Pushing the docs to dev/ for branch: master, commit 026e10a24ffb9788ad914e642efe3b1b9559378e

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -42,7 +42,7 @@
 from sklearn.linear_model import SGDClassifier
 from sklearn.linear_model import Perceptron
 from sklearn.linear_model import PassiveAggressiveClassifier
-from sklearn.naive_bayes import BernoulliNB, MultinomialNB
+from sklearn.naive_bayes import BernoulliNB, ComplementNB, MultinomialNB
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.neighbors import NearestCentroid
 from sklearn.ensemble import RandomForestClassifier
@@ -283,6 +283,7 @@ def benchmark(clf):
 print("Naive Bayes")
 results.append(benchmark(MultinomialNB(alpha=.01)))
 results.append(benchmark(BernoulliNB(alpha=.01)))
+results.append(benchmark(ComplementNB(alpha=.1)))
 
 print('=' * 80)
 print("LinearSVC with L1-based feature selection")

dev/_downloads/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n\n# Code source: Ga\u00ebl Varoquaux\n#              Andreas M\u00fcller\n# Modified for documentation by Jaques Grobler\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.colors import ListedColormap\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.datasets import make_moons, make_circles, make_classification\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n\nh = .02  # step size in the mesh\n\nnames = [\"Nearest Neighbors\", \"Linear SVM\", \"RBF SVM\", \"Gaussian Process\",\n         \"Decision Tree\", \"Random Forest\", \"Neural Net\", \"AdaBoost\",\n         \"Naive Bayes\", \"QDA\"]\n\nclassifiers = [\n    KNeighborsClassifier(3),\n    SVC(kernel=\"linear\", C=0.025),\n    SVC(gamma=2, C=1),\n    GaussianProcessClassifier(1.0 * RBF(1.0), warm_start=True),\n    DecisionTreeClassifier(max_depth=5),\n    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),\n    MLPClassifier(alpha=1),\n    AdaBoostClassifier(),\n    GaussianNB(),\n    QuadraticDiscriminantAnalysis()]\n\nX, y = make_classification(n_features=2, n_redundant=0, n_informative=2,\n                           random_state=1, n_clusters_per_class=1)\nrng = np.random.RandomState(2)\nX += 2 * rng.uniform(size=X.shape)\nlinearly_separable = (X, y)\n\ndatasets = [make_moons(noise=0.3, random_state=0),\n            make_circles(noise=0.2, factor=0.5, random_state=1),\n            linearly_separable\n            ]\n\nfigure = plt.figure(figsize=(27, 9))\ni = 1\n# iterate over datasets\nfor ds_cnt, ds in enumerate(datasets):\n    # preprocess dataset, split into training and test part\n    X, y = ds\n    X = StandardScaler().fit_transform(X)\n    X_train, X_test, y_train, y_test = \\\n        train_test_split(X, y, test_size=.4, random_state=42)\n\n    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5\n    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n                         np.arange(y_min, y_max, h))\n\n    # just plot the dataset first\n    cm = plt.cm.RdBu\n    cm_bright = ListedColormap(['#FF0000', '#0000FF'])\n    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n    if ds_cnt == 0:\n        ax.set_title(\"Input data\")\n    # Plot the training points\n    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,\n               edgecolors='k')\n    # and testing points\n    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,\n               edgecolors='k')\n    ax.set_xlim(xx.min(), xx.max())\n    ax.set_ylim(yy.min(), yy.max())\n    ax.set_xticks(())\n    ax.set_yticks(())\n    i += 1\n\n    # iterate over classifiers\n    for name, clf in zip(names, classifiers):\n        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n        clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n\n        # Plot the decision boundary. For that, we will assign a color to each\n        # point in the mesh [x_min, x_max]x[y_min, y_max].\n        if hasattr(clf, \"decision_function\"):\n            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\n        else:\n            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]\n\n        # Put the result into a color plot\n        Z = Z.reshape(xx.shape)\n        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)\n\n        # Plot also the training points\n        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,\n                   edgecolors='k')\n        # and testing points\n        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,\n                   edgecolors='k', alpha=0.6)\n\n        ax.set_xlim(xx.min(), xx.max())\n        ax.set_ylim(yy.min(), yy.max())\n        ax.set_xticks(())\n        ax.set_yticks(())\n        if ds_cnt == 0:\n            ax.set_title(name)\n        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),\n                size=15, horizontalalignment='right')\n        i += 1\n\nplt.tight_layout()\nplt.show()"
+        "print(__doc__)\n\n\n# Code source: Ga\u00ebl Varoquaux\n#              Andreas M\u00fcller\n# Modified for documentation by Jaques Grobler\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.colors import ListedColormap\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.datasets import make_moons, make_circles, make_classification\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n\nh = .02  # step size in the mesh\n\nnames = [\"Nearest Neighbors\", \"Linear SVM\", \"RBF SVM\", \"Gaussian Process\",\n         \"Decision Tree\", \"Random Forest\", \"Neural Net\", \"AdaBoost\",\n         \"Naive Bayes\", \"QDA\"]\n\nclassifiers = [\n    KNeighborsClassifier(3),\n    SVC(kernel=\"linear\", C=0.025),\n    SVC(gamma=2, C=1),\n    GaussianProcessClassifier(1.0 * RBF(1.0)),\n    DecisionTreeClassifier(max_depth=5),\n    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),\n    MLPClassifier(alpha=1),\n    AdaBoostClassifier(),\n    GaussianNB(),\n    QuadraticDiscriminantAnalysis()]\n\nX, y = make_classification(n_features=2, n_redundant=0, n_informative=2,\n                           random_state=1, n_clusters_per_class=1)\nrng = np.random.RandomState(2)\nX += 2 * rng.uniform(size=X.shape)\nlinearly_separable = (X, y)\n\ndatasets = [make_moons(noise=0.3, random_state=0),\n            make_circles(noise=0.2, factor=0.5, random_state=1),\n            linearly_separable\n            ]\n\nfigure = plt.figure(figsize=(27, 9))\ni = 1\n# iterate over datasets\nfor ds_cnt, ds in enumerate(datasets):\n    # preprocess dataset, split into training and test part\n    X, y = ds\n    X = StandardScaler().fit_transform(X)\n    X_train, X_test, y_train, y_test = \\\n        train_test_split(X, y, test_size=.4, random_state=42)\n\n    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5\n    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n                         np.arange(y_min, y_max, h))\n\n    # just plot the dataset first\n    cm = plt.cm.RdBu\n    cm_bright = ListedColormap(['#FF0000', '#0000FF'])\n    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n    if ds_cnt == 0:\n        ax.set_title(\"Input data\")\n    # Plot the training points\n    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,\n               edgecolors='k')\n    # and testing points\n    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,\n               edgecolors='k')\n    ax.set_xlim(xx.min(), xx.max())\n    ax.set_ylim(yy.min(), yy.max())\n    ax.set_xticks(())\n    ax.set_yticks(())\n    i += 1\n\n    # iterate over classifiers\n    for name, clf in zip(names, classifiers):\n        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n        clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n\n        # Plot the decision boundary. For that, we will assign a color to each\n        # point in the mesh [x_min, x_max]x[y_min, y_max].\n        if hasattr(clf, \"decision_function\"):\n            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\n        else:\n            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]\n\n        # Put the result into a color plot\n        Z = Z.reshape(xx.shape)\n        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)\n\n        # Plot also the training points\n        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,\n                   edgecolors='k')\n        # and testing points\n        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,\n                   edgecolors='k', alpha=0.6)\n\n        ax.set_xlim(xx.min(), xx.max())\n        ax.set_ylim(yy.min(), yy.max())\n        ax.set_xticks(())\n        ax.set_yticks(())\n        if ds_cnt == 0:\n            ax.set_title(name)\n        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),\n                size=15, horizontalalignment='right')\n        i += 1\n\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/document_classification_20newsgroups.ipynb

@@ -54,7 +54,7 @@
     KNeighborsClassifier(3),
     SVC(kernel="linear", C=0.025),
     SVC(gamma=2, C=1),
-    GaussianProcessClassifier(1.0 * RBF(1.0), warm_start=True),
+    GaussianProcessClassifier(1.0 * RBF(1.0)),
     DecisionTreeClassifier(max_depth=5),
     RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
     MLPClassifier(alpha=1),