diff --git a/Korean/Fraud detection analysis with NN/Fraud detection analysis with NN.ipynb b/Korean/Fraud detection analysis with NN/Fraud detection analysis with NN.ipynb
index ac63181..9a622da 100644
--- a/Korean/Fraud detection analysis with NN/Fraud detection analysis with NN.ipynb	
+++ b/Korean/Fraud detection analysis with NN/Fraud detection analysis with NN.ipynb	
@@ -1975,47 +1975,27 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-<<<<<<< HEAD
        "      <th>63634</th>\n",
-=======
-       "      <th>16863</th>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>578.28934</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-<<<<<<< HEAD
        "      <th>108258</th>\n",
-=======
-       "      <th>241254</th>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>578.28934</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-<<<<<<< HEAD
        "      <th>82400</th>\n",
-=======
-       "      <th>76929</th>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>578.28934</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-<<<<<<< HEAD
        "      <th>229712</th>\n",
-=======
-       "      <th>235634</th>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>578.28934</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-<<<<<<< HEAD
        "      <th>239499</th>\n",
-=======
-       "      <th>23308</th>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>578.28934</td>\n",
        "      <td>0.0</td>\n",
        "    </tr>\n",
@@ -2025,19 +2005,11 @@
       ],
       "text/plain": [
        "            Fraud  Normal\n",
-<<<<<<< HEAD
        "63634   578.28934     0.0\n",
        "108258  578.28934     0.0\n",
        "82400   578.28934     0.0\n",
        "229712  578.28934     0.0\n",
        "239499  578.28934     0.0"
-=======
-       "16863   578.28934     0.0\n",
-       "241254  578.28934     0.0\n",
-       "76929   578.28934     0.0\n",
-       "235634  578.28934     0.0\n",
-       "23308   578.28934     0.0"
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
       ]
      },
      "execution_count": 30,
@@ -2173,7 +2145,6 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mean</th>\n",
-<<<<<<< HEAD
        "      <td>-0.001558</td>\n",
        "      <td>0.000875</td>\n",
        "      <td>-0.001892</td>\n",
@@ -2271,111 +2242,11 @@
        "      <td>-3.438550</td>\n",
        "      <td>-21.900531</td>\n",
        "      <td>-26.225413</td>\n",
-=======
-       "      <td>-0.001224</td>\n",
-       "      <td>-0.001042</td>\n",
-       "      <td>-0.002830</td>\n",
-       "      <td>-0.005544</td>\n",
-       "      <td>0.005997</td>\n",
-       "      <td>0.000293</td>\n",
-       "      <td>0.001331</td>\n",
-       "      <td>-0.005805</td>\n",
-       "      <td>-0.004224</td>\n",
-       "      <td>0.003585</td>\n",
-       "      <td>-0.003315</td>\n",
-       "      <td>0.006343</td>\n",
-       "      <td>0.014670</td>\n",
-       "      <td>-0.005487</td>\n",
-       "      <td>0.004601</td>\n",
-       "      <td>-0.002224</td>\n",
-       "      <td>-0.000504</td>\n",
-       "      <td>-0.001790</td>\n",
-       "      <td>-0.006839</td>\n",
-       "      <td>0.001810</td>\n",
-       "      <td>-0.002665</td>\n",
-       "      <td>-0.002930</td>\n",
-       "      <td>0.001825</td>\n",
-       "      <td>0.000312</td>\n",
-       "      <td>0.002653</td>\n",
-       "      <td>-0.001334</td>\n",
-       "      <td>0.001097</td>\n",
-       "      <td>0.000116</td>\n",
-       "      <td>0.000894</td>\n",
-       "      <td>0.001173</td>\n",
-       "      <td>-0.000229</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>1.001920</td>\n",
-       "      <td>1.020089</td>\n",
-       "      <td>1.018808</td>\n",
-       "      <td>1.011348</td>\n",
-       "      <td>0.998416</td>\n",
-       "      <td>0.999303</td>\n",
-       "      <td>0.998207</td>\n",
-       "      <td>1.018658</td>\n",
-       "      <td>1.088381</td>\n",
-       "      <td>0.991733</td>\n",
-       "      <td>0.990113</td>\n",
-       "      <td>0.997706</td>\n",
-       "      <td>0.996597</td>\n",
-       "      <td>1.001690</td>\n",
-       "      <td>0.990480</td>\n",
-       "      <td>0.996792</td>\n",
-       "      <td>0.996392</td>\n",
-       "      <td>0.991946</td>\n",
-       "      <td>0.997001</td>\n",
-       "      <td>1.001586</td>\n",
-       "      <td>1.009827</td>\n",
-       "      <td>1.068501</td>\n",
-       "      <td>1.009975</td>\n",
-       "      <td>1.072639</td>\n",
-       "      <td>1.003264</td>\n",
-       "      <td>1.003527</td>\n",
-       "      <td>1.003375</td>\n",
-       "      <td>1.010746</td>\n",
-       "      <td>1.039948</td>\n",
-       "      <td>0.985931</td>\n",
-       "      <td>0.997525</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>-1.996369</td>\n",
-       "      <td>-20.661780</td>\n",
-       "      <td>-28.722479</td>\n",
-       "      <td>-22.213271</td>\n",
-       "      <td>-3.717201</td>\n",
-       "      <td>-21.540062</td>\n",
-       "      <td>-15.052954</td>\n",
-       "      <td>-33.551864</td>\n",
-       "      <td>-61.302416</td>\n",
-       "      <td>-12.227994</td>\n",
-       "      <td>-22.411893</td>\n",
-       "      <td>-4.363472</td>\n",
-       "      <td>-17.242432</td>\n",
-       "      <td>-5.819382</td>\n",
-       "      <td>-19.292570</td>\n",
-       "      <td>-4.584886</td>\n",
-       "      <td>-14.141290</td>\n",
-       "      <td>-26.540290</td>\n",
-       "      <td>-10.846039</td>\n",
-       "      <td>-6.059567</td>\n",
-       "      <td>-29.624863</td>\n",
-       "      <td>-47.418984</td>\n",
-       "      <td>-12.246104</td>\n",
-       "      <td>-58.716303</td>\n",
-       "      <td>-4.584519</td>\n",
-       "      <td>-16.683278</td>\n",
-       "      <td>-3.847473</td>\n",
-       "      <td>-24.515479</td>\n",
-       "      <td>-25.260665</td>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>-0.353229</td>\n",
        "      <td>-0.046062</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>25%</th>\n",
-<<<<<<< HEAD
        "      <td>-0.853642</td>\n",
        "      <td>-0.466209</td>\n",
        "      <td>-0.362183</td>\n",
@@ -2406,43 +2277,10 @@
        "      <td>-0.174948</td>\n",
        "      <td>-0.158387</td>\n",
        "      <td>-0.330520</td>\n",
-=======
-       "      <td>-0.858169</td>\n",
-       "      <td>-0.470222</td>\n",
-       "      <td>-0.358188</td>\n",
-       "      <td>-0.589043</td>\n",
-       "      <td>-0.592879</td>\n",
-       "      <td>-0.497053</td>\n",
-       "      <td>-0.575976</td>\n",
-       "      <td>-0.445508</td>\n",
-       "      <td>-0.175328</td>\n",
-       "      <td>-0.575156</td>\n",
-       "      <td>-0.487916</td>\n",
-       "      <td>-0.740248</td>\n",
-       "      <td>-0.391293</td>\n",
-       "      <td>-0.656250</td>\n",
-       "      <td>-0.439695</td>\n",
-       "      <td>-0.634752</td>\n",
-       "      <td>-0.535462</td>\n",
-       "      <td>-0.571714</td>\n",
-       "      <td>-0.596332</td>\n",
-       "      <td>-0.557152</td>\n",
-       "      <td>-0.272606</td>\n",
-       "      <td>-0.309250</td>\n",
-       "      <td>-0.744022</td>\n",
-       "      <td>-0.257902</td>\n",
-       "      <td>-0.579922</td>\n",
-       "      <td>-0.605941</td>\n",
-       "      <td>-0.679235</td>\n",
-       "      <td>-0.175332</td>\n",
-       "      <td>-0.159296</td>\n",
-       "      <td>-0.331279</td>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>-0.046062</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50%</th>\n",
-<<<<<<< HEAD
        "      <td>-0.215398</td>\n",
        "      <td>0.010908</td>\n",
        "      <td>0.039725</td>\n",
@@ -2473,43 +2311,10 @@
        "      <td>0.003776</td>\n",
        "      <td>0.034129</td>\n",
        "      <td>-0.264951</td>\n",
-=======
-       "      <td>-0.214577</td>\n",
-       "      <td>0.013992</td>\n",
-       "      <td>0.035383</td>\n",
-       "      <td>0.112973</td>\n",
-       "      <td>-0.000758</td>\n",
-       "      <td>-0.042363</td>\n",
-       "      <td>-0.203824</td>\n",
-       "      <td>0.030520</td>\n",
-       "      <td>0.020143</td>\n",
-       "      <td>-0.039460</td>\n",
-       "      <td>-0.085708</td>\n",
-       "      <td>-0.024836</td>\n",
-       "      <td>0.153613</td>\n",
-       "      <td>-0.018689</td>\n",
-       "      <td>0.055610</td>\n",
-       "      <td>0.047554</td>\n",
-       "      <td>0.077496</td>\n",
-       "      <td>-0.079770</td>\n",
-       "      <td>-0.010362</td>\n",
-       "      <td>0.005983</td>\n",
-       "      <td>-0.080698</td>\n",
-       "      <td>-0.041409</td>\n",
-       "      <td>0.007294</td>\n",
-       "      <td>-0.017332</td>\n",
-       "      <td>0.072023</td>\n",
-       "      <td>0.028636</td>\n",
-       "      <td>-0.115717</td>\n",
-       "      <td>0.003963</td>\n",
-       "      <td>0.032194</td>\n",
-       "      <td>-0.263912</td>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>-0.046062</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>75%</th>\n",
-<<<<<<< HEAD
        "      <td>0.935794</td>\n",
        "      <td>0.671981</td>\n",
        "      <td>0.486347</td>\n",
@@ -2540,43 +2345,10 @@
        "      <td>0.229667</td>\n",
        "      <td>0.236983</td>\n",
        "      <td>-0.043378</td>\n",
-=======
-       "      <td>0.939522</td>\n",
-       "      <td>0.672490</td>\n",
-       "      <td>0.487033</td>\n",
-       "      <td>0.677709</td>\n",
-       "      <td>0.534019</td>\n",
-       "      <td>0.439335</td>\n",
-       "      <td>0.301598</td>\n",
-       "      <td>0.458236</td>\n",
-       "      <td>0.275742</td>\n",
-       "      <td>0.550495</td>\n",
-       "      <td>0.403495</td>\n",
-       "      <td>0.730971</td>\n",
-       "      <td>0.625753</td>\n",
-       "      <td>0.662847</td>\n",
-       "      <td>0.513317</td>\n",
-       "      <td>0.699394</td>\n",
-       "      <td>0.593329</td>\n",
-       "      <td>0.468597</td>\n",
-       "      <td>0.592829</td>\n",
-       "      <td>0.564164</td>\n",
-       "      <td>0.173084</td>\n",
-       "      <td>0.252904</td>\n",
-       "      <td>0.733052</td>\n",
-       "      <td>0.236988</td>\n",
-       "      <td>0.729891</td>\n",
-       "      <td>0.668831</td>\n",
-       "      <td>0.496408</td>\n",
-       "      <td>0.227238</td>\n",
-       "      <td>0.231837</td>\n",
-       "      <td>-0.039260</td>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>-0.046062</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
-<<<<<<< HEAD
        "      <td>1.641950</td>\n",
        "      <td>1.240880</td>\n",
        "      <td>9.990545</td>\n",
@@ -2607,38 +2379,6 @@
        "      <td>20.039391</td>\n",
        "      <td>48.865274</td>\n",
        "      <td>40.424940</td>\n",
-=======
-       "      <td>1.641929</td>\n",
-       "      <td>1.229413</td>\n",
-       "      <td>13.000116</td>\n",
-       "      <td>2.657487</td>\n",
-       "      <td>8.568820</td>\n",
-       "      <td>21.022418</td>\n",
-       "      <td>15.993545</td>\n",
-       "      <td>25.484930</td>\n",
-       "      <td>15.697933</td>\n",
-       "      <td>9.388014</td>\n",
-       "      <td>12.531076</td>\n",
-       "      <td>11.432405</td>\n",
-       "      <td>7.854665</td>\n",
-       "      <td>3.923102</td>\n",
-       "      <td>10.981446</td>\n",
-       "      <td>6.211952</td>\n",
-       "      <td>6.528161</td>\n",
-       "      <td>8.592238</td>\n",
-       "      <td>4.522099</td>\n",
-       "      <td>5.897892</td>\n",
-       "      <td>34.033648</td>\n",
-       "      <td>37.034649</td>\n",
-       "      <td>14.473016</td>\n",
-       "      <td>30.430985</td>\n",
-       "      <td>6.642261</td>\n",
-       "      <td>14.425293</td>\n",
-       "      <td>7.181774</td>\n",
-       "      <td>21.576490</td>\n",
-       "      <td>68.528383</td>\n",
-       "      <td>51.265692</td>\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "      <td>21.709793</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
@@ -2648,7 +2388,6 @@
       "text/plain": [
        "               Time            V1            V2            V3            V4  \\\n",
        "count  56961.000000  56961.000000  56961.000000  56961.000000  56961.000000   \n",
-<<<<<<< HEAD
        "mean      -0.001558      0.000875     -0.001892     -0.001439     -0.003383   \n",
        "std        0.998500      0.991199      0.990627      0.992018      0.997557   \n",
        "min       -1.996495    -17.189967    -30.511117    -20.154062     -3.927001   \n",
@@ -2711,70 +2450,6 @@
        "count      56961.000000  \n",
        "mean           0.004354  \n",
        "std            1.046103  \n",
-=======
-       "mean      -0.001224     -0.001042     -0.002830     -0.005544      0.005997   \n",
-       "std        1.001920      1.020089      1.018808      1.011348      0.998416   \n",
-       "min       -1.996369    -20.661780    -28.722479    -22.213271     -3.717201   \n",
-       "25%       -0.858169     -0.470222     -0.358188     -0.589043     -0.592879   \n",
-       "50%       -0.214577      0.013992      0.035383      0.112973     -0.000758   \n",
-       "75%        0.939522      0.672490      0.487033      0.677709      0.534019   \n",
-       "max        1.641929      1.229413     13.000116      2.657487      8.568820   \n",
-       "\n",
-       "                 V5            V6            V7            V8            V9  \\\n",
-       "count  56961.000000  56961.000000  56961.000000  56961.000000  56961.000000   \n",
-       "mean       0.000293      0.001331     -0.005805     -0.004224      0.003585   \n",
-       "std        0.999303      0.998207      1.018658      1.088381      0.991733   \n",
-       "min      -21.540062    -15.052954    -33.551864    -61.302416    -12.227994   \n",
-       "25%       -0.497053     -0.575976     -0.445508     -0.175328     -0.575156   \n",
-       "50%       -0.042363     -0.203824      0.030520      0.020143     -0.039460   \n",
-       "75%        0.439335      0.301598      0.458236      0.275742      0.550495   \n",
-       "max       21.022418     15.993545     25.484930     15.697933      9.388014   \n",
-       "\n",
-       "                V10           V11           V12           V13           V14  \\\n",
-       "count  56961.000000  56961.000000  56961.000000  56961.000000  56961.000000   \n",
-       "mean      -0.003315      0.006343      0.014670     -0.005487      0.004601   \n",
-       "std        0.990113      0.997706      0.996597      1.001690      0.990480   \n",
-       "min      -22.411893     -4.363472    -17.242432     -5.819382    -19.292570   \n",
-       "25%       -0.487916     -0.740248     -0.391293     -0.656250     -0.439695   \n",
-       "50%       -0.085708     -0.024836      0.153613     -0.018689      0.055610   \n",
-       "75%        0.403495      0.730971      0.625753      0.662847      0.513317   \n",
-       "max       12.531076     11.432405      7.854665      3.923102     10.981446   \n",
-       "\n",
-       "                V15           V16           V17           V18           V19  \\\n",
-       "count  56961.000000  56961.000000  56961.000000  56961.000000  56961.000000   \n",
-       "mean      -0.002224     -0.000504     -0.001790     -0.006839      0.001810   \n",
-       "std        0.996792      0.996392      0.991946      0.997001      1.001586   \n",
-       "min       -4.584886    -14.141290    -26.540290    -10.846039     -6.059567   \n",
-       "25%       -0.634752     -0.535462     -0.571714     -0.596332     -0.557152   \n",
-       "50%        0.047554      0.077496     -0.079770     -0.010362      0.005983   \n",
-       "75%        0.699394      0.593329      0.468597      0.592829      0.564164   \n",
-       "max        6.211952      6.528161      8.592238      4.522099      5.897892   \n",
-       "\n",
-       "                V20           V21           V22           V23           V24  \\\n",
-       "count  56961.000000  56961.000000  56961.000000  56961.000000  56961.000000   \n",
-       "mean      -0.002665     -0.002930      0.001825      0.000312      0.002653   \n",
-       "std        1.009827      1.068501      1.009975      1.072639      1.003264   \n",
-       "min      -29.624863    -47.418984    -12.246104    -58.716303     -4.584519   \n",
-       "25%       -0.272606     -0.309250     -0.744022     -0.257902     -0.579922   \n",
-       "50%       -0.080698     -0.041409      0.007294     -0.017332      0.072023   \n",
-       "75%        0.173084      0.252904      0.733052      0.236988      0.729891   \n",
-       "max       34.033648     37.034649     14.473016     30.430985      6.642261   \n",
-       "\n",
-       "                V25           V26           V27           V28        Amount  \\\n",
-       "count  56961.000000  56961.000000  56961.000000  56961.000000  56961.000000   \n",
-       "mean      -0.001334      0.001097      0.000116      0.000894      0.001173   \n",
-       "std        1.003527      1.003375      1.010746      1.039948      0.985931   \n",
-       "min      -16.683278     -3.847473    -24.515479    -25.260665     -0.353229   \n",
-       "25%       -0.605941     -0.679235     -0.175332     -0.159296     -0.331279   \n",
-       "50%        0.028636     -0.115717      0.003963      0.032194     -0.263912   \n",
-       "75%        0.668831      0.496408      0.227238      0.231837     -0.039260   \n",
-       "max       14.425293      7.181774     21.576490     68.528383     51.265692   \n",
-       "\n",
-       "       Amount_max_fraud  \n",
-       "count      56961.000000  \n",
-       "mean          -0.000229  \n",
-       "std            0.997525  \n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
        "min           -0.046062  \n",
        "25%           -0.046062  \n",
        "50%           -0.046062  \n",
@@ -2981,7 +2656,6 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-<<<<<<< HEAD
       "Epoch: 0 Acc = 0.97776 Cost = 82759.57812 Valid_Acc = 0.97767 Valid_Cost =  8259.38965\n",
       "Epoch: 5 Acc = 0.98852 Cost = 73093.75781 Valid_Acc = 0.98971 Valid_Cost =  7532.35059\n",
       "Epoch: 10 Acc = 0.99023 Cost = 62864.16406 Valid_Acc = 0.99094 Valid_Cost =  7449.86719\n",
@@ -3003,29 +2677,6 @@
       "Epoch: 90 Acc = 0.99820 Cost = 4898.35400 Valid_Acc = 0.99789 Valid_Cost =  49322.94531\n",
       "Epoch: 95 Acc = 0.99793 Cost = 5422.48340 Valid_Acc = 0.99758 Valid_Cost =  50593.96094\n",
       "Epoch: 100 Acc = 0.99080 Cost = 7493.91504 Valid_Acc = 0.99020 Valid_Cost =  40995.75781\n",
-=======
-      "Epoch: 0 Acc = 0.98030 Cost = 70089.28125 Valid_Acc = 0.98034 Valid_Cost =  15254.80078\n",
-      "Epoch: 5 Acc = 0.98767 Cost = 58580.29297 Valid_Acc = 0.98750 Valid_Cost =  14394.41895\n",
-      "Epoch: 10 Acc = 0.98854 Cost = 48541.71875 Valid_Acc = 0.98883 Valid_Cost =  14806.13574\n",
-      "Epoch: 15 Acc = 0.98865 Cost = 39388.20703 Valid_Acc = 0.98894 Valid_Cost =  16517.65625\n",
-      "Epoch: 20 Acc = 0.99094 Cost = 31618.80859 Valid_Acc = 0.99122 Valid_Cost =  20146.30859\n",
-      "Epoch: 25 Acc = 0.99130 Cost = 22800.29883 Valid_Acc = 0.99136 Valid_Cost =  24841.26758\n",
-      "Epoch: 30 Acc = 0.99118 Cost = 18227.08789 Valid_Acc = 0.99143 Valid_Cost =  28714.44141\n",
-      "Epoch: 35 Acc = 0.99246 Cost = 11901.30176 Valid_Acc = 0.99305 Valid_Cost =  36806.41406\n",
-      "Epoch: 40 Acc = 0.99238 Cost = 14242.89941 Valid_Acc = 0.99238 Valid_Cost =  45021.91797\n",
-      "Epoch: 45 Acc = 0.99631 Cost = 9457.01465 Valid_Acc = 0.99586 Valid_Cost =  56201.80469\n",
-      "Epoch: 50 Acc = 0.99604 Cost = 10883.57422 Valid_Acc = 0.99582 Valid_Cost =  58257.39453\n",
-      "Epoch: 55 Acc = 0.99695 Cost = 6030.76562 Valid_Acc = 0.99666 Valid_Cost =  62535.69531\n",
-      "Epoch: 60 Acc = 0.99780 Cost = 6262.52979 Valid_Acc = 0.99758 Valid_Cost =  74222.21094\n",
-      "Epoch: 65 Acc = 0.99716 Cost = 4710.59668 Valid_Acc = 0.99673 Valid_Cost =  65601.07031\n",
-      "Epoch: 70 Acc = 0.99813 Cost = 4759.97021 Valid_Acc = 0.99726 Valid_Cost =  75777.33594\n",
-      "Epoch: 75 Acc = 0.99081 Cost = 6893.59326 Valid_Acc = 0.99119 Valid_Cost =  59490.25781\n",
-      "Epoch: 80 Acc = 0.99744 Cost = 2822.39600 Valid_Acc = 0.99695 Valid_Cost =  82329.80469\n",
-      "Epoch: 85 Acc = 0.99785 Cost = 2602.71289 Valid_Acc = 0.99740 Valid_Cost =  94100.67969\n",
-      "Epoch: 90 Acc = 0.99610 Cost = 3647.93262 Valid_Acc = 0.99582 Valid_Cost =  75909.85156\n",
-      "Epoch: 95 Acc = 0.99828 Cost = 3060.12622 Valid_Acc = 0.99775 Valid_Cost =  99243.14844\n",
-      "Epoch: 100 Acc = 0.99632 Cost = 3478.99805 Valid_Acc = 0.99558 Valid_Cost =  93043.17969\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
       "\n",
       "Optimization Finished!\n",
       "\n",
@@ -3118,11 +2769,7 @@
    "outputs": [
     {
      "data": {
-<<<<<<< HEAD
       "image/png": "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\n",
-=======
-      "image/png": "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\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
       "text/plain": [
        "<Figure size 720x288 with 2 Axes>"
       ]
@@ -3171,11 +2818,7 @@
      "output_type": "stream",
      "text": [
       "INFO:tensorflow:Restoring parameters from ./model/model.ckpt\n",
-<<<<<<< HEAD
       "Testing Accuracy = 0.9904498\n"
-=======
-      "Testing Accuracy = 0.9961027\n"
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
      ]
     }
    ],
@@ -3582,11 +3225,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 47,
-=======
-   "execution_count": 48,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {},
    "outputs": [
     {
@@ -3612,11 +3251,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 48,
-=======
-   "execution_count": 49,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {
     "_cell_guid": "78dcafd6-c7e5-4396-b4f4-cba7ae30de9f",
     "_uuid": "e9eb5647ea9a1daf4f91f4577f3d4d0e8064f096"
@@ -3629,11 +3264,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 49,
-=======
-   "execution_count": 50,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {},
    "outputs": [
     {
@@ -4097,11 +3728,7 @@
        "130872 -0.560888  1354.98                 0  "
       ]
      },
-<<<<<<< HEAD
      "execution_count": 49,
-=======
-     "execution_count": 50,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -4119,11 +3746,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 50,
-=======
-   "execution_count": 51,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {
     "_cell_guid": "952ab8e5-cccd-4188-8690-c33e405545d4",
     "_uuid": "7ae50c4c16bf36e9b001f658909116004a86aed3"
@@ -4136,11 +3759,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 51,
-=======
-   "execution_count": 52,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {
     "_cell_guid": "5c03b27c-581a-452b-86dd-ae4ce2b37877",
     "_uuid": "92cce9a63827d1a9e11bc143b46f605f3879eeae"
@@ -4174,11 +3793,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 52,
-=======
-   "execution_count": 53,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {
     "_cell_guid": "94bb1a46-193f-47fd-bf1f-f0e917492298",
     "_uuid": "add388ac1620f9fb2eb1850b35a81411c30055a6"
@@ -4191,11 +3806,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
    "execution_count": 53,
-=======
-   "execution_count": 65,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
    "metadata": {},
    "outputs": [
     {
@@ -4205,11 +3816,7 @@
        "       [1., 0.]], dtype=float32)"
       ]
      },
-<<<<<<< HEAD
      "execution_count": 53,
-=======
-     "execution_count": 65,
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -4224,7 +3831,6 @@
    "source": [
     "입력 데이터셋에 정규화(Centering and Scaling)를 적용합니다."
    ]
-<<<<<<< HEAD
   },
   {
    "cell_type": "code",
@@ -4792,630 +4398,36 @@
    "metadata": {
     "_cell_guid": "e45c27c0-1e29-47cf-befe-bba155dd21cf",
     "_uuid": "a6790157aaf0370faa31223ebd4c1faeeaf84f9a"
-=======
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "56962/56962 [==============================] - 2s 38us/step\n",
+      "Test score: 0.027562282392704363\n",
+      "Test accuracy: 0.9982795547909132\n"
+     ]
+    }
+   ],
+   "source": [
+    "score, acc = model.evaluate(X_test, Y_test)\n",
+    "print('Test score:', score)\n",
+    "print('Test accuracy:', acc)"
+   ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 59,
-   "metadata": {
-    "_cell_guid": "9136cfd3-7e69-4fdf-a658-d0677cb32e26",
-    "_uuid": "94754afc163a673cfc20a64ae01032d0b6e60454"
-   },
-   "outputs": [],
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "#Names of all of the features in X_train.\n",
-    "features = X_train.columns.values\n",
-    "\n",
-    "for feature in features:\n",
-    "    mean, std = data[feature].mean(), data[feature].std()\n",
-    "    X_train.loc[:, feature] = (X_train[feature] - mean) / std\n",
-    "    X_test.loc[:, feature] = (X_test[feature] - mean) / std"
+    "**99.82%의 정확도를 Test에서 얻을 수 있습니다!** 이걸로 충분할까요? 10 epoch 이상으로 적용하면 아마 더 도움이 될 것입니다."
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 60,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>Time</th>\n",
-       "      <th>V1</th>\n",
-       "      <th>V2</th>\n",
-       "      <th>V3</th>\n",
-       "      <th>V4</th>\n",
-       "      <th>V5</th>\n",
-       "      <th>V6</th>\n",
-       "      <th>V7</th>\n",
-       "      <th>V8</th>\n",
-       "      <th>V9</th>\n",
-       "      <th>V10</th>\n",
-       "      <th>V11</th>\n",
-       "      <th>V12</th>\n",
-       "      <th>V13</th>\n",
-       "      <th>V14</th>\n",
-       "      <th>V15</th>\n",
-       "      <th>V16</th>\n",
-       "      <th>V17</th>\n",
-       "      <th>V18</th>\n",
-       "      <th>V19</th>\n",
-       "      <th>V20</th>\n",
-       "      <th>V21</th>\n",
-       "      <th>V22</th>\n",
-       "      <th>V23</th>\n",
-       "      <th>V24</th>\n",
-       "      <th>V25</th>\n",
-       "      <th>V26</th>\n",
-       "      <th>V27</th>\n",
-       "      <th>V28</th>\n",
-       "      <th>Amount</th>\n",
-       "      <th>Amount_max_fraud</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "      <td>56962.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>0.005139</td>\n",
-       "      <td>0.006783</td>\n",
-       "      <td>0.004003</td>\n",
-       "      <td>-0.002811</td>\n",
-       "      <td>0.001057</td>\n",
-       "      <td>-0.002541</td>\n",
-       "      <td>-0.002311</td>\n",
-       "      <td>0.000114</td>\n",
-       "      <td>-0.005443</td>\n",
-       "      <td>0.001423</td>\n",
-       "      <td>0.002917</td>\n",
-       "      <td>-0.008161</td>\n",
-       "      <td>-0.000041</td>\n",
-       "      <td>-0.000321</td>\n",
-       "      <td>-0.003872</td>\n",
-       "      <td>0.003222</td>\n",
-       "      <td>-0.001978</td>\n",
-       "      <td>0.000035</td>\n",
-       "      <td>0.003967</td>\n",
-       "      <td>0.000940</td>\n",
-       "      <td>-0.003482</td>\n",
-       "      <td>-0.003067</td>\n",
-       "      <td>-0.006804</td>\n",
-       "      <td>0.006418</td>\n",
-       "      <td>-0.001680</td>\n",
-       "      <td>-0.001673</td>\n",
-       "      <td>0.009358</td>\n",
-       "      <td>0.003430</td>\n",
-       "      <td>-0.006029</td>\n",
-       "      <td>-0.002762</td>\n",
-       "      <td>-0.005195</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>0.998959</td>\n",
-       "      <td>0.991084</td>\n",
-       "      <td>0.975726</td>\n",
-       "      <td>1.000395</td>\n",
-       "      <td>1.002287</td>\n",
-       "      <td>1.037301</td>\n",
-       "      <td>1.020548</td>\n",
-       "      <td>1.052306</td>\n",
-       "      <td>1.005681</td>\n",
-       "      <td>1.004602</td>\n",
-       "      <td>1.005792</td>\n",
-       "      <td>0.995285</td>\n",
-       "      <td>0.998488</td>\n",
-       "      <td>0.999305</td>\n",
-       "      <td>0.995902</td>\n",
-       "      <td>0.996960</td>\n",
-       "      <td>1.002095</td>\n",
-       "      <td>0.991084</td>\n",
-       "      <td>0.997565</td>\n",
-       "      <td>1.006987</td>\n",
-       "      <td>0.991601</td>\n",
-       "      <td>1.001834</td>\n",
-       "      <td>1.006337</td>\n",
-       "      <td>0.995456</td>\n",
-       "      <td>0.997595</td>\n",
-       "      <td>0.999471</td>\n",
-       "      <td>0.999232</td>\n",
-       "      <td>1.032498</td>\n",
-       "      <td>0.986538</td>\n",
-       "      <td>1.031676</td>\n",
-       "      <td>0.942043</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>-1.996537</td>\n",
-       "      <td>-18.640252</td>\n",
-       "      <td>-28.722479</td>\n",
-       "      <td>-31.871677</td>\n",
-       "      <td>-3.927001</td>\n",
-       "      <td>-82.407952</td>\n",
-       "      <td>-15.052954</td>\n",
-       "      <td>-22.807581</td>\n",
-       "      <td>-34.734141</td>\n",
-       "      <td>-8.630238</td>\n",
-       "      <td>-19.239745</td>\n",
-       "      <td>-3.927948</td>\n",
-       "      <td>-18.568526</td>\n",
-       "      <td>-3.867219</td>\n",
-       "      <td>-20.044245</td>\n",
-       "      <td>-4.470963</td>\n",
-       "      <td>-14.449819</td>\n",
-       "      <td>-25.561333</td>\n",
-       "      <td>-10.569916</td>\n",
-       "      <td>-5.674207</td>\n",
-       "      <td>-70.691337</td>\n",
-       "      <td>-29.434190</td>\n",
-       "      <td>-11.841840</td>\n",
-       "      <td>-52.571789</td>\n",
-       "      <td>-4.660608</td>\n",
-       "      <td>-16.683278</td>\n",
-       "      <td>-3.687188</td>\n",
-       "      <td>-21.996904</td>\n",
-       "      <td>-46.746035</td>\n",
-       "      <td>-0.353229</td>\n",
-       "      <td>-0.046062</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>-0.853426</td>\n",
-       "      <td>-0.463875</td>\n",
-       "      <td>-0.363474</td>\n",
-       "      <td>-0.589585</td>\n",
-       "      <td>-0.598655</td>\n",
-       "      <td>-0.502851</td>\n",
-       "      <td>-0.578069</td>\n",
-       "      <td>-0.445477</td>\n",
-       "      <td>-0.176824</td>\n",
-       "      <td>-0.584429</td>\n",
-       "      <td>-0.491456</td>\n",
-       "      <td>-0.752641</td>\n",
-       "      <td>-0.406027</td>\n",
-       "      <td>-0.651183</td>\n",
-       "      <td>-0.442192</td>\n",
-       "      <td>-0.629025</td>\n",
-       "      <td>-0.538465</td>\n",
-       "      <td>-0.570989</td>\n",
-       "      <td>-0.590404</td>\n",
-       "      <td>-0.559835</td>\n",
-       "      <td>-0.274473</td>\n",
-       "      <td>-0.313414</td>\n",
-       "      <td>-0.756551</td>\n",
-       "      <td>-0.256508</td>\n",
-       "      <td>-0.588789</td>\n",
-       "      <td>-0.605699</td>\n",
-       "      <td>-0.669323</td>\n",
-       "      <td>-0.173930</td>\n",
-       "      <td>-0.158599</td>\n",
-       "      <td>-0.330780</td>\n",
-       "      <td>-0.046062</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>-0.201890</td>\n",
-       "      <td>0.018508</td>\n",
-       "      <td>0.037449</td>\n",
-       "      <td>0.112718</td>\n",
-       "      <td>-0.015604</td>\n",
-       "      <td>-0.037550</td>\n",
-       "      <td>-0.209371</td>\n",
-       "      <td>0.031651</td>\n",
-       "      <td>0.016664</td>\n",
-       "      <td>-0.047884</td>\n",
-       "      <td>-0.087869</td>\n",
-       "      <td>-0.042653</td>\n",
-       "      <td>0.140433</td>\n",
-       "      <td>-0.013747</td>\n",
-       "      <td>0.048731</td>\n",
-       "      <td>0.056303</td>\n",
-       "      <td>0.075434</td>\n",
-       "      <td>-0.078295</td>\n",
-       "      <td>-0.006511</td>\n",
-       "      <td>0.004373</td>\n",
-       "      <td>-0.080084</td>\n",
-       "      <td>-0.044081</td>\n",
-       "      <td>-0.000454</td>\n",
-       "      <td>-0.014947</td>\n",
-       "      <td>0.066119</td>\n",
-       "      <td>0.034672</td>\n",
-       "      <td>-0.099246</td>\n",
-       "      <td>0.003594</td>\n",
-       "      <td>0.034397</td>\n",
-       "      <td>-0.265671</td>\n",
-       "      <td>-0.046062</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>0.935415</td>\n",
-       "      <td>0.673778</td>\n",
-       "      <td>0.485168</td>\n",
-       "      <td>0.670664</td>\n",
-       "      <td>0.521721</td>\n",
-       "      <td>0.445901</td>\n",
-       "      <td>0.294835</td>\n",
-       "      <td>0.460571</td>\n",
-       "      <td>0.272035</td>\n",
-       "      <td>0.545800</td>\n",
-       "      <td>0.416090</td>\n",
-       "      <td>0.713728</td>\n",
-       "      <td>0.617349</td>\n",
-       "      <td>0.671185</td>\n",
-       "      <td>0.508547</td>\n",
-       "      <td>0.708872</td>\n",
-       "      <td>0.594398</td>\n",
-       "      <td>0.474034</td>\n",
-       "      <td>0.599056</td>\n",
-       "      <td>0.563700</td>\n",
-       "      <td>0.170239</td>\n",
-       "      <td>0.251604</td>\n",
-       "      <td>0.722727</td>\n",
-       "      <td>0.240184</td>\n",
-       "      <td>0.722627</td>\n",
-       "      <td>0.669307</td>\n",
-       "      <td>0.508652</td>\n",
-       "      <td>0.224801</td>\n",
-       "      <td>0.234739</td>\n",
-       "      <td>-0.043378</td>\n",
-       "      <td>-0.046062</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>1.641907</td>\n",
-       "      <td>1.249048</td>\n",
-       "      <td>11.446954</td>\n",
-       "      <td>2.628480</td>\n",
-       "      <td>10.809043</td>\n",
-       "      <td>21.022418</td>\n",
-       "      <td>55.020053</td>\n",
-       "      <td>97.478068</td>\n",
-       "      <td>15.307174</td>\n",
-       "      <td>9.439610</td>\n",
-       "      <td>13.992774</td>\n",
-       "      <td>11.775017</td>\n",
-       "      <td>4.850326</td>\n",
-       "      <td>7.160723</td>\n",
-       "      <td>7.742518</td>\n",
-       "      <td>9.699100</td>\n",
-       "      <td>19.760405</td>\n",
-       "      <td>9.105285</td>\n",
-       "      <td>4.883746</td>\n",
-       "      <td>6.869402</td>\n",
-       "      <td>25.613973</td>\n",
-       "      <td>30.788496</td>\n",
-       "      <td>9.357086</td>\n",
-       "      <td>33.314118</td>\n",
-       "      <td>7.569671</td>\n",
-       "      <td>14.425293</td>\n",
-       "      <td>7.293962</td>\n",
-       "      <td>78.319259</td>\n",
-       "      <td>68.528383</td>\n",
-       "      <td>102.362063</td>\n",
-       "      <td>21.709793</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "               Time            V1            V2            V3            V4  \\\n",
-       "count  56962.000000  56962.000000  56962.000000  56962.000000  56962.000000   \n",
-       "mean       0.005139      0.006783      0.004003     -0.002811      0.001057   \n",
-       "std        0.998959      0.991084      0.975726      1.000395      1.002287   \n",
-       "min       -1.996537    -18.640252    -28.722479    -31.871677     -3.927001   \n",
-       "25%       -0.853426     -0.463875     -0.363474     -0.589585     -0.598655   \n",
-       "50%       -0.201890      0.018508      0.037449      0.112718     -0.015604   \n",
-       "75%        0.935415      0.673778      0.485168      0.670664      0.521721   \n",
-       "max        1.641907      1.249048     11.446954      2.628480     10.809043   \n",
-       "\n",
-       "                 V5            V6            V7            V8            V9  \\\n",
-       "count  56962.000000  56962.000000  56962.000000  56962.000000  56962.000000   \n",
-       "mean      -0.002541     -0.002311      0.000114     -0.005443      0.001423   \n",
-       "std        1.037301      1.020548      1.052306      1.005681      1.004602   \n",
-       "min      -82.407952    -15.052954    -22.807581    -34.734141     -8.630238   \n",
-       "25%       -0.502851     -0.578069     -0.445477     -0.176824     -0.584429   \n",
-       "50%       -0.037550     -0.209371      0.031651      0.016664     -0.047884   \n",
-       "75%        0.445901      0.294835      0.460571      0.272035      0.545800   \n",
-       "max       21.022418     55.020053     97.478068     15.307174      9.439610   \n",
-       "\n",
-       "                V10           V11           V12           V13           V14  \\\n",
-       "count  56962.000000  56962.000000  56962.000000  56962.000000  56962.000000   \n",
-       "mean       0.002917     -0.008161     -0.000041     -0.000321     -0.003872   \n",
-       "std        1.005792      0.995285      0.998488      0.999305      0.995902   \n",
-       "min      -19.239745     -3.927948    -18.568526     -3.867219    -20.044245   \n",
-       "25%       -0.491456     -0.752641     -0.406027     -0.651183     -0.442192   \n",
-       "50%       -0.087869     -0.042653      0.140433     -0.013747      0.048731   \n",
-       "75%        0.416090      0.713728      0.617349      0.671185      0.508547   \n",
-       "max       13.992774     11.775017      4.850326      7.160723      7.742518   \n",
-       "\n",
-       "                V15           V16           V17           V18           V19  \\\n",
-       "count  56962.000000  56962.000000  56962.000000  56962.000000  56962.000000   \n",
-       "mean       0.003222     -0.001978      0.000035      0.003967      0.000940   \n",
-       "std        0.996960      1.002095      0.991084      0.997565      1.006987   \n",
-       "min       -4.470963    -14.449819    -25.561333    -10.569916     -5.674207   \n",
-       "25%       -0.629025     -0.538465     -0.570989     -0.590404     -0.559835   \n",
-       "50%        0.056303      0.075434     -0.078295     -0.006511      0.004373   \n",
-       "75%        0.708872      0.594398      0.474034      0.599056      0.563700   \n",
-       "max        9.699100     19.760405      9.105285      4.883746      6.869402   \n",
-       "\n",
-       "                V20           V21           V22           V23           V24  \\\n",
-       "count  56962.000000  56962.000000  56962.000000  56962.000000  56962.000000   \n",
-       "mean      -0.003482     -0.003067     -0.006804      0.006418     -0.001680   \n",
-       "std        0.991601      1.001834      1.006337      0.995456      0.997595   \n",
-       "min      -70.691337    -29.434190    -11.841840    -52.571789     -4.660608   \n",
-       "25%       -0.274473     -0.313414     -0.756551     -0.256508     -0.588789   \n",
-       "50%       -0.080084     -0.044081     -0.000454     -0.014947      0.066119   \n",
-       "75%        0.170239      0.251604      0.722727      0.240184      0.722627   \n",
-       "max       25.613973     30.788496      9.357086     33.314118      7.569671   \n",
-       "\n",
-       "                V25           V26           V27           V28        Amount  \\\n",
-       "count  56962.000000  56962.000000  56962.000000  56962.000000  56962.000000   \n",
-       "mean      -0.001673      0.009358      0.003430     -0.006029     -0.002762   \n",
-       "std        0.999471      0.999232      1.032498      0.986538      1.031676   \n",
-       "min      -16.683278     -3.687188    -21.996904    -46.746035     -0.353229   \n",
-       "25%       -0.605699     -0.669323     -0.173930     -0.158599     -0.330780   \n",
-       "50%        0.034672     -0.099246      0.003594      0.034397     -0.265671   \n",
-       "75%        0.669307      0.508652      0.224801      0.234739     -0.043378   \n",
-       "max       14.425293      7.293962     78.319259     68.528383    102.362063   \n",
-       "\n",
-       "       Amount_max_fraud  \n",
-       "count      56962.000000  \n",
-       "mean          -0.005195  \n",
-       "std            0.942043  \n",
-       "min           -0.046062  \n",
-       "25%           -0.046062  \n",
-       "50%           -0.046062  \n",
-       "75%           -0.046062  \n",
-       "max           21.709793  "
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "X_test.describe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "그리고 Kearas 모델을 구축합니다."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "metadata": {
-    "_cell_guid": "6c0f7416-412a-4415-94e8-362fa13948ea",
-    "_uuid": "9c648e3b03efea588dea1d20893bf148151447f7"
-   },
-   "outputs": [],
-   "source": [
-    "# fix random seed for reproducibility\n",
-    "np.random.seed(2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "5 층 네트워크로 마지막은 결과 레이어로 구성하였습니다. 첫 레이어는 Input Dimension을 X_train 칼럼 수인 31로 하였습니다. 마지막 레이어는 softmax 활성화를 사용하였고 나머지는 relu로 활성화하였습니다. 모든 레이어는 0.9인 dropout을 적용합니다. (각 층의 90%의 정보만 사용한다는 뜻입니다.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "metadata": {
-    "_cell_guid": "bbf4cf25-3052-4b8f-9ac7-700865de4905",
-    "_uuid": "cf449dc135ffd673be7ef9b800df733c6c48831d"
-   },
-   "outputs": [],
-   "source": [
-    "model = Sequential()\n",
-    "model.add(Dense(64, input_dim=31, activation='relu'))\n",
-    "model.add(Dropout(0.9))\n",
-    "model.add(Dense(64, activation='relu'))\n",
-    "model.add(Dropout(0.9))\n",
-    "model.add(Dense(64, activation='relu'))\n",
-    "model.add(Dropout(0.9))\n",
-    "model.add(Dense(64, activation='relu'))\n",
-    "model.add(Dropout(0.9))\n",
-    "model.add(Dense(2, activation='softmax'))  # With 2 outputs"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "loss는 binary cross-entropy로, optimizer는 adam으로 모델을 학습할 수 있도록 설정(compile)합니다. 평가기준(metrics)은 정확도(accuracy)로 받습니다."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 67,
-   "metadata": {
-    "_cell_guid": "2dec00ca-e47c-4142-89bc-e7a445314ebc",
-    "_uuid": "086c950d76895f638b313701200a144fdf3851b6"
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "56962/56962 [==============================] - 2s 38us/step\n",
-      "Test score: 0.027562282392704363\n",
-      "Test accuracy: 0.9982795547909132\n"
-     ]
-    }
-   ],
-   "source": [
-    "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "컴파일된 모델을 Training 데이터로 학습(Fit)합니다. 일단 batch_size 2048로 두고 10 epoch(세대)만 학습합니다."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 68,
-   "metadata": {
-    "_cell_guid": "bbbd50fb-41e8-4f71-b497-f8e19038dad0",
-    "_uuid": "239658b1175b942a7aa179f8ae8b71dccbcb8f6d"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch 1/10\n",
-      "227845/227845 [==============================] - 5s 20us/step - loss: 0.9254 - acc: 0.8761\n",
-      "Epoch 2/10\n",
-      "227845/227845 [==============================] - 3s 12us/step - loss: 0.1404 - acc: 0.9815\n",
-      "Epoch 3/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0815 - acc: 0.9913\n",
-      "Epoch 4/10\n",
-      "227845/227845 [==============================] - 3s 14us/step - loss: 0.0603 - acc: 0.9949\n",
-      "Epoch 5/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0497 - acc: 0.9961: 1s\n",
-      "Epoch 6/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0447 - acc: 0.9970\n",
-      "Epoch 7/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0401 - acc: 0.9972\n",
-      "Epoch 8/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0373 - acc: 0.9977\n",
-      "Epoch 9/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0356 - acc: 0.9978\n",
-      "Epoch 10/10\n",
-      "227845/227845 [==============================] - 3s 13us/step - loss: 0.0345 - acc: 0.9979\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "<keras.callbacks.History at 0x2ea76744898>"
-      ]
-     },
-     "execution_count": 68,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "epoch = 10\n",
-    "batch_size = 2048\n",
-    "model.fit(X_train, Y_train, epochs=epoch, batch_size=batch_size)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 69,
-   "metadata": {
-    "_cell_guid": "e45c27c0-1e29-47cf-befe-bba155dd21cf",
-    "_uuid": "a6790157aaf0370faa31223ebd4c1faeeaf84f9a"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "56962/56962 [==============================] - 4s 67us/step\n",
-      "Test score: 0.027575257398611885\n",
-      "Test accuracy: 0.9982795547909132\n"
-     ]
-    }
-   ],
-   "source": [
-    "score, acc = model.evaluate(X_test, Y_test)\n",
-    "print('Test score:', score)\n",
-    "print('Test accuracy:', acc)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-<<<<<<< HEAD
-   "source": [
-    "**99.82%의 정확도를 Test에서 얻을 수 있습니다!** 이걸로 충분할까요? 10 epoch 이상으로 적용하면 아마 더 도움이 될 것입니다."
-   ]
-  },
-  {
-   "cell_type": "markdown",
+   "cell_type": "markdown",
    "metadata": {},
    "source": [
     "### Training과 Testing, 그리고 loss vs epoch:\n",
-=======
-   "source": [
-    "**99.82%의 정확도를 Test에서 얻을 수 있습니다!** 이걸로 충분할까요? 10 epoch 이상으로 적용하면 아마 더 도움이 될 것입니다."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "_cell_guid": "130799f9-6a91-4c74-b761-26c00c3bd8c6",
-    "_uuid": "343bbc820dd1043196daef8b36ec7b8da445eaec"
-   },
-   "source": [
-    "### Training and testing accuracy and loss vs epoch:\n",
->>>>>>> d920615aad30be02d15aefebe44d1a20b2c111f3
     "\n",
     "일단 모델을 다시 실행하여 Train과 Test의 정확도와 epoch에 따른 loss를 살펴보도록 하겠습니다."
    ]