DOC improve svm sample weight example

examples/svm/plot_weighted_samples.py

@@ -5,34 +5,56 @@ SVM: Weighted samples
 
 Plot decision function of a weighted dataset, where the size of points
 is proportional to its weight.
+
+The sample weighting rescales the C parameter, which means that the classifier
+puts more emphasis on getting these points right. The effect might often be
+subtle.
 """
 print(__doc__)
 
 import numpy as np
-import pylab as pl
+import matplotlib.pyplot as plt
 from sklearn import svm
 
+
+def plot_decision_function(classifier, sample_weight, axis, title):
+    # plot the decision function
+    xx, yy = np.meshgrid(np.linspace(-4, 5, 500), np.linspace(-4, 5, 500))
+
+    Z = classifier.decision_function(np.c_[xx.ravel(), yy.ravel()])
+    Z = Z.reshape(xx.shape)
+
+    # plot the line, the points, and the nearest vectors to the plane
+    axis.contourf(xx, yy, Z, alpha=0.75, cmap=plt.cm.bone)
+    axis.scatter(X[:, 0], X[:, 1], c=Y, s=100 * sample_weight, alpha=0.9,
+                 cmap=plt.cm.bone)
+
+    axis.axis('off')
+    axis.set_title(title)
+
+
 # we create 20 points
 np.random.seed(0)
 X = np.r_[np.random.randn(10, 2) + [1, 1], np.random.randn(10, 2)]
 Y = [1] * 10 + [-1] * 10
-sample_weight = 100 * np.abs(np.random.randn(20))
-# and assign a bigger weight to the last 10 samples
-sample_weight[:10] *= 10
+sample_weight_last_ten = abs(np.random.randn(len(X)))
+sample_weight_constant = np.ones(len(X))
+# and assign a bigger weight to the last 5 samples
+sample_weight_last_ten[15:] *= 5
 
-# # fit the model
-clf = svm.SVC()
-clf.fit(X, Y, sample_weight=sample_weight)
+# for reference, first fit without class weights
 
-# plot the decision function
-xx, yy = np.meshgrid(np.linspace(-4, 5, 500), np.linspace(-4, 5, 500))
+# fit the model
+clf_weights = svm.SVC()
+clf_weights.fit(X, Y, sample_weight=sample_weight_last_ten)
 
-Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
-Z = Z.reshape(xx.shape)
+clf_no_weights = svm.SVC()
+clf_no_weights.fit(X, Y)
 
-# plot the line, the points, and the nearest vectors to the plane
-pl.contourf(xx, yy, Z, alpha=0.75, cmap=pl.cm.bone)
-pl.scatter(X[:, 0], X[:, 1], c=Y, s=sample_weight, alpha=0.9, cmap=pl.cm.bone)
+fig, axes = plt.subplots(1, 2, figsize=(14, 6))
+plot_decision_function(clf_no_weights, sample_weight_constant, axes[0],
+                       "Constant weights")
+plot_decision_function(clf_weights, sample_weight_last_ten, axes[1],
+                       "Modified weights")
 
-pl.axis('off')
-pl.show()
+plt.show()