Pushing the docs to 0.20/ for branch: 0.20.X, commit 8d8939bdc3ed91ef5a84aa73628cb776af0d986d

Author: sklearn-ci

0.20/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 7ec53ea0763238f487c61d94c6d77d05
+config: 8fb17fab1fef49a19957d9b86d458a0c
 tags: 645f666f9bcd5a90fca523b33c5a78b7

0.20/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Peter Prettenhofer <[email protected]>,\n#         Noel Dawe <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.metrics import zero_one_loss\nfrom sklearn.ensemble import AdaBoostClassifier\n\n\nn_estimators = 400\n# A learning rate of 1. may not be optimal for both SAMME and SAMME.R\nlearning_rate = 1.\n\nX, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)\n\nX_test, y_test = X[2000:], y[2000:]\nX_train, y_train = X[:2000], y[:2000]\n\ndt_stump = DecisionTreeClassifier(max_depth=1)\ndt_stump.fit(X_train, y_train)\ndt_stump_err = 1.0 - dt_stump.score(X_test, y_test)\n\ndt = DecisionTreeClassifier(max_depth=9)\ndt.fit(X_train, y_train)\ndt_err = 1.0 - dt.score(X_test, y_test)\n\nada_discrete = AdaBoostClassifier(\n    base_estimator=dt_stump,\n    learning_rate=learning_rate,\n    n_estimators=n_estimators,\n    algorithm=\"SAMME\")\nada_discrete.fit(X_train, y_train)\n\nada_real = AdaBoostClassifier(\n    base_estimator=dt_stump,\n    learning_rate=learning_rate,\n    n_estimators=n_estimators,\n    algorithm=\"SAMME.R\")\nada_real.fit(X_train, y_train)\n\nfig = plt.figure()\nax = fig.add_subplot(111)\n\nax.plot([1, n_estimators], [dt_stump_err] * 2, 'k-',\n        label='Decision Stump Error')\nax.plot([1, n_estimators], [dt_err] * 2, 'k--',\n        label='Decision Tree Error')\n\nada_discrete_err = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_discrete.staged_predict(X_test)):\n    ada_discrete_err[i] = zero_one_loss(y_pred, y_test)\n\nada_discrete_err_train = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_discrete.staged_predict(X_train)):\n    ada_discrete_err_train[i] = zero_one_loss(y_pred, y_train)\n\nada_real_err = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_real.staged_predict(X_test)):\n    ada_real_err[i] = zero_one_loss(y_pred, y_test)\n\nada_real_err_train = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_real.staged_predict(X_train)):\n    ada_real_err_train[i] = zero_one_loss(y_pred, y_train)\n\nax.plot(np.arange(n_estimators) + 1, ada_discrete_err,\n        label='Discrete AdaBoost Test Error',\n        color='red')\nax.plot(np.arange(n_estimators) + 1, ada_discrete_err_train,\n        label='Discrete AdaBoost Train Error',\n        color='blue')\nax.plot(np.arange(n_estimators) + 1, ada_real_err,\n        label='Real AdaBoost Test Error',\n        color='orange')\nax.plot(np.arange(n_estimators) + 1, ada_real_err_train,\n        label='Real AdaBoost Train Error',\n        color='green')\n\nax.set_ylim((0.0, 0.5))\nax.set_xlabel('n_estimators')\nax.set_ylabel('error rate')\n\nleg = ax.legend(loc='upper right', fancybox=True)\nleg.get_frame().set_alpha(0.7)\n\nplt.show()"
+        "print(__doc__)\n\n# Author: Peter Prettenhofer <[email protected]>,\n#         Noel Dawe <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.metrics import zero_one_loss\nfrom sklearn.ensemble import AdaBoostClassifier\n\n\nn_estimators = 400\n# A learning rate of 1. may not be optimal for both SAMME and SAMME.R\nlearning_rate = 1.\n\nX, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)\n\nX_test, y_test = X[2000:], y[2000:]\nX_train, y_train = X[:2000], y[:2000]\n\ndt_stump = DecisionTreeClassifier(max_depth=1, min_samples_leaf=1)\ndt_stump.fit(X_train, y_train)\ndt_stump_err = 1.0 - dt_stump.score(X_test, y_test)\n\ndt = DecisionTreeClassifier(max_depth=9, min_samples_leaf=1)\ndt.fit(X_train, y_train)\ndt_err = 1.0 - dt.score(X_test, y_test)\n\nada_discrete = AdaBoostClassifier(\n    base_estimator=dt_stump,\n    learning_rate=learning_rate,\n    n_estimators=n_estimators,\n    algorithm=\"SAMME\")\nada_discrete.fit(X_train, y_train)\n\nada_real = AdaBoostClassifier(\n    base_estimator=dt_stump,\n    learning_rate=learning_rate,\n    n_estimators=n_estimators,\n    algorithm=\"SAMME.R\")\nada_real.fit(X_train, y_train)\n\nfig = plt.figure()\nax = fig.add_subplot(111)\n\nax.plot([1, n_estimators], [dt_stump_err] * 2, 'k-',\n        label='Decision Stump Error')\nax.plot([1, n_estimators], [dt_err] * 2, 'k--',\n        label='Decision Tree Error')\n\nada_discrete_err = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_discrete.staged_predict(X_test)):\n    ada_discrete_err[i] = zero_one_loss(y_pred, y_test)\n\nada_discrete_err_train = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_discrete.staged_predict(X_train)):\n    ada_discrete_err_train[i] = zero_one_loss(y_pred, y_train)\n\nada_real_err = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_real.staged_predict(X_test)):\n    ada_real_err[i] = zero_one_loss(y_pred, y_test)\n\nada_real_err_train = np.zeros((n_estimators,))\nfor i, y_pred in enumerate(ada_real.staged_predict(X_train)):\n    ada_real_err_train[i] = zero_one_loss(y_pred, y_train)\n\nax.plot(np.arange(n_estimators) + 1, ada_discrete_err,\n        label='Discrete AdaBoost Test Error',\n        color='red')\nax.plot(np.arange(n_estimators) + 1, ada_discrete_err_train,\n        label='Discrete AdaBoost Train Error',\n        color='blue')\nax.plot(np.arange(n_estimators) + 1, ada_real_err,\n        label='Real AdaBoost Test Error',\n        color='orange')\nax.plot(np.arange(n_estimators) + 1, ada_real_err_train,\n        label='Real AdaBoost Train Error',\n        color='green')\n\nax.set_ylim((0.0, 0.5))\nax.set_xlabel('n_estimators')\nax.set_ylabel('error rate')\n\nleg = ax.legend(loc='upper right', fancybox=True)\nleg.get_frame().set_alpha(0.7)\n\nplt.show()"
       ]
     }
   ],

0.20/_downloads/auto_examples_python.zip

@@ -43,11 +43,11 @@
 X_test, y_test = X[2000:], y[2000:]
 X_train, y_train = X[:2000], y[:2000]
 
-dt_stump = DecisionTreeClassifier(max_depth=1)
+dt_stump = DecisionTreeClassifier(max_depth=1, min_samples_leaf=1)
 dt_stump.fit(X_train, y_train)
 dt_stump_err = 1.0 - dt_stump.score(X_test, y_test)
 
-dt = DecisionTreeClassifier(max_depth=9)
+dt = DecisionTreeClassifier(max_depth=9, min_samples_leaf=1)
 dt.fit(X_train, y_train)
 dt_err = 1.0 - dt.score(X_test, y_test)
 

0.20/_downloads/plot_adaboost_hastie_10_2.ipynb

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Plot classification probability\n\n\nPlot the classification probability for different classifiers. We use a 3\nclass dataset, and we classify it with a Support Vector classifier, L1\nand L2 penalized logistic regression with either a One-Vs-Rest or multinomial\nsetting, and Gaussian process classification.\n\nThe logistic regression is not a multiclass classifier out of the box. As\na result it can identify only the first class.\n\n"
+        "\n# Plot classification probability\n\n\nPlot the classification probability for different classifiers. We use a 3 class\ndataset, and we classify it with a Support Vector classifier, L1 and L2\npenalized logistic regression with either a One-Vs-Rest or multinomial setting,\nand Gaussian process classification.\n\nLinear SVC is not a probabilistic classifier by default but it has a built-in\ncalibration option enabled in this example (`probability=True`).\n\nThe logistic regression with One-Vs-Rest is not a multiclass classifier out of\nthe box. As a result it has more trouble in separating class 2 and 3 than the\nother estimators.\n\n"
       ]
     },
     {
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Alexandre Gramfort <[email protected]>\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.svm import SVC\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn import datasets\n\niris = datasets.load_iris()\nX = iris.data[:, 0:2]  # we only take the first two features for visualization\ny = iris.target\n\nn_features = X.shape[1]\n\nC = 1.0\nkernel = 1.0 * RBF([1.0, 1.0])  # for GPC\n\n# Create different classifiers. The logistic regression cannot do\n# multiclass out of the box.\nclassifiers = {'L1 logistic': LogisticRegression(C=C, penalty='l1'),\n               'L2 logistic (OvR)': LogisticRegression(C=C, penalty='l2'),\n               'Linear SVC': SVC(kernel='linear', C=C, probability=True,\n                                 random_state=0),\n               'L2 logistic (Multinomial)': LogisticRegression(\n                C=C, solver='lbfgs', multi_class='multinomial'),\n               'GPC': GaussianProcessClassifier(kernel)\n               }\n\nn_classifiers = len(classifiers)\n\nplt.figure(figsize=(3 * 2, n_classifiers * 2))\nplt.subplots_adjust(bottom=.2, top=.95)\n\nxx = np.linspace(3, 9, 100)\nyy = np.linspace(1, 5, 100).T\nxx, yy = np.meshgrid(xx, yy)\nXfull = np.c_[xx.ravel(), yy.ravel()]\n\nfor index, (name, classifier) in enumerate(classifiers.items()):\n    classifier.fit(X, y)\n\n    y_pred = classifier.predict(X)\n    classif_rate = np.mean(y_pred.ravel() == y.ravel()) * 100\n    print(\"classif_rate for %s : %f \" % (name, classif_rate))\n\n    # View probabilities=\n    probas = classifier.predict_proba(Xfull)\n    n_classes = np.unique(y_pred).size\n    for k in range(n_classes):\n        plt.subplot(n_classifiers, n_classes, index * n_classes + k + 1)\n        plt.title(\"Class %d\" % k)\n        if k == 0:\n            plt.ylabel(name)\n        imshow_handle = plt.imshow(probas[:, k].reshape((100, 100)),\n                                   extent=(3, 9, 1, 5), origin='lower')\n        plt.xticks(())\n        plt.yticks(())\n        idx = (y_pred == k)\n        if idx.any():\n            plt.scatter(X[idx, 0], X[idx, 1], marker='o', c='w', edgecolor='k')\n\nax = plt.axes([0.15, 0.04, 0.7, 0.05])\nplt.title(\"Probability\")\nplt.colorbar(imshow_handle, cax=ax, orientation='horizontal')\n\nplt.show()"
+        "print(__doc__)\n\n# Author: Alexandre Gramfort <[email protected]>\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.svm import SVC\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn import datasets\n\niris = datasets.load_iris()\nX = iris.data[:, 0:2]  # we only take the first two features for visualization\ny = iris.target\n\nn_features = X.shape[1]\n\nC = 10\nkernel = 1.0 * RBF([1.0, 1.0])  # for GPC\n\n# Create different classifiers.\nclassifiers = {\n    'L1 logistic': LogisticRegression(C=C, penalty='l1',\n                                      solver='saga',\n                                      multi_class='multinomial',\n                                      max_iter=10000),\n    'L2 logistic (Multinomial)': LogisticRegression(C=C, penalty='l2',\n                                                    solver='saga',\n                                                    multi_class='multinomial',\n                                                    max_iter=10000),\n    'L2 logistic (OvR)': LogisticRegression(C=C, penalty='l2',\n                                            solver='saga',\n                                            multi_class='ovr',\n                                            max_iter=10000),\n    'Linear SVC': SVC(kernel='linear', C=C, probability=True,\n                      random_state=0),\n    'GPC': GaussianProcessClassifier(kernel)\n}\n\nn_classifiers = len(classifiers)\n\nplt.figure(figsize=(3 * 2, n_classifiers * 2))\nplt.subplots_adjust(bottom=.2, top=.95)\n\nxx = np.linspace(3, 9, 100)\nyy = np.linspace(1, 5, 100).T\nxx, yy = np.meshgrid(xx, yy)\nXfull = np.c_[xx.ravel(), yy.ravel()]\n\nfor index, (name, classifier) in enumerate(classifiers.items()):\n    classifier.fit(X, y)\n\n    y_pred = classifier.predict(X)\n    accuracy = accuracy_score(y, y_pred)\n    print(\"Accuracy (train) for %s: %0.1f%% \" % (name, accuracy * 100))\n\n    # View probabilities:\n    probas = classifier.predict_proba(Xfull)\n    n_classes = np.unique(y_pred).size\n    for k in range(n_classes):\n        plt.subplot(n_classifiers, n_classes, index * n_classes + k + 1)\n        plt.title(\"Class %d\" % k)\n        if k == 0:\n            plt.ylabel(name)\n        imshow_handle = plt.imshow(probas[:, k].reshape((100, 100)),\n                                   extent=(3, 9, 1, 5), origin='lower')\n        plt.xticks(())\n        plt.yticks(())\n        idx = (y_pred == k)\n        if idx.any():\n            plt.scatter(X[idx, 0], X[idx, 1], marker='o', c='w', edgecolor='k')\n\nax = plt.axes([0.15, 0.04, 0.7, 0.05])\nplt.title(\"Probability\")\nplt.colorbar(imshow_handle, cax=ax, orientation='horizontal')\n\nplt.show()"
       ]
     }
   ],

0.20/_downloads/plot_adaboost_hastie_10_2.py

@@ -3,13 +3,17 @@
 Plot classification probability
 ===============================
 
-Plot the classification probability for different classifiers. We use a 3
-class dataset, and we classify it with a Support Vector classifier, L1
-and L2 penalized logistic regression with either a One-Vs-Rest or multinomial
-setting, and Gaussian process classification.
+Plot the classification probability for different classifiers. We use a 3 class
+dataset, and we classify it with a Support Vector classifier, L1 and L2
+penalized logistic regression with either a One-Vs-Rest or multinomial setting,
+and Gaussian process classification.
 
-The logistic regression is not a multiclass classifier out of the box. As
-a result it can identify only the first class.
+Linear SVC is not a probabilistic classifier by default but it has a built-in
+calibration option enabled in this example (`probability=True`).
+
+The logistic regression with One-Vs-Rest is not a multiclass classifier out of
+the box. As a result it has more trouble in separating class 2 and 3 than the
+other estimators.
 """
 print(__doc__)
 
@@ -19,6 +23,7 @@ class dataset, and we classify it with a Support Vector classifier, L1
 import matplotlib.pyplot as plt
 import numpy as np
 
+from sklearn.metrics import accuracy_score
 from sklearn.linear_model import LogisticRegression
 from sklearn.svm import SVC
 from sklearn.gaussian_process import GaussianProcessClassifier
@@ -31,19 +36,27 @@ class dataset, and we classify it with a Support Vector classifier, L1
 
 n_features = X.shape[1]
 
-C = 1.0
+C = 10
 kernel = 1.0 * RBF([1.0, 1.0])  # for GPC
 
-# Create different classifiers. The logistic regression cannot do
-# multiclass out of the box.
-classifiers = {'L1 logistic': LogisticRegression(C=C, penalty='l1'),
-               'L2 logistic (OvR)': LogisticRegression(C=C, penalty='l2'),
-               'Linear SVC': SVC(kernel='linear', C=C, probability=True,
-                                 random_state=0),
-               'L2 logistic (Multinomial)': LogisticRegression(
-                C=C, solver='lbfgs', multi_class='multinomial'),
-               'GPC': GaussianProcessClassifier(kernel)
-               }
+# Create different classifiers.
+classifiers = {
+    'L1 logistic': LogisticRegression(C=C, penalty='l1',
+                                      solver='saga',
+                                      multi_class='multinomial',
+                                      max_iter=10000),
+    'L2 logistic (Multinomial)': LogisticRegression(C=C, penalty='l2',
+                                                    solver='saga',
+                                                    multi_class='multinomial',
+                                                    max_iter=10000),
+    'L2 logistic (OvR)': LogisticRegression(C=C, penalty='l2',
+                                            solver='saga',
+                                            multi_class='ovr',
+                                            max_iter=10000),
+    'Linear SVC': SVC(kernel='linear', C=C, probability=True,
+                      random_state=0),
+    'GPC': GaussianProcessClassifier(kernel)
+}
 
 n_classifiers = len(classifiers)
 
@@ -59,10 +72,10 @@ class dataset, and we classify it with a Support Vector classifier, L1
     classifier.fit(X, y)
 
     y_pred = classifier.predict(X)
-    classif_rate = np.mean(y_pred.ravel() == y.ravel()) * 100
-    print("classif_rate for %s : %f " % (name, classif_rate))
+    accuracy = accuracy_score(y, y_pred)
+    print("Accuracy (train) for %s: %0.1f%% " % (name, accuracy * 100))
 
-    # View probabilities=
+    # View probabilities:
     probas = classifier.predict_proba(Xfull)
     n_classes = np.unique(y_pred).size
     for k in range(n_classes):