Pushing the docs to dev/ for branch: master, commit 3a724107bb9e31f223c18f79a521b1616bcb393a

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -24,26 +24,13 @@
 
 First example
 -------------
-The first example illustrates how robust covariance estimation can help
-concentrating on a relevant cluster when another one exists. Here, many
-observations are confounded into one and break down the empirical covariance
-estimation.
-Of course, some screening tools would have pointed out the presence of two
-clusters (Support Vector Machines, Gaussian Mixture Models, univariate
-outlier detection, ...). But had it been a high-dimensional example, none
-of these could be applied that easily.
-
-Second example
---------------
-The second example shows the ability of the Minimum Covariance Determinant
-robust estimator of covariance to concentrate on the main mode of the data
-distribution: the ___location seems to be well estimated, although the covariance
-is hard to estimate due to the banana-shaped distribution. Anyway, we can
-get rid of some outlying observations.
-The One-Class SVM is able to capture the real data structure, but the
-difficulty is to adjust its kernel bandwidth parameter so as to obtain
-a good compromise between the shape of the data scatter matrix and the
-risk of over-fitting the data.
+The first example illustrates how the Minimum Covariance Determinant
+robust estimator can help concentrate on a relevant cluster when outlying
+points exist. Here the empirical covariance estimation is skewed by points
+outside of the main cluster. Of course, some screening tools would have pointed
+out the presence of two clusters (Support Vector Machines, Gaussian Mixture
+Models, univariate outlier detection, ...). But had it been a high-dimensional
+example, none of these could be applied that easily.
 
 """
 print(__doc__)
@@ -56,68 +43,88 @@
 from sklearn.svm import OneClassSVM
 import matplotlib.pyplot as plt
 import matplotlib.font_manager
-from sklearn.datasets import load_boston
-
-# Get data
-X1 = load_boston()['data'][:, [8, 10]]  # two clusters
-X2 = load_boston()['data'][:, [5, 12]]  # "banana"-shaped
+from sklearn.datasets import load_wine
 
 # Define "classifiers" to be used
 classifiers = {
     "Empirical Covariance": EllipticEnvelope(support_fraction=1.,
-                                             contamination=0.261),
+                                             contamination=0.25),
     "Robust Covariance (Minimum Covariance Determinant)":
-    EllipticEnvelope(contamination=0.261),
-    "OCSVM": OneClassSVM(nu=0.261, gamma=0.05)}
+    EllipticEnvelope(contamination=0.25),
+    "OCSVM": OneClassSVM(nu=0.25, gamma=0.35)}
 colors = ['m', 'g', 'b']
 legend1 = {}
 legend2 = {}
 
+# Get data
+X1 = load_wine()['data'][:, [1, 2]]  # two clusters
+
 # Learn a frontier for outlier detection with several classifiers
-xx1, yy1 = np.meshgrid(np.linspace(-8, 28, 500), np.linspace(3, 40, 500))
-xx2, yy2 = np.meshgrid(np.linspace(3, 10, 500), np.linspace(-5, 45, 500))
+xx1, yy1 = np.meshgrid(np.linspace(0, 6, 500), np.linspace(1, 4.5, 500))
 for i, (clf_name, clf) in enumerate(classifiers.items()):
     plt.figure(1)
     clf.fit(X1)
     Z1 = clf.decision_function(np.c_[xx1.ravel(), yy1.ravel()])
     Z1 = Z1.reshape(xx1.shape)
     legend1[clf_name] = plt.contour(
         xx1, yy1, Z1, levels=[0], linewidths=2, colors=colors[i])
-    plt.figure(2)
-    clf.fit(X2)
-    Z2 = clf.decision_function(np.c_[xx2.ravel(), yy2.ravel()])
-    Z2 = Z2.reshape(xx2.shape)
-    legend2[clf_name] = plt.contour(
-        xx2, yy2, Z2, levels=[0], linewidths=2, colors=colors[i])
 
 legend1_values_list = list(legend1.values())
 legend1_keys_list = list(legend1.keys())
 
 # Plot the results (= shape of the data points cloud)
 plt.figure(1)  # two clusters
-plt.title("Outlier detection on a real data set (boston housing)")
+plt.title("Outlier detection on a real data set (wine recognition)")
 plt.scatter(X1[:, 0], X1[:, 1], color='black')
 bbox_args = dict(boxstyle="round", fc="0.8")
 arrow_args = dict(arrowstyle="->")
-plt.annotate("several confounded points", xy=(24, 19),
+plt.annotate("outlying points", xy=(4, 2),
              xycoords="data", textcoords="data",
-             xytext=(13, 10), bbox=bbox_args, arrowprops=arrow_args)
+             xytext=(3, 1.25), bbox=bbox_args, arrowprops=arrow_args)
 plt.xlim((xx1.min(), xx1.max()))
 plt.ylim((yy1.min(), yy1.max()))
 plt.legend((legend1_values_list[0].collections[0],
             legend1_values_list[1].collections[0],
             legend1_values_list[2].collections[0]),
            (legend1_keys_list[0], legend1_keys_list[1], legend1_keys_list[2]),
            loc="upper center",
-           prop=matplotlib.font_manager.FontProperties(size=12))
-plt.ylabel("accessibility to radial highways")
-plt.xlabel("pupil-teacher ratio by town")
+           prop=matplotlib.font_manager.FontProperties(size=11))
+plt.ylabel("ash")
+plt.xlabel("malic_acid")
+
+plt.show()
+
+##############################################################################
+# Second example
+# --------------
+# The second example shows the ability of the Minimum Covariance Determinant
+# robust estimator of covariance to concentrate on the main mode of the data
+# distribution: the ___location seems to be well estimated, although the
+# covariance is hard to estimate due to the banana-shaped distribution. Anyway,
+# we can get rid of some outlying observations. The One-Class SVM is able to
+# capture the real data structure, but the difficulty is to adjust its kernel
+# bandwidth parameter so as to obtain a good compromise between the shape of
+# the data scatter matrix and the risk of over-fitting the data.
+
+# Get data
+X2 = load_wine()['data'][:, [6, 9]]  # "banana"-shaped
+
+# Learn a frontier for outlier detection with several classifiers
+xx2, yy2 = np.meshgrid(np.linspace(-1, 5.5, 500), np.linspace(-2.5, 19, 500))
+for i, (clf_name, clf) in enumerate(classifiers.items()):
+    plt.figure(2)
+    clf.fit(X2)
+    Z2 = clf.decision_function(np.c_[xx2.ravel(), yy2.ravel()])
+    Z2 = Z2.reshape(xx2.shape)
+    legend2[clf_name] = plt.contour(
+        xx2, yy2, Z2, levels=[0], linewidths=2, colors=colors[i])
 
 legend2_values_list = list(legend2.values())
 legend2_keys_list = list(legend2.keys())
 
+# Plot the results (= shape of the data points cloud)
 plt.figure(2)  # "banana" shape
-plt.title("Outlier detection on a real data set (boston housing)")
+plt.title("Outlier detection on a real data set (wine recognition)")
 plt.scatter(X2[:, 0], X2[:, 1], color='black')
 plt.xlim((xx2.min(), xx2.max()))
 plt.ylim((yy2.min(), yy2.max()))
@@ -126,8 +133,8 @@
             legend2_values_list[2].collections[0]),
            (legend2_keys_list[0], legend2_keys_list[1], legend2_keys_list[2]),
            loc="upper center",
-           prop=matplotlib.font_manager.FontProperties(size=12))
-plt.ylabel("% lower status of the population")
-plt.xlabel("average number of rooms per dwelling")
+           prop=matplotlib.font_manager.FontProperties(size=11))
+plt.ylabel("color_intensity")
+plt.xlabel("flavanoids")
 
 plt.show()