Pushing the docs for revision for branch: master, commit 28bcb43dd2eacfaa98f0215ec8481e0da9f8ec5d

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -24,7 +24,7 @@
       "execution_count": null, 
       "cell_type": "code", 
       "source": [
-        "from __future__ import print_function\n\nfrom time import time\nimport logging\nimport matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.datasets import fetch_lfw_people\nfrom sklearn.metrics import classification_report\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.decomposition import RandomizedPCA\nfrom sklearn.svm import SVC\n\n\nprint(__doc__)\n\n# Display progress logs on stdout\nlogging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')"
+        "from __future__ import print_function\n\nfrom time import time\nimport logging\nimport matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.datasets import fetch_lfw_people\nfrom sklearn.metrics import classification_report\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.decomposition import PCA\nfrom sklearn.svm import SVC\n\n\nprint(__doc__)\n\n# Display progress logs on stdout\nlogging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')"
       ], 
       "outputs": [], 
       "metadata": {
@@ -78,7 +78,7 @@
       "execution_count": null, 
       "cell_type": "code", 
       "source": [
-        "n_components = 150\n\nprint(\"Extracting the top %d eigenfaces from %d faces\"\n      % (n_components, X_train.shape[0]))\nt0 = time()\npca = RandomizedPCA(n_components=n_components, whiten=True).fit(X_train)\nprint(\"done in %0.3fs\" % (time() - t0))\n\neigenfaces = pca.components_.reshape((n_components, h, w))\n\nprint(\"Projecting the input data on the eigenfaces orthonormal basis\")\nt0 = time()\nX_train_pca = pca.transform(X_train)\nX_test_pca = pca.transform(X_test)\nprint(\"done in %0.3fs\" % (time() - t0))"
+        "n_components = 150\n\nprint(\"Extracting the top %d eigenfaces from %d faces\"\n      % (n_components, X_train.shape[0]))\nt0 = time()\npca = PCA(n_components=n_components, svd_solver='randomized',\n          whiten=True).fit(X_train)\nprint(\"done in %0.3fs\" % (time() - t0))\n\neigenfaces = pca.components_.reshape((n_components, h, w))\n\nprint(\"Projecting the input data on the eigenfaces orthonormal basis\")\nt0 = time()\nX_train_pca = pca.transform(X_train)\nX_test_pca = pca.transform(X_test)\nprint(\"done in %0.3fs\" % (time() - t0))"
       ], 
       "outputs": [], 
       "metadata": {

dev/_downloads/auto_examples_python.zip

@@ -38,7 +38,7 @@
 from sklearn.datasets import fetch_lfw_people
 from sklearn.metrics import classification_report
 from sklearn.metrics import confusion_matrix
-from sklearn.decomposition import RandomizedPCA
+from sklearn.decomposition import PCA
 from sklearn.svm import SVC
 
 
@@ -88,7 +88,8 @@
 print("Extracting the top %d eigenfaces from %d faces"
       % (n_components, X_train.shape[0]))
 t0 = time()
-pca = RandomizedPCA(n_components=n_components, whiten=True).fit(X_train)
+pca = PCA(n_components=n_components, svd_solver='randomized',
+          whiten=True).fit(X_train)
 print("done in %0.3fs" % (time() - t0))
 
 eigenfaces = pca.components_.reshape((n_components, h, w))

dev/_downloads/face_recognition.ipynb

@@ -71,7 +71,7 @@
       "execution_count": null, 
       "cell_type": "code", 
       "source": [
-        "estimators = [\n    ('Eigenfaces - RandomizedPCA',\n     decomposition.RandomizedPCA(n_components=n_components, whiten=True),\n     True),\n\n    ('Non-negative components - NMF',\n     decomposition.NMF(n_components=n_components, init='nndsvda', tol=5e-3),\n     False),\n\n    ('Independent components - FastICA',\n     decomposition.FastICA(n_components=n_components, whiten=True),\n     True),\n\n    ('Sparse comp. - MiniBatchSparsePCA',\n     decomposition.MiniBatchSparsePCA(n_components=n_components, alpha=0.8,\n                                      n_iter=100, batch_size=3,\n                                      random_state=rng),\n     True),\n\n    ('MiniBatchDictionaryLearning',\n        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,\n                                                  n_iter=50, batch_size=3,\n                                                  random_state=rng),\n     True),\n\n    ('Cluster centers - MiniBatchKMeans',\n        MiniBatchKMeans(n_clusters=n_components, tol=1e-3, batch_size=20,\n                        max_iter=50, random_state=rng),\n     True),\n\n    ('Factor Analysis components - FA',\n     decomposition.FactorAnalysis(n_components=n_components, max_iter=2),\n     True),\n]"
+        "estimators = [\n    ('Eigenfaces - PCA using randomized SVD',\n     decomposition.PCA(n_components=n_components, svd_solver='randomized',\n                       whiten=True),\n     True),\n\n    ('Non-negative components - NMF',\n     decomposition.NMF(n_components=n_components, init='nndsvda', tol=5e-3),\n     False),\n\n    ('Independent components - FastICA',\n     decomposition.FastICA(n_components=n_components, whiten=True),\n     True),\n\n    ('Sparse comp. - MiniBatchSparsePCA',\n     decomposition.MiniBatchSparsePCA(n_components=n_components, alpha=0.8,\n                                      n_iter=100, batch_size=3,\n                                      random_state=rng),\n     True),\n\n    ('MiniBatchDictionaryLearning',\n        decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,\n                                                  n_iter=50, batch_size=3,\n                                                  random_state=rng),\n     True),\n\n    ('Cluster centers - MiniBatchKMeans',\n        MiniBatchKMeans(n_clusters=n_components, tol=1e-3, batch_size=20,\n                        max_iter=50, random_state=rng),\n     True),\n\n    ('Factor Analysis components - FA',\n     decomposition.FactorAnalysis(n_components=n_components, max_iter=2),\n     True),\n]"
       ], 
       "outputs": [], 
       "metadata": {
@@ -107,7 +107,7 @@
       "execution_count": null, 
       "cell_type": "code", 
       "source": [
-        "for name, estimator, center in estimators:\n    print(\"Extracting the top %d %s...\" % (n_components, name))\n    t0 = time()\n    data = faces\n    if center:\n        data = faces_centered\n    estimator.fit(data)\n    train_time = (time() - t0)\n    print(\"done in %0.3fs\" % train_time)\n    if hasattr(estimator, 'cluster_centers_'):\n        components_ = estimator.cluster_centers_\n    else:\n        components_ = estimator.components_\n    if hasattr(estimator, 'noise_variance_'):\n        plot_gallery(\"Pixelwise variance\",\n                     estimator.noise_variance_.reshape(1, -1), n_col=1,\n                     n_row=1)\n    plot_gallery('%s - Train time %.1fs' % (name, train_time),\n                 components_[:n_components])\n\nplt.show()"
+        "for name, estimator, center in estimators:\n    print(\"Extracting the top %d %s...\" % (n_components, name))\n    t0 = time()\n    data = faces\n    if center:\n        data = faces_centered\n    estimator.fit(data)\n    train_time = (time() - t0)\n    print(\"done in %0.3fs\" % train_time)\n    if hasattr(estimator, 'cluster_centers_'):\n        components_ = estimator.cluster_centers_\n    else:\n        components_ = estimator.components_\n\n    # Plot an image representing the pixelwise variance provided by the\n    # estimator e.g its noise_variance_ attribute. The Eigenfaces estimator,\n    # via the PCA decomposition, also provides a scalar noise_variance_\n    # (the mean of pixelwise variance) that cannot be displayed as an image\n    # so we skip it.\n    if (hasattr(estimator, 'noise_variance_') and\n            estimator.noise_variance_.ndim > 0):  # Skip the Eigenfaces case\n        plot_gallery(\"Pixelwise variance\",\n                     estimator.noise_variance_.reshape(1, -1), n_col=1,\n                     n_row=1)\n    plot_gallery('%s - Train time %.1fs' % (name, train_time),\n                 components_[:n_components])\n\nplt.show()"
       ], 
       "outputs": [], 
       "metadata": {

dev/_downloads/face_recognition.py

@@ -66,8 +66,9 @@ def plot_gallery(title, images, n_col=n_col, n_row=n_row):
 # List of the different estimators, whether to center and transpose the
 # problem, and whether the transformer uses the clustering API.
 estimators = [
-    ('Eigenfaces - RandomizedPCA',
-     decomposition.RandomizedPCA(n_components=n_components, whiten=True),
+    ('Eigenfaces - PCA using randomized SVD',
+     decomposition.PCA(n_components=n_components, svd_solver='randomized',
+                       whiten=True),
      True),
 
     ('Non-negative components - NMF',
@@ -122,7 +123,14 @@ def plot_gallery(title, images, n_col=n_col, n_row=n_row):
         components_ = estimator.cluster_centers_
     else:
         components_ = estimator.components_
-    if hasattr(estimator, 'noise_variance_'):
+
+    # Plot an image representing the pixelwise variance provided by the
+    # estimator e.g its noise_variance_ attribute. The Eigenfaces estimator,
+    # via the PCA decomposition, also provides a scalar noise_variance_
+    # (the mean of pixelwise variance) that cannot be displayed as an image
+    # so we skip it.
+    if (hasattr(estimator, 'noise_variance_') and
+            estimator.noise_variance_.ndim > 0):  # Skip the Eigenfaces case
         plot_gallery("Pixelwise variance",
                      estimator.noise_variance_.reshape(1, -1), n_col=1,
                      n_row=1)