Pushing the docs to dev/ for branch: master, commit 81d2178ed0971586be7679e1efee56d3577c8810

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -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()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -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))