added small feature to PCA slides

doc/pub/DimRed/html/._DimRed-bs007.html

@@ -182,6 +182,11 @@ correlation_matrix <span style="color: #666666">=</span> cancerpd<span style="co
 <span style="color: #408080; font-style: italic"># annot = True to print the values inside the square</span>
 sns<span style="color: #666666">.</span>heatmap(data<span style="color: #666666">=</span>correlation_matrix, annot<span style="color: #666666">=</span><span style="color: #008000">True</span>)
 plt<span style="color: #666666">.</span>show()
+
+<span style="color: #408080; font-style: italic">#print eigvalues of correlation matrix</span>
+EigValues, EigVectors <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>eig(correlation_matrix)
+<span style="color: #008000; font-weight: bold">print</span>(EigValues)
+
 <span style="color: #408080; font-style: italic">#split into train and test and then scale thereafter</span>
 X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(cancer<span style="color: #666666">.</span>data,cancer<span style="color: #666666">.</span>target,random_state<span style="color: #666666">=0</span>)
 <span style="color: #008000; font-weight: bold">print</span>(X_train<span style="color: #666666">.</span>shape)

doc/pub/DimRed/html/DimRed-reveal.html

@@ -459,6 +459,11 @@ correlation_matrix = cancerpd.corr().round(<span style="color: #B452CD">1</span>
 <span style="color: #228B22"># annot = True to print the values inside the square</span>
 sns.heatmap(data=correlation_matrix, annot=<span style="color: #658b00">True</span>)
 plt.show()
+
+<span style="color: #228B22">#print eigvalues of correlation matrix</span>
+EigValues, EigVectors = np.linalg.eig(correlation_matrix)
+<span style="color: #8B008B; font-weight: bold">print</span>(EigValues)
+
 <span style="color: #228B22">#split into train and test and then scale thereafter</span>
 X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=<span style="color: #B452CD">0</span>)
 <span style="color: #8B008B; font-weight: bold">print</span>(X_train.shape)

doc/pub/DimRed/html/DimRed-solarized.html

@@ -442,6 +442,11 @@ correlation_matrix = cancerpd.corr().round(<span style="color: #B452CD">1</span>
 <span style="color: #228B22"># annot = True to print the values inside the square</span>
 sns.heatmap(data=correlation_matrix, annot=<span style="color: #658b00">True</span>)
 plt.show()
+
+<span style="color: #228B22">#print eigvalues of correlation matrix</span>
+EigValues, EigVectors = np.linalg.eig(correlation_matrix)
+<span style="color: #8B008B; font-weight: bold">print</span>(EigValues)
+
 <span style="color: #228B22">#split into train and test and then scale thereafter</span>
 X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=<span style="color: #B452CD">0</span>)
 <span style="color: #8B008B; font-weight: bold">print</span>(X_train.shape)

doc/pub/DimRed/html/DimRed.html

@@ -447,6 +447,11 @@ correlation_matrix <span style="color: #666666">=</span> cancerpd<span style="co
 <span style="color: #408080; font-style: italic"># annot = True to print the values inside the square</span>
 sns<span style="color: #666666">.</span>heatmap(data<span style="color: #666666">=</span>correlation_matrix, annot<span style="color: #666666">=</span><span style="color: #008000">True</span>)
 plt<span style="color: #666666">.</span>show()
+
+<span style="color: #408080; font-style: italic">#print eigvalues of correlation matrix</span>
+EigValues, EigVectors <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>eig(correlation_matrix)
+<span style="color: #008000; font-weight: bold">print</span>(EigValues)
+
 <span style="color: #408080; font-style: italic">#split into train and test and then scale thereafter</span>
 X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(cancer<span style="color: #666666">.</span>data,cancer<span style="color: #666666">.</span>target,random_state<span style="color: #666666">=0</span>)
 <span style="color: #008000; font-weight: bold">print</span>(X_train<span style="color: #666666">.</span>shape)

doc/pub/DimRed/ipynb/DimRed.ipynb

@@ -330,6 +330,11 @@
     "# annot = True to print the values inside the square\n",
     "sns.heatmap(data=correlation_matrix, annot=True)\n",
     "plt.show()\n",
+    "\n",
+    "#print eigvalues of correlation matrix\n",
+    "EigValues, EigVectors = np.linalg.eig(correlation_matrix)\n",
+    "print(EigValues)\n",
+    "\n",
     "#split into train and test and then scale thereafter\n",
     "X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)\n",
     "print(X_train.shape)\n",

doc/src/DimRed/DimRed.do.txt

@@ -287,6 +287,11 @@ correlation_matrix = cancerpd.corr().round(1)
 # annot = True to print the values inside the square
 sns.heatmap(data=correlation_matrix, annot=True)
 plt.show()
+
+#print eigvalues of correlation matrix
+EigValues, EigVectors = np.linalg.eig(correlation_matrix)
+print(EigValues)
+
 #split into train and test and then scale thereafter
 X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)
 print(X_train.shape)

doc/src/DimRed/PCAcancer.py

@@ -8,22 +8,6 @@ import pandas as pd
 
 cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)
 
-fig, axes = plt.subplots(15,2,figsize=(10,20))
-malignant = cancer.data[cancer.target == 0]
-benign = cancer.data[cancer.target == 1]
-ax = axes.ravel()
-
-for i in range(30):
-    _, bins = np.histogram(cancer.data[:,i], bins =50)
-    ax[i].hist(malignant[:,i], bins = bins, alpha = 0.5)
-    ax[i].hist(benign[:,i], bins = bins, alpha = 0.5)
-    ax[i].set_title(cancer.feature_names[i])
-    ax[i].set_yticks(())
-ax[0].set_xlabel("Feature magnitude")
-ax[0].set_ylabel("Frequency")
-ax[0].legend(["Malignant", "Benign"], loc ="best")
-fig.tight_layout()
-plt.show()
 
 import seaborn as sns
 correlation_matrix = cancerpd.corr().round(1)
@@ -31,6 +15,9 @@ correlation_matrix = cancerpd.corr().round(1)
 # annot = True to print the values inside the square
 sns.heatmap(data=correlation_matrix, annot=True)
 plt.show()
+EigValues, EigVectors = np.linalg.eig(correlation_matrix)
+print(EigValues)
+
 X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)
 print(X_train.shape)
 print(X_test.shape)