Pushing the docs to dev/ for branch: main, commit f4959ead4846005194ef02d82329b91f88e419e2

Author: sklearn-ci

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib\nimport matplotlib.lines as mlines\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.neighbors import LocalOutlierFactor\n\nnp.random.seed(42)\n\nxx, yy = np.meshgrid(np.linspace(-5, 5, 500), np.linspace(-5, 5, 500))\n# Generate normal (not abnormal) training observations\nX = 0.3 * np.random.randn(100, 2)\nX_train = np.r_[X + 2, X - 2]\n# Generate new normal (not abnormal) observations\nX = 0.3 * np.random.randn(20, 2)\nX_test = np.r_[X + 2, X - 2]\n# Generate some abnormal novel observations\nX_outliers = np.random.uniform(low=-4, high=4, size=(20, 2))\n\n# fit the model for novelty detection (novelty=True)\nclf = LocalOutlierFactor(n_neighbors=20, novelty=True, contamination=0.1)\nclf.fit(X_train)\n# DO NOT use predict, decision_function and score_samples on X_train as this\n# would give wrong results but only on new unseen data (not used in X_train),\n# e.g. X_test, X_outliers or the meshgrid\ny_pred_test = clf.predict(X_test)\ny_pred_outliers = clf.predict(X_outliers)\nn_error_test = y_pred_test[y_pred_test == -1].size\nn_error_outliers = y_pred_outliers[y_pred_outliers == 1].size\n\n# plot the learned frontier, the points, and the nearest vectors to the plane\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\n\nplt.title(\"Novelty Detection with LOF\")\nplt.contourf(xx, yy, Z, levels=np.linspace(Z.min(), 0, 7), cmap=plt.cm.PuBu)\na = plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors=\"darkred\")\nplt.contourf(xx, yy, Z, levels=[0, Z.max()], colors=\"palevioletred\")\n\ns = 40\nb1 = plt.scatter(X_train[:, 0], X_train[:, 1], c=\"white\", s=s, edgecolors=\"k\")\nb2 = plt.scatter(X_test[:, 0], X_test[:, 1], c=\"blueviolet\", s=s, edgecolors=\"k\")\nc = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c=\"gold\", s=s, edgecolors=\"k\")\nplt.axis(\"tight\")\nplt.xlim((-5, 5))\nplt.ylim((-5, 5))\nplt.legend(\n    [mlines.Line2D([], [], color=\"darkred\"), b1, b2, c],\n    [\n        \"learned frontier\",\n        \"training observations\",\n        \"new regular observations\",\n        \"new abnormal observations\",\n    ],\n    loc=\"upper left\",\n    prop=matplotlib.font_manager.FontProperties(size=11),\n)\nplt.xlabel(\n    \"errors novel regular: %d/40 ; errors novel abnormal: %d/40\"\n    % (n_error_test, n_error_outliers)\n)\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib\nimport matplotlib.lines as mlines\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.neighbors import LocalOutlierFactor\n\nnp.random.seed(42)\n\nxx, yy = np.meshgrid(np.linspace(-5, 5, 500), np.linspace(-5, 5, 500))\n# Generate normal (not abnormal) training observations\nX = 0.3 * np.random.randn(100, 2)\nX_train = np.r_[X + 2, X - 2]\n# Generate new normal (not abnormal) observations\nX = 0.3 * np.random.randn(20, 2)\nX_test = np.r_[X + 2, X - 2]\n# Generate some abnormal novel observations\nX_outliers = np.random.uniform(low=-4, high=4, size=(20, 2))\n\n# fit the model for novelty detection (novelty=True)\nclf = LocalOutlierFactor(n_neighbors=20, novelty=True, contamination=0.1)\nclf.fit(X_train)\n# DO NOT use predict, decision_function and score_samples on X_train as this\n# would give wrong results but only on new unseen data (not used in X_train),\n# e.g. X_test, X_outliers or the meshgrid\ny_pred_test = clf.predict(X_test)\ny_pred_outliers = clf.predict(X_outliers)\nn_error_test = y_pred_test[y_pred_test == -1].size\nn_error_outliers = y_pred_outliers[y_pred_outliers == 1].size\n\n# plot the learned frontier, the points, and the nearest vectors to the plane\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\n\nplt.title(\"Novelty Detection with LOF\")\nplt.contourf(xx, yy, Z, levels=np.linspace(Z.min(), 0, 7), cmap=plt.cm.PuBu)\na = plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors=\"darkred\")\nplt.contourf(xx, yy, Z, levels=[0, Z.max()], colors=\"palevioletred\")\n\ns = 40\nb1 = plt.scatter(X_train[:, 0], X_train[:, 1], c=\"white\", s=s, edgecolors=\"k\")\nb2 = plt.scatter(X_test[:, 0], X_test[:, 1], c=\"blueviolet\", s=s, edgecolors=\"k\")\nc = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c=\"gold\", s=s, edgecolors=\"k\")\nplt.axis(\"tight\")\nplt.xlim((-5, 5))\nplt.ylim((-5, 5))\nplt.legend(\n    [mlines.Line2D([], [], color=\"darkred\"), b1, b2, c],\n    [\n        \"learned frontier\",\n        \"training observations\",\n        \"new regular observations\",\n        \"new abnormal observations\",\n    ],\n    loc=(1.05, 0.4),\n    prop=matplotlib.font_manager.FontProperties(size=11),\n)\nplt.xlabel(\n    \"errors novel regular: %d/40 ; errors novel abnormal: %d/40\"\n    % (n_error_test, n_error_outliers)\n)\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -82,11 +82,12 @@
         "new regular observations",
         "new abnormal observations",
     ],
-    loc="upper left",
+    loc=(1.05, 0.4),
     prop=matplotlib.font_manager.FontProperties(size=11),
 )
 plt.xlabel(
     "errors novel regular: %d/40 ; errors novel abnormal: %d/40"
     % (n_error_test, n_error_outliers)
 )
+plt.tight_layout()
 plt.show()