Pushing the docs to dev/ for branch: master, commit 53622e856c2747c7b559d3d29410cd37ca0addd2

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Alexandre Gramfort <[email protected]>\n#         Albert Thomas <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\nimport matplotlib\nimport matplotlib.pyplot as plt\n\nfrom sklearn import svm\nfrom sklearn.datasets import make_moons, make_blobs\nfrom sklearn.covariance import EllipticEnvelope\nfrom sklearn.ensemble import IsolationForest\nfrom sklearn.neighbors import LocalOutlierFactor\n\nprint(__doc__)\n\nmatplotlib.rcParams['contour.negative_linestyle'] = 'solid'\n\n# Example settings\nn_samples = 300\noutliers_fraction = 0.15\nn_outliers = int(outliers_fraction * n_samples)\nn_inliers = n_samples - n_outliers\n\n# define outlier/anomaly detection methods to be compared\nanomaly_algorithms = [\n    (\"Robust covariance\", EllipticEnvelope(contamination=outliers_fraction)),\n    (\"One-Class SVM\", svm.OneClassSVM(nu=outliers_fraction, kernel=\"rbf\",\n                                      gamma=0.1)),\n    (\"Isolation Forest\", IsolationForest(contamination=outliers_fraction,\n                                         random_state=42)),\n    (\"Local Outlier Factor\", LocalOutlierFactor(\n        n_neighbors=35, contamination=outliers_fraction))]\n\n# Define datasets\nblobs_params = dict(random_state=0, n_samples=n_inliers, n_features=2)\ndatasets = [\n    make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5,\n               **blobs_params)[0],\n    make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[0.5, 0.5],\n               **blobs_params)[0],\n    make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[1.5, .3],\n               **blobs_params)[0],\n    4. * (make_moons(n_samples=n_samples, noise=.05, random_state=0)[0] -\n          np.array([0.5, 0.25])),\n    14. * (np.random.RandomState(42).rand(n_samples, 2) - 0.5)]\n\n# Compare given classifiers under given settings\nxx, yy = np.meshgrid(np.linspace(-7, 7, 150),\n                     np.linspace(-7, 7, 150))\n\nplt.figure(figsize=(len(anomaly_algorithms) * 2 + 3, 12.5))\nplt.subplots_adjust(left=.02, right=.98, bottom=.001, top=.96, wspace=.05,\n                    hspace=.01)\n\nplot_num = 1\nrng = np.random.RandomState(42)\n\nfor i_dataset, X in enumerate(datasets):\n    # Add outliers\n    X = np.concatenate([X, rng.uniform(low=-6, high=6,\n                       size=(n_outliers, 2))], axis=0)\n\n    for name, algorithm in anomaly_algorithms:\n        t0 = time.time()\n        algorithm.fit(X)\n        t1 = time.time()\n        plt.subplot(len(datasets), len(anomaly_algorithms), plot_num)\n        if i_dataset == 0:\n            plt.title(name, size=18)\n\n        # fit the data and tag outliers\n        if name == \"Local Outlier Factor\":\n            y_pred = algorithm.fit_predict(X)\n        else:\n            y_pred = algorithm.fit(X).predict(X)\n\n        # plot the levels lines and the points\n        if name != \"Local Outlier Factor\":  # LOF does not implement predict\n            Z = algorithm.predict(np.c_[xx.ravel(), yy.ravel()])\n            Z = Z.reshape(xx.shape)\n            plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors='black')\n\n        colors = np.array(['#377eb8', '#ff7f00'])\n        plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[(y_pred + 1) // 2])\n\n        plt.xlim(-7, 7)\n        plt.ylim(-7, 7)\n        plt.xticks(())\n        plt.yticks(())\n        plt.text(.99, .01, ('%.2fs' % (t1 - t0)).lstrip('0'),\n                 transform=plt.gca().transAxes, size=15,\n                 horizontalalignment='right')\n        plot_num += 1\n\nplt.show()"
+        "# Author: Alexandre Gramfort <[email protected]>\n#         Albert Thomas <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\nimport matplotlib\nimport matplotlib.pyplot as plt\n\nfrom sklearn import svm\nfrom sklearn.datasets import make_moons, make_blobs\nfrom sklearn.covariance import EllipticEnvelope\nfrom sklearn.ensemble import IsolationForest\nfrom sklearn.neighbors import LocalOutlierFactor\n\nprint(__doc__)\n\nmatplotlib.rcParams['contour.negative_linestyle'] = 'solid'\n\n# Example settings\nn_samples = 300\noutliers_fraction = 0.15\nn_outliers = int(outliers_fraction * n_samples)\nn_inliers = n_samples - n_outliers\n\n# define outlier/anomaly detection methods to be compared\nanomaly_algorithms = [\n    (\"Robust covariance\", EllipticEnvelope(contamination=outliers_fraction)),\n    (\"One-Class SVM\", svm.OneClassSVM(nu=outliers_fraction, kernel=\"rbf\",\n                                      gamma=0.1)),\n    (\"Isolation Forest\", IsolationForest(behaviour='new',\n                                         contamination=outliers_fraction,\n                                         random_state=42)),\n    (\"Local Outlier Factor\", LocalOutlierFactor(\n        n_neighbors=35, contamination=outliers_fraction))]\n\n# Define datasets\nblobs_params = dict(random_state=0, n_samples=n_inliers, n_features=2)\ndatasets = [\n    make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5,\n               **blobs_params)[0],\n    make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[0.5, 0.5],\n               **blobs_params)[0],\n    make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[1.5, .3],\n               **blobs_params)[0],\n    4. * (make_moons(n_samples=n_samples, noise=.05, random_state=0)[0] -\n          np.array([0.5, 0.25])),\n    14. * (np.random.RandomState(42).rand(n_samples, 2) - 0.5)]\n\n# Compare given classifiers under given settings\nxx, yy = np.meshgrid(np.linspace(-7, 7, 150),\n                     np.linspace(-7, 7, 150))\n\nplt.figure(figsize=(len(anomaly_algorithms) * 2 + 3, 12.5))\nplt.subplots_adjust(left=.02, right=.98, bottom=.001, top=.96, wspace=.05,\n                    hspace=.01)\n\nplot_num = 1\nrng = np.random.RandomState(42)\n\nfor i_dataset, X in enumerate(datasets):\n    # Add outliers\n    X = np.concatenate([X, rng.uniform(low=-6, high=6,\n                       size=(n_outliers, 2))], axis=0)\n\n    for name, algorithm in anomaly_algorithms:\n        t0 = time.time()\n        algorithm.fit(X)\n        t1 = time.time()\n        plt.subplot(len(datasets), len(anomaly_algorithms), plot_num)\n        if i_dataset == 0:\n            plt.title(name, size=18)\n\n        # fit the data and tag outliers\n        if name == \"Local Outlier Factor\":\n            y_pred = algorithm.fit_predict(X)\n        else:\n            y_pred = algorithm.fit(X).predict(X)\n\n        # plot the levels lines and the points\n        if name != \"Local Outlier Factor\":  # LOF does not implement predict\n            Z = algorithm.predict(np.c_[xx.ravel(), yy.ravel()])\n            Z = Z.reshape(xx.shape)\n            plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors='black')\n\n        colors = np.array(['#377eb8', '#ff7f00'])\n        plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[(y_pred + 1) // 2])\n\n        plt.xlim(-7, 7)\n        plt.ylim(-7, 7)\n        plt.xticks(())\n        plt.yticks(())\n        plt.text(.99, .01, ('%.2fs' % (t1 - t0)).lstrip('0'),\n                 transform=plt.gca().transAxes, size=15,\n                 horizontalalignment='right')\n        plot_num += 1\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -80,7 +80,8 @@
     ("Robust covariance", EllipticEnvelope(contamination=outliers_fraction)),
     ("One-Class SVM", svm.OneClassSVM(nu=outliers_fraction, kernel="rbf",
                                       gamma=0.1)),
-    ("Isolation Forest", IsolationForest(contamination=outliers_fraction,
+    ("Isolation Forest", IsolationForest(behaviour='new',
+                                         contamination=outliers_fraction,
                                          random_state=42)),
     ("Local Outlier Factor", LocalOutlierFactor(
         n_neighbors=35, contamination=outliers_fraction))]

dev/_downloads/plot_anomaly_comparison.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.ensemble import IsolationForest\n\nrng = np.random.RandomState(42)\n\n# Generate train data\nX = 0.3 * rng.randn(100, 2)\nX_train = np.r_[X + 2, X - 2]\n# Generate some regular novel observations\nX = 0.3 * rng.randn(20, 2)\nX_test = np.r_[X + 2, X - 2]\n# Generate some abnormal novel observations\nX_outliers = rng.uniform(low=-4, high=4, size=(20, 2))\n\n# fit the model\nclf = IsolationForest(max_samples=100, random_state=rng, contamination='auto')\nclf.fit(X_train)\ny_pred_train = clf.predict(X_train)\ny_pred_test = clf.predict(X_test)\ny_pred_outliers = clf.predict(X_outliers)\n\n# plot the line, the samples, and the nearest vectors to the plane\nxx, yy = np.meshgrid(np.linspace(-5, 5, 50), np.linspace(-5, 5, 50))\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\n\nplt.title(\"IsolationForest\")\nplt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r)\n\nb1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white',\n                 s=20, edgecolor='k')\nb2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green',\n                 s=20, edgecolor='k')\nc = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red',\n                s=20, edgecolor='k')\nplt.axis('tight')\nplt.xlim((-5, 5))\nplt.ylim((-5, 5))\nplt.legend([b1, b2, c],\n           [\"training observations\",\n            \"new regular observations\", \"new abnormal observations\"],\n           loc=\"upper left\")\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.ensemble import IsolationForest\n\nrng = np.random.RandomState(42)\n\n# Generate train data\nX = 0.3 * rng.randn(100, 2)\nX_train = np.r_[X + 2, X - 2]\n# Generate some regular novel observations\nX = 0.3 * rng.randn(20, 2)\nX_test = np.r_[X + 2, X - 2]\n# Generate some abnormal novel observations\nX_outliers = rng.uniform(low=-4, high=4, size=(20, 2))\n\n# fit the model\nclf = IsolationForest(behaviour='new', max_samples=100,\n                      random_state=rng, contamination='auto')\nclf.fit(X_train)\ny_pred_train = clf.predict(X_train)\ny_pred_test = clf.predict(X_test)\ny_pred_outliers = clf.predict(X_outliers)\n\n# plot the line, the samples, and the nearest vectors to the plane\nxx, yy = np.meshgrid(np.linspace(-5, 5, 50), np.linspace(-5, 5, 50))\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\n\nplt.title(\"IsolationForest\")\nplt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r)\n\nb1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white',\n                 s=20, edgecolor='k')\nb2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green',\n                 s=20, edgecolor='k')\nc = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red',\n                s=20, edgecolor='k')\nplt.axis('tight')\nplt.xlim((-5, 5))\nplt.ylim((-5, 5))\nplt.legend([b1, b2, c],\n           [\"training observations\",\n            \"new regular observations\", \"new abnormal observations\"],\n           loc=\"upper left\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_anomaly_comparison.py

@@ -40,7 +40,8 @@
 X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
 
 # fit the model
-clf = IsolationForest(max_samples=100, random_state=rng, contamination='auto')
+clf = IsolationForest(behaviour='new', max_samples=100,
+                      random_state=rng, contamination='auto')
 clf.fit(X_train)
 y_pred_train = clf.predict(X_train)
 y_pred_test = clf.predict(X_test)