Pushing the docs to dev/ for branch: master, commit 43c0efa1b9ec1b2af22849f231355fae4e1051e7

Author: sklearn-ci

dev/_downloads/28477181ee2a477248e703cf646f97f1/plot_sparse_logistic_regression_20newsgroups.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import timeit\nimport warnings\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import fetch_20newsgroups_vectorized\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.exceptions import ConvergenceWarning\n\nprint(__doc__)\n# Author: Arthur Mensch\n\nwarnings.filterwarnings(\"ignore\", category=ConvergenceWarning,\n                        module=\"sklearn\")\nt0 = timeit.default_timer()\n\n# We use SAGA solver\nsolver = 'saga'\n\n# Turn down for faster run time\nn_samples = 10000\n\nX, y = fetch_20newsgroups_vectorized('all', return_X_y=True)\nX = X[:n_samples]\ny = y[:n_samples]\n\nX_train, X_test, y_train, y_test = train_test_split(X, y,\n                                                    random_state=42,\n                                                    stratify=y,\n                                                    test_size=0.1)\ntrain_samples, n_features = X_train.shape\nn_classes = np.unique(y).shape[0]\n\nprint('Dataset 20newsgroup, train_samples=%i, n_features=%i, n_classes=%i'\n      % (train_samples, n_features, n_classes))\n\nmodels = {'ovr': {'name': 'One versus Rest', 'iters': [1, 2, 4]},\n          'multinomial': {'name': 'Multinomial', 'iters': [1, 3, 7]}}\n\nfor model in models:\n    # Add initial chance-level values for plotting purpose\n    accuracies = [1 / n_classes]\n    times = [0]\n    densities = [1]\n\n    model_params = models[model]\n\n    # Small number of epochs for fast runtime\n    for this_max_iter in model_params['iters']:\n        print('[model=%s, solver=%s] Number of epochs: %s' %\n              (model_params['name'], solver, this_max_iter))\n        lr = LogisticRegression(solver=solver,\n                                multi_class=model,\n                                penalty='l1',\n                                max_iter=this_max_iter,\n                                random_state=42,\n                                )\n        t1 = timeit.default_timer()\n        lr.fit(X_train, y_train)\n        train_time = timeit.default_timer() - t1\n\n        y_pred = lr.predict(X_test)\n        accuracy = np.sum(y_pred == y_test) / y_test.shape[0]\n        density = np.mean(lr.coef_ != 0, axis=1) * 100\n        accuracies.append(accuracy)\n        densities.append(density)\n        times.append(train_time)\n    models[model]['times'] = times\n    models[model]['densities'] = densities\n    models[model]['accuracies'] = accuracies\n    print('Test accuracy for model %s: %.4f' % (model, accuracies[-1]))\n    print('%% non-zero coefficients for model %s, '\n          'per class:\\n %s' % (model, densities[-1]))\n    print('Run time (%i epochs) for model %s:'\n          '%.2f' % (model_params['iters'][-1], model, times[-1]))\n\nfig = plt.figure()\nax = fig.add_subplot(111)\n\nfor model in models:\n    name = models[model]['name']\n    times = models[model]['times']\n    accuracies = models[model]['accuracies']\n    ax.plot(times, accuracies, marker='o',\n            label='Model: %s' % name)\n    ax.set_xlabel('Train time (s)')\n    ax.set_ylabel('Test accuracy')\nax.legend()\nfig.suptitle('Multinomial vs One-vs-Rest Logistic L1\\n'\n             'Dataset %s' % '20newsgroups')\nfig.tight_layout()\nfig.subplots_adjust(top=0.85)\nrun_time = timeit.default_timer() - t0\nprint('Example run in %.3f s' % run_time)\nplt.show()"
+        "import timeit\nimport warnings\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import fetch_20newsgroups_vectorized\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.exceptions import ConvergenceWarning\n\nprint(__doc__)\n# Author: Arthur Mensch\n\nwarnings.filterwarnings(\"ignore\", category=ConvergenceWarning,\n                        module=\"sklearn\")\nt0 = timeit.default_timer()\n\n# We use SAGA solver\nsolver = 'saga'\n\n# Turn down for faster run time\nn_samples = 10000\n\nX, y = fetch_20newsgroups_vectorized(subset='all', return_X_y=True)\nX = X[:n_samples]\ny = y[:n_samples]\n\nX_train, X_test, y_train, y_test = train_test_split(X, y,\n                                                    random_state=42,\n                                                    stratify=y,\n                                                    test_size=0.1)\ntrain_samples, n_features = X_train.shape\nn_classes = np.unique(y).shape[0]\n\nprint('Dataset 20newsgroup, train_samples=%i, n_features=%i, n_classes=%i'\n      % (train_samples, n_features, n_classes))\n\nmodels = {'ovr': {'name': 'One versus Rest', 'iters': [1, 2, 4]},\n          'multinomial': {'name': 'Multinomial', 'iters': [1, 3, 7]}}\n\nfor model in models:\n    # Add initial chance-level values for plotting purpose\n    accuracies = [1 / n_classes]\n    times = [0]\n    densities = [1]\n\n    model_params = models[model]\n\n    # Small number of epochs for fast runtime\n    for this_max_iter in model_params['iters']:\n        print('[model=%s, solver=%s] Number of epochs: %s' %\n              (model_params['name'], solver, this_max_iter))\n        lr = LogisticRegression(solver=solver,\n                                multi_class=model,\n                                penalty='l1',\n                                max_iter=this_max_iter,\n                                random_state=42,\n                                )\n        t1 = timeit.default_timer()\n        lr.fit(X_train, y_train)\n        train_time = timeit.default_timer() - t1\n\n        y_pred = lr.predict(X_test)\n        accuracy = np.sum(y_pred == y_test) / y_test.shape[0]\n        density = np.mean(lr.coef_ != 0, axis=1) * 100\n        accuracies.append(accuracy)\n        densities.append(density)\n        times.append(train_time)\n    models[model]['times'] = times\n    models[model]['densities'] = densities\n    models[model]['accuracies'] = accuracies\n    print('Test accuracy for model %s: %.4f' % (model, accuracies[-1]))\n    print('%% non-zero coefficients for model %s, '\n          'per class:\\n %s' % (model, densities[-1]))\n    print('Run time (%i epochs) for model %s:'\n          '%.2f' % (model_params['iters'][-1], model, times[-1]))\n\nfig = plt.figure()\nax = fig.add_subplot(111)\n\nfor model in models:\n    name = models[model]['name']\n    times = models[model]['times']\n    accuracies = models[model]['accuracies']\n    ax.plot(times, accuracies, marker='o',\n            label='Model: %s' % name)\n    ax.set_xlabel('Train time (s)')\n    ax.set_ylabel('Test accuracy')\nax.legend()\nfig.suptitle('Multinomial vs One-vs-Rest Logistic L1\\n'\n             'Dataset %s' % '20newsgroups')\nfig.tight_layout()\nfig.subplots_adjust(top=0.85)\nrun_time = timeit.default_timer() - t0\nprint('Example run in %.3f s' % run_time)\nplt.show()"
       ]
     }
   ],

dev/_downloads/2f467d575019742cbcf00d6b53858c0d/plot_lle_digits.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Mathieu Blondel <[email protected]>\n#         Alexandre Gramfort <[email protected]>\n#         Balazs Kegl <[email protected]>\n#         Jan Hendrik Metzen <[email protected]>\n# License: BSD Style.\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib import cm\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.metrics import brier_score_loss\nfrom sklearn.calibration import CalibratedClassifierCV\nfrom sklearn.model_selection import train_test_split\n\n\nn_samples = 50000\nn_bins = 3  # use 3 bins for calibration_curve as we have 3 clusters here\n\n# Generate 3 blobs with 2 classes where the second blob contains\n# half positive samples and half negative samples. Probability in this\n# blob is therefore 0.5.\ncenters = [(-5, -5), (0, 0), (5, 5)]\nX, y = make_blobs(n_samples=n_samples, centers=centers, shuffle=False,\n                  random_state=42)\n\ny[:n_samples // 2] = 0\ny[n_samples // 2:] = 1\nsample_weight = np.random.RandomState(42).rand(y.shape[0])\n\n# split train, test for calibration\nX_train, X_test, y_train, y_test, sw_train, sw_test = \\\n    train_test_split(X, y, sample_weight, test_size=0.9, random_state=42)\n\n# Gaussian Naive-Bayes with no calibration\nclf = GaussianNB()\nclf.fit(X_train, y_train)  # GaussianNB itself does not support sample-weights\nprob_pos_clf = clf.predict_proba(X_test)[:, 1]\n\n# Gaussian Naive-Bayes with isotonic calibration\nclf_isotonic = CalibratedClassifierCV(clf, cv=2, method='isotonic')\nclf_isotonic.fit(X_train, y_train, sw_train)\nprob_pos_isotonic = clf_isotonic.predict_proba(X_test)[:, 1]\n\n# Gaussian Naive-Bayes with sigmoid calibration\nclf_sigmoid = CalibratedClassifierCV(clf, cv=2, method='sigmoid')\nclf_sigmoid.fit(X_train, y_train, sw_train)\nprob_pos_sigmoid = clf_sigmoid.predict_proba(X_test)[:, 1]\n\nprint(\"Brier scores: (the smaller the better)\")\n\nclf_score = brier_score_loss(y_test, prob_pos_clf, sw_test)\nprint(\"No calibration: %1.3f\" % clf_score)\n\nclf_isotonic_score = brier_score_loss(y_test, prob_pos_isotonic, sw_test)\nprint(\"With isotonic calibration: %1.3f\" % clf_isotonic_score)\n\nclf_sigmoid_score = brier_score_loss(y_test, prob_pos_sigmoid, sw_test)\nprint(\"With sigmoid calibration: %1.3f\" % clf_sigmoid_score)\n\n# #############################################################################\n# Plot the data and the predicted probabilities\nplt.figure()\ny_unique = np.unique(y)\ncolors = cm.rainbow(np.linspace(0.0, 1.0, y_unique.size))\nfor this_y, color in zip(y_unique, colors):\n    this_X = X_train[y_train == this_y]\n    this_sw = sw_train[y_train == this_y]\n    plt.scatter(this_X[:, 0], this_X[:, 1], s=this_sw * 50,\n                c=color[np.newaxis, :],\n                alpha=0.5, edgecolor='k',\n                label=\"Class %s\" % this_y)\nplt.legend(loc=\"best\")\nplt.title(\"Data\")\n\nplt.figure()\norder = np.lexsort((prob_pos_clf, ))\nplt.plot(prob_pos_clf[order], 'r', label='No calibration (%1.3f)' % clf_score)\nplt.plot(prob_pos_isotonic[order], 'g', linewidth=3,\n         label='Isotonic calibration (%1.3f)' % clf_isotonic_score)\nplt.plot(prob_pos_sigmoid[order], 'b', linewidth=3,\n         label='Sigmoid calibration (%1.3f)' % clf_sigmoid_score)\nplt.plot(np.linspace(0, y_test.size, 51)[1::2],\n         y_test[order].reshape(25, -1).mean(1),\n         'k', linewidth=3, label=r'Empirical')\nplt.ylim([-0.05, 1.05])\nplt.xlabel(\"Instances sorted according to predicted probability \"\n           \"(uncalibrated GNB)\")\nplt.ylabel(\"P(y=1)\")\nplt.legend(loc=\"upper left\")\nplt.title(\"Gaussian naive Bayes probabilities\")\n\nplt.show()"
+        "print(__doc__)\n\n# Author: Mathieu Blondel <[email protected]>\n#         Alexandre Gramfort <[email protected]>\n#         Balazs Kegl <[email protected]>\n#         Jan Hendrik Metzen <[email protected]>\n# License: BSD Style.\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib import cm\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.metrics import brier_score_loss\nfrom sklearn.calibration import CalibratedClassifierCV\nfrom sklearn.model_selection import train_test_split\n\n\nn_samples = 50000\nn_bins = 3  # use 3 bins for calibration_curve as we have 3 clusters here\n\n# Generate 3 blobs with 2 classes where the second blob contains\n# half positive samples and half negative samples. Probability in this\n# blob is therefore 0.5.\ncenters = [(-5, -5), (0, 0), (5, 5)]\nX, y = make_blobs(n_samples=n_samples, centers=centers, shuffle=False,\n                  random_state=42)\n\ny[:n_samples // 2] = 0\ny[n_samples // 2:] = 1\nsample_weight = np.random.RandomState(42).rand(y.shape[0])\n\n# split train, test for calibration\nX_train, X_test, y_train, y_test, sw_train, sw_test = \\\n    train_test_split(X, y, sample_weight, test_size=0.9, random_state=42)\n\n# Gaussian Naive-Bayes with no calibration\nclf = GaussianNB()\nclf.fit(X_train, y_train)  # GaussianNB itself does not support sample-weights\nprob_pos_clf = clf.predict_proba(X_test)[:, 1]\n\n# Gaussian Naive-Bayes with isotonic calibration\nclf_isotonic = CalibratedClassifierCV(clf, cv=2, method='isotonic')\nclf_isotonic.fit(X_train, y_train, sample_weight=sw_train)\nprob_pos_isotonic = clf_isotonic.predict_proba(X_test)[:, 1]\n\n# Gaussian Naive-Bayes with sigmoid calibration\nclf_sigmoid = CalibratedClassifierCV(clf, cv=2, method='sigmoid')\nclf_sigmoid.fit(X_train, y_train, sample_weight=sw_train)\nprob_pos_sigmoid = clf_sigmoid.predict_proba(X_test)[:, 1]\n\nprint(\"Brier scores: (the smaller the better)\")\n\nclf_score = brier_score_loss(y_test, prob_pos_clf, sample_weight=sw_test)\nprint(\"No calibration: %1.3f\" % clf_score)\n\nclf_isotonic_score = brier_score_loss(y_test, prob_pos_isotonic,\n                                      sample_weight=sw_test)\nprint(\"With isotonic calibration: %1.3f\" % clf_isotonic_score)\n\nclf_sigmoid_score = brier_score_loss(y_test, prob_pos_sigmoid,\n                                     sample_weight=sw_test)\nprint(\"With sigmoid calibration: %1.3f\" % clf_sigmoid_score)\n\n# #############################################################################\n# Plot the data and the predicted probabilities\nplt.figure()\ny_unique = np.unique(y)\ncolors = cm.rainbow(np.linspace(0.0, 1.0, y_unique.size))\nfor this_y, color in zip(y_unique, colors):\n    this_X = X_train[y_train == this_y]\n    this_sw = sw_train[y_train == this_y]\n    plt.scatter(this_X[:, 0], this_X[:, 1], s=this_sw * 50,\n                c=color[np.newaxis, :],\n                alpha=0.5, edgecolor='k',\n                label=\"Class %s\" % this_y)\nplt.legend(loc=\"best\")\nplt.title(\"Data\")\n\nplt.figure()\norder = np.lexsort((prob_pos_clf, ))\nplt.plot(prob_pos_clf[order], 'r', label='No calibration (%1.3f)' % clf_score)\nplt.plot(prob_pos_isotonic[order], 'g', linewidth=3,\n         label='Isotonic calibration (%1.3f)' % clf_isotonic_score)\nplt.plot(prob_pos_sigmoid[order], 'b', linewidth=3,\n         label='Sigmoid calibration (%1.3f)' % clf_sigmoid_score)\nplt.plot(np.linspace(0, y_test.size, 51)[1::2],\n         y_test[order].reshape(25, -1).mean(1),\n         'k', linewidth=3, label=r'Empirical')\nplt.ylim([-0.05, 1.05])\nplt.xlabel(\"Instances sorted according to predicted probability \"\n           \"(uncalibrated GNB)\")\nplt.ylabel(\"P(y=1)\")\nplt.legend(loc=\"upper left\")\nplt.title(\"Gaussian naive Bayes probabilities\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -173,7 +173,8 @@
 # #############################################################################
 # Cluster using affinity propagation
 
-_, labels = cluster.affinity_propagation(edge_model.covariance_)
+_, labels = cluster.affinity_propagation(edge_model.covariance_,
+                                         random_state=0)
 n_labels = labels.max()
 
 for i in range(n_labels + 1):

dev/_downloads/38082c4eb06099bc72a5e5fbfff35118/plot_calibration.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors : Vincent Michel, 2010\n#           Alexandre Gramfort, 2010\n#           Gael Varoquaux, 2010\n# License: BSD 3 clause\n\nprint(__doc__)\n\nimport time as time\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport mpl_toolkits.mplot3d.axes3d as p3\nfrom sklearn.cluster import AgglomerativeClustering\nfrom sklearn.datasets import make_swiss_roll\n\n# #############################################################################\n# Generate data (swiss roll dataset)\nn_samples = 1500\nnoise = 0.05\nX, _ = make_swiss_roll(n_samples, noise)\n# Make it thinner\nX[:, 1] *= .5\n\n# #############################################################################\n# Compute clustering\nprint(\"Compute unstructured hierarchical clustering...\")\nst = time.time()\nward = AgglomerativeClustering(n_clusters=6, linkage='ward').fit(X)\nelapsed_time = time.time() - st\nlabel = ward.labels_\nprint(\"Elapsed time: %.2fs\" % elapsed_time)\nprint(\"Number of points: %i\" % label.size)\n\n# #############################################################################\n# Plot result\nfig = plt.figure()\nax = p3.Axes3D(fig)\nax.view_init(7, -80)\nfor l in np.unique(label):\n    ax.scatter(X[label == l, 0], X[label == l, 1], X[label == l, 2],\n               color=plt.cm.jet(np.float(l) / np.max(label + 1)),\n               s=20, edgecolor='k')\nplt.title('Without connectivity constraints (time %.2fs)' % elapsed_time)\n\n\n# #############################################################################\n# Define the structure A of the data. Here a 10 nearest neighbors\nfrom sklearn.neighbors import kneighbors_graph\nconnectivity = kneighbors_graph(X, n_neighbors=10, include_self=False)\n\n# #############################################################################\n# Compute clustering\nprint(\"Compute structured hierarchical clustering...\")\nst = time.time()\nward = AgglomerativeClustering(n_clusters=6, connectivity=connectivity,\n                               linkage='ward').fit(X)\nelapsed_time = time.time() - st\nlabel = ward.labels_\nprint(\"Elapsed time: %.2fs\" % elapsed_time)\nprint(\"Number of points: %i\" % label.size)\n\n# #############################################################################\n# Plot result\nfig = plt.figure()\nax = p3.Axes3D(fig)\nax.view_init(7, -80)\nfor l in np.unique(label):\n    ax.scatter(X[label == l, 0], X[label == l, 1], X[label == l, 2],\n               color=plt.cm.jet(float(l) / np.max(label + 1)),\n               s=20, edgecolor='k')\nplt.title('With connectivity constraints (time %.2fs)' % elapsed_time)\n\nplt.show()"
+        "# Authors : Vincent Michel, 2010\n#           Alexandre Gramfort, 2010\n#           Gael Varoquaux, 2010\n# License: BSD 3 clause\n\nprint(__doc__)\n\nimport time as time\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport mpl_toolkits.mplot3d.axes3d as p3\nfrom sklearn.cluster import AgglomerativeClustering\nfrom sklearn.datasets import make_swiss_roll\n\n# #############################################################################\n# Generate data (swiss roll dataset)\nn_samples = 1500\nnoise = 0.05\nX, _ = make_swiss_roll(n_samples, noise=noise)\n# Make it thinner\nX[:, 1] *= .5\n\n# #############################################################################\n# Compute clustering\nprint(\"Compute unstructured hierarchical clustering...\")\nst = time.time()\nward = AgglomerativeClustering(n_clusters=6, linkage='ward').fit(X)\nelapsed_time = time.time() - st\nlabel = ward.labels_\nprint(\"Elapsed time: %.2fs\" % elapsed_time)\nprint(\"Number of points: %i\" % label.size)\n\n# #############################################################################\n# Plot result\nfig = plt.figure()\nax = p3.Axes3D(fig)\nax.view_init(7, -80)\nfor l in np.unique(label):\n    ax.scatter(X[label == l, 0], X[label == l, 1], X[label == l, 2],\n               color=plt.cm.jet(np.float(l) / np.max(label + 1)),\n               s=20, edgecolor='k')\nplt.title('Without connectivity constraints (time %.2fs)' % elapsed_time)\n\n\n# #############################################################################\n# Define the structure A of the data. Here a 10 nearest neighbors\nfrom sklearn.neighbors import kneighbors_graph\nconnectivity = kneighbors_graph(X, n_neighbors=10, include_self=False)\n\n# #############################################################################\n# Compute clustering\nprint(\"Compute structured hierarchical clustering...\")\nst = time.time()\nward = AgglomerativeClustering(n_clusters=6, connectivity=connectivity,\n                               linkage='ward').fit(X)\nelapsed_time = time.time() - st\nlabel = ward.labels_\nprint(\"Elapsed time: %.2fs\" % elapsed_time)\nprint(\"Number of points: %i\" % label.size)\n\n# #############################################################################\n# Plot result\nfig = plt.figure()\nax = p3.Axes3D(fig)\nax.view_init(7, -80)\nfor l in np.unique(label):\n    ax.scatter(X[label == l, 0], X[label == l, 1], X[label == l, 2],\n               color=plt.cm.jet(float(l) / np.max(label + 1)),\n               s=20, edgecolor='k')\nplt.title('With connectivity constraints (time %.2fs)' % elapsed_time)\n\nplt.show()"
       ]
     }
   ],