corrected typos

doc/LectureNotes/_build/html/_sources/exercisesweek43.ipynb

@@ -32,15 +32,15 @@
     "editable": true
    },
    "source": [
-    "# Overarching aims of the exercises weeks 43 and 44\n",
+    "# Overarching aims of the exercises for week 43\n",
     "\n",
     "The aim of the exercises this week is to gain some confidence with\n",
     "ways to visualize the results of a classification problem.  We will\n",
     "target three ways of setting up the analysis. The first and simplest\n",
     "one is the\n",
-    "1. so-called confusion matrix, and the next is the\n",
+    "1. so-called confusion matrix. The next one is the so-called\n",
     "\n",
-    "2. ROC curve and finally the\n",
+    "2. ROC curve. Finally we have the\n",
     "\n",
     "3. Cumulative gain curve.\n",
     "\n",
@@ -446,7 +446,10 @@
    "id": "be9ff0b9",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -518,7 +521,10 @@
    "id": "d20bb8be",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -547,7 +553,10 @@
    "id": "d271f0ba",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -589,7 +598,10 @@
    "id": "3b045d56",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -611,7 +623,25 @@
    ]
   }
  ],
- "metadata": {},
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 5
 }

doc/LectureNotes/_build/html/exercisesweek43.html

@@ -414,7 +414,7 @@ document.write(`
             <nav aria-label="Page">
                 <ul class="visible nav section-nav flex-column">
 <li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Exercises week 43</a></li>
-<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#overarching-aims-of-the-exercises-weeks-43-and-44">Overarching aims of the exercises weeks 43 and 44</a><ul class="visible nav section-nav flex-column">
+<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#overarching-aims-of-the-exercises-for-week-43">Overarching aims of the exercises for week 43</a><ul class="visible nav section-nav flex-column">
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#confusion-matrix">Confusion Matrix</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#roc-curve">ROC Curve</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cumulative-gain">Cumulative Gain</a></li>
@@ -446,15 +446,15 @@ doconce format html exercisesweek43.do.txt  -->
 <p><strong>October 20-24, 2025</strong></p>
 <p>Date: <strong>Deadline Friday October 24 at midnight</strong></p>
 </section>
-<section class="tex2jax_ignore mathjax_ignore" id="overarching-aims-of-the-exercises-weeks-43-and-44">
-<h1>Overarching aims of the exercises weeks 43 and 44<a class="headerlink" href="#overarching-aims-of-the-exercises-weeks-43-and-44" title="Link to this heading">#</a></h1>
+<section class="tex2jax_ignore mathjax_ignore" id="overarching-aims-of-the-exercises-for-week-43">
+<h1>Overarching aims of the exercises for week 43<a class="headerlink" href="#overarching-aims-of-the-exercises-for-week-43" title="Link to this heading">#</a></h1>
 <p>The aim of the exercises this week is to gain some confidence with
 ways to visualize the results of a classification problem.  We will
 target three ways of setting up the analysis. The first and simplest
 one is the</p>
 <ol class="arabic simple">
-<li><p>so-called confusion matrix, and the next is the</p></li>
-<li><p>ROC curve and finally the</p></li>
+<li><p>so-called confusion matrix. The next one is the so-called</p></li>
+<li><p>ROC curve. Finally we have the</p></li>
 <li><p>Cumulative gain curve.</p></li>
 </ol>
 <p>We will use Logistic Regression as method for the classification in
@@ -615,41 +615,41 @@ At the end it sets up the confusion matrix and the ROC and cumulative gain curve
 Feel free to use these functionalities (we don’t expect you to write your own code for say the confusion matrix).</p>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-none notranslate"><div class="highlight"><pre><span></span>%matplotlib inline
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="o">%</span><span class="k">matplotlib</span> inline
 
-import matplotlib.pyplot as plt
-import numpy as np
-from sklearn.model_selection import  train_test_split 
-# from sklearn.datasets import fill in the data set
-from sklearn.linear_model import LogisticRegression
+<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
+<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
+<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span>  <span class="n">train_test_split</span> 
+<span class="c1"># from sklearn.datasets import fill in the data set</span>
+<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
 
-# Load the data, fill inn
-mydata.data = ?
+<span class="c1"># Load the data, fill inn</span>
+<span class="n">mydata</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="o">?</span>
 
-X_train, X_test, y_train, y_test = train_test_split(mydata.data,cancer.target,random_state=0)
-print(X_train.shape)
-print(X_test.shape)
-# Logistic Regression
-# define which type of problem, binary or multiclass
-logreg = LogisticRegression(solver=&#39;lbfgs&#39;)
-logreg.fit(X_train, y_train)
+<span class="n">X_train</span><span class="p">,</span> <span class="n">X_test</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">y_test</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">mydata</span><span class="o">.</span><span class="n">data</span><span class="p">,</span><span class="n">cancer</span><span class="o">.</span><span class="n">target</span><span class="p">,</span><span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">X_test</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
+<span class="c1"># Logistic Regression</span>
+<span class="c1"># define which type of problem, binary or multiclass</span>
+<span class="n">logreg</span> <span class="o">=</span> <span class="n">LogisticRegression</span><span class="p">(</span><span class="n">solver</span><span class="o">=</span><span class="s1">&#39;lbfgs&#39;</span><span class="p">)</span>
+<span class="n">logreg</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">)</span>
 
-from sklearn.preprocessing import LabelEncoder
-from sklearn.model_selection import cross_validate
-#Cross validation
-accuracy = cross_validate(logreg,X_test,y_test,cv=10)[&#39;test_score&#39;]
-print(accuracy)
-print(&quot;Test set accuracy with Logistic Regression: {:.2f}&quot;.format(logreg.score(X_test,y_test)))
+<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">LabelEncoder</span>
+<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">cross_validate</span>
+<span class="c1">#Cross validation</span>
+<span class="n">accuracy</span> <span class="o">=</span> <span class="n">cross_validate</span><span class="p">(</span><span class="n">logreg</span><span class="p">,</span><span class="n">X_test</span><span class="p">,</span><span class="n">y_test</span><span class="p">,</span><span class="n">cv</span><span class="o">=</span><span class="mi">10</span><span class="p">)[</span><span class="s1">&#39;test_score&#39;</span><span class="p">]</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">accuracy</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Test set accuracy with Logistic Regression: </span><span class="si">{:.2f}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">logreg</span><span class="o">.</span><span class="n">score</span><span class="p">(</span><span class="n">X_test</span><span class="p">,</span><span class="n">y_test</span><span class="p">)))</span>
 
-import scikitplot as skplt
-y_pred = logreg.predict(X_test)
-skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
-plt.show()
-y_probas = logreg.predict_proba(X_test)
-skplt.metrics.plot_roc(y_test, y_probas)
-plt.show()
-skplt.metrics.plot_cumulative_gain(y_test, y_probas)
-plt.show()
+<span class="kn">import</span> <span class="nn">scikitplot</span> <span class="k">as</span> <span class="nn">skplt</span>
+<span class="n">y_pred</span> <span class="o">=</span> <span class="n">logreg</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
+<span class="n">skplt</span><span class="o">.</span><span class="n">metrics</span><span class="o">.</span><span class="n">plot_confusion_matrix</span><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">y_pred</span><span class="p">,</span> <span class="n">normalize</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
+<span class="n">y_probas</span> <span class="o">=</span> <span class="n">logreg</span><span class="o">.</span><span class="n">predict_proba</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
+<span class="n">skplt</span><span class="o">.</span><span class="n">metrics</span><span class="o">.</span><span class="n">plot_roc</span><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">y_probas</span><span class="p">)</span>
+<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
+<span class="n">skplt</span><span class="o">.</span><span class="n">metrics</span><span class="o">.</span><span class="n">plot_cumulative_gain</span><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">y_probas</span><span class="p">)</span>
+<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
 </div>
@@ -664,9 +664,9 @@ plt.show()
 the MNIST data set and just specialize to two numbers. To do so you can use the following code lines</p>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-none notranslate"><div class="highlight"><pre><span></span>from sklearn.datasets import load_digits
-digits = load_digits(n_class=2) # Load only two classes, e.g., 0 and 1
-X, y = digits.data, digits.target
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">load_digits</span>
+<span class="n">digits</span> <span class="o">=</span> <span class="n">load_digits</span><span class="p">(</span><span class="n">n_class</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> <span class="c1"># Load only two classes, e.g., 0 and 1</span>
+<span class="n">X</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">digits</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">digits</span><span class="o">.</span><span class="n">target</span>
 </pre></div>
 </div>
 </div>
@@ -678,8 +678,8 @@ n_classes=2. You can also control the number of samples, features,
 informative features, redundant features, and more.</p>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-none notranslate"><div class="highlight"><pre><span></span>from sklearn.datasets import make_classification
-X, y = make_classification(n_samples=1000, n_features=20, n_informative=10, n_redundant=5, n_classes=2, random_state=42)
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">make_classification</span>
+<span class="n">X</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">make_classification</span><span class="p">(</span><span class="n">n_samples</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">n_features</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">n_informative</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">n_redundant</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">n_classes</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">42</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
@@ -696,10 +696,10 @@ the exercises from weeks 41 and 42. This is a three-class data set and
 you can set it up using <strong>scikit-learn</strong>,</p>
 <div class="cell docutils container">
 <div class="cell_input docutils container">
-<div class="highlight-none notranslate"><div class="highlight"><pre><span></span>from sklearn.datasets import load_iris
-iris = load_iris()
-X = iris.data  # Features
-y = iris.target # Target labels
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">load_iris</span>
+<span class="n">iris</span> <span class="o">=</span> <span class="n">load_iris</span><span class="p">()</span>
+<span class="n">X</span> <span class="o">=</span> <span class="n">iris</span><span class="o">.</span><span class="n">data</span>  <span class="c1"># Features</span>
+<span class="n">y</span> <span class="o">=</span> <span class="n">iris</span><span class="o">.</span><span class="n">target</span> <span class="c1"># Target labels</span>
 </pre></div>
 </div>
 </div>
@@ -775,7 +775,7 @@ gain curve for this (or other) multiclass data set.</p>
   <nav class="bd-toc-nav page-toc">
     <ul class="visible nav section-nav flex-column">
 <li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Exercises week 43</a></li>
-<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#overarching-aims-of-the-exercises-weeks-43-and-44">Overarching aims of the exercises weeks 43 and 44</a><ul class="visible nav section-nav flex-column">
+<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#overarching-aims-of-the-exercises-for-week-43">Overarching aims of the exercises for week 43</a><ul class="visible nav section-nav flex-column">
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#confusion-matrix">Confusion Matrix</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#roc-curve">ROC Curve</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cumulative-gain">Cumulative Gain</a></li>

doc/LectureNotes/_build/jupyter_execute/exercisesweek43.ipynb

@@ -32,15 +32,15 @@
     "editable": true
    },
    "source": [
-    "# Overarching aims of the exercises weeks 43 and 44\n",
+    "# Overarching aims of the exercises for week 43\n",
     "\n",
     "The aim of the exercises this week is to gain some confidence with\n",
     "ways to visualize the results of a classification problem.  We will\n",
     "target three ways of setting up the analysis. The first and simplest\n",
     "one is the\n",
-    "1. so-called confusion matrix, and the next is the\n",
+    "1. so-called confusion matrix. The next one is the so-called\n",
     "\n",
-    "2. ROC curve and finally the\n",
+    "2. ROC curve. Finally we have the\n",
     "\n",
     "3. Cumulative gain curve.\n",
     "\n",
@@ -446,7 +446,10 @@
    "id": "be9ff0b9",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -518,7 +521,10 @@
    "id": "d20bb8be",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -547,7 +553,10 @@
    "id": "d271f0ba",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -589,7 +598,10 @@
    "id": "3b045d56",
    "metadata": {
     "collapsed": false,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -611,7 +623,25 @@
    ]
   }
  ],
- "metadata": {},
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 5
 }