Pushing the docs to 0.20/ for branch: 0.20.X, commit 6ccb5e44b188059e9b7459ac02ec97e32a9ab7ba

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: 726aaa28f936aa10264bf852fdf9bba1
+config: 76a21e8239c81e76ffaf2e22051b6f01
 tags: 645f666f9bcd5a90fca523b33c5a78b7

0.20/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Manoj Kumar <[email protected]\n#          Alexandre Gramfort <[email protected]>\n# License: BSD 3 clause\n\nprint(__doc__)\n\nfrom itertools import cycle\nfrom time import time\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.colors as colors\n\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.cluster import Birch, MiniBatchKMeans\nfrom sklearn.datasets.samples_generator import make_blobs\n\n\n# Generate centers for the blobs so that it forms a 10 X 10 grid.\nxx = np.linspace(-22, 22, 10)\nyy = np.linspace(-22, 22, 10)\nxx, yy = np.meshgrid(xx, yy)\nn_centres = np.hstack((np.ravel(xx)[:, np.newaxis],\n                       np.ravel(yy)[:, np.newaxis]))\n\n# Generate blobs to do a comparison between MiniBatchKMeans and Birch.\nX, y = make_blobs(n_samples=100000, centers=n_centres, random_state=0)\n\n# Use all colors that matplotlib provides by default.\ncolors_ = cycle(colors.cnames.keys())\n\nfig = plt.figure(figsize=(12, 4))\nfig.subplots_adjust(left=0.04, right=0.98, bottom=0.1, top=0.9)\n\n# Compute clustering with Birch with and without the final clustering step\n# and plot.\nbirch_models = [Birch(threshold=1.7, n_clusters=None),\n                Birch(threshold=1.7, n_clusters=100)]\nfinal_step = ['without global clustering', 'with global clustering']\n\nfor ind, (birch_model, info) in enumerate(zip(birch_models, final_step)):\n    t = time()\n    birch_model.fit(X)\n    time_ = time() - t\n    print(\"Birch %s as the final step took %0.2f seconds\" % (\n          info, (time() - t)))\n\n    # Plot result\n    labels = birch_model.labels_\n    centroids = birch_model.subcluster_centers_\n    n_clusters = np.unique(labels).size\n    print(\"n_clusters : %d\" % n_clusters)\n\n    ax = fig.add_subplot(1, 3, ind + 1)\n    for this_centroid, k, col in zip(centroids, range(n_clusters), colors_):\n        mask = labels == k\n        ax.scatter(X[mask, 0], X[mask, 1],\n                   c='w', edgecolor=col, marker='.', alpha=0.5)\n        if birch_model.n_clusters is None:\n            ax.scatter(this_centroid[0], this_centroid[1], marker='+',\n                       c='k', s=25)\n    ax.set_ylim([-25, 25])\n    ax.set_xlim([-25, 25])\n    ax.set_autoscaley_on(False)\n    ax.set_title('Birch %s' % info)\n\n# Compute clustering with MiniBatchKMeans.\nmbk = MiniBatchKMeans(init='k-means++', n_clusters=100, batch_size=100,\n                      n_init=10, max_no_improvement=10, verbose=0,\n                      random_state=0)\nt0 = time()\nmbk.fit(X)\nt_mini_batch = time() - t0\nprint(\"Time taken to run MiniBatchKMeans %0.2f seconds\" % t_mini_batch)\nmbk_means_labels_unique = np.unique(mbk.labels_)\n\nax = fig.add_subplot(1, 3, 3)\nfor this_centroid, k, col in zip(mbk.cluster_centers_,\n                                 range(n_clusters), colors_):\n    mask = mbk.labels_ == k\n    ax.scatter(X[mask, 0], X[mask, 1], marker='.',\n               c='w', edgecolor=col, alpha=0.5)\n    ax.scatter(this_centroid[0], this_centroid[1], marker='+',\n               c='k', s=25)\nax.set_xlim([-25, 25])\nax.set_ylim([-25, 25])\nax.set_title(\"MiniBatchKMeans\")\nax.set_autoscaley_on(False)\nplt.show()"
+        "# Authors: Manoj Kumar <[email protected]\n#          Alexandre Gramfort <[email protected]>\n# License: BSD 3 clause\n\nprint(__doc__)\n\nfrom itertools import cycle\nfrom time import time\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.colors as colors\n\nfrom sklearn.cluster import Birch, MiniBatchKMeans\nfrom sklearn.datasets.samples_generator import make_blobs\n\n\n# Generate centers for the blobs so that it forms a 10 X 10 grid.\nxx = np.linspace(-22, 22, 10)\nyy = np.linspace(-22, 22, 10)\nxx, yy = np.meshgrid(xx, yy)\nn_centres = np.hstack((np.ravel(xx)[:, np.newaxis],\n                       np.ravel(yy)[:, np.newaxis]))\n\n# Generate blobs to do a comparison between MiniBatchKMeans and Birch.\nX, y = make_blobs(n_samples=100000, centers=n_centres, random_state=0)\n\n# Use all colors that matplotlib provides by default.\ncolors_ = cycle(colors.cnames.keys())\n\nfig = plt.figure(figsize=(12, 4))\nfig.subplots_adjust(left=0.04, right=0.98, bottom=0.1, top=0.9)\n\n# Compute clustering with Birch with and without the final clustering step\n# and plot.\nbirch_models = [Birch(threshold=1.7, n_clusters=None),\n                Birch(threshold=1.7, n_clusters=100)]\nfinal_step = ['without global clustering', 'with global clustering']\n\nfor ind, (birch_model, info) in enumerate(zip(birch_models, final_step)):\n    t = time()\n    birch_model.fit(X)\n    time_ = time() - t\n    print(\"Birch %s as the final step took %0.2f seconds\" % (\n          info, (time() - t)))\n\n    # Plot result\n    labels = birch_model.labels_\n    centroids = birch_model.subcluster_centers_\n    n_clusters = np.unique(labels).size\n    print(\"n_clusters : %d\" % n_clusters)\n\n    ax = fig.add_subplot(1, 3, ind + 1)\n    for this_centroid, k, col in zip(centroids, range(n_clusters), colors_):\n        mask = labels == k\n        ax.scatter(X[mask, 0], X[mask, 1],\n                   c='w', edgecolor=col, marker='.', alpha=0.5)\n        if birch_model.n_clusters is None:\n            ax.scatter(this_centroid[0], this_centroid[1], marker='+',\n                       c='k', s=25)\n    ax.set_ylim([-25, 25])\n    ax.set_xlim([-25, 25])\n    ax.set_autoscaley_on(False)\n    ax.set_title('Birch %s' % info)\n\n# Compute clustering with MiniBatchKMeans.\nmbk = MiniBatchKMeans(init='k-means++', n_clusters=100, batch_size=100,\n                      n_init=10, max_no_improvement=10, verbose=0,\n                      random_state=0)\nt0 = time()\nmbk.fit(X)\nt_mini_batch = time() - t0\nprint(\"Time taken to run MiniBatchKMeans %0.2f seconds\" % t_mini_batch)\nmbk_means_labels_unique = np.unique(mbk.labels_)\n\nax = fig.add_subplot(1, 3, 3)\nfor this_centroid, k, col in zip(mbk.cluster_centers_,\n                                 range(n_clusters), colors_):\n    mask = mbk.labels_ == k\n    ax.scatter(X[mask, 0], X[mask, 1], marker='.',\n               c='w', edgecolor=col, alpha=0.5)\n    ax.scatter(this_centroid[0], this_centroid[1], marker='+',\n               c='k', s=25)\nax.set_xlim([-25, 25])\nax.set_ylim([-25, 25])\nax.set_title(\"MiniBatchKMeans\")\nax.set_autoscaley_on(False)\nplt.show()"
       ]
     }
   ],

0.20/_downloads/auto_examples_python.zip

@@ -25,7 +25,6 @@
 import matplotlib.pyplot as plt
 import matplotlib.colors as colors
 
-from sklearn.preprocessing import StandardScaler
 from sklearn.cluster import Birch, MiniBatchKMeans
 from sklearn.datasets.samples_generator import make_blobs
 

0.20/_downloads/plot_birch_vs_minibatchkmeans.ipynb

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Robert McGibbon, Joel Nothman, Guillaume Lemaitre\n\nfrom __future__ import print_function, division\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import load_digits\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.svm import LinearSVC\nfrom sklearn.decomposition import PCA, NMF\nfrom sklearn.feature_selection import SelectKBest, chi2\n\nprint(__doc__)\n\npipe = Pipeline([\n    ('reduce_dim', PCA()),\n    ('classify', LinearSVC())\n])\n\nN_FEATURES_OPTIONS = [2, 4, 8]\nC_OPTIONS = [1, 10, 100, 1000]\nparam_grid = [\n    {\n        'reduce_dim': [PCA(iterated_power=7), NMF()],\n        'reduce_dim__n_components': N_FEATURES_OPTIONS,\n        'classify__C': C_OPTIONS\n    },\n    {\n        'reduce_dim': [SelectKBest(chi2)],\n        'reduce_dim__k': N_FEATURES_OPTIONS,\n        'classify__C': C_OPTIONS\n    },\n]\nreducer_labels = ['PCA', 'NMF', 'KBest(chi2)']\n\ngrid = GridSearchCV(pipe, cv=5, n_jobs=1, param_grid=param_grid)\ndigits = load_digits()\ngrid.fit(digits.data, digits.target)\n\nmean_scores = np.array(grid.cv_results_['mean_test_score'])\n# scores are in the order of param_grid iteration, which is alphabetical\nmean_scores = mean_scores.reshape(len(C_OPTIONS), -1, len(N_FEATURES_OPTIONS))\n# select score for best C\nmean_scores = mean_scores.max(axis=0)\nbar_offsets = (np.arange(len(N_FEATURES_OPTIONS)) *\n               (len(reducer_labels) + 1) + .5)\n\nplt.figure()\nCOLORS = 'bgrcmyk'\nfor i, (label, reducer_scores) in enumerate(zip(reducer_labels, mean_scores)):\n    plt.bar(bar_offsets + i, reducer_scores, label=label, color=COLORS[i])\n\nplt.title(\"Comparing feature reduction techniques\")\nplt.xlabel('Reduced number of features')\nplt.xticks(bar_offsets + len(reducer_labels) / 2, N_FEATURES_OPTIONS)\nplt.ylabel('Digit classification accuracy')\nplt.ylim((0, 1))\nplt.legend(loc='upper left')\n\nplt.show()"
+        "# Authors: Robert McGibbon, Joel Nothman, Guillaume Lemaitre\n\nfrom __future__ import print_function, division\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import load_digits\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.svm import LinearSVC\nfrom sklearn.decomposition import PCA, NMF\nfrom sklearn.feature_selection import SelectKBest, chi2\n\nprint(__doc__)\n\npipe = Pipeline([\n    # the reduce_dim stage is populated by the param_grid\n    ('reduce_dim', None),\n    ('classify', LinearSVC())\n])\n\nN_FEATURES_OPTIONS = [2, 4, 8]\nC_OPTIONS = [1, 10, 100, 1000]\nparam_grid = [\n    {\n        'reduce_dim': [PCA(iterated_power=7), NMF()],\n        'reduce_dim__n_components': N_FEATURES_OPTIONS,\n        'classify__C': C_OPTIONS\n    },\n    {\n        'reduce_dim': [SelectKBest(chi2)],\n        'reduce_dim__k': N_FEATURES_OPTIONS,\n        'classify__C': C_OPTIONS\n    },\n]\nreducer_labels = ['PCA', 'NMF', 'KBest(chi2)']\n\ngrid = GridSearchCV(pipe, cv=5, n_jobs=1, param_grid=param_grid)\ndigits = load_digits()\ngrid.fit(digits.data, digits.target)\n\nmean_scores = np.array(grid.cv_results_['mean_test_score'])\n# scores are in the order of param_grid iteration, which is alphabetical\nmean_scores = mean_scores.reshape(len(C_OPTIONS), -1, len(N_FEATURES_OPTIONS))\n# select score for best C\nmean_scores = mean_scores.max(axis=0)\nbar_offsets = (np.arange(len(N_FEATURES_OPTIONS)) *\n               (len(reducer_labels) + 1) + .5)\n\nplt.figure()\nCOLORS = 'bgrcmyk'\nfor i, (label, reducer_scores) in enumerate(zip(reducer_labels, mean_scores)):\n    plt.bar(bar_offsets + i, reducer_scores, label=label, color=COLORS[i])\n\nplt.title(\"Comparing feature reduction techniques\")\nplt.xlabel('Reduced number of features')\nplt.xticks(bar_offsets + len(reducer_labels) / 2, N_FEATURES_OPTIONS)\nplt.ylabel('Digit classification accuracy')\nplt.ylim((0, 1))\nplt.legend(loc='upper left')\n\nplt.show()"
       ]
     },
     {
@@ -51,7 +51,7 @@
       },
       "outputs": [],
       "source": [
-        "from tempfile import mkdtemp\nfrom shutil import rmtree\nfrom sklearn.utils import Memory\n\n# Create a temporary folder to store the transformers of the pipeline\ncachedir = mkdtemp()\nmemory = Memory(cachedir=cachedir, verbose=10)\ncached_pipe = Pipeline([('reduce_dim', PCA()),\n                        ('classify', LinearSVC())],\n                       memory=memory)\n\n# This time, a cached pipeline will be used within the grid search\ngrid = GridSearchCV(cached_pipe, cv=5, n_jobs=1, param_grid=param_grid)\ndigits = load_digits()\ngrid.fit(digits.data, digits.target)\n\n# Delete the temporary cache before exiting\nrmtree(cachedir)"
+        "from tempfile import mkdtemp\nfrom shutil import rmtree\nfrom joblib import Memory\n\n# Create a temporary folder to store the transformers of the pipeline\ncachedir = mkdtemp()\nmemory = Memory(cachedir=cachedir, verbose=10)\ncached_pipe = Pipeline([('reduce_dim', PCA()),\n                        ('classify', LinearSVC())],\n                       memory=memory)\n\n# This time, a cached pipeline will be used within the grid search\ngrid = GridSearchCV(cached_pipe, cv=5, n_jobs=1, param_grid=param_grid)\ndigits = load_digits()\ngrid.fit(digits.data, digits.target)\n\n# Delete the temporary cache before exiting\nrmtree(cachedir)"
       ]
     },
     {

0.20/_downloads/plot_birch_vs_minibatchkmeans.py

@@ -43,7 +43,8 @@
 print(__doc__)
 
 pipe = Pipeline([
-    ('reduce_dim', PCA()),
+    # the reduce_dim stage is populated by the param_grid
+    ('reduce_dim', None),
     ('classify', LinearSVC())
 ])
 
@@ -104,7 +105,7 @@
 
 from tempfile import mkdtemp
 from shutil import rmtree
-from sklearn.utils import Memory
+from joblib import Memory
 
 # Create a temporary folder to store the transformers of the pipeline
 cachedir = mkdtemp()

0.20/_downloads/plot_compare_reduction.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\n\nfrom sklearn.cluster import DBSCAN\nfrom sklearn import metrics\nfrom sklearn.datasets.samples_generator import make_blobs\nfrom sklearn.preprocessing import StandardScaler\n\n\n# #############################################################################\n# Generate sample data\ncenters = [[1, 1], [-1, -1], [1, -1]]\nX, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,\n                            random_state=0)\n\nX = StandardScaler().fit_transform(X)\n\n# #############################################################################\n# Compute DBSCAN\ndb = DBSCAN(eps=0.3, min_samples=10).fit(X)\ncore_samples_mask = np.zeros_like(db.labels_, dtype=bool)\ncore_samples_mask[db.core_sample_indices_] = True\nlabels = db.labels_\n\n# Number of clusters in labels, ignoring noise if present.\nn_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)\n\nprint('Estimated number of clusters: %d' % n_clusters_)\nprint(\"Homogeneity: %0.3f\" % metrics.homogeneity_score(labels_true, labels))\nprint(\"Completeness: %0.3f\" % metrics.completeness_score(labels_true, labels))\nprint(\"V-measure: %0.3f\" % metrics.v_measure_score(labels_true, labels))\nprint(\"Adjusted Rand Index: %0.3f\"\n      % metrics.adjusted_rand_score(labels_true, labels))\nprint(\"Adjusted Mutual Information: %0.3f\"\n      % metrics.adjusted_mutual_info_score(labels_true, labels))\nprint(\"Silhouette Coefficient: %0.3f\"\n      % metrics.silhouette_score(X, labels))\n\n# #############################################################################\n# Plot result\nimport matplotlib.pyplot as plt\n\n# Black removed and is used for noise instead.\nunique_labels = set(labels)\ncolors = [plt.cm.Spectral(each)\n          for each in np.linspace(0, 1, len(unique_labels))]\nfor k, col in zip(unique_labels, colors):\n    if k == -1:\n        # Black used for noise.\n        col = [0, 0, 0, 1]\n\n    class_member_mask = (labels == k)\n\n    xy = X[class_member_mask & core_samples_mask]\n    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),\n             markeredgecolor='k', markersize=14)\n\n    xy = X[class_member_mask & ~core_samples_mask]\n    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),\n             markeredgecolor='k', markersize=6)\n\nplt.title('Estimated number of clusters: %d' % n_clusters_)\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\n\nfrom sklearn.cluster import DBSCAN\nfrom sklearn import metrics\nfrom sklearn.datasets.samples_generator import make_blobs\nfrom sklearn.preprocessing import StandardScaler\n\n\n# #############################################################################\n# Generate sample data\ncenters = [[1, 1], [-1, -1], [1, -1]]\nX, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,\n                            random_state=0)\n\nX = StandardScaler().fit_transform(X)\n\n# #############################################################################\n# Compute DBSCAN\ndb = DBSCAN(eps=0.3, min_samples=10).fit(X)\ncore_samples_mask = np.zeros_like(db.labels_, dtype=bool)\ncore_samples_mask[db.core_sample_indices_] = True\nlabels = db.labels_\n\n# Number of clusters in labels, ignoring noise if present.\nn_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)\nn_noise_ = list(labels).count(-1)\n\nprint('Estimated number of clusters: %d' % n_clusters_)\nprint('Estimated number of noise points: %d' % n_noise_)\nprint(\"Homogeneity: %0.3f\" % metrics.homogeneity_score(labels_true, labels))\nprint(\"Completeness: %0.3f\" % metrics.completeness_score(labels_true, labels))\nprint(\"V-measure: %0.3f\" % metrics.v_measure_score(labels_true, labels))\nprint(\"Adjusted Rand Index: %0.3f\"\n      % metrics.adjusted_rand_score(labels_true, labels))\nprint(\"Adjusted Mutual Information: %0.3f\"\n      % metrics.adjusted_mutual_info_score(labels_true, labels))\nprint(\"Silhouette Coefficient: %0.3f\"\n      % metrics.silhouette_score(X, labels))\n\n# #############################################################################\n# Plot result\nimport matplotlib.pyplot as plt\n\n# Black removed and is used for noise instead.\nunique_labels = set(labels)\ncolors = [plt.cm.Spectral(each)\n          for each in np.linspace(0, 1, len(unique_labels))]\nfor k, col in zip(unique_labels, colors):\n    if k == -1:\n        # Black used for noise.\n        col = [0, 0, 0, 1]\n\n    class_member_mask = (labels == k)\n\n    xy = X[class_member_mask & core_samples_mask]\n    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),\n             markeredgecolor='k', markersize=14)\n\n    xy = X[class_member_mask & ~core_samples_mask]\n    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),\n             markeredgecolor='k', markersize=6)\n\nplt.title('Estimated number of clusters: %d' % n_clusters_)\nplt.show()"
       ]
     }
   ],

0.20/_downloads/plot_compare_reduction.py

@@ -34,8 +34,10 @@
 
 # Number of clusters in labels, ignoring noise if present.
 n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
+n_noise_ = list(labels).count(-1)
 
 print('Estimated number of clusters: %d' % n_clusters_)
+print('Estimated number of noise points: %d' % n_noise_)
 print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
 print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
 print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))