852d28e7" class="cell" data-execution_count="15">
+<div id="c9bcda35" class="cell" data-execution_count="15">
 <div class="sourceCode cell-code" id="cb28"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb28-1"><a href="#cb28-1" aria-hidden="true" tabindex="-1"></a>df_list <span class="op">=</span> pd.DataFrame([<span class="dv">1</span>, <span class="dv">2</span>, <span class="dv">3</span>], columns<span class="op">=</span>[<span class="st">"Numbers"</span>])</span>
 <span id="cb28-2"><a href="#cb28-2" aria-hidden="true" tabindex="-1"></a>df_list</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="15">
@@ -792,7 +654,7 @@ <h5 data-number="2.2.2.1.2" class="anchored" data-anchor-id="using-a-list-and-co
 </div>
 </div>
 <p>The second creates a <code>DataFrame</code> with the columns <code>Numbers</code> and <code>Description</code>. Notice how a 2D list of values is required to initialize the second <code>DataFrame</code> — each nested list represents a single row of data.</p>
-<div id="e47f7aca" class="cell" data-execution_count="16">
+<div id="add6cf4a" class="cell" data-execution_count="16">
 <div class="sourceCode cell-code" id="cb29"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb29-1"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a>df_list <span class="op">=</span> pd.DataFrame([[<span class="dv">1</span>, <span class="st">"one"</span>], [<span class="dv">2</span>, <span class="st">"two"</span>]], columns <span class="op">=</span> [<span class="st">"Number"</span>, <span class="st">"Description"</span>])</span>
 <span id="cb29-2"><a href="#cb29-2" aria-hidden="true" tabindex="-1"></a>df_list</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="16">
@@ -829,7 +691,7 @@ <h5 data-number="2.2.2.1.2" class="anchored" data-anchor-id="using-a-list-and-co
 <h5 data-number="2.2.2.1.3" class="anchored" data-anchor-id="from-a-dictionary"><span class="header-section-number">2.2.2.1.3</span> From a Dictionary</h5>
 <p>A third (and more common) way to create a <code>DataFrame</code> is with a dictionary. The dictionary keys represent the column names, and the dictionary values represent the column values.</p>
 <p>Below are two ways of implementing this approach. The first is based on specifying the columns of the <code>DataFrame</code>, whereas the second is based on specifying the rows of the <code>DataFrame</code>.</p>
-<div id="1897bb57" class="cell" data-execution_count="17">
+<div id="92737954" class="cell" data-execution_count="17">
 <div class="sourceCode cell-code" id="cb30"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb30-1"><a href="#cb30-1" aria-hidden="true" tabindex="-1"></a>df_dict <span class="op">=</span> pd.DataFrame({</span>
 <span id="cb30-2"><a href="#cb30-2" aria-hidden="true" tabindex="-1"></a>    <span class="st">"Fruit"</span>: [<span class="st">"Strawberry"</span>, <span class="st">"Orange"</span>], </span>
 <span id="cb30-3"><a href="#cb30-3" aria-hidden="true" tabindex="-1"></a>    <span class="st">"Price"</span>: [<span class="fl">5.49</span>, <span class="fl">3.99</span>]</span>
@@ -864,7 +726,7 @@ <h5 data-number="2.2.2.1.3" class="anchored" data-anchor-id="from-a-dictionary">
 </div>
 </div>
 </div>
-<div id="6cd06fae" class="cell" data-execution_count="18">
+<div id="5a6dcc02" class="cell" data-execution_count="18">
 <div class="sourceCode cell-code" id="cb31"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb31-1"><a href="#cb31-1" aria-hidden="true" tabindex="-1"></a>df_dict <span class="op">=</span> pd.DataFrame(</span>
 <span id="cb31-2"><a href="#cb31-2" aria-hidden="true" tabindex="-1"></a>    [</span>
 <span id="cb31-3"><a href="#cb31-3" aria-hidden="true" tabindex="-1"></a>        {<span class="st">"Fruit"</span>:<span class="st">"Strawberry"</span>, <span class="st">"Price"</span>:<span class="fl">5.49</span>}, </span>
@@ -906,14 +768,14 @@ <h5 data-number="2.2.2.1.3" class="anchored" data-anchor-id="from-a-dictionary">
 <h5 data-number="2.2.2.1.4" class="anchored" data-anchor-id="from-a-series"><span class="header-section-number">2.2.2.1.4</span> From a <code>Series</code></h5>
 <p>Earlier, we explained how a <code>Series</code> was synonymous to a column in a <code>DataFrame</code>. It follows, then, that a <code>DataFrame</code> is equivalent to a collection of <code>Series</code>, which all share the same <code>Index</code>.</p>
 <p>In fact, we can initialize a <code>DataFrame</code> by merging two or more <code>Series</code>. Consider the <code>Series</code> <code>s_a</code> and <code>s_b</code>.</p>
-<div id="9e582efd" class="cell" data-execution_count="19">
+<div id="8d6f386a" class="cell" data-execution_count="19">
 <div class="sourceCode cell-code" id="cb32"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb32-1"><a href="#cb32-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Notice how our indices, or row labels, are the same</span></span>
 <span id="cb32-2"><a href="#cb32-2" aria-hidden="true" tabindex="-1"></a></span>
 <span id="cb32-3"><a href="#cb32-3" aria-hidden="true" tabindex="-1"></a>s_a <span class="op">=</span> pd.Series([<span class="st">"a1"</span>, <span class="st">"a2"</span>, <span class="st">"a3"</span>], index <span class="op">=</span> [<span class="st">"r1"</span>, <span class="st">"r2"</span>, <span class="st">"r3"</span>])</span>
 <span id="cb32-4"><a href="#cb32-4" aria-hidden="true" tabindex="-1"></a>s_b <span class="op">=</span> pd.Series([<span class="st">"b1"</span>, <span class="st">"b2"</span>, <span class="st">"b3"</span>], index <span class="op">=</span> [<span class="st">"r1"</span>, <span class="st">"r2"</span>, <span class="st">"r3"</span>])</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </div>
 <p>We can turn individual <code>Series</code> into a <code>DataFrame</code> using two common methods (shown below):</p>
-<div id="d5b6fdba" class="cell" data-execution_count="20">
+<div id="5c23567e" class="cell" data-execution_count="20">
 <div class="sourceCode cell-code" id="cb33"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb33-1"><a href="#cb33-1" aria-hidden="true" tabindex="-1"></a>pd.DataFrame(s_a)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="20">
 <div>
@@ -945,7 +807,7 @@ <h5 data-number="2.2.2.1.4" class="anchored" data-anchor-id="from-a-series"><spa
 </div>
 </div>
 </div>
-<div id="2f768126" class="cell" data-execution_count="21">
+<div id="2edbe8c0" class="cell" data-execution_count="21">
 <div class="sourceCode cell-code" id="cb34"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb34-1"><a href="#cb34-1" aria-hidden="true" tabindex="-1"></a>s_b.to_frame()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="21">
 <div>
@@ -978,7 +840,7 @@ <h5 data-number="2.2.2.1.4" class="anchored" data-anchor-id="from-a-series"><spa
 </div>
 </div>
 <p>To merge the two <code>Series</code> and specify their column names, we use the following syntax:</p>
-<div id="a504dc4d" class="cell" data-execution_count="22">
+<div id="189acd5a" class="cell" data-execution_count="22">
 <div class="sourceCode cell-code" id="cb35"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb35-1"><a href="#cb35-1" aria-hidden="true" tabindex="-1"></a>pd.DataFrame({</span>
 <span id="cb35-2"><a href="#cb35-2" aria-hidden="true" tabindex="-1"></a>    <span class="st">"A-column"</span>: s_a, </span>
 <span id="cb35-3"><a href="#cb35-3" aria-hidden="true" tabindex="-1"></a>    <span class="st">"B-column"</span>: s_b</span>
@@ -1023,7 +885,7 @@ <h5 data-number="2.2.2.1.4" class="anchored" data-anchor-id="from-a-series"><spa
 <section id="indices" class="level3" data-number="2.2.3">
 <h3 data-number="2.2.3" class="anchored" data-anchor-id="indices"><span class="header-section-number">2.2.3</span> Indices</h3>
 <p>On a more technical note, an index doesn’t have to be an integer, nor does it have to be unique. For example, we can set the index of the <code>elections</code> <code>DataFrame</code> to be the name of presidential candidates.</p>
-<div id="3de138e2" class="cell" data-execution_count="23">
+<div id="883cd007" class="cell" data-execution_count="23">
 <div class="sourceCode cell-code" id="cb36"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb36-1"><a href="#cb36-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Creating a DataFrame from a CSV file and specifying the index column</span></span>
 <span id="cb36-2"><a href="#cb36-2" aria-hidden="true" tabindex="-1"></a>elections <span class="op">=</span> pd.read_csv(<span class="st">"data/elections.csv"</span>, index_col <span class="op">=</span> <span class="st">"Candidate"</span>)</span>
 <span id="cb36-3"><a href="#cb36-3" aria-hidden="true" tabindex="-1"></a>elections</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1147,7 +1009,7 @@ <h3 data-number="2.2.3" class="anchored" data-anchor-id="indices"><span class="h
 </div>
 </div>
 <p>We can also select a new column and set it as the index of the <code>DataFrame</code>. For example, we can set the index of the <code>elections</code> <code>DataFrame</code> to represent the candidate’s party.</p>
-<div id="ab8ac690" class="cell" data-execution_count="24">
+<div id="7bbcec42" class="cell" data-execution_count="24">
 <div class="sourceCode cell-code" id="cb37"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb37-1"><a href="#cb37-1" aria-hidden="true" tabindex="-1"></a>elections.reset_index(inplace <span class="op">=</span> <span class="va">True</span>) <span class="co"># Resetting the index so we can set it again</span></span>
 <span id="cb37-2"><a href="#cb37-2" aria-hidden="true" tabindex="-1"></a><span class="co"># This sets the index to the "Party" column</span></span>
 <span id="cb37-3"><a href="#cb37-3" aria-hidden="true" tabindex="-1"></a>elections.set_index(<span class="st">"Party"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1271,7 +1133,7 @@ <h3 data-number="2.2.3" class="anchored" data-anchor-id="indices"><span class="h
 </div>
 </div>
 <p>And, if we’d like, we can revert the index back to the default list of integers.</p>
-<div id="c5371d59" class="cell" data-execution_count="25">
+<div id="4c6f3eb3" class="cell" data-execution_count="25">
 <div class="sourceCode cell-code" id="cb38"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb38-1"><a href="#cb38-1" aria-hidden="true" tabindex="-1"></a><span class="co"># This resets the index to be the default list of integer</span></span>
 <span id="cb38-2"><a href="#cb38-2" aria-hidden="true" tabindex="-1"></a>elections.reset_index(inplace<span class="op">=</span><span class="va">True</span>) </span>
 <span id="cb38-3"><a href="#cb38-3" aria-hidden="true" tabindex="-1"></a>elections.index</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1294,7 +1156,7 @@ <h3 data-number="2.2.3" class="anchored" data-anchor-id="indices"><span class="h
 <h2 data-number="2.3" class="anchored" data-anchor-id="dataframe-attributes-index-columns-and-shape"><span class="header-section-number">2.3</span> <code>DataFrame</code> Attributes: Index, Columns, and Shape</h2>
 <p>On the other hand, column names in a <code>DataFrame</code> are almost always unique. Looking back to the <code>elections</code> dataset, it wouldn’t make sense to have two columns named <code>"Candidate"</code>. Sometimes, you’ll want to extract these different values, in particular, the list of row and column labels.</p>
 <p>For index/row labels, use <code>DataFrame.index</code>:</p>
-<div id="12e6b0d8" class="cell" data-execution_count="26">
+<div id="84d37899" class="cell" data-execution_count="26">
 <div class="sourceCode cell-code" id="cb40"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb40-1"><a href="#cb40-1" aria-hidden="true" tabindex="-1"></a>elections.set_index(<span class="st">"Party"</span>, inplace <span class="op">=</span> <span class="va">True</span>)</span>
 <span id="cb40-2"><a href="#cb40-2" aria-hidden="true" tabindex="-1"></a>elections.index</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="26">
@@ -1309,14 +1171,14 @@ <h2 data-number="2.3" class="anchored" data-anchor-id="dataframe-attributes-inde
 </div>
 </div>
 <p>For column labels, use <code>DataFrame.columns</code>:</p>
-<div id="ebbb5a76" class="cell" data-execution_count="27">
+<div id="b1b34ae4" class="cell" data-execution_count="27">
 <div class="sourceCode cell-code" id="cb42"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb42-1"><a href="#cb42-1" aria-hidden="true" tabindex="-1"></a>elections.columns</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="27">
 <pre><code>Index(['index', 'Candidate', 'Year', 'Popular vote', 'Result', '%'], dtype='object')</code></pre>
 </div>
 </div>
 <p>And for the shape of the <code>DataFrame</code>, we can use <code>DataFrame.shape</code> to get the number of rows followed by the number of columns:</p>
-<div id="f00f1446" class="cell" data-execution_count="28">
+<div id="758c3ec1" class="cell" data-execution_count="28">
 <div class="sourceCode cell-code" id="cb44"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb44-1"><a href="#cb44-1" aria-hidden="true" tabindex="-1"></a>elections.shape</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="28">
 <pre><code>(182, 6)</code></pre>
@@ -1345,13 +1207,13 @@ <h2 data-number="2.4" class="anchored" data-anchor-id="slicing-in-dataframes"><s
 <h3 data-number="2.4.1" class="anchored" data-anchor-id="extracting-data-with-.head-and-.tail"><span class="header-section-number">2.4.1</span> Extracting data with <code>.head</code> and <code>.tail</code></h3>
 <p>The simplest scenario in which we want to extract data is when we simply want to select the first or last few rows of the <code>DataFrame</code>.</p>
 <p>To extract the first <code>n</code> rows of a <code>DataFrame</code> <code>df</code>, we use the syntax <code>df.head(n)</code>.</p>
-<div id="a10cdd75" class="cell" data-execution_count="29">
+<div id="0763048a" class="cell" data-execution_count="29">
 <details class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb46"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb46-1"><a href="#cb46-1" aria-hidden="true" tabindex="-1"></a>elections <span class="op">=</span> pd.read_csv(<span class="st">"data/elections.csv"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="b45fd028" class="cell" data-execution_count="30">
+<div id="e83a008c" class="cell" data-execution_count="30">
 <div class="sourceCode cell-code" id="cb47"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb47-1"><a href="#cb47-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Extract the first 5 rows of the DataFrame</span></span>
 <span id="cb47-2"><a href="#cb47-2" aria-hidden="true" tabindex="-1"></a>elections.head(<span class="dv">5</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="30">
@@ -1423,7 +1285,7 @@ <h3 data-number="2.4.1" class="anchored" data-anchor-id="extracting-data-with-.h
 </div>
 </div>
 <p>Similarly, calling <code>df.tail(n)</code> allows us to extract the last <code>n</code> rows of the <code>DataFrame</code>.</p>
-<div id="7077ba19" class="cell" data-execution_count="31">
+<div id="b28a90ac" class="cell" data-execution_count="31">
 <div class="sourceCode cell-code" id="cb48"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb48-1"><a href="#cb48-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Extract the last 5 rows of the DataFrame</span></span>
 <span id="cb48-2"><a href="#cb48-2" aria-hidden="true" tabindex="-1"></a>elections.tail(<span class="dv">5</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="31">
@@ -1509,14 +1371,14 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 <li>A list.</li>
 </ul>
 <p>For example, to select a single value, we can select the row labeled <code>0</code> and the column labeled <code>Candidate</code> from the <code>elections</code> <code>DataFrame</code>.</p>
-<div id="3e21e302" class="cell" data-execution_count="32">
+<div id="e1d1ca54" class="cell" data-execution_count="32">
 <div class="sourceCode cell-code" id="cb49"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb49-1"><a href="#cb49-1" aria-hidden="true" tabindex="-1"></a>elections.loc[<span class="dv">0</span>, <span class="st">'Candidate'</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="32">
 <pre><code>'Andrew Jackson'</code></pre>
 </div>
 </div>
 <p>Keep in mind that passing in just one argument as a single value will produce a <code>Series</code>. Below, we’ve extracted a subset of the <code>"Popular vote"</code> column as a <code>Series</code>.</p>
-<div id="864aa865" class="cell" data-execution_count="33">
+<div id="a5d51bad" class="cell" data-execution_count="33">
 <div class="sourceCode cell-code" id="cb51"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb51-1"><a href="#cb51-1" aria-hidden="true" tabindex="-1"></a>elections.loc[[<span class="dv">87</span>, <span class="dv">25</span>, <span class="dv">179</span>], <span class="st">"Popular vote"</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="33">
 <pre><code>87     15761254
@@ -1526,7 +1388,7 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 </div>
 </div>
 <p>To select <em>multiple</em> rows and columns, we can use Python slice notation. Here, we select the rows from labels <code>0</code> to <code>3</code> and the columns from labels <code>"Year"</code> to <code>"Popular vote"</code>. Notice that unlike Python slicing, <code>.loc</code> is <em>inclusive</em> of the right upper bound.</p>
-<div id="68712dc8" class="cell" data-execution_count="34">
+<div id="d261b154" class="cell" data-execution_count="34">
 <div class="sourceCode cell-code" id="cb53"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb53-1"><a href="#cb53-1" aria-hidden="true" tabindex="-1"></a>elections.loc[<span class="dv">0</span>:<span class="dv">3</span>, <span class="st">'Year'</span>:<span class="st">'Popular vote'</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="34">
 <div>
@@ -1578,7 +1440,7 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 </div>
 </div>
 <p>Suppose that instead, we want to extract <em>all</em> column values for the first four rows in the <code>elections</code> <code>DataFrame</code>. The shorthand <code>:</code> is useful for this.</p>
-<div id="fc7d4ab3" class="cell" data-execution_count="35">
+<div id="14868023" class="cell" data-execution_count="35">
 <div class="sourceCode cell-code" id="cb54"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb54-1"><a href="#cb54-1" aria-hidden="true" tabindex="-1"></a>elections.loc[<span class="dv">0</span>:<span class="dv">3</span>, :]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="35">
 <div>
@@ -1640,7 +1502,7 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 </div>
 </div>
 <p>We can use the same shorthand to extract all rows.</p>
-<div id="9d204072" class="cell" data-execution_count="36">
+<div id="cb1a7309" class="cell" data-execution_count="36">
 <div class="sourceCode cell-code" id="cb55"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb55-1"><a href="#cb55-1" aria-hidden="true" tabindex="-1"></a>elections.loc[:, [<span class="st">"Year"</span>, <span class="st">"Candidate"</span>, <span class="st">"Result"</span>]]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="36">
 <div>
@@ -1731,7 +1593,7 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 </div>
 <p>There are a couple of things we should note. Firstly, unlike conventional Python, <code>pandas</code> allows us to slice string values (in our example, the column labels). Secondly, slicing with <code>.loc</code> is <em>inclusive</em>. Notice how our resulting <code>DataFrame</code> includes every row and column between and including the slice labels we specified.</p>
 <p>Equivalently, we can use a list to obtain multiple rows and columns in our <code>elections</code> <code>DataFrame</code>.</p>
-<div id="b488759c" class="cell" data-execution_count="37">
+<div id="0f6168a0" class="cell" data-execution_count="37">
 <div class="sourceCode cell-code" id="cb56"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb56-1"><a href="#cb56-1" aria-hidden="true" tabindex="-1"></a>elections.loc[[<span class="dv">0</span>, <span class="dv">1</span>, <span class="dv">2</span>, <span class="dv">3</span>], [<span class="st">'Year'</span>, <span class="st">'Candidate'</span>, <span class="st">'Party'</span>, <span class="st">'Popular vote'</span>]]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="37">
 <div>
@@ -1783,7 +1645,7 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 </div>
 </div>
 <p>Lastly, we can interchange list and slicing notation.</p>
-<div id="5e68745c" class="cell" data-execution_count="38">
+<div id="3312d4df" class="cell" data-execution_count="38">
 <div class="sourceCode cell-code" id="cb57"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb57-1"><a href="#cb57-1" aria-hidden="true" tabindex="-1"></a>elections.loc[[<span class="dv">0</span>, <span class="dv">1</span>, <span class="dv">2</span>, <span class="dv">3</span>], :]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="38">
 <div>
@@ -1849,7 +1711,7 @@ <h3 data-number="2.4.2" class="anchored" data-anchor-id="label-based-extraction-
 <h3 data-number="2.4.3" class="anchored" data-anchor-id="integer-based-extraction-indexing-with-.iloc"><span class="header-section-number">2.4.3</span> Integer-based Extraction: Indexing with <code>.iloc</code></h3>
 <p>Slicing with <code>.iloc</code> works similarly to <code>.loc</code>. However, <code>.iloc</code> uses the <em>index positions</em> of rows and columns rather than the labels (think to yourself: <strong>l</strong>oc uses <strong>l</strong>ables; <strong>i</strong>loc uses <strong>i</strong>ndices). The arguments to the <code>.iloc</code> function also behave similarly — single values, lists, indices, and any combination of these are permitted.</p>
 <p>Let’s begin reproducing our results from above. We’ll begin by selecting the first presidential candidate in our <code>elections</code> <code>DataFrame</code>:</p>
-<div id="cac24bb3" class="cell" data-execution_count="39">
+<div id="2f20d686" class="cell" data-execution_count="39">
 <div class="sourceCode cell-code" id="cb58"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb58-1"><a href="#cb58-1" aria-hidden="true" tabindex="-1"></a><span class="co"># elections.loc[0, "Candidate"] - Previous approach</span></span>
 <span id="cb58-2"><a href="#cb58-2" aria-hidden="true" tabindex="-1"></a>elections.iloc[<span class="dv">0</span>, <span class="dv">1</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="39">
@@ -1858,7 +1720,7 @@ <h3 data-number="2.4.3" class="anchored" data-anchor-id="integer-based-extractio
 </div>
 <p>Notice how the first argument to both <code>.loc</code> and <code>.iloc</code> are the same. This is because the row with a label of <code>0</code> is conveniently in the <span class="math inline">\(0^{\text{th}}\)</span> (equivalently, the first position) of the <code>elections</code> <code>DataFrame</code>. Generally, this is true of any <code>DataFrame</code> where the row labels are incremented in ascending order from 0.</p>
 <p>And, as before, if we were to pass in only one single value argument, our result would be a <code>Series</code>.</p>
-<div id="7d808090" class="cell" data-execution_count="40">
+<div id="9c0e118a" class="cell" data-execution_count="40">
 <div class="sourceCode cell-code" id="cb60"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb60-1"><a href="#cb60-1" aria-hidden="true" tabindex="-1"></a>elections.iloc[[<span class="dv">1</span>,<span class="dv">2</span>,<span class="dv">3</span>],<span class="dv">1</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="40">
 <pre><code>1    John Quincy Adams
@@ -1868,7 +1730,7 @@ <h3 data-number="2.4.3" class="anchored" data-anchor-id="integer-based-extractio
 </div>
 </div>
 <p>However, when we select the first four rows and columns using <code>.iloc</code>, we notice something.</p>
-<div id="35c09089" class="cell" data-execution_count="41">
+<div id="fb1cb194" class="cell" data-execution_count="41">
 <div class="sourceCode cell-code" id="cb62"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb62-1"><a href="#cb62-1" aria-hidden="true" tabindex="-1"></a><span class="co"># elections.loc[0:3, 'Year':'Popular vote'] - Previous approach</span></span>
 <span id="cb62-2"><a href="#cb62-2" aria-hidden="true" tabindex="-1"></a>elections.iloc[<span class="dv">0</span>:<span class="dv">4</span>, <span class="dv">0</span>:<span class="dv">4</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="41">
@@ -1922,7 +1784,7 @@ <h3 data-number="2.4.3" class="anchored" data-anchor-id="integer-based-extractio
 </div>
 <p>Slicing is no longer inclusive in <code>.iloc</code> — it’s <em>exclusive</em>. In other words, the right end of a slice is not included when using <code>.iloc</code>. This is one of the subtleties of <code>pandas</code> syntax; you will get used to it with practice.</p>
 <p>List behavior works just as expected.</p>
-<div id="85af7f54" class="cell" data-execution_count="42">
+<div id="13cb96f3" class="cell" data-execution_count="42">
 <div class="sourceCode cell-code" id="cb63"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb63-1"><a href="#cb63-1" aria-hidden="true" tabindex="-1"></a><span class="co">#elections.loc[[0, 1, 2, 3], ['Year', 'Candidate', 'Party', 'Popular vote']] - Previous Approach</span></span>
 <span id="cb63-2"><a href="#cb63-2" aria-hidden="true" tabindex="-1"></a>elections.iloc[[<span class="dv">0</span>, <span class="dv">1</span>, <span class="dv">2</span>, <span class="dv">3</span>], [<span class="dv">0</span>, <span class="dv">1</span>, <span class="dv">2</span>, <span class="dv">3</span>]]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="42">
@@ -1975,7 +1837,7 @@ <h3 data-number="2.4.3" class="anchored" data-anchor-id="integer-based-extractio
 </div>
 </div>
 <p>And just like with <code>.loc</code>, we can use a colon with <code>.iloc</code> to extract all rows or columns.</p>
-<div id="fb933316" class="cell" data-execution_count="43">
+<div id="53009da4" class="cell" data-execution_count="43">
 <div class="sourceCode cell-code" id="cb64"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb64-1"><a href="#cb64-1" aria-hidden="true" tabindex="-1"></a>elections.iloc[:, <span class="dv">0</span>:<span class="dv">3</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="43">
 <div>
@@ -2083,7 +1945,7 @@ <h3 data-number="2.4.4" class="anchored" data-anchor-id="context-dependent-extra
 <section id="a-slice-of-row-numbers" class="level4" data-number="2.4.4.1">
 <h4 data-number="2.4.4.1" class="anchored" data-anchor-id="a-slice-of-row-numbers"><span class="header-section-number">2.4.4.1</span> A slice of row numbers</h4>
 <p>Say we wanted the first four rows of our <code>elections</code> <code>DataFrame</code>.</p>
-<div id="7c91009c" class="cell" data-execution_count="44">
+<div id="b0ec349d" class="cell" data-execution_count="44">
 <div class="sourceCode cell-code" id="cb65"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb65-1"><a href="#cb65-1" aria-hidden="true" tabindex="-1"></a>elections[<span class="dv">0</span>:<span class="dv">4</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="44">
 <div>
@@ -2148,7 +2010,7 @@ <h4 data-number="2.4.4.1" class="anchored" data-anchor-id="a-slice-of-row-number
 <section id="a-list-of-column-labels" class="level4" data-number="2.4.4.2">
 <h4 data-number="2.4.4.2" class="anchored" data-anchor-id="a-list-of-column-labels"><span class="header-section-number">2.4.4.2</span> A list of column labels</h4>
 <p>Suppose we now want the first four columns.</p>
-<div id="927372a5" class="cell" data-execution_count="45">
+<div id="ad9bcf43" class="cell" data-execution_count="45">
 <div class="sourceCode cell-code" id="cb66"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb66-1"><a href="#cb66-1" aria-hidden="true" tabindex="-1"></a>elections[[<span class="st">"Year"</span>, <span class="st">"Candidate"</span>, <span class="st">"Party"</span>, <span class="st">"Popular vote"</span>]]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="45">
 <div>
@@ -2253,7 +2115,7 @@ <h4 data-number="2.4.4.2" class="anchored" data-anchor-id="a-list-of-column-labe
 <section id="a-single-column-label" class="level4" data-number="2.4.4.3">
 <h4 data-number="2.4.4.3" class="anchored" data-anchor-id="a-single-column-label"><span class="header-section-number">2.4.4.3</span> A single-column label</h4>
 <p>Lastly, <code>[]</code> allows us to extract only the <code>"Candidate"</code> column.</p>
-<div id="72e1ba96" class="cell" data-execution_count="46">
+<div id="01abbe41" class="cell" data-execution_count="46">
 <div class="sourceCode cell-code" id="cb67"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb67-1"><a href="#cb67-1" aria-hidden="true" tabindex="-1"></a>elections[<span class="st">"Candidate"</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="46">
 <pre><code>0         Andrew Jackson
diff --git a/docs/pandas_2/pandas_2.html b/docs/pandas_2/pandas_2.html
index 4c70c8486..fb66f5679 100644
--- a/docs/pandas_2/pandas_2.html
+++ b/docs/pandas_2/pandas_2.html
@@ -64,7 +64,6 @@
 <script src="../site_libs/quarto-search/fuse.min.js"></script>
 <script src="../site_libs/quarto-search/quarto-search.js"></script>
 <meta name="quarto:offset" content="../">
-<link href="../pandas_3/pandas_3.html" rel="next">
 <link href="../pandas_1/pandas_1.html" rel="prev">
 <link href="../data100_logo.png" rel="icon" type="image/png">
 <script src="../site_libs/quarto-html/quarto.js"></script>
@@ -172,144 +171,6 @@
   <a href="../pandas_2/pandas_2.html" class="sidebar-item-text sidebar-link active">
  <span class="menu-text"><span class="chapter-number">3</span>&nbsp; <span class="chapter-title">Pandas II</span></span></a>
   </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../pandas_3/pandas_3.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">4</span>&nbsp; <span class="chapter-title">Pandas III</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../eda/eda.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">5</span>&nbsp; <span class="chapter-title">Data Cleaning and EDA</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../regex/regex.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">6</span>&nbsp; <span class="chapter-title">Regular Expressions</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../visualization_1/visualization_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">7</span>&nbsp; <span class="chapter-title">Visualization I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../visualization_2/visualization_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">8</span>&nbsp; <span class="chapter-title">Visualization II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../sampling/sampling.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">9</span>&nbsp; <span class="chapter-title">Sampling</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../intro_to_modeling/intro_to_modeling.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">10</span>&nbsp; <span class="chapter-title">Introduction to Modeling</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../constant_model_loss_transformations/loss_transformations.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">11</span>&nbsp; <span class="chapter-title">Constant Model, Loss, and Transformations</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../ols/ols.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">12</span>&nbsp; <span class="chapter-title">Ordinary Least Squares</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../gradient_descent/gradient_descent.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">13</span>&nbsp; <span class="chapter-title">sklearn and Gradient Descent</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../feature_engineering/feature_engineering.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">14</span>&nbsp; <span class="chapter-title">Feature Engineering</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../case_study_HCE/case_study_HCE.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">15</span>&nbsp; <span class="chapter-title">Case Study in Human Contexts and Ethics</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../cv_regularization/cv_reg.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">16</span>&nbsp; <span class="chapter-title">Cross Validation and Regularization</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../probability_1/probability_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">17</span>&nbsp; <span class="chapter-title">Random Variables</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../probability_2/probability_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">18</span>&nbsp; <span class="chapter-title">Estimators, Bias, and Variance</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../inference_causality/inference_causality.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">19</span>&nbsp; <span class="chapter-title">Causal Inference and Confounding</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../sql_I/sql_I.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">20</span>&nbsp; <span class="chapter-title">SQL I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../sql_II/sql_II.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">21</span>&nbsp; <span class="chapter-title">SQL II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../logistic_regression_1/logistic_reg_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">22</span>&nbsp; <span class="chapter-title">Logistic Regression I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../logistic_regression_2/logistic_reg_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">23</span>&nbsp; <span class="chapter-title">Logistic Regression II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../pca_1/pca_1.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">24</span>&nbsp; <span class="chapter-title">PCA I</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../pca_2/pca_2.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">25</span>&nbsp; <span class="chapter-title">PCA II</span></span></a>
-  </div>
-</li>
-        <li class="sidebar-item">
-  <div class="sidebar-item-container"> 
-  <a href="../clustering/clustering.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text"><span class="chapter-number">26</span>&nbsp; <span class="chapter-title">Clustering</span></span></a>
-  </div>
 </li>
     </ul>
     </div>
@@ -382,7 +243,7 @@ <h1 class="title"><span class="chapter-number">3</span>&nbsp; <span class="chapt
 <p>Last time, we introduced the <code>pandas</code> library as a toolkit for processing data. We learned the <code>DataFrame</code> and <code>Series</code> data structures, familiarized ourselves with the basic syntax for manipulating tabular data, and began writing our first lines of <code>pandas</code> code.</p>
 <p>In this lecture, we’ll start to dive into some advanced <code>pandas</code> syntax. You may find it helpful to follow along with a notebook of your own as we walk through these new pieces of code.</p>
 <p>We’ll start by loading the <code>babynames</code> dataset.</p>
-<div id="afa65131" class="cell" data-execution_count="1">
+<div id="82ea8e54" class="cell" data-execution_count="1">
 <details class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="co"># This code pulls census data and loads it into a DataFrame</span></span>
@@ -475,7 +336,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 <p>Conditional selection allows us to select a subset of rows in a <code>DataFrame</code> that satisfy some specified condition.</p>
 <p>To understand how to use conditional selection, we must look at another possible input of the <code>.loc</code> and <code>[]</code> methods – a boolean array, which is simply an array or <code>Series</code> where each element is either <code>True</code> or <code>False</code>. This boolean array must have a length equal to the number of rows in the <code>DataFrame</code>. It will return all rows that correspond to a value of <code>True</code> in the array. We used a very similar technique when performing conditional extraction from a <code>Series</code> in the last lecture.</p>
 <p>To see this in action, let’s select all even-indexed rows in the first 10 rows of our <code>DataFrame</code>.</p>
-<div id="4da79509" class="cell" data-execution_count="2">
+<div id="89f05952" class="cell" data-execution_count="2">
 <div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Ask yourself: why is :9 is the correct slice to select the first 10 rows?</span></span>
 <span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a>babynames_first_10_rows <span class="op">=</span> babynames.loc[:<span class="dv">9</span>, :]</span>
 <span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a></span>
@@ -544,7 +405,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 </div>
 <p>We can perform a similar operation using <code>.loc</code>.</p>
-<div id="ced2ea5a" class="cell" data-execution_count="3">
+<div id="168b19bf" class="cell" data-execution_count="3">
 <div class="sourceCode cell-code" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>babynames_first_10_rows.loc[[<span class="va">True</span>, <span class="va">False</span>, <span class="va">True</span>, <span class="va">False</span>, <span class="va">True</span>, <span class="va">False</span>, <span class="va">True</span>, <span class="va">False</span>, <span class="va">True</span>, <span class="va">False</span>], :]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="3">
 <div>
@@ -610,7 +471,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 <p>These techniques worked well in this example, but you can imagine how tedious it might be to list out <code>True</code> and <code>False</code>for every row in a larger <code>DataFrame</code>. To make things easier, we can instead provide a logical condition as an input to <code>.loc</code> or <code>[]</code> that returns a boolean array with the necessary length.</p>
 <p>For example, to return all names associated with <code>F</code> sex:</p>
-<div id="d392c24c" class="cell" data-execution_count="4">
+<div id="678be2bf" class="cell" data-execution_count="4">
 <div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="co"># First, use a logical condition to generate a boolean array</span></span>
 <span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a>logical_operator <span class="op">=</span> (babynames[<span class="st">"Sex"</span>] <span class="op">==</span> <span class="st">"F"</span>)</span>
 <span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a></span>
@@ -680,7 +541,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 <p>Recall from the previous lecture that <code>.head()</code> will return only the first few rows in the <code>DataFrame</code>. In reality, <code>babynames[logical operator]</code> contains as many rows as there are entries in the original <code>babynames</code> <code>DataFrame</code> with sex <code>"F"</code>.</p>
 <p>Here, <code>logical_operator</code> evaluates to a <code>Series</code> of boolean values with length 407428.</p>
-<div id="cd4fe8ee" class="cell" data-execution_count="5">
+<div id="29f15cf5" class="cell" data-execution_count="5">
 <details class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="st">"There are a total of </span><span class="sc">{}</span><span class="st"> values in 'logical_operator'"</span>.<span class="bu">format</span>(<span class="bu">len</span>(logical_operator)))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -690,7 +551,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 </div>
 <p>Rows starting at row 0 and ending at row 239536 evaluate to <code>True</code> and are thus returned in the <code>DataFrame</code>. Rows from 239537 onwards evaluate to <code>False</code> and are omitted from the output.</p>
-<div id="923370a3" class="cell" data-execution_count="6">
+<div id="e238b464" class="cell" data-execution_count="6">
 <details class="code-fold">
 <summary>Code</summary>
 <div class="sourceCode cell-code" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="st">"The 0th item in this 'logical_operator' is: </span><span class="sc">{}</span><span class="st">"</span>.<span class="bu">format</span>(logical_operator.iloc[<span class="dv">0</span>]))</span>
@@ -705,7 +566,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 <p>Passing a <code>Series</code> as an argument to <code>babynames[]</code> has the same effect as using a boolean array. In fact, the <code>[]</code> selection operator can take a boolean <code>Series</code>, array, and list as arguments. These three are used interchangeably throughout the course.</p>
 <p>We can also use <code>.loc</code> to achieve similar results.</p>
-<div id="7b366de6" class="cell" data-execution_count="7">
+<div id="c526e197" class="cell" data-execution_count="7">
 <div class="sourceCode cell-code" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>babynames.loc[babynames[<span class="st">"Sex"</span>] <span class="op">==</span> <span class="st">"F"</span>].head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="7">
 <div>
@@ -803,7 +664,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </table>
 <p>When combining multiple conditions with logical operators, we surround each individual condition with a set of parenthesis <code>()</code>. This imposes an order of operations on <code>pandas</code> evaluating your logic and can avoid code erroring.</p>
 <p>For example, if we want to return data on all names with sex <code>"F"</code> born before the year 2000, we can write:</p>
-<div id="3f2f42de" class="cell" data-execution_count="8">
+<div id="4ea116e0" class="cell" data-execution_count="8">
 <div class="sourceCode cell-code" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>babynames[(babynames[<span class="st">"Sex"</span>] <span class="op">==</span> <span class="st">"F"</span>) <span class="op">&amp;</span> (babynames[<span class="st">"Year"</span>] <span class="op">&lt;</span> <span class="dv">2000</span>)].head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="8">
 <div>
@@ -868,12 +729,12 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 </div>
 <p>Note that we’re working with <code>Series</code>, so using <code>and</code> in place of <code>&amp;</code>, or <code>or</code> in place <code>|</code> will error.</p>
-<div id="2334970b" class="cell" data-execution_count="9">
+<div id="6cd3a45f" class="cell" data-execution_count="9">
 <div class="sourceCode cell-code" id="cb11"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="co"># This line of code will raise a ValueError</span></span>
 <span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a><span class="co"># babynames[(babynames["Sex"] == "F") and (babynames["Year"] &lt; 2000)].head()</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </div>
 <p>If we want to return data on all names with sex <code>"F"</code> <em>or</em> all born before the year 2000, we can write:</p>
-<div id="a1c9cc6b" class="cell" data-execution_count="10">
+<div id="4caac733" class="cell" data-execution_count="10">
 <div class="sourceCode cell-code" id="cb12"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a>babynames[(babynames[<span class="st">"Sex"</span>] <span class="op">==</span> <span class="st">"F"</span>) <span class="op">|</span> (babynames[<span class="st">"Year"</span>] <span class="op">&lt;</span> <span class="dv">2000</span>)].head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="10">
 <div>
@@ -938,7 +799,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 </div>
 <p>Boolean array selection is a useful tool, but can lead to overly verbose code for complex conditions. In the example below, our boolean condition is long enough to extend for several lines of code.</p>
-<div id="a7d93327" class="cell" data-execution_count="11">
+<div id="b8b91eb9" class="cell" data-execution_count="11">
 <div class="sourceCode cell-code" id="cb13"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Note: The parentheses surrounding the code make it possible to break the code on to multiple lines for readability</span></span>
 <span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a>(</span>
 <span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a>    babynames[(babynames[<span class="st">"Name"</span>] <span class="op">==</span> <span class="st">"Bella"</span>) <span class="op">|</span> </span>
@@ -1010,7 +871,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 <p>Fortunately, <code>pandas</code> provides many alternative methods for constructing boolean filters.</p>
 <p>The <code>.isin</code> function is one such example. This method evaluates if the values in a <code>Series</code> are contained in a different sequence (list, array, or <code>Series</code>) of values. In the cell below, we achieve equivalent results to the <code>DataFrame</code> above with far more concise code.</p>
-<div id="64546e43" class="cell" data-execution_count="12">
+<div id="05ae6b6d" class="cell" data-execution_count="12">
 <div class="sourceCode cell-code" id="cb14"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a>names <span class="op">=</span> [<span class="st">"Bella"</span>, <span class="st">"Alex"</span>, <span class="st">"Narges"</span>, <span class="st">"Lisa"</span>]</span>
 <span id="cb14-2"><a href="#cb14-2" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"Name"</span>].isin(names).head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="12">
@@ -1022,7 +883,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 Name: Name, dtype: bool</code></pre>
 </div>
 </div>
-<div id="786c5202" class="cell" data-execution_count="13">
+<div id="5575eb2e" class="cell" data-execution_count="13">
 <div class="sourceCode cell-code" id="cb16"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a>babynames[babynames[<span class="st">"Name"</span>].isin(names)].head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="13">
 <div>
@@ -1087,7 +948,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 </div>
 </div>
 <p>The function <code>str.startswith</code> can be used to define a filter based on string values in a <code>Series</code> object. It checks to see if string values in a <code>Series</code> start with a particular character.</p>
-<div id="37e19bdb" class="cell" data-execution_count="14">
+<div id="c644221a" class="cell" data-execution_count="14">
 <div class="sourceCode cell-code" id="cb17"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb17-1"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Identify whether names begin with the letter "N"</span></span>
 <span id="cb17-2"><a href="#cb17-2" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"Name"</span>].<span class="bu">str</span>.startswith(<span class="st">"N"</span>).head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="14">
@@ -1099,7 +960,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 Name: Name, dtype: bool</code></pre>
 </div>
 </div>
-<div id="2c011dd3" class="cell" data-execution_count="15">
+<div id="0bf83b57" class="cell" data-execution_count="15">
 <div class="sourceCode cell-code" id="cb19"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb19-1"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Extracting names that begin with the letter "N"</span></span>
 <span id="cb19-2"><a href="#cb19-2" aria-hidden="true" tabindex="-1"></a>babynames[babynames[<span class="st">"Name"</span>].<span class="bu">str</span>.startswith(<span class="st">"N"</span>)].head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="15">
@@ -1169,7 +1030,7 @@ <h2 data-number="3.1" class="anchored" data-anchor-id="conditional-selection"><s
 <h2 data-number="3.2" class="anchored" data-anchor-id="adding-removing-and-modifying-columns"><span class="header-section-number">3.2</span> Adding, Removing, and Modifying Columns</h2>
 <p>In many data science tasks, we may need to change the columns contained in our <code>DataFrame</code> in some way. Fortunately, the syntax to do so is fairly straightforward.</p>
 <p>To add a new column to a <code>DataFrame</code>, we use a syntax similar to that used when accessing an existing column. Specify the name of the new column by writing <code>df["column"]</code>, then assign this to a <code>Series</code> or array containing the values that will populate this column.</p>
-<div id="66087634" class="cell" data-execution_count="16">
+<div id="ef98e365" class="cell" data-execution_count="16">
 <div class="sourceCode cell-code" id="cb20"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Create a Series of the length of each name. </span></span>
 <span id="cb20-2"><a href="#cb20-2" aria-hidden="true" tabindex="-1"></a>babyname_lengths <span class="op">=</span> babynames[<span class="st">"Name"</span>].<span class="bu">str</span>.<span class="bu">len</span>()</span>
 <span id="cb20-3"><a href="#cb20-3" aria-hidden="true" tabindex="-1"></a></span>
@@ -1245,7 +1106,7 @@ <h2 data-number="3.2" class="anchored" data-anchor-id="adding-removing-and-modif
 </div>
 </div>
 <p>If we need to later modify an existing column, we can do so by referencing this column again with the syntax <code>df["column"]</code>, then re-assigning it to a new <code>Series</code> or array of the appropriate length.</p>
-<div id="0467ae45" class="cell" data-execution_count="17">
+<div id="2c316c34" class="cell" data-execution_count="17">
 <div class="sourceCode cell-code" id="cb21"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb21-1"><a href="#cb21-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Modify the “name_lengths” column to be one less than its original value</span></span>
 <span id="cb21-2"><a href="#cb21-2" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"name_lengths"</span>] <span class="op">=</span> babynames[<span class="st">"name_lengths"</span>] <span class="op">-</span> <span class="dv">1</span></span>
 <span id="cb21-3"><a href="#cb21-3" aria-hidden="true" tabindex="-1"></a>babynames.head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1318,7 +1179,7 @@ <h2 data-number="3.2" class="anchored" data-anchor-id="adding-removing-and-modif
 </div>
 </div>
 <p>We can rename a column using the <code>.rename()</code> method. It takes in a dictionary that maps old column names to their new ones.</p>
-<div id="3b37f6cb" class="cell" data-execution_count="18">
+<div id="49cd9bc1" class="cell" data-execution_count="18">
 <div class="sourceCode cell-code" id="cb22"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb22-1"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Rename “name_lengths” to “Length”</span></span>
 <span id="cb22-2"><a href="#cb22-2" aria-hidden="true" tabindex="-1"></a>babynames <span class="op">=</span> babynames.rename(columns<span class="op">=</span>{<span class="st">"name_lengths"</span>:<span class="st">"Length"</span>})</span>
 <span id="cb22-3"><a href="#cb22-3" aria-hidden="true" tabindex="-1"></a>babynames.head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1391,7 +1252,7 @@ <h2 data-number="3.2" class="anchored" data-anchor-id="adding-removing-and-modif
 </div>
 </div>
 <p>If we want to remove a column or row of a <code>DataFrame</code>, we can call the <code>.drop</code> <a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.drop.html">(documentation)</a> method. Use the <code>axis</code> parameter to specify whether a column or row should be dropped. Unless otherwise specified, <code>pandas</code> will assume that we are dropping a row by default.</p>
-<div id="dee0fa14" class="cell" data-execution_count="19">
+<div id="1fe58bc6" class="cell" data-execution_count="19">
 <div class="sourceCode cell-code" id="cb23"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb23-1"><a href="#cb23-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Drop our new "Length" column from the DataFrame</span></span>
 <span id="cb23-2"><a href="#cb23-2" aria-hidden="true" tabindex="-1"></a>babynames <span class="op">=</span> babynames.drop(<span class="st">"Length"</span>, axis<span class="op">=</span><span class="st">"columns"</span>)</span>
 <span id="cb23-3"><a href="#cb23-3" aria-hidden="true" tabindex="-1"></a>babynames.head(<span class="dv">5</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1459,7 +1320,7 @@ <h2 data-number="3.2" class="anchored" data-anchor-id="adding-removing-and-modif
 </div>
 <p>Notice that we <em>re-assigned</em> <code>babynames</code> to the result of <code>babynames.drop(...)</code>. This is a subtle but important point: <code>pandas</code> table operations <strong>do not occur in-place</strong>. Calling <code>df.drop(...)</code> will output a <em>copy</em> of <code>df</code> with the row/column of interest removed without modifying the original <code>df</code> table.</p>
 <p>In other words, if we simply call:</p>
-<div id="5fed1d10" class="cell" data-execution_count="20">
+<div id="362ca941" class="cell" data-execution_count="20">
 <div class="sourceCode cell-code" id="cb24"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a><span class="co"># This creates a copy of `babynames` and removes the column "Name"...</span></span>
 <span id="cb24-2"><a href="#cb24-2" aria-hidden="true" tabindex="-1"></a>babynames.drop(<span class="st">"Name"</span>, axis<span class="op">=</span><span class="st">"columns"</span>)</span>
 <span id="cb24-3"><a href="#cb24-3" aria-hidden="true" tabindex="-1"></a></span>
@@ -1547,7 +1408,7 @@ <h2 data-number="3.3" class="anchored" data-anchor-id="useful-utility-functions"
 <section id="numpy" class="level3" data-number="3.3.1">
 <h3 data-number="3.3.1" class="anchored" data-anchor-id="numpy"><span class="header-section-number">3.3.1</span> <code>NumPy</code></h3>
 <p><code>pandas</code> is designed to work well with <code>NumPy</code>, the framework for array computations you encountered in <a href="https://www.data8.org/su23/reference/#array-functions-and-methods">Data 8</a>. Just about any <code>NumPy</code> function can be applied to <code>pandas</code> <code>DataFrame</code>s and <code>Series</code>.</p>
-<div id="e60666c1" class="cell" data-execution_count="21">
+<div id="1dd6d681" class="cell" data-execution_count="21">
 <div class="sourceCode cell-code" id="cb25"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb25-1"><a href="#cb25-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Pull out the number of babies named Yash each year</span></span>
 <span id="cb25-2"><a href="#cb25-2" aria-hidden="true" tabindex="-1"></a>yash_count <span class="op">=</span> babynames[babynames[<span class="st">"Name"</span>] <span class="op">==</span> <span class="st">"Yash"</span>][<span class="st">"Count"</span>]</span>
 <span id="cb25-3"><a href="#cb25-3" aria-hidden="true" tabindex="-1"></a>yash_count.head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
@@ -1560,18 +1421,18 @@ <h3 data-number="3.3.1" class="anchored" data-anchor-id="numpy"><span class="hea
 Name: Count, dtype: int64</code></pre>
 </div>
 </div>
-<div id="6a5d640d" class="cell" data-execution_count="22">
+<div id="be0ab4d3" class="cell" data-execution_count="22">
 <div class="sourceCode cell-code" id="cb27"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb27-1"><a href="#cb27-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Average number of babies named Yash each year</span></span>
 <span id="cb27-2"><a href="#cb27-2" aria-hidden="true" tabindex="-1"></a>np.mean(yash_count)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="22">
-<pre><code>np.float64(17.142857142857142)</code></pre>
+<pre><code>17.142857142857142</code></pre>
 </div>
 </div>
-<div id="da4cfab9" class="cell" data-execution_count="23">
+<div id="d909c694" class="cell" data-execution_count="23">
 <div class="sourceCode cell-code" id="cb29"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb29-1"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Max number of babies named Yash born in any one year</span></span>
 <span id="cb29-2"><a href="#cb29-2" aria-hidden="true" tabindex="-1"></a>np.<span class="bu">max</span>(yash_count)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="23">
-<pre><code>np.int64(29)</code></pre>
+<pre><code>29</code></pre>
 </div>
 </div>
 </section>
@@ -1579,14 +1440,14 @@ <h3 data-number="3.3.1" class="anchored" data-anchor-id="numpy"><span class="hea
 <h3 data-number="3.3.2" class="anchored" data-anchor-id="shape-and-.size"><span class="header-section-number">3.3.2</span> <code>.shape</code> and <code>.size</code></h3>
 <p><code>.shape</code> and <code>.size</code> are attributes of <code>Series</code> and <code>DataFrame</code>s that measure the “amount” of data stored in the structure. Calling <code>.shape</code> returns a tuple containing the number of rows and columns present in the <code>DataFrame</code> or <code>Series</code>. <code>.size</code> is used to find the total number of elements in a structure, equivalent to the number of rows times the number of columns.</p>
 <p>Many functions strictly require the dimensions of the arguments along certain axes to match. Calling these dimension-finding functions is much faster than counting all of the items by hand.</p>
-<div id="3b90ca62" class="cell" data-execution_count="24">
+<div id="f08353d0" class="cell" data-execution_count="24">
 <div class="sourceCode cell-code" id="cb31"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb31-1"><a href="#cb31-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Return the shape of the DataFrame, in the format (num_rows, num_columns)</span></span>
 <span id="cb31-2"><a href="#cb31-2" aria-hidden="true" tabindex="-1"></a>babynames.shape</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="24">
 <pre><code>(407428, 5)</code></pre>
 </div>
 </div>
-<div id="ccb39079" class="cell" data-execution_count="25">
+<div id="c3c193d9" class="cell" data-execution_count="25">
 <div class="sourceCode cell-code" id="cb33"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb33-1"><a href="#cb33-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Return the size of the DataFrame, equal to num_rows * num_columns</span></span>
 <span id="cb33-2"><a href="#cb33-2" aria-hidden="true" tabindex="-1"></a>babynames.size</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="25">
@@ -1597,7 +1458,7 @@ <h3 data-number="3.3.2" class="anchored" data-anchor-id="shape-and-.size"><span
 <section id="describe" class="level3" data-number="3.3.3">
 <h3 data-number="3.3.3" class="anchored" data-anchor-id="describe"><span class="header-section-number">3.3.3</span> <code>.describe()</code></h3>
 <p>If many statistics are required from a <code>DataFrame</code> (minimum value, maximum value, mean value, etc.), then <code>.describe()</code> <a href="https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.describe.html">(documentation)</a> can be used to compute all of them at once.</p>
-<div id="dd9e7930" class="cell" data-execution_count="26">
+<div id="0cb1e656" class="cell" data-execution_count="26">
 <div class="sourceCode cell-code" id="cb35"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb35-1"><a href="#cb35-1" aria-hidden="true" tabindex="-1"></a>babynames.describe()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="26">
 <div>
@@ -1659,7 +1520,7 @@ <h3 data-number="3.3.3" class="anchored" data-anchor-id="describe"><span class="
 </div>
 </div>
 <p>A different set of statistics will be reported if <code>.describe()</code> is called on a <code>Series</code>.</p>
-<div id="4620ad5b" class="cell" data-execution_count="27">
+<div id="25a46c35" class="cell" data-execution_count="27">
 <div class="sourceCode cell-code" id="cb36"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb36-1"><a href="#cb36-1" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"Sex"</span>].describe()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="27">
 <pre><code>count     407428
@@ -1674,7 +1535,7 @@ <h3 data-number="3.3.3" class="anchored" data-anchor-id="describe"><span class="
 <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="header-section-number">3.3.4</span> <code>.sample()</code></h3>
 <p>As we will see later in the semester, random processes are at the heart of many data science techniques (for example, train-test splits, bootstrapping, and cross-validation). <code>.sample()</code> <a href="https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.sample.html">(documentation)</a> lets us quickly select random entries (a row if called from a <code>DataFrame</code>, or a value if called from a <code>Series</code>).</p>
 <p>By default, <code>.sample()</code> selects entries <em>without</em> replacement. Pass in the argument <code>replace=True</code> to sample with replacement.</p>
-<div id="e1c959cd" class="cell" data-execution_count="28">
+<div id="cd0aeba0" class="cell" data-execution_count="28">
 <div class="sourceCode cell-code" id="cb38"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb38-1"><a href="#cb38-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Sample a single row</span></span>
 <span id="cb38-2"><a href="#cb38-2" aria-hidden="true" tabindex="-1"></a>babynames.sample()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="28">
@@ -1694,12 +1555,12 @@ <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="he
 </thead>
 <tbody>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">28158</td>
+<td data-quarto-table-cell-role="th">234881</td>
 <td>CA</td>
 <td>F</td>
-<td>1950</td>
-<td>Vikki</td>
-<td>14</td>
+<td>2021</td>
+<td>Khelani</td>
+<td>7</td>
 </tr>
 </tbody>
 </table>
@@ -1708,7 +1569,7 @@ <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="he
 </div>
 </div>
 <p>Naturally, this can be chained with other methods and operators (<code>iloc</code>, etc.).</p>
-<div id="b04de187" class="cell" data-execution_count="29">
+<div id="89af80e4" class="cell" data-execution_count="29">
 <div class="sourceCode cell-code" id="cb39"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb39-1"><a href="#cb39-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Sample 5 random rows, and select all columns after column 2</span></span>
 <span id="cb39-2"><a href="#cb39-2" aria-hidden="true" tabindex="-1"></a>babynames.sample(<span class="dv">5</span>).iloc[:, <span class="dv">2</span>:]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="29">
@@ -1726,34 +1587,34 @@ <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="he
 </thead>
 <tbody>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">82058</td>
-<td>1979</td>
-<td>Lakesha</td>
-<td>11</td>
+<td data-quarto-table-cell-role="th">98030</td>
+<td>1985</td>
+<td>Beatris</td>
+<td>14</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">387687</td>
-<td>2016</td>
-<td>Zayn</td>
-<td>101</td>
+<td data-quarto-table-cell-role="th">23304</td>
+<td>1946</td>
+<td>Clarice</td>
+<td>11</td>
 </tr>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">105977</td>
-<td>1988</td>
-<td>Cecilia</td>
-<td>213</td>
+<td data-quarto-table-cell-role="th">49990</td>
+<td>1964</td>
+<td>Iris</td>
+<td>30</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">75257</td>
-<td>1976</td>
-<td>Clarice</td>
-<td>7</td>
+<td data-quarto-table-cell-role="th">16618</td>
+<td>1939</td>
+<td>Robin</td>
+<td>29</td>
 </tr>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">7685</td>
-<td>1925</td>
-<td>Elia</td>
-<td>5</td>
+<td data-quarto-table-cell-role="th">125906</td>
+<td>1993</td>
+<td>Kelcey</td>
+<td>10</td>
 </tr>
 </tbody>
 </table>
@@ -1761,7 +1622,7 @@ <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="he
 </div>
 </div>
 </div>
-<div id="de6e4bd5" class="cell" data-execution_count="30">
+<div id="4fb754a9" class="cell" data-execution_count="30">
 <div class="sourceCode cell-code" id="cb40"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb40-1"><a href="#cb40-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Randomly sample 4 names from the year 2000, with replacement, and select all columns after column 2</span></span>
 <span id="cb40-2"><a href="#cb40-2" aria-hidden="true" tabindex="-1"></a>babynames[babynames[<span class="st">"Year"</span>] <span class="op">==</span> <span class="dv">2000</span>].sample(<span class="dv">4</span>, replace <span class="op">=</span> <span class="va">True</span>).iloc[:, <span class="dv">2</span>:]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="30">
@@ -1779,28 +1640,28 @@ <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="he
 </thead>
 <tbody>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">342973</td>
+<td data-quarto-table-cell-role="th">149143</td>
 <td>2000</td>
-<td>Grayson</td>
-<td>46</td>
+<td>Mariah</td>
+<td>534</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">151608</td>
+<td data-quarto-table-cell-role="th">342485</td>
 <td>2000</td>
-<td>Roshni</td>
-<td>8</td>
+<td>Isaac</td>
+<td>1297</td>
 </tr>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">343172</td>
+<td data-quarto-table-cell-role="th">149650</td>
 <td>2000</td>
-<td>Dwayne</td>
-<td>27</td>
+<td>Arielle</td>
+<td>59</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">343039</td>
+<td data-quarto-table-cell-role="th">343016</td>
 <td>2000</td>
-<td>Jair</td>
-<td>38</td>
+<td>Darrell</td>
+<td>40</td>
 </tr>
 </tbody>
 </table>
@@ -1813,7 +1674,7 @@ <h3 data-number="3.3.4" class="anchored" data-anchor-id="sample"><span class="he
 <h3 data-number="3.3.5" class="anchored" data-anchor-id="value_counts"><span class="header-section-number">3.3.5</span> <code>.value_counts()</code></h3>
 <p>The <code>Series.value_counts()</code> <a href="https://pandas.pydata.org/docs/reference/api/pandas.Series.value_counts.html">(documentation)</a> method counts the number of occurrence of each unique value in a <code>Series</code>. In other words, it <em>counts</em> the number of times each unique <em>value</em> appears. This is often useful for determining the most or least common entries in a <code>Series</code>.</p>
 <p>In the example below, we can determine the name with the most years in which at least one person has taken that name by counting the number of times each name appears in the <code>"Name"</code> column of <code>babynames</code>. Note that the return value is also a <code>Series</code>.</p>
-<div id="8ce0395f" class="cell" data-execution_count="31">
+<div id="ddc2fbab" class="cell" data-execution_count="31">
 <div class="sourceCode cell-code" id="cb41"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb41-1"><a href="#cb41-1" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"Name"</span>].value_counts().head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="31">
 <pre><code>Name
@@ -1829,7 +1690,7 @@ <h3 data-number="3.3.5" class="anchored" data-anchor-id="value_counts"><span cla
 <section id="unique" class="level3" data-number="3.3.6">
 <h3 data-number="3.3.6" class="anchored" data-anchor-id="unique"><span class="header-section-number">3.3.6</span> <code>.unique()</code></h3>
 <p>If we have a <code>Series</code> with many repeated values, then <code>.unique()</code> <a href="https://pandas.pydata.org/docs/reference/api/pandas.unique.html">(documentation)</a> can be used to identify only the <em>unique</em> values. Here we return an array of all the names in <code>babynames</code>.</p>
-<div id="7a7e69da" class="cell" data-execution_count="32">
+<div id="a93c60e5" class="cell" data-execution_count="32">
 <div class="sourceCode cell-code" id="cb43"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb43-1"><a href="#cb43-1" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"Name"</span>].unique()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="32">
 <pre><code>array(['Mary', 'Helen', 'Dorothy', ..., 'Zae', 'Zai', 'Zayvier'],
@@ -1840,7 +1701,7 @@ <h3 data-number="3.3.6" class="anchored" data-anchor-id="unique"><span class="he
 <section id="sort_values" class="level3" data-number="3.3.7">
 <h3 data-number="3.3.7" class="anchored" data-anchor-id="sort_values"><span class="header-section-number">3.3.7</span> <code>.sort_values()</code></h3>
 <p>Ordering a <code>DataFrame</code> can be useful for isolating extreme values. For example, the first 5 entries of a row sorted in descending order (that is, from highest to lowest) are the largest 5 values. <code>.sort_values</code> <a href="https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.sort_values.html">(documentation)</a> allows us to order a <code>DataFrame</code> or <code>Series</code> by a specified column. We can choose to either receive the rows in <code>ascending</code> order (default) or <code>descending</code> order.</p>
-<div id="72d5b39a" class="cell" data-execution_count="33">
+<div id="0f6f16f8" class="cell" data-execution_count="33">
 <div class="sourceCode cell-code" id="cb45"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb45-1"><a href="#cb45-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Sort the "Count" column from highest to lowest</span></span>
 <span id="cb45-2"><a href="#cb45-2" aria-hidden="true" tabindex="-1"></a>babynames.sort_values(by<span class="op">=</span><span class="st">"Count"</span>, ascending<span class="op">=</span><span class="va">False</span>).head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="33">
@@ -1906,7 +1767,7 @@ <h3 data-number="3.3.7" class="anchored" data-anchor-id="sort_values"><span clas
 </div>
 </div>
 <p>Unlike when calling <code>.value_counts()</code> on a <code>DataFrame</code>, we do not need to explicitly specify the column used for sorting when calling <code>.value_counts()</code> on a <code>Series</code>. We can still specify the ordering paradigm – that is, whether values are sorted in ascending or descending order.</p>
-<div id="e78e42b4" class="cell" data-execution_count="34">
+<div id="483f69c8" class="cell" data-execution_count="34">
 <div class="sourceCode cell-code" id="cb46"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb46-1"><a href="#cb46-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Sort the "Name" Series alphabetically</span></span>
 <span id="cb46-2"><a href="#cb46-2" aria-hidden="true" tabindex="-1"></a>babynames[<span class="st">"Name"</span>].sort_values(ascending<span class="op">=</span><span class="va">True</span>).head()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output cell-output-display" data-execution_count="34">
@@ -2356,9 +2217,6 @@ <h2 data-number="3.4" class="anchored" data-anchor-id="parting-note"><span class
       </a>          
   </div>
   <div class="nav-page nav-page-next">
-      <a href="../pandas_3/pandas_3.html" class="pagination-link" aria-label="Pandas III">
-        <span class="nav-page-text"><span class="chapter-number">4</span>&nbsp; <span class="chapter-title">Pandas III</span></span> <i class="bi bi-arrow-right-short"></i>
-      </a>
   </div>
 </nav>
 </div> <!-- /content -->
diff --git a/docs/search.json b/docs/search.json
index ed56e2191..9ce1fc63d 100644
--- a/docs/search.json
+++ b/docs/search.json
@@ -48,5 +48,115 @@
     "crumbs": [
       "<span class='chapter-number'>1</span>  <span class='chapter-title'>Introduction</span>"
     ]
+  },
+  {
+    "objectID": "pandas_1/pandas_1.html",
+    "href": "pandas_1/pandas_1.html",
+    "title": "2  Pandas I",
+    "section": "",
+    "text": "2.1 Tabular Data\nData scientists work with data stored in a variety of formats. This class focuses primarily on tabular data — data that is stored in a table.\nTabular data is one of the most common systems that data scientists use to organize data. This is in large part due to the simplicity and flexibility of tables. Tables allow us to represent each observation, or instance of collecting data from an individual, as its own row. We can record each observation’s distinct characteristics, or features, in separate columns.\nTo see this in action, we’ll explore the elections dataset, which stores information about political candidates who ran for president of the United States in previous years.\nIn the elections dataset, each row (blue box) represents one instance of a candidate running for president in a particular year. For example, the first row represents Andrew Jackson running for president in the year 1824. Each column (yellow box) represents one characteristic piece of information about each presidential candidate. For example, the column named “Result” stores whether or not the candidate won the election.\nYour work in Data 8 helped you grow very familiar with using and interpreting data stored in a tabular format. Back then, you used the Table class of the datascience library, a special programming library created specifically for Data 8 students.\nIn Data 100, we will be working with the programming library pandas, which is generally accepted in the data science community as the industry- and academia-standard tool for manipulating tabular data (as well as the inspiration for Petey, our panda bear mascot).\nUsing pandas, we can",
+    "crumbs": [
+      "<span class='chapter-number'>2</span>  <span class='chapter-title'>Pandas I</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_1/pandas_1.html#tabular-data",
+    "href": "pandas_1/pandas_1.html#tabular-data",
+    "title": "2  Pandas I",
+    "section": "",
+    "text": "Arrange data in a tabular format.\nExtract useful information filtered by specific conditions.\nOperate on data to gain new insights.\nApply NumPy functions to our data (our friends from Data 8).\nPerform vectorized computations to speed up our analysis (Lab 1).",
+    "crumbs": [
+      "<span class='chapter-number'>2</span>  <span class='chapter-title'>Pandas I</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_1/pandas_1.html#series-dataframes-and-indices",
+    "href": "pandas_1/pandas_1.html#series-dataframes-and-indices",
+    "title": "2  Pandas I",
+    "section": "2.2 Series, DataFrames, and Indices",
+    "text": "2.2 Series, DataFrames, and Indices\nTo begin our work in pandas, we must first import the library into our Python environment. This will allow us to use pandas data structures and methods in our code.\n\n# `pd` is the conventional alias for Pandas, as `np` is for NumPy\nimport pandas as pd\n\nThere are three fundamental data structures in pandas:\n\nSeries: 1D labeled array data; best thought of as columnar data.\nDataFrame: 2D tabular data with rows and columns.\nIndex: A sequence of row/column labels.\n\nDataFrames, Series, and Indices can be represented visually in the following diagram, which considers the first few rows of the elections dataset.\n\n\n\nNotice how the DataFrame is a two-dimensional object — it contains both rows and columns. The Series above is a singular column of this DataFrame, namely the Result column. Both contain an Index, or a shared list of row labels (the integers from 0 to 4, inclusive).\n\n2.2.1 Series\nA Series represents a column of a DataFrame; more generally, it can be any 1-dimensional array-like object. It contains both:\n\nA sequence of values of the same type.\nA sequence of data labels called the index.\n\nIn the cell below, we create a Series named s.\n\ns = pd.Series([\"welcome\", \"to\", \"data 100\"])\ns\n\n0     welcome\n1          to\n2    data 100\ndtype: object\n\n\n\n # Accessing data values within the Series\n s.values\n\narray(['welcome', 'to', 'data 100'], dtype=object)\n\n\n\n # Accessing the Index of the Series\n s.index\n\nRangeIndex(start=0, stop=3, step=1)\n\n\nBy default, the index of a Series is a sequential list of integers beginning from 0. Optionally, a manually specified list of desired indices can be passed to the index argument.\n\ns = pd.Series([-1, 10, 2], index = [\"a\", \"b\", \"c\"])\ns\n\na    -1\nb    10\nc     2\ndtype: int64\n\n\n\ns.index\n\nIndex(['a', 'b', 'c'], dtype='object')\n\n\nIndices can also be changed after initialization.\n\ns.index = [\"first\", \"second\", \"third\"]\ns\n\nfirst     -1\nsecond    10\nthird      2\ndtype: int64\n\n\n\ns.index\n\nIndex(['first', 'second', 'third'], dtype='object')\n\n\n\n2.2.1.1 Selection in Series\nMuch like when working with NumPy arrays, we can select a single value or a set of values from a Series. To do so, there are three primary methods:\n\nA single label.\nA list of labels.\nA filtering condition.\n\nTo demonstrate this, let’s define the Series ser.\n\nser = pd.Series([4, -2, 0, 6], index = [\"a\", \"b\", \"c\", \"d\"])\nser\n\na    4\nb   -2\nc    0\nd    6\ndtype: int64\n\n\n\n2.2.1.1.1 A Single Label\n\n# We return the value stored at the index label \"a\"\nser[\"a\"] \n\n4\n\n\n\n\n2.2.1.1.2 A List of Labels\n\n# We return a Series of the values stored at the index labels \"a\" and \"c\"\nser[[\"a\", \"c\"]] \n\na    4\nc    0\ndtype: int64\n\n\n\n\n2.2.1.1.3 A Filtering Condition\nPerhaps the most interesting (and useful) method of selecting data from a Series is by using a filtering condition.\nFirst, we apply a boolean operation to the Series. This creates a new Series of boolean values.\n\n# Filter condition: select all elements greater than 0\nser &gt; 0 \n\na     True\nb    False\nc    False\nd     True\ndtype: bool\n\n\nWe then use this boolean condition to index into our original Series. pandas will select only the entries in the original Series that satisfy the condition.\n\nser[ser &gt; 0] \n\na    4\nd    6\ndtype: int64\n\n\n\n\n\n\n2.2.2 DataFrames\nTypically, we will work with Series using the perspective that they are columns in a DataFrame. We can think of a DataFrame as a collection of Series that all share the same Index.\nIn Data 8, you encountered the Table class of the datascience library, which represented tabular data. In Data 100, we’ll be using the DataFrame class of the pandas library.\n\n2.2.2.1 Creating a DataFrame\nThere are many ways to create a DataFrame. Here, we will cover the most popular approaches:\n\nFrom a CSV file.\nUsing a list and column name(s).\nFrom a dictionary.\nFrom a Series.\n\nMore generally, the syntax for creating a DataFrame is:\n pandas.DataFrame(data, index, columns)\n\n2.2.2.1.1 From a CSV file\nIn Data 100, our data are typically stored in a CSV (comma-separated values) file format. We can import a CSV file into a DataFrame by passing the data path as an argument to the following pandas function.   pd.read_csv(\"filename.csv\")\nWith our new understanding of pandas in hand, let’s return to the elections dataset from before. Now, we can recognize that it is represented as a pandas DataFrame.\n\nelections = pd.read_csv(\"data/elections.csv\")\nelections\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\nResult\n%\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\nloss\n57.210122\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\nwin\n42.789878\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\nwin\n56.203927\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\nloss\n43.796073\n\n\n4\n1832\nAndrew Jackson\nDemocratic\n702735\nwin\n54.574789\n\n\n...\n...\n...\n...\n...\n...\n...\n\n\n177\n2016\nJill Stein\nGreen\n1457226\nloss\n1.073699\n\n\n178\n2020\nJoseph Biden\nDemocratic\n81268924\nwin\n51.311515\n\n\n179\n2020\nDonald Trump\nRepublican\n74216154\nloss\n46.858542\n\n\n180\n2020\nJo Jorgensen\nLibertarian\n1865724\nloss\n1.177979\n\n\n181\n2020\nHoward Hawkins\nGreen\n405035\nloss\n0.255731\n\n\n\n\n182 rows × 6 columns\n\n\n\nThis code stores our DataFrame object in the elections variable. Upon inspection, our elections DataFrame has 182 rows and 6 columns (Year, Candidate, Party, Popular Vote, Result, %). Each row represents a single record — in our example, a presidential candidate from some particular year. Each column represents a single attribute or feature of the record.\n\n\n2.2.2.1.2 Using a List and Column Name(s)\nWe’ll now explore creating a DataFrame with data of our own.\nConsider the following examples. The first code cell creates a DataFrame with a single column Numbers.\n\ndf_list = pd.DataFrame([1, 2, 3], columns=[\"Numbers\"])\ndf_list\n\n\n\n\n\n\n\n\nNumbers\n\n\n\n\n0\n1\n\n\n1\n2\n\n\n2\n3\n\n\n\n\n\n\n\nThe second creates a DataFrame with the columns Numbers and Description. Notice how a 2D list of values is required to initialize the second DataFrame — each nested list represents a single row of data.\n\ndf_list = pd.DataFrame([[1, \"one\"], [2, \"two\"]], columns = [\"Number\", \"Description\"])\ndf_list\n\n\n\n\n\n\n\n\nNumber\nDescription\n\n\n\n\n0\n1\none\n\n\n1\n2\ntwo\n\n\n\n\n\n\n\n\n\n2.2.2.1.3 From a Dictionary\nA third (and more common) way to create a DataFrame is with a dictionary. The dictionary keys represent the column names, and the dictionary values represent the column values.\nBelow are two ways of implementing this approach. The first is based on specifying the columns of the DataFrame, whereas the second is based on specifying the rows of the DataFrame.\n\ndf_dict = pd.DataFrame({\n    \"Fruit\": [\"Strawberry\", \"Orange\"], \n    \"Price\": [5.49, 3.99]\n})\ndf_dict\n\n\n\n\n\n\n\n\nFruit\nPrice\n\n\n\n\n0\nStrawberry\n5.49\n\n\n1\nOrange\n3.99\n\n\n\n\n\n\n\n\ndf_dict = pd.DataFrame(\n    [\n        {\"Fruit\":\"Strawberry\", \"Price\":5.49}, \n        {\"Fruit\": \"Orange\", \"Price\":3.99}\n    ]\n)\ndf_dict\n\n\n\n\n\n\n\n\nFruit\nPrice\n\n\n\n\n0\nStrawberry\n5.49\n\n\n1\nOrange\n3.99\n\n\n\n\n\n\n\n\n\n2.2.2.1.4 From a Series\nEarlier, we explained how a Series was synonymous to a column in a DataFrame. It follows, then, that a DataFrame is equivalent to a collection of Series, which all share the same Index.\nIn fact, we can initialize a DataFrame by merging two or more Series. Consider the Series s_a and s_b.\n\n# Notice how our indices, or row labels, are the same\n\ns_a = pd.Series([\"a1\", \"a2\", \"a3\"], index = [\"r1\", \"r2\", \"r3\"])\ns_b = pd.Series([\"b1\", \"b2\", \"b3\"], index = [\"r1\", \"r2\", \"r3\"])\n\nWe can turn individual Series into a DataFrame using two common methods (shown below):\n\npd.DataFrame(s_a)\n\n\n\n\n\n\n\n\n0\n\n\n\n\nr1\na1\n\n\nr2\na2\n\n\nr3\na3\n\n\n\n\n\n\n\n\ns_b.to_frame()\n\n\n\n\n\n\n\n\n0\n\n\n\n\nr1\nb1\n\n\nr2\nb2\n\n\nr3\nb3\n\n\n\n\n\n\n\nTo merge the two Series and specify their column names, we use the following syntax:\n\npd.DataFrame({\n    \"A-column\": s_a, \n    \"B-column\": s_b\n})\n\n\n\n\n\n\n\n\nA-column\nB-column\n\n\n\n\nr1\na1\nb1\n\n\nr2\na2\nb2\n\n\nr3\na3\nb3\n\n\n\n\n\n\n\n\n\n\n\n2.2.3 Indices\nOn a more technical note, an index doesn’t have to be an integer, nor does it have to be unique. For example, we can set the index of the elections DataFrame to be the name of presidential candidates.\n\n# Creating a DataFrame from a CSV file and specifying the index column\nelections = pd.read_csv(\"data/elections.csv\", index_col = \"Candidate\")\nelections\n\n\n\n\n\n\n\n\nYear\nParty\nPopular vote\nResult\n%\n\n\nCandidate\n\n\n\n\n\n\n\n\n\nAndrew Jackson\n1824\nDemocratic-Republican\n151271\nloss\n57.210122\n\n\nJohn Quincy Adams\n1824\nDemocratic-Republican\n113142\nwin\n42.789878\n\n\nAndrew Jackson\n1828\nDemocratic\n642806\nwin\n56.203927\n\n\nJohn Quincy Adams\n1828\nNational Republican\n500897\nloss\n43.796073\n\n\nAndrew Jackson\n1832\nDemocratic\n702735\nwin\n54.574789\n\n\n...\n...\n...\n...\n...\n...\n\n\nJill Stein\n2016\nGreen\n1457226\nloss\n1.073699\n\n\nJoseph Biden\n2020\nDemocratic\n81268924\nwin\n51.311515\n\n\nDonald Trump\n2020\nRepublican\n74216154\nloss\n46.858542\n\n\nJo Jorgensen\n2020\nLibertarian\n1865724\nloss\n1.177979\n\n\nHoward Hawkins\n2020\nGreen\n405035\nloss\n0.255731\n\n\n\n\n182 rows × 5 columns\n\n\n\nWe can also select a new column and set it as the index of the DataFrame. For example, we can set the index of the elections DataFrame to represent the candidate’s party.\n\nelections.reset_index(inplace = True) # Resetting the index so we can set it again\n# This sets the index to the \"Party\" column\nelections.set_index(\"Party\")\n\n\n\n\n\n\n\n\nCandidate\nYear\nPopular vote\nResult\n%\n\n\nParty\n\n\n\n\n\n\n\n\n\nDemocratic-Republican\nAndrew Jackson\n1824\n151271\nloss\n57.210122\n\n\nDemocratic-Republican\nJohn Quincy Adams\n1824\n113142\nwin\n42.789878\n\n\nDemocratic\nAndrew Jackson\n1828\n642806\nwin\n56.203927\n\n\nNational Republican\nJohn Quincy Adams\n1828\n500897\nloss\n43.796073\n\n\nDemocratic\nAndrew Jackson\n1832\n702735\nwin\n54.574789\n\n\n...\n...\n...\n...\n...\n...\n\n\nGreen\nJill Stein\n2016\n1457226\nloss\n1.073699\n\n\nDemocratic\nJoseph Biden\n2020\n81268924\nwin\n51.311515\n\n\nRepublican\nDonald Trump\n2020\n74216154\nloss\n46.858542\n\n\nLibertarian\nJo Jorgensen\n2020\n1865724\nloss\n1.177979\n\n\nGreen\nHoward Hawkins\n2020\n405035\nloss\n0.255731\n\n\n\n\n182 rows × 5 columns\n\n\n\nAnd, if we’d like, we can revert the index back to the default list of integers.\n\n# This resets the index to be the default list of integer\nelections.reset_index(inplace=True) \nelections.index\n\nRangeIndex(start=0, stop=182, step=1)\n\n\nIt is also important to note that the row labels that constitute an index don’t have to be unique. While index values can be unique and numeric, acting as a row number, they can also be named and non-unique.\nHere we see unique and numeric index values.\n\n\n\nHowever, here the index values are not unique.",
+    "crumbs": [
+      "<span class='chapter-number'>2</span>  <span class='chapter-title'>Pandas I</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_1/pandas_1.html#dataframe-attributes-index-columns-and-shape",
+    "href": "pandas_1/pandas_1.html#dataframe-attributes-index-columns-and-shape",
+    "title": "2  Pandas I",
+    "section": "2.3 DataFrame Attributes: Index, Columns, and Shape",
+    "text": "2.3 DataFrame Attributes: Index, Columns, and Shape\nOn the other hand, column names in a DataFrame are almost always unique. Looking back to the elections dataset, it wouldn’t make sense to have two columns named \"Candidate\". Sometimes, you’ll want to extract these different values, in particular, the list of row and column labels.\nFor index/row labels, use DataFrame.index:\n\nelections.set_index(\"Party\", inplace = True)\nelections.index\n\nIndex(['Democratic-Republican', 'Democratic-Republican', 'Democratic',\n       'National Republican', 'Democratic', 'National Republican',\n       'Anti-Masonic', 'Whig', 'Democratic', 'Whig',\n       ...\n       'Constitution', 'Republican', 'Independent', 'Libertarian',\n       'Democratic', 'Green', 'Democratic', 'Republican', 'Libertarian',\n       'Green'],\n      dtype='object', name='Party', length=182)\n\n\nFor column labels, use DataFrame.columns:\n\nelections.columns\n\nIndex(['index', 'Candidate', 'Year', 'Popular vote', 'Result', '%'], dtype='object')\n\n\nAnd for the shape of the DataFrame, we can use DataFrame.shape to get the number of rows followed by the number of columns:\n\nelections.shape\n\n(182, 6)",
+    "crumbs": [
+      "<span class='chapter-number'>2</span>  <span class='chapter-title'>Pandas I</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_1/pandas_1.html#slicing-in-dataframes",
+    "href": "pandas_1/pandas_1.html#slicing-in-dataframes",
+    "title": "2  Pandas I",
+    "section": "2.4 Slicing in DataFrames",
+    "text": "2.4 Slicing in DataFrames\nNow that we’ve learned more about DataFrames, let’s dive deeper into their capabilities.\nThe API (Application Programming Interface) for the DataFrame class is enormous. In this section, we’ll discuss several methods of the DataFrame API that allow us to extract subsets of data.\nThe simplest way to manipulate a DataFrame is to extract a subset of rows and columns, known as slicing.\nCommon ways we may want to extract data are grabbing:\n\nThe first or last n rows in the DataFrame.\nData with a certain label.\nData at a certain position.\n\nWe will do so with four primary methods of the DataFrame class:\n\n.head and .tail\n.loc\n.iloc\n[]\n\n\n2.4.1 Extracting data with .head and .tail\nThe simplest scenario in which we want to extract data is when we simply want to select the first or last few rows of the DataFrame.\nTo extract the first n rows of a DataFrame df, we use the syntax df.head(n).\n\n\nCode\nelections = pd.read_csv(\"data/elections.csv\")\n\n\n\n# Extract the first 5 rows of the DataFrame\nelections.head(5)\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\nResult\n%\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\nloss\n57.210122\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\nwin\n42.789878\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\nwin\n56.203927\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\nloss\n43.796073\n\n\n4\n1832\nAndrew Jackson\nDemocratic\n702735\nwin\n54.574789\n\n\n\n\n\n\n\nSimilarly, calling df.tail(n) allows us to extract the last n rows of the DataFrame.\n\n# Extract the last 5 rows of the DataFrame\nelections.tail(5)\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\nResult\n%\n\n\n\n\n177\n2016\nJill Stein\nGreen\n1457226\nloss\n1.073699\n\n\n178\n2020\nJoseph Biden\nDemocratic\n81268924\nwin\n51.311515\n\n\n179\n2020\nDonald Trump\nRepublican\n74216154\nloss\n46.858542\n\n\n180\n2020\nJo Jorgensen\nLibertarian\n1865724\nloss\n1.177979\n\n\n181\n2020\nHoward Hawkins\nGreen\n405035\nloss\n0.255731\n\n\n\n\n\n\n\n\n\n2.4.2 Label-based Extraction: Indexing with .loc\nFor the more complex task of extracting data with specific column or index labels, we can use .loc. The .loc accessor allows us to specify the labels of rows and columns we wish to extract. The labels (commonly referred to as the indices) are the bold text on the far left of a DataFrame, while the column labels are the column names found at the top of a DataFrame.\n\n\n\nTo grab data with .loc, we must specify the row and column label(s) where the data exists. The row labels are the first argument to the .loc function; the column labels are the second.\nArguments to .loc can be:\n\nA single value.\nA slice.\nA list.\n\nFor example, to select a single value, we can select the row labeled 0 and the column labeled Candidate from the elections DataFrame.\n\nelections.loc[0, 'Candidate']\n\n'Andrew Jackson'\n\n\nKeep in mind that passing in just one argument as a single value will produce a Series. Below, we’ve extracted a subset of the \"Popular vote\" column as a Series.\n\nelections.loc[[87, 25, 179], \"Popular vote\"]\n\n87     15761254\n25       848019\n179    74216154\nName: Popular vote, dtype: int64\n\n\nTo select multiple rows and columns, we can use Python slice notation. Here, we select the rows from labels 0 to 3 and the columns from labels \"Year\" to \"Popular vote\". Notice that unlike Python slicing, .loc is inclusive of the right upper bound.\n\nelections.loc[0:3, 'Year':'Popular vote']\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\n\n\n\n\n\n\n\nSuppose that instead, we want to extract all column values for the first four rows in the elections DataFrame. The shorthand : is useful for this.\n\nelections.loc[0:3, :]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\nResult\n%\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\nloss\n57.210122\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\nwin\n42.789878\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\nwin\n56.203927\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\nloss\n43.796073\n\n\n\n\n\n\n\nWe can use the same shorthand to extract all rows.\n\nelections.loc[:, [\"Year\", \"Candidate\", \"Result\"]]\n\n\n\n\n\n\n\n\nYear\nCandidate\nResult\n\n\n\n\n0\n1824\nAndrew Jackson\nloss\n\n\n1\n1824\nJohn Quincy Adams\nwin\n\n\n2\n1828\nAndrew Jackson\nwin\n\n\n3\n1828\nJohn Quincy Adams\nloss\n\n\n4\n1832\nAndrew Jackson\nwin\n\n\n...\n...\n...\n...\n\n\n177\n2016\nJill Stein\nloss\n\n\n178\n2020\nJoseph Biden\nwin\n\n\n179\n2020\nDonald Trump\nloss\n\n\n180\n2020\nJo Jorgensen\nloss\n\n\n181\n2020\nHoward Hawkins\nloss\n\n\n\n\n182 rows × 3 columns\n\n\n\nThere are a couple of things we should note. Firstly, unlike conventional Python, pandas allows us to slice string values (in our example, the column labels). Secondly, slicing with .loc is inclusive. Notice how our resulting DataFrame includes every row and column between and including the slice labels we specified.\nEquivalently, we can use a list to obtain multiple rows and columns in our elections DataFrame.\n\nelections.loc[[0, 1, 2, 3], ['Year', 'Candidate', 'Party', 'Popular vote']]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\n\n\n\n\n\n\n\nLastly, we can interchange list and slicing notation.\n\nelections.loc[[0, 1, 2, 3], :]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\nResult\n%\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\nloss\n57.210122\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\nwin\n42.789878\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\nwin\n56.203927\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\nloss\n43.796073\n\n\n\n\n\n\n\n\n\n2.4.3 Integer-based Extraction: Indexing with .iloc\nSlicing with .iloc works similarly to .loc. However, .iloc uses the index positions of rows and columns rather than the labels (think to yourself: loc uses lables; iloc uses indices). The arguments to the .iloc function also behave similarly — single values, lists, indices, and any combination of these are permitted.\nLet’s begin reproducing our results from above. We’ll begin by selecting the first presidential candidate in our elections DataFrame:\n\n# elections.loc[0, \"Candidate\"] - Previous approach\nelections.iloc[0, 1]\n\n'Andrew Jackson'\n\n\nNotice how the first argument to both .loc and .iloc are the same. This is because the row with a label of 0 is conveniently in the \\(0^{\\text{th}}\\) (equivalently, the first position) of the elections DataFrame. Generally, this is true of any DataFrame where the row labels are incremented in ascending order from 0.\nAnd, as before, if we were to pass in only one single value argument, our result would be a Series.\n\nelections.iloc[[1,2,3],1]\n\n1    John Quincy Adams\n2       Andrew Jackson\n3    John Quincy Adams\nName: Candidate, dtype: object\n\n\nHowever, when we select the first four rows and columns using .iloc, we notice something.\n\n# elections.loc[0:3, 'Year':'Popular vote'] - Previous approach\nelections.iloc[0:4, 0:4]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\n\n\n\n\n\n\n\nSlicing is no longer inclusive in .iloc — it’s exclusive. In other words, the right end of a slice is not included when using .iloc. This is one of the subtleties of pandas syntax; you will get used to it with practice.\nList behavior works just as expected.\n\n#elections.loc[[0, 1, 2, 3], ['Year', 'Candidate', 'Party', 'Popular vote']] - Previous Approach\nelections.iloc[[0, 1, 2, 3], [0, 1, 2, 3]]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\n\n\n\n\n\n\n\nAnd just like with .loc, we can use a colon with .iloc to extract all rows or columns.\n\nelections.iloc[:, 0:3]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n\n\n4\n1832\nAndrew Jackson\nDemocratic\n\n\n...\n...\n...\n...\n\n\n177\n2016\nJill Stein\nGreen\n\n\n178\n2020\nJoseph Biden\nDemocratic\n\n\n179\n2020\nDonald Trump\nRepublican\n\n\n180\n2020\nJo Jorgensen\nLibertarian\n\n\n181\n2020\nHoward Hawkins\nGreen\n\n\n\n\n182 rows × 3 columns\n\n\n\nThis discussion begs the question: when should we use .loc vs. .iloc? In most cases, .loc is generally safer to use. You can imagine .iloc may return incorrect values when applied to a dataset where the ordering of data can change. However, .iloc can still be useful — for example, if you are looking at a DataFrame of sorted movie earnings and want to get the median earnings for a given year, you can use .iloc to index into the middle.\nOverall, it is important to remember that:\n\n.loc performances label-based extraction.\n.iloc performs integer-based extraction.\n\n\n\n2.4.4 Context-dependent Extraction: Indexing with []\nThe [] selection operator is the most baffling of all, yet the most commonly used. It only takes a single argument, which may be one of the following:\n\nA slice of row numbers.\nA list of column labels.\nA single-column label.\n\nThat is, [] is context-dependent. Let’s see some examples.\n\n2.4.4.1 A slice of row numbers\nSay we wanted the first four rows of our elections DataFrame.\n\nelections[0:4]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\nResult\n%\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\nloss\n57.210122\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\nwin\n42.789878\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\nwin\n56.203927\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\nloss\n43.796073\n\n\n\n\n\n\n\n\n\n2.4.4.2 A list of column labels\nSuppose we now want the first four columns.\n\nelections[[\"Year\", \"Candidate\", \"Party\", \"Popular vote\"]]\n\n\n\n\n\n\n\n\nYear\nCandidate\nParty\nPopular vote\n\n\n\n\n0\n1824\nAndrew Jackson\nDemocratic-Republican\n151271\n\n\n1\n1824\nJohn Quincy Adams\nDemocratic-Republican\n113142\n\n\n2\n1828\nAndrew Jackson\nDemocratic\n642806\n\n\n3\n1828\nJohn Quincy Adams\nNational Republican\n500897\n\n\n4\n1832\nAndrew Jackson\nDemocratic\n702735\n\n\n...\n...\n...\n...\n...\n\n\n177\n2016\nJill Stein\nGreen\n1457226\n\n\n178\n2020\nJoseph Biden\nDemocratic\n81268924\n\n\n179\n2020\nDonald Trump\nRepublican\n74216154\n\n\n180\n2020\nJo Jorgensen\nLibertarian\n1865724\n\n\n181\n2020\nHoward Hawkins\nGreen\n405035\n\n\n\n\n182 rows × 4 columns\n\n\n\n\n\n2.4.4.3 A single-column label\nLastly, [] allows us to extract only the \"Candidate\" column.\n\nelections[\"Candidate\"]\n\n0         Andrew Jackson\n1      John Quincy Adams\n2         Andrew Jackson\n3      John Quincy Adams\n4         Andrew Jackson\n             ...        \n177           Jill Stein\n178         Joseph Biden\n179         Donald Trump\n180         Jo Jorgensen\n181       Howard Hawkins\nName: Candidate, Length: 182, dtype: object\n\n\nThe output is a Series! In this course, we’ll become very comfortable with [], especially for selecting columns. In practice, [] is much more common than .loc, especially since it is far more concise.",
+    "crumbs": [
+      "<span class='chapter-number'>2</span>  <span class='chapter-title'>Pandas I</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_1/pandas_1.html#parting-note",
+    "href": "pandas_1/pandas_1.html#parting-note",
+    "title": "2  Pandas I",
+    "section": "2.5 Parting Note",
+    "text": "2.5 Parting Note\nThe pandas library is enormous and contains many useful functions. Here is a link to its documentation. We certainly don’t expect you to memorize each and every method of the library, and we will give you a reference sheet for exams.\nThe introductory Data 100 pandas lectures will provide a high-level view of the key data structures and methods that will form the foundation of your pandas knowledge. A goal of this course is to help you build your familiarity with the real-world programming practice of … Googling! Answers to your questions can be found in documentation, Stack Overflow, etc. Being able to search for, read, and implement documentation is an important life skill for any data scientist.\nWith that, we will move on to Pandas II!",
+    "crumbs": [
+      "<span class='chapter-number'>2</span>  <span class='chapter-title'>Pandas I</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_2/pandas_2.html",
+    "href": "pandas_2/pandas_2.html",
+    "title": "3  Pandas II",
+    "section": "",
+    "text": "3.1 Conditional Selection\nConditional selection allows us to select a subset of rows in a DataFrame that satisfy some specified condition.\nTo understand how to use conditional selection, we must look at another possible input of the .loc and [] methods – a boolean array, which is simply an array or Series where each element is either True or False. This boolean array must have a length equal to the number of rows in the DataFrame. It will return all rows that correspond to a value of True in the array. We used a very similar technique when performing conditional extraction from a Series in the last lecture.\nTo see this in action, let’s select all even-indexed rows in the first 10 rows of our DataFrame.\n# Ask yourself: why is :9 is the correct slice to select the first 10 rows?\nbabynames_first_10_rows = babynames.loc[:9, :]\n\n# Notice how we have exactly 10 elements in our boolean array argument\nbabynames_first_10_rows[[True, False, True, False, True, False, True, False, True, False]]\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n4\nCA\nF\n1910\nFrances\n134\n\n\n6\nCA\nF\n1910\nEvelyn\n126\n\n\n8\nCA\nF\n1910\nVirginia\n101\nWe can perform a similar operation using .loc.\nbabynames_first_10_rows.loc[[True, False, True, False, True, False, True, False, True, False], :]\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n4\nCA\nF\n1910\nFrances\n134\n\n\n6\nCA\nF\n1910\nEvelyn\n126\n\n\n8\nCA\nF\n1910\nVirginia\n101\nThese techniques worked well in this example, but you can imagine how tedious it might be to list out True and Falsefor every row in a larger DataFrame. To make things easier, we can instead provide a logical condition as an input to .loc or [] that returns a boolean array with the necessary length.\nFor example, to return all names associated with F sex:\n# First, use a logical condition to generate a boolean array\nlogical_operator = (babynames[\"Sex\"] == \"F\")\n\n# Then, use this boolean array to filter the DataFrame\nbabynames[logical_operator].head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n1\nCA\nF\n1910\nHelen\n239\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n3\nCA\nF\n1910\nMargaret\n163\n\n\n4\nCA\nF\n1910\nFrances\n134\nRecall from the previous lecture that .head() will return only the first few rows in the DataFrame. In reality, babynames[logical operator] contains as many rows as there are entries in the original babynames DataFrame with sex \"F\".\nHere, logical_operator evaluates to a Series of boolean values with length 407428.\nCode\nprint(\"There are a total of {} values in 'logical_operator'\".format(len(logical_operator)))\n\n\nThere are a total of 407428 values in 'logical_operator'\nRows starting at row 0 and ending at row 239536 evaluate to True and are thus returned in the DataFrame. Rows from 239537 onwards evaluate to False and are omitted from the output.\nCode\nprint(\"The 0th item in this 'logical_operator' is: {}\".format(logical_operator.iloc[0]))\nprint(\"The 239536th item in this 'logical_operator' is: {}\".format(logical_operator.iloc[239536]))\nprint(\"The 239537th item in this 'logical_operator' is: {}\".format(logical_operator.iloc[239537]))\n\n\nThe 0th item in this 'logical_operator' is: True\nThe 239536th item in this 'logical_operator' is: True\nThe 239537th item in this 'logical_operator' is: False\nPassing a Series as an argument to babynames[] has the same effect as using a boolean array. In fact, the [] selection operator can take a boolean Series, array, and list as arguments. These three are used interchangeably throughout the course.\nWe can also use .loc to achieve similar results.\nbabynames.loc[babynames[\"Sex\"] == \"F\"].head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n1\nCA\nF\n1910\nHelen\n239\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n3\nCA\nF\n1910\nMargaret\n163\n\n\n4\nCA\nF\n1910\nFrances\n134\nBoolean conditions can be combined using various bitwise operators, allowing us to filter results by multiple conditions. In the table below, p and q are boolean arrays or Series.\nWhen combining multiple conditions with logical operators, we surround each individual condition with a set of parenthesis (). This imposes an order of operations on pandas evaluating your logic and can avoid code erroring.\nFor example, if we want to return data on all names with sex \"F\" born before the year 2000, we can write:\nbabynames[(babynames[\"Sex\"] == \"F\") & (babynames[\"Year\"] &lt; 2000)].head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n1\nCA\nF\n1910\nHelen\n239\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n3\nCA\nF\n1910\nMargaret\n163\n\n\n4\nCA\nF\n1910\nFrances\n134\nNote that we’re working with Series, so using and in place of &, or or in place | will error.\n# This line of code will raise a ValueError\n# babynames[(babynames[\"Sex\"] == \"F\") and (babynames[\"Year\"] &lt; 2000)].head()\nIf we want to return data on all names with sex \"F\" or all born before the year 2000, we can write:\nbabynames[(babynames[\"Sex\"] == \"F\") | (babynames[\"Year\"] &lt; 2000)].head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n1\nCA\nF\n1910\nHelen\n239\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n3\nCA\nF\n1910\nMargaret\n163\n\n\n4\nCA\nF\n1910\nFrances\n134\nBoolean array selection is a useful tool, but can lead to overly verbose code for complex conditions. In the example below, our boolean condition is long enough to extend for several lines of code.\n# Note: The parentheses surrounding the code make it possible to break the code on to multiple lines for readability\n(\n    babynames[(babynames[\"Name\"] == \"Bella\") | \n              (babynames[\"Name\"] == \"Alex\") |\n              (babynames[\"Name\"] == \"Ani\") |\n              (babynames[\"Name\"] == \"Lisa\")]\n).head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n6289\nCA\nF\n1923\nBella\n5\n\n\n7512\nCA\nF\n1925\nBella\n8\n\n\n12368\nCA\nF\n1932\nLisa\n5\n\n\n14741\nCA\nF\n1936\nLisa\n8\n\n\n17084\nCA\nF\n1939\nLisa\n5\nFortunately, pandas provides many alternative methods for constructing boolean filters.\nThe .isin function is one such example. This method evaluates if the values in a Series are contained in a different sequence (list, array, or Series) of values. In the cell below, we achieve equivalent results to the DataFrame above with far more concise code.\nnames = [\"Bella\", \"Alex\", \"Narges\", \"Lisa\"]\nbabynames[\"Name\"].isin(names).head()\n\n0    False\n1    False\n2    False\n3    False\n4    False\nName: Name, dtype: bool\nbabynames[babynames[\"Name\"].isin(names)].head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n6289\nCA\nF\n1923\nBella\n5\n\n\n7512\nCA\nF\n1925\nBella\n8\n\n\n12368\nCA\nF\n1932\nLisa\n5\n\n\n14741\nCA\nF\n1936\nLisa\n8\n\n\n17084\nCA\nF\n1939\nLisa\n5\nThe function str.startswith can be used to define a filter based on string values in a Series object. It checks to see if string values in a Series start with a particular character.\n# Identify whether names begin with the letter \"N\"\nbabynames[\"Name\"].str.startswith(\"N\").head()\n\n0    False\n1    False\n2    False\n3    False\n4    False\nName: Name, dtype: bool\n# Extracting names that begin with the letter \"N\"\nbabynames[babynames[\"Name\"].str.startswith(\"N\")].head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n76\nCA\nF\n1910\nNorma\n23\n\n\n83\nCA\nF\n1910\nNellie\n20\n\n\n127\nCA\nF\n1910\nNina\n11\n\n\n198\nCA\nF\n1910\nNora\n6\n\n\n310\nCA\nF\n1911\nNellie\n23",
+    "crumbs": [
+      "<span class='chapter-number'>3</span>  <span class='chapter-title'>Pandas II</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_2/pandas_2.html#conditional-selection",
+    "href": "pandas_2/pandas_2.html#conditional-selection",
+    "title": "3  Pandas II",
+    "section": "",
+    "text": "Symbol\nUsage\nMeaning\n\n\n\n\n~\n~p\nReturns negation of p\n\n\n|\np | q\np OR q\n\n\n&\np & q\np AND q\n\n\n^\np ^ q\np XOR q (exclusive or)",
+    "crumbs": [
+      "<span class='chapter-number'>3</span>  <span class='chapter-title'>Pandas II</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_2/pandas_2.html#adding-removing-and-modifying-columns",
+    "href": "pandas_2/pandas_2.html#adding-removing-and-modifying-columns",
+    "title": "3  Pandas II",
+    "section": "3.2 Adding, Removing, and Modifying Columns",
+    "text": "3.2 Adding, Removing, and Modifying Columns\nIn many data science tasks, we may need to change the columns contained in our DataFrame in some way. Fortunately, the syntax to do so is fairly straightforward.\nTo add a new column to a DataFrame, we use a syntax similar to that used when accessing an existing column. Specify the name of the new column by writing df[\"column\"], then assign this to a Series or array containing the values that will populate this column.\n\n# Create a Series of the length of each name. \nbabyname_lengths = babynames[\"Name\"].str.len()\n\n# Add a column named \"name_lengths\" that includes the length of each name\nbabynames[\"name_lengths\"] = babyname_lengths\nbabynames.head(5)\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\nname_lengths\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n4\n\n\n1\nCA\nF\n1910\nHelen\n239\n5\n\n\n2\nCA\nF\n1910\nDorothy\n220\n7\n\n\n3\nCA\nF\n1910\nMargaret\n163\n8\n\n\n4\nCA\nF\n1910\nFrances\n134\n7\n\n\n\n\n\n\n\nIf we need to later modify an existing column, we can do so by referencing this column again with the syntax df[\"column\"], then re-assigning it to a new Series or array of the appropriate length.\n\n# Modify the “name_lengths” column to be one less than its original value\nbabynames[\"name_lengths\"] = babynames[\"name_lengths\"] - 1\nbabynames.head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\nname_lengths\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n3\n\n\n1\nCA\nF\n1910\nHelen\n239\n4\n\n\n2\nCA\nF\n1910\nDorothy\n220\n6\n\n\n3\nCA\nF\n1910\nMargaret\n163\n7\n\n\n4\nCA\nF\n1910\nFrances\n134\n6\n\n\n\n\n\n\n\nWe can rename a column using the .rename() method. It takes in a dictionary that maps old column names to their new ones.\n\n# Rename “name_lengths” to “Length”\nbabynames = babynames.rename(columns={\"name_lengths\":\"Length\"})\nbabynames.head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\nLength\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n3\n\n\n1\nCA\nF\n1910\nHelen\n239\n4\n\n\n2\nCA\nF\n1910\nDorothy\n220\n6\n\n\n3\nCA\nF\n1910\nMargaret\n163\n7\n\n\n4\nCA\nF\n1910\nFrances\n134\n6\n\n\n\n\n\n\n\nIf we want to remove a column or row of a DataFrame, we can call the .drop (documentation) method. Use the axis parameter to specify whether a column or row should be dropped. Unless otherwise specified, pandas will assume that we are dropping a row by default.\n\n# Drop our new \"Length\" column from the DataFrame\nbabynames = babynames.drop(\"Length\", axis=\"columns\")\nbabynames.head(5)\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n1\nCA\nF\n1910\nHelen\n239\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n3\nCA\nF\n1910\nMargaret\n163\n\n\n4\nCA\nF\n1910\nFrances\n134\n\n\n\n\n\n\n\nNotice that we re-assigned babynames to the result of babynames.drop(...). This is a subtle but important point: pandas table operations do not occur in-place. Calling df.drop(...) will output a copy of df with the row/column of interest removed without modifying the original df table.\nIn other words, if we simply call:\n\n# This creates a copy of `babynames` and removes the column \"Name\"...\nbabynames.drop(\"Name\", axis=\"columns\")\n\n# ...but the original `babynames` is unchanged! \n# Notice that the \"Name\" column is still present\nbabynames.head(5)\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n0\nCA\nF\n1910\nMary\n295\n\n\n1\nCA\nF\n1910\nHelen\n239\n\n\n2\nCA\nF\n1910\nDorothy\n220\n\n\n3\nCA\nF\n1910\nMargaret\n163\n\n\n4\nCA\nF\n1910\nFrances\n134",
+    "crumbs": [
+      "<span class='chapter-number'>3</span>  <span class='chapter-title'>Pandas II</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_2/pandas_2.html#useful-utility-functions",
+    "href": "pandas_2/pandas_2.html#useful-utility-functions",
+    "title": "3  Pandas II",
+    "section": "3.3 Useful Utility Functions",
+    "text": "3.3 Useful Utility Functions\npandas contains an extensive library of functions that can help shorten the process of setting and getting information from its data structures. In the following section, we will give overviews of each of the main utility functions that will help us in Data 100.\nDiscussing all functionality offered by pandas could take an entire semester! We will walk you through the most commonly-used functions and encourage you to explore and experiment on your own.\n\nNumPy and built-in function support\n.shape\n.size\n.describe()\n.sample()\n.value_counts()\n.unique()\n.sort_values()\n\nThe pandas documentation will be a valuable resource in Data 100 and beyond.\n\n3.3.1 NumPy\npandas is designed to work well with NumPy, the framework for array computations you encountered in Data 8. Just about any NumPy function can be applied to pandas DataFrames and Series.\n\n# Pull out the number of babies named Yash each year\nyash_count = babynames[babynames[\"Name\"] == \"Yash\"][\"Count\"]\nyash_count.head()\n\n331824     8\n334114     9\n336390    11\n338773    12\n341387    10\nName: Count, dtype: int64\n\n\n\n# Average number of babies named Yash each year\nnp.mean(yash_count)\n\n17.142857142857142\n\n\n\n# Max number of babies named Yash born in any one year\nnp.max(yash_count)\n\n29\n\n\n\n\n3.3.2 .shape and .size\n.shape and .size are attributes of Series and DataFrames that measure the “amount” of data stored in the structure. Calling .shape returns a tuple containing the number of rows and columns present in the DataFrame or Series. .size is used to find the total number of elements in a structure, equivalent to the number of rows times the number of columns.\nMany functions strictly require the dimensions of the arguments along certain axes to match. Calling these dimension-finding functions is much faster than counting all of the items by hand.\n\n# Return the shape of the DataFrame, in the format (num_rows, num_columns)\nbabynames.shape\n\n(407428, 5)\n\n\n\n# Return the size of the DataFrame, equal to num_rows * num_columns\nbabynames.size\n\n2037140\n\n\n\n\n3.3.3 .describe()\nIf many statistics are required from a DataFrame (minimum value, maximum value, mean value, etc.), then .describe() (documentation) can be used to compute all of them at once.\n\nbabynames.describe()\n\n\n\n\n\n\n\n\nYear\nCount\n\n\n\n\ncount\n407428.000000\n407428.000000\n\n\nmean\n1985.733609\n79.543456\n\n\nstd\n27.007660\n293.698654\n\n\nmin\n1910.000000\n5.000000\n\n\n25%\n1969.000000\n7.000000\n\n\n50%\n1992.000000\n13.000000\n\n\n75%\n2008.000000\n38.000000\n\n\nmax\n2022.000000\n8260.000000\n\n\n\n\n\n\n\nA different set of statistics will be reported if .describe() is called on a Series.\n\nbabynames[\"Sex\"].describe()\n\ncount     407428\nunique         2\ntop            F\nfreq      239537\nName: Sex, dtype: object\n\n\n\n\n3.3.4 .sample()\nAs we will see later in the semester, random processes are at the heart of many data science techniques (for example, train-test splits, bootstrapping, and cross-validation). .sample() (documentation) lets us quickly select random entries (a row if called from a DataFrame, or a value if called from a Series).\nBy default, .sample() selects entries without replacement. Pass in the argument replace=True to sample with replacement.\n\n# Sample a single row\nbabynames.sample()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n234881\nCA\nF\n2021\nKhelani\n7\n\n\n\n\n\n\n\nNaturally, this can be chained with other methods and operators (iloc, etc.).\n\n# Sample 5 random rows, and select all columns after column 2\nbabynames.sample(5).iloc[:, 2:]\n\n\n\n\n\n\n\n\nYear\nName\nCount\n\n\n\n\n98030\n1985\nBeatris\n14\n\n\n23304\n1946\nClarice\n11\n\n\n49990\n1964\nIris\n30\n\n\n16618\n1939\nRobin\n29\n\n\n125906\n1993\nKelcey\n10\n\n\n\n\n\n\n\n\n# Randomly sample 4 names from the year 2000, with replacement, and select all columns after column 2\nbabynames[babynames[\"Year\"] == 2000].sample(4, replace = True).iloc[:, 2:]\n\n\n\n\n\n\n\n\nYear\nName\nCount\n\n\n\n\n149143\n2000\nMariah\n534\n\n\n342485\n2000\nIsaac\n1297\n\n\n149650\n2000\nArielle\n59\n\n\n343016\n2000\nDarrell\n40\n\n\n\n\n\n\n\n\n\n3.3.5 .value_counts()\nThe Series.value_counts() (documentation) method counts the number of occurrence of each unique value in a Series. In other words, it counts the number of times each unique value appears. This is often useful for determining the most or least common entries in a Series.\nIn the example below, we can determine the name with the most years in which at least one person has taken that name by counting the number of times each name appears in the \"Name\" column of babynames. Note that the return value is also a Series.\n\nbabynames[\"Name\"].value_counts().head()\n\nName\nJean         223\nFrancis      221\nGuadalupe    218\nJessie       217\nMarion       214\nName: count, dtype: int64\n\n\n\n\n3.3.6 .unique()\nIf we have a Series with many repeated values, then .unique() (documentation) can be used to identify only the unique values. Here we return an array of all the names in babynames.\n\nbabynames[\"Name\"].unique()\n\narray(['Mary', 'Helen', 'Dorothy', ..., 'Zae', 'Zai', 'Zayvier'],\n      dtype=object)\n\n\n\n\n3.3.7 .sort_values()\nOrdering a DataFrame can be useful for isolating extreme values. For example, the first 5 entries of a row sorted in descending order (that is, from highest to lowest) are the largest 5 values. .sort_values (documentation) allows us to order a DataFrame or Series by a specified column. We can choose to either receive the rows in ascending order (default) or descending order.\n\n# Sort the \"Count\" column from highest to lowest\nbabynames.sort_values(by=\"Count\", ascending=False).head()\n\n\n\n\n\n\n\n\nState\nSex\nYear\nName\nCount\n\n\n\n\n268041\nCA\nM\n1957\nMichael\n8260\n\n\n267017\nCA\nM\n1956\nMichael\n8258\n\n\n317387\nCA\nM\n1990\nMichael\n8246\n\n\n281850\nCA\nM\n1969\nMichael\n8245\n\n\n283146\nCA\nM\n1970\nMichael\n8196\n\n\n\n\n\n\n\nUnlike when calling .value_counts() on a DataFrame, we do not need to explicitly specify the column used for sorting when calling .value_counts() on a Series. We can still specify the ordering paradigm – that is, whether values are sorted in ascending or descending order.\n\n# Sort the \"Name\" Series alphabetically\nbabynames[\"Name\"].sort_values(ascending=True).head()\n\n366001      Aadan\n384005      Aadan\n369120      Aadan\n398211    Aadarsh\n370306      Aaden\nName: Name, dtype: object",
+    "crumbs": [
+      "<span class='chapter-number'>3</span>  <span class='chapter-title'>Pandas II</span>"
+    ]
+  },
+  {
+    "objectID": "pandas_2/pandas_2.html#parting-note",
+    "href": "pandas_2/pandas_2.html#parting-note",
+    "title": "3  Pandas II",
+    "section": "3.4 Parting Note",
+    "text": "3.4 Parting Note\nManipulating DataFrames is not a skill that is mastered in just one day. Due to the flexibility of pandas, there are many different ways to get from point A to point B. We recommend trying multiple different ways to solve the same problem to gain even more practice and reach that point of mastery sooner.\nNext, we will start digging deeper into the mechanics behind grouping data.",
+    "crumbs": [
+      "<span class='chapter-number'>3</span>  <span class='chapter-title'>Pandas II</span>"
+    ]
   }
 ]
\ No newline at end of file