Pushing the docs to dev/ for branch: master, commit f1fa2ed15f4aa7f4f34e630abf3b16569e4b3527

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -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=3, 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')"
+        "# 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=3, 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()"
       ]
     },
     {
@@ -60,17 +60,6 @@
       "source": [
         "The ``PCA`` fitting is only computed at the evaluation of the first\nconfiguration of the ``C`` parameter of the ``LinearSVC`` classifier. The\nother configurations of ``C`` will trigger the loading of the cached ``PCA``\nestimator data, leading to save processing time. Therefore, the use of\ncaching the pipeline using ``memory`` is highly beneficial when fitting\na transformer is costly.\n\n"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "plt.show()"
-      ]
     }
   ],
   "metadata": {

dev/_downloads/auto_examples_python.zip

@@ -87,6 +87,8 @@
 plt.ylim((0, 1))
 plt.legend(loc='upper left')
 
+plt.show()
+
 ###############################################################################
 # Caching transformers within a ``Pipeline``
 ###############################################################################
@@ -126,5 +128,3 @@
 # estimator data, leading to save processing time. Therefore, the use of
 # caching the pipeline using ``memory`` is highly beneficial when fitting
 # a transformer is costly.
-
-plt.show()