publish note 11

DS-100 · Oct 3, 2024 · a37f8a5 · a37f8a5
1 parent 4660fc0
commit a37f8a5
Show file tree

Hide file tree

Showing 99 changed files with 3,660 additions and 603 deletions.
diff --git a/_quarto.yml b/_quarto.yml
@@ -26,7 +26,7 @@ book:
         - visualization_2/visualization_2.qmd
         - sampling/sampling.qmd
         - intro_to_modeling/intro_to_modeling.qmd
-        # - constant_model_loss_transformations/loss_transformations.qmd
+        - constant_model_loss_transformations/loss_transformations.qmd
         # - ols/ols.qmd
         # - gradient_descent/gradient_descent.qmd
         # - feature_engineering/feature_engineering.qmd

diff --git a/constant_model_loss_transformations/loss_transformations.qmd b/constant_model_loss_transformations/loss_transformations.qmd
diff --git a/docs/constant_model_loss_transformations/images/bulge.png b/docs/constant_model_loss_transformations/images/bulge.png
diff --git a/docs/constant_model_loss_transformations/images/constant_loss_surface.png b/docs/constant_model_loss_transformations/images/constant_loss_surface.png
diff --git a/docs/constant_model_loss_transformations/images/dugong_rug.png b/docs/constant_model_loss_transformations/images/dugong_rug.png
diff --git a/docs/constant_model_loss_transformations/images/dugong_scatter.png b/docs/constant_model_loss_transformations/images/dugong_scatter.png
diff --git a/docs/constant_model_loss_transformations/images/error.png b/docs/constant_model_loss_transformations/images/error.png
diff --git a/docs/constant_model_loss_transformations/images/mae_loss_infinite.png b/docs/constant_model_loss_transformations/images/mae_loss_infinite.png
diff --git a/docs/constant_model_loss_transformations/images/mse_loss_26.png b/docs/constant_model_loss_transformations/images/mse_loss_26.png
diff --git a/docs/constant_model_loss_transformations/images/outliers.png b/docs/constant_model_loss_transformations/images/outliers.png
diff --git a/docs/constant_model_loss_transformations/images/slr_loss_surface.png b/docs/constant_model_loss_transformations/images/slr_loss_surface.png
diff --git a/docs/constant_model_loss_transformations/images/slr_modeling.png b/docs/constant_model_loss_transformations/images/slr_modeling.png
diff --git a/docs/constant_model_loss_transformations/loss_transformations.html b/docs/constant_model_loss_transformations/loss_transformations.html
diff --git a/...oss_transformations/loss_transformations_files/figure-html/cell-13-output-1.png b/...oss_transformations/loss_transformations_files/figure-html/cell-13-output-1.png
diff --git a/...oss_transformations/loss_transformations_files/figure-html/cell-14-output-1.png b/...oss_transformations/loss_transformations_files/figure-html/cell-14-output-1.png
diff --git a/...oss_transformations/loss_transformations_files/figure-html/cell-15-output-1.png b/...oss_transformations/loss_transformations_files/figure-html/cell-15-output-1.png
diff --git a/...loss_transformations/loss_transformations_files/figure-html/cell-4-output-1.png b/...loss_transformations/loss_transformations_files/figure-html/cell-4-output-1.png
diff --git a/...loss_transformations/loss_transformations_files/figure-html/cell-5-output-1.png b/...loss_transformations/loss_transformations_files/figure-html/cell-5-output-1.png
diff --git a/...loss_transformations/loss_transformations_files/figure-html/cell-7-output-2.png b/...loss_transformations/loss_transformations_files/figure-html/cell-7-output-2.png
diff --git a/...loss_transformations/loss_transformations_files/figure-html/cell-8-output-1.png b/...loss_transformations/loss_transformations_files/figure-html/cell-8-output-1.png
diff --git a/...ant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-13-output-1.pdf b/...ant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-13-output-1.pdf
diff --git a/...ant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-14-output-1.pdf b/...ant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-14-output-1.pdf
diff --git a/...ant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-15-output-1.pdf b/...ant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-15-output-1.pdf
diff --git a/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-4-output-1.pdf b/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-4-output-1.pdf
diff --git a/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-5-output-1.pdf b/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-5-output-1.pdf
diff --git a/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-7-output-2.pdf b/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-7-output-2.pdf
diff --git a/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-8-output-1.pdf b/...tant_model_loss_transformations/loss_transformations_files/figure-pdf/cell-8-output-1.pdf
diff --git a/docs/eda/eda.html b/docs/eda/eda.html
diff --git a/docs/eda/eda_files/figure-pdf/cell-62-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-62-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-67-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-67-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-68-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-68-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-69-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-69-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-71-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-71-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-75-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-75-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-76-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-76-output-1.pdf
diff --git a/docs/eda/eda_files/figure-pdf/cell-77-output-1.pdf b/docs/eda/eda_files/figure-pdf/cell-77-output-1.pdf
diff --git a/docs/index.html b/docs/index.html
@@ -188,6 +188,12 @@
   <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>
     </ul>
     </div>

diff --git a/docs/intro_lec/introduction.html b/docs/intro_lec/introduction.html
@@ -177,6 +177,12 @@
   <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>
     </ul>
     </div>

diff --git a/docs/intro_to_modeling/intro_to_modeling.html b/docs/intro_to_modeling/intro_to_modeling.html
@@ -64,6 +64,7 @@
 <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="../constant_model_loss_transformations/loss_transformations.html" rel="next">
 <link href="../sampling/sampling.html" rel="prev">
 <link href="../data100_logo.png" rel="icon" type="image/png">
 <script src="../site_libs/quarto-html/quarto.js"></script>
@@ -239,6 +240,12 @@
   <a href="../intro_to_modeling/intro_to_modeling.html" class="sidebar-item-text sidebar-link active">
  <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>
     </ul>
     </div>
@@ -387,7 +394,7 @@ <h2 data-number="10.2" class="anchored" data-anchor-id="simple-linear-regression
 <li><span class="math inline">\(\text{regression estimate} = y\text{-intercept} + \text{slope}\cdot\text{}x\)</span></li>
 <li><span class="math inline">\(\text{residual} =\text{observed }y - \text{regression estimate}\)</span></li>
 </ul>
-<div id="2342e5b1" class="cell" data-execution_count="1">
+<div id="50d969cc" 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="im">import</span> pandas <span class="im">as</span> pd</span>
@@ -434,7 +441,7 @@ <h4 data-number="10.2.1.2" class="anchored" data-anchor-id="correlation"><span c
 <li>Correlations range between -1 and 1: <span class="math inline">\(|r| \leq 1\)</span>, with <span class="math inline">\(r=1\)</span> indicating perfect positive linear association, and <span class="math inline">\(r=-1\)</span> indicating perfect negative association. The closer <span class="math inline">\(r\)</span> is to <span class="math inline">\(0\)</span>, the weaker the linear association is.</li>
 <li>Correlation says nothing about causation and non-linear association. Correlation does <strong>not</strong> imply causation. When <span class="math inline">\(r = 0\)</span>, the two variables are uncorrelated. However, they could still be related through some non-linear relationship.</li>
 </ol>
-<div id="f07efd37" class="cell" data-execution_count="2">
+<div id="6ce48d20" class="cell" data-execution_count="2">
 <details class="code-fold">
 <summary>Code</summary>
 <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="kw">def</span> plot_and_get_corr(ax, x, y, title):</span>
@@ -658,7 +665,7 @@ <h2 data-number="10.7" class="anchored" data-anchor-id="evaluating-the-slr-model
 <section id="four-mysterious-datasets-anscombes-quartet" class="level3" data-number="10.7.1">
 <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datasets-anscombes-quartet"><span class="header-section-number">10.7.1</span> Four Mysterious Datasets (Anscombe’s quartet)</h3>
 <p>Let’s take a look at four different datasets.</p>
-<div id="dc45719f" class="cell" data-execution_count="3">
+<div id="77c429ab" class="cell" data-execution_count="3">
 <details class="code-fold">
 <summary>Code</summary>
 <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="im">import</span> numpy <span class="im">as</span> np</span>
@@ -670,7 +677,7 @@ <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datase
 <span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> mpl_toolkits.mplot3d <span class="im">import</span> Axes3D</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="a29af7cd" class="cell" data-execution_count="4">
+<div id="dcfbe15a" class="cell" data-execution_count="4">
 <details class="code-fold">
 <summary>Code</summary>
 <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"># Big font helper</span></span>
@@ -724,7 +731,7 @@ <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datase
 <span id="cb4-49"><a href="#cb4-49" aria-hidden="true" tabindex="-1"></a>plt.style.use(<span class="st">"default"</span>)  <span class="co"># Revert style to default mpl</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="40b40b77" class="cell" data-execution_count="5">
+<div id="858023dc" 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>plt.style.use(<span class="st">"default"</span>)  <span class="co"># Revert style to default mpl</span></span>
@@ -763,7 +770,7 @@ <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datase
 <span id="cb5-34"><a href="#cb5-34" aria-hidden="true" tabindex="-1"></a>    <span class="cf">return</span> fig</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </details>
 </div>
-<div id="eeae5630" class="cell" data-execution_count="6">
+<div id="2373151e" class="cell" data-execution_count="6">
 <details class="code-fold">
 <summary>Code</summary>
 <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"># Load in four different datasets: I, II, III, IV</span></span>
@@ -806,7 +813,7 @@ <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datase
 </div>
 </div>
 <p>While these four sets of datapoints look very different, they actually all have identical means <span class="math inline">\(\bar x\)</span>, <span class="math inline">\(\bar y\)</span>, standard deviations <span class="math inline">\(\sigma_x\)</span>, <span class="math inline">\(\sigma_y\)</span>, correlation <span class="math inline">\(r\)</span>, and RMSE! If we only look at these statistics, we would probably be inclined to say that these datasets are similar.</p>
-<div id="831b3b49" class="cell" data-execution_count="7">
+<div id="dc089a8b" class="cell" data-execution_count="7">
 <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="cf">for</span> dataset <span class="kw">in</span> [<span class="st">"I"</span>, <span class="st">"II"</span>, <span class="st">"III"</span>, <span class="st">"IV"</span>]:</span>
@@ -853,7 +860,7 @@ <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datase
 </div>
 <p>We may also wish to visualize the model’s <strong>residuals</strong>, defined as the difference between the observed and predicted <span class="math inline">\(y_i\)</span> value (<span class="math inline">\(e_i = y_i - \hat{y}_i\)</span>). This gives a high-level view of how “off” each prediction is from the true observed value. Recall that you explored this concept in <a href="https://inferentialthinking.com/chapters/15/5/Visual_Diagnostics.html?highlight=heteroscedasticity#detecting-heteroscedasticity">Data 8</a>: a good regression fit should display no clear pattern in its plot of residuals. The residual plots for Anscombe’s quartet are displayed below. Note how only the first plot shows no clear pattern to the magnitude of residuals. This is an indication that SLR is not the best choice of model for the remaining three sets of points.</p>
 <!-- <img src="images/residual.png" alt='residual' width='600'> -->
-<div id="2a6b1d76" class="cell" data-execution_count="8">
+<div id="9d85a518" class="cell" data-execution_count="8">
 <details class="code-fold">
 <summary>Code</summary>
 <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><span class="co"># Residual visualization</span></span>
@@ -1337,6 +1344,9 @@ <h3 data-number="10.7.1" class="anchored" data-anchor-id="four-mysterious-datase
       </a>          
   </div>
   <div class="nav-page nav-page-next">
+      <a href="../constant_model_loss_transformations/loss_transformations.html" class="pagination-link" aria-label="<span class='chapter-number'>11</span>&nbsp; <span class='chapter-title'>Constant Model, Loss, and Transformations</span>">
+        <span class="nav-page-text"><span class="chapter-number">11</span>&nbsp; <span class="chapter-title">Constant Model, Loss, and Transformations</span></span> <i class="bi bi-arrow-right-short"></i>
+      </a>
   </div>
 </nav><div class="modal fade" id="quarto-embedded-source-code-modal" tabindex="-1" aria-labelledby="quarto-embedded-source-code-modal-label" aria-hidden="true"><div class="modal-dialog modal-dialog-scrollable"><div class="modal-content"><div class="modal-header"><h5 class="modal-title" id="quarto-embedded-source-code-modal-label">Source Code</h5><button class="btn-close" data-bs-dismiss="modal"></button></div><div class="modal-body"><div class="">
 <div class="sourceCode" id="cb10" data-shortcodes="false"><pre class="sourceCode markdown code-with-copy"><code class="sourceCode markdown"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="co">---</span></span>

diff --git a/docs/intro_to_modeling/intro_to_modeling_files/figure-html/cell-2-output-1.png b/docs/intro_to_modeling/intro_to_modeling_files/figure-html/cell-2-output-1.png
diff --git a/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-2-output-1.pdf b/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-2-output-1.pdf
diff --git a/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-3-output-1.pdf b/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-3-output-1.pdf
diff --git a/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-7-output-1.pdf b/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-7-output-1.pdf
diff --git a/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-9-output-1.pdf b/docs/intro_to_modeling/intro_to_modeling_files/figure-pdf/cell-9-output-1.pdf