updating sql I db

docs/pandas_2/pandas_2.html

@@ -1650,12 +1650,12 @@ <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">366772</td>
+<td data-quarto-table-cell-role="th">291690</td>
 <td>CA</td>
 <td>M</td>
-<td>2008</td>
-<td>Neeraj</td>
-<td>5</td>
+<td>1976</td>
+<td>Devin</td>
+<td>72</td>
 </tr>
 </tbody>
 </table>
@@ -1682,34 +1682,34 @@ <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">167084</td>
-<td>2004</td>
-<td>Vicki</td>
+<td data-quarto-table-cell-role="th">403504</td>
+<td>2021</td>
+<td>Abhiram</td>
 <td>8</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">210217</td>
-<td>2015</td>
-<td>Mabel</td>
-<td>63</td>
+<td data-quarto-table-cell-role="th">129477</td>
+<td>1994</td>
+<td>Cheri</td>
+<td>11</td>
 </tr>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">262294</td>
-<td>1950</td>
-<td>Quentin</td>
-<td>5</td>
+<td data-quarto-table-cell-role="th">356274</td>
+<td>2005</td>
+<td>Reyes</td>
+<td>23</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">198220</td>
-<td>2012</td>
-<td>Vienna</td>
-<td>55</td>
+<td data-quarto-table-cell-role="th">275317</td>
+<td>1963</td>
+<td>Rolf</td>
+<td>18</td>
 </tr>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">79888</td>
-<td>1978</td>
-<td>Letisha</td>
-<td>8</td>
+<td data-quarto-table-cell-role="th">387880</td>
+<td>2016</td>
+<td>Ben</td>
+<td>55</td>
 </tr>
 </tbody>
 </table>
@@ -1735,28 +1735,28 @@ <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">151306</td>
+<td data-quarto-table-cell-role="th">342715</td>
 <td>2000</td>
-<td>Janina</td>
-<td>9</td>
+<td>Darren</td>
+<td>139</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">150540</td>
+<td data-quarto-table-cell-role="th">149156</td>
 <td>2000</td>
-<td>Abrianna</td>
-<td>16</td>
+<td>Trinity</td>
+<td>481</td>
 </tr>
 <tr class="odd">
-<td data-quarto-table-cell-role="th">152423</td>
+<td data-quarto-table-cell-role="th">343955</td>
 <td>2000</td>
-<td>Deven</td>
-<td>5</td>
+<td>Rajan</td>
+<td>9</td>
 </tr>
 <tr class="even">
-<td data-quarto-table-cell-role="th">344406</td>
+<td data-quarto-table-cell-role="th">151213</td>
 <td>2000</td>
-<td>Chadwick</td>
-<td>6</td>
+<td>Tasha</td>
+<td>10</td>
 </tr>
 </tbody>
 </table>

docs/regex/regex.html

@@ -686,11 +686,11 @@ <h4 data-number="6.2.1.2" class="anchored" data-anchor-id="canonicalization-with
 <span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a>county_and_state[<span class="st">'clean_county_pandas'</span>] <span class="op">=</span> canonicalize_county_series(county_and_state[<span class="st">'County'</span>])</span>
 <span id="cb6-14"><a href="#cb6-14" aria-hidden="true" tabindex="-1"></a>display(county_and_pop), display(county_and_state)<span class="op">;</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-stderr">
-<pre><code>/var/folders/7t/zbwy02ts2m7cn64fvwjqb8xw0000gp/T/ipykernel_49929/2523629438.py:3: FutureWarning:
+<pre><code>/var/folders/7t/zbwy02ts2m7cn64fvwjqb8xw0000gp/T/ipykernel_59489/2523629438.py:3: FutureWarning:
 
 The default value of regex will change from True to False in a future version. In addition, single character regular expressions will *not* be treated as literal strings when regex=True.
 
-/var/folders/7t/zbwy02ts2m7cn64fvwjqb8xw0000gp/T/ipykernel_49929/2523629438.py:3: FutureWarning:
+/var/folders/7t/zbwy02ts2m7cn64fvwjqb8xw0000gp/T/ipykernel_59489/2523629438.py:3: FutureWarning:
 
 The default value of regex will change from True to False in a future version. In addition, single character regular expressions will *not* be treated as literal strings when regex=True.
 </code></pre>

docs/sampling/sampling.html

@@ -704,7 +704,7 @@ <h4 data-number="9.3.3.3" class="anchored" data-anchor-id="simple-random-sample"
 <span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a>random_sample <span class="op">=</span> movie.sample(n, replace <span class="op">=</span> <span class="va">False</span>) <span class="co">## By default, replace = False</span></span>
 <span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a>np.mean(random_sample[<span class="st">"barbie"</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="9">
-<pre><code>0.5296914823759864</code></pre>
+<pre><code>0.530662556066289</code></pre>
 </div>
 </div>
 <p>This is very close to the actual vote of 0.5302792307692308!</p>
@@ -722,7 +722,7 @@ <h4 data-number="9.3.3.3" class="anchored" data-anchor-id="simple-random-sample"
 <span id="cb15-10"><a href="#cb15-10" aria-hidden="true" tabindex="-1"></a>Markdown(<span class="ss">f"**Actual** = </span><span class="sc">{</span>actual_barbie<span class="sc">:.4f}</span><span class="ss">, **Sample** = </span><span class="sc">{</span>sample_barbie<span class="sc">:.4f}</span><span class="ss">, "</span></span>
 <span id="cb15-11"><a href="#cb15-11" aria-hidden="true" tabindex="-1"></a>         <span class="ss">f"**Err** = </span><span class="sc">{</span><span class="dv">100</span><span class="op">*</span>err<span class="sc">:.2f}</span><span class="ss">%."</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">
-<p><strong>Actual</strong> = 0.5303, <strong>Sample</strong> = 0.5337, <strong>Err</strong> = 0.65%.</p>
+<p><strong>Actual</strong> = 0.5303, <strong>Sample</strong> = 0.5487, <strong>Err</strong> = 3.48%.</p>
 </div>
 </div>
 <p>We’ll learn how to choose this number when we (re)learn the Central Limit Theorem later in the semester.</p>

docs/sql_I/sql_I.html

@@ -365,7 +365,7 @@ <h2 data-number="20.2" class="anchored" data-anchor-id="intro-to-sql"><span clas
 <p>For the purposes of Data 100, we use SQLite or DuckDB. SQLite is an easy-to-use library that allows users to directly manipulate a database file or an in-memory database with a simplified version of SQL. It’s commonly used to store data for small apps on mobile devices and is optimized for simplicity and speed of simple data tasks. DuckDB is an easy-to-use library that lets you directly manipulate a database file, collection of table formatted files (e.g., CSV), or in-memory <code>pandas</code> <code>DataFrame</code>s using a more complete version of SQL. It’s optimized for simplicity and speed of advanced data analysis tasks and is becoming increasingly popular for data analysis tasks on large datasets.</p>
 <p>It is important to reiterate that SQL is an entirely different language from Python. However, Python <em>does</em> have special engines that allow us to run SQL code in a Jupyter notebook. While this is typically not how SQL is used outside of an educational setting, we will use this workflow to illustrate how SQL queries are constructed using the tools we’ve already worked with this semester. You will learn more about how to run SQL queries in Jupyter in Lab 10 and Homework 10.</p>
 <p>The syntax below will seem unfamiliar to you; for now, just focus on understanding the output displayed. We will clarify the SQL code in a bit.</p>
-<p>To start, we’ll look at a database called <code>basic_examples.db</code> and connect to it using SQLite.</p>
+<p>To start, we’ll look at a database called <code>example_duck.db</code> and connect to it using SQLite.</p>
 <div class="cell" data-vscode="{&quot;languageId&quot;:&quot;python&quot;}" data-execution_count="1">
 <details>
 <summary>Code</summary>
@@ -380,7 +380,7 @@ <h2 data-number="20.2" class="anchored" data-anchor-id="intro-to-sql"><span clas
 </div>
 <div class="cell" data-vscode="{&quot;languageId&quot;:&quot;python&quot;}" 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><span class="co"># Connect to the database</span></span>
-<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>sql duckdb:<span class="op">///</span>data<span class="op">/</span>basic_examples.db <span class="op">--</span>alias duck</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>sql duckdb:<span class="op">///</span>data<span class="op">/</span>example_duck.db <span class="op">--</span>alias duck</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </div>
 <p>Now that we’re connected, let’s make some queries!</p>
 <div class="cell" data-vscode="{&quot;languageId&quot;:&quot;python&quot;}" data-execution_count="4">
@@ -461,31 +461,24 @@ <h2 data-number="20.3" class="anchored" data-anchor-id="tables-and-schema"><span
 <tbody>
 <tr class="odd">
 <td>table</td>
-<td>sqlite_sequence</td>
-<td>sqlite_sequence</td>
+<td>dish</td>
+<td>dish</td>
 <td>0</td>
-<td>CREATE TABLE sqlite_sequence("name" BLOB, seq BLOB);</td>
+<td>CREATE TABLE dish("name" VARCHAR PRIMARY KEY, "type" VARCHAR, "cost" INTEGER, CHECK(("cost" &gt;= 0)));</td>
 </tr>
 <tr class="even">
 <td>table</td>
-<td>Dragon</td>
-<td>Dragon</td>
+<td>dragon</td>
+<td>dragon</td>
 <td>0</td>
-<td>CREATE TABLE Dragon("name" VARCHAR PRIMARY KEY, "year" BIGINT, cute BIGINT);</td>
+<td>CREATE TABLE dragon("name" VARCHAR PRIMARY KEY, "year" INTEGER, cute INTEGER, CHECK(("year" &gt;= 2000)));</td>
 </tr>
 <tr class="odd">
 <td>table</td>
-<td>Dish</td>
-<td>Dish</td>
+<td>scene</td>
+<td>scene</td>
 <td>0</td>
-<td>CREATE TABLE Dish("name" VARCHAR PRIMARY KEY, "type" VARCHAR, "cost" BIGINT);</td>
-</tr>
-<tr class="even">
-<td>table</td>
-<td>Scene</td>
-<td>Scene</td>
-<td>0</td>
-<td>CREATE TABLE Scene(id BIGINT PRIMARY KEY, biome VARCHAR NOT NULL, city VARCHAR NOT NULL, visitors BIGINT, created_at TIMESTAMP DEFAULT(datetime('now')));</td>
+<td>CREATE TABLE scene(id INTEGER PRIMARY KEY, biome VARCHAR NOT NULL, city VARCHAR NOT NULL, visitors INTEGER, created_at TIMESTAMP DEFAULT(current_date()), CHECK((visitors &gt;= 0)));</td>
 </tr>
 </tbody>
 </table>
@@ -720,10 +713,10 @@ <h4 data-number="20.4.1.3" class="anchored" data-anchor-id="uniqueness-with-dist
 </thead>
 <tbody>
 <tr class="odd">
-<td>2011</td>
+<td>2010</td>
 </tr>
 <tr class="even">
-<td>2010</td>
+<td>2011</td>
 </tr>
 <tr class="odd">
 <td>2019</td>
@@ -1204,13 +1197,13 @@ <h2 data-number="20.5" class="anchored" data-anchor-id="aggregating-with-group-b
 </thead>
 <tbody>
 <tr class="odd">
-<td>entree</td>
-<td>30</td>
-</tr>
-<tr class="even">
 <td>appetizer</td>
 <td>12</td>
 </tr>
+<tr class="even">
+<td>entree</td>
+<td>30</td>
+</tr>
 <tr class="odd">
 <td>dessert</td>
 <td>5</td>
@@ -1259,17 +1252,17 @@ <h2 data-number="20.5" class="anchored" data-anchor-id="aggregating-with-group-b
 <td>taco</td>
 </tr>
 <tr class="even">
-<td>appetizer</td>
-<td>12</td>
-<td>4</td>
-<td>potsticker</td>
-</tr>
-<tr class="odd">
 <td>dessert</td>
 <td>5</td>
 <td>5</td>
 <td>ice cream</td>
 </tr>
+<tr class="odd">
+<td>appetizer</td>
+<td>12</td>
+<td>4</td>
+<td>potsticker</td>
+</tr>
 </tbody>
 </table>
 
@@ -1295,11 +1288,11 @@ <h2 data-number="20.5" class="anchored" data-anchor-id="aggregating-with-group-b
 </thead>
 <tbody>
 <tr class="odd">
-<td>2011</td>
+<td>2010</td>
 <td>2</td>
 </tr>
 <tr class="even">
-<td>2010</td>
+<td>2011</td>
 <td>2</td>
 </tr>
 <tr class="odd">
@@ -1331,13 +1324,13 @@ <h2 data-number="20.5" class="anchored" data-anchor-id="aggregating-with-group-b
 </thead>
 <tbody>
 <tr class="odd">
-<td>2011</td>
-<td>1</td>
-</tr>
-<tr class="even">
 <td>2010</td>
 <td>2</td>
 </tr>
+<tr class="even">
+<td>2011</td>
+<td>1</td>
+</tr>
 <tr class="odd">
 <td>2019</td>
 <td>1</td>
@@ -1728,7 +1721,7 @@ <h2 data-number="20.6" class="anchored" data-anchor-id="summary"><span class="he
 <span id="cb32-56"><a href="#cb32-56" aria-hidden="true" tabindex="-1"></a></span>
 <span id="cb32-57"><a href="#cb32-57" aria-hidden="true" tabindex="-1"></a>The syntax below will seem unfamiliar to you; for now, just focus on understanding the output displayed. We will clarify the SQL code in a bit.</span>
 <span id="cb32-58"><a href="#cb32-58" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb32-59"><a href="#cb32-59" aria-hidden="true" tabindex="-1"></a>To start, we'll look at a database called <span class="in">`basic_examples.db`</span> and connect to it using SQLite.</span>
+<span id="cb32-59"><a href="#cb32-59" aria-hidden="true" tabindex="-1"></a>To start, we'll look at a database called <span class="in">`example_duck.db`</span> and connect to it using SQLite.</span>
 <span id="cb32-60"><a href="#cb32-60" aria-hidden="true" tabindex="-1"></a></span>
 <span id="cb32-63"><a href="#cb32-63" aria-hidden="true" tabindex="-1"></a><span class="in">```{python}</span></span>
 <span id="cb32-64"><a href="#cb32-64" aria-hidden="true" tabindex="-1"></a><span class="co">#| code-fold: true</span></span>
@@ -1747,7 +1740,7 @@ <h2 data-number="20.6" class="anchored" data-anchor-id="summary"><span class="he
 <span id="cb32-81"><a href="#cb32-81" aria-hidden="true" tabindex="-1"></a><span class="in">```{python}</span></span>
 <span id="cb32-82"><a href="#cb32-82" aria-hidden="true" tabindex="-1"></a><span class="co">#| vscode: {languageId: python}</span></span>
 <span id="cb32-83"><a href="#cb32-83" aria-hidden="true" tabindex="-1"></a><span class="co"># Connect to the database</span></span>
-<span id="cb32-84"><a href="#cb32-84" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>sql duckdb:<span class="op">///</span>data<span class="op">/</span>basic_examples.db <span class="op">--</span>alias duck</span>
+<span id="cb32-84"><a href="#cb32-84" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>sql duckdb:<span class="op">///</span>data<span class="op">/</span>example_duck.db <span class="op">--</span>alias duck</span>
 <span id="cb32-85"><a href="#cb32-85" aria-hidden="true" tabindex="-1"></a><span class="in">```</span></span>
 <span id="cb32-86"><a href="#cb32-86" aria-hidden="true" tabindex="-1"></a></span>
 <span id="cb32-87"><a href="#cb32-87" aria-hidden="true" tabindex="-1"></a>Now that we’re connected, let’s make some queries!</span>

index.log

@@ -1,4 +1,4 @@
-This is XeTeX, Version 3.141592653-2.6-0.999995 (TeX Live 2023) (preloaded format=xelatex 2024.3.3)  2 APR 2024 17:00
+This is XeTeX, Version 3.141592653-2.6-0.999995 (TeX Live 2023) (preloaded format=xelatex 2024.3.3)  2 APR 2024 22:01
 entering extended mode
  restricted \write18 enabled.
  %&-line parsing enabled.