EXA plot_confusion_matrix example breaks down if not all classes present (scikit-learn#13126)

MLopez-Ibanez · jnothman · commit a1a29c2fa2cf · 2019-02-19T21:29:43.000+11:00
* fix scikit-learn#12700 plot_confusion_matrix example breaks down if not all classes are present in the test data * plot_confusion_matrix: update function call, fix style issues * remove redundant confusion_matrix call
diff --git a/examples/model_selection/plot_confusion_matrix.py b/examples/model_selection/plot_confusion_matrix.py
@@ -26,13 +26,13 @@
 
 print(__doc__)
 
-import itertools
 import numpy as np
 import matplotlib.pyplot as plt
 
 from sklearn import svm, datasets
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import confusion_matrix
+from sklearn.utils.multiclass import unique_labels
 
 # import some data to play with
 iris = datasets.load_iris()
@@ -49,14 +49,24 @@
 y_pred = classifier.fit(X_train, y_train).predict(X_test)
 
 
-def plot_confusion_matrix(cm, classes,
+def plot_confusion_matrix(y_true, y_pred, classes,
                           normalize=False,
-                          title='Confusion matrix',
+                          title=None,
                           cmap=plt.cm.Blues):
     """
     This function prints and plots the confusion matrix.
     Normalization can be applied by setting `normalize=True`.
     """
+    if not title:
+        if normalize:
+            title = 'Normalized confusion matrix'
+        else:
+            title = 'Confusion matrix, without normalization'
+
+    # Compute confusion matrix
+    cm = confusion_matrix(y_true, y_pred)
+    # Only use the labels that appear in the data
+    classes = classes[unique_labels(y_true, y_pred)]
     if normalize:
         cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
         print("Normalized confusion matrix")
@@ -65,37 +75,42 @@ def plot_confusion_matrix(cm, classes,
 
     print(cm)
 
-    plt.imshow(cm, interpolation='nearest', cmap=cmap)
-    plt.title(title)
-    plt.colorbar()
-    tick_marks = np.arange(len(classes))
-    plt.xticks(tick_marks, classes, rotation=45)
-    plt.yticks(tick_marks, classes)
-
+    fig, ax = plt.subplots()
+    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
+    ax.figure.colorbar(im, ax=ax)
+    # We want to show all ticks...
+    ax.set(xticks=np.arange(cm.shape[1]),
+           yticks=np.arange(cm.shape[0]),
+           # ... and label them with the respective list entries
+           xticklabels=classes, yticklabels=classes,
+           title=title,
+           ylabel='True label',
+           xlabel='Predicted label')
+
+    # Rotate the tick labels and set their alignment.
+    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
+             rotation_mode="anchor")
+
+    # Loop over data dimensions and create text annotations.
     fmt = '.2f' if normalize else 'd'
     thresh = cm.max() / 2.
-    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
-        plt.text(j, i, format(cm[i, j], fmt),
-                 horizontalalignment="center",
-                 color="white" if cm[i, j] > thresh else "black")
-
-    plt.ylabel('True label')
-    plt.xlabel('Predicted label')
-    plt.tight_layout()
+    for i in range(cm.shape[0]):
+        for j in range(cm.shape[1]):
+            ax.text(j, i, format(cm[i, j], fmt),
+                    ha="center", va="center",
+                    color="white" if cm[i, j] > thresh else "black")
+    fig.tight_layout()
+    return ax
 
 
-# Compute confusion matrix
-cnf_matrix = confusion_matrix(y_test, y_pred)
 np.set_printoptions(precision=2)
 
 # Plot non-normalized confusion matrix
-plt.figure()
-plot_confusion_matrix(cnf_matrix, classes=class_names,
+plot_confusion_matrix(y_test, y_pred, classes=class_names,
                       title='Confusion matrix, without normalization')
 
 # Plot normalized confusion matrix
-plt.figure()
-plot_confusion_matrix(cnf_matrix, classes=class_names, normalize=True,
+plot_confusion_matrix(y_test, y_pred, classes=class_names, normalize=True,
                       title='Normalized confusion matrix')
 
 plt.show()
