Pushing the docs to dev/ for branch: master, commit 9fda73654361521b1f7e5a3d72d347be82e3075a

Author: sklearn-ci

dev/_downloads/01fdc7c95204e4a420de7cd297711693/plot_feature_union.py

@@ -33,7 +33,7 @@
 # This dataset is way too high-dimensional. Better do PCA:
 pca = PCA(n_components=2)
 
-# Maybe some original features where good, too?
+# Maybe some original features were good, too?
 selection = SelectKBest(k=1)
 
 # Build estimator from PCA and Univariate selection:

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Andreas Mueller <[email protected]>\n#\n# License: BSD 3 clause\n\nfrom sklearn.pipeline import Pipeline, FeatureUnion\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.svm import SVC\nfrom sklearn.datasets import load_iris\nfrom sklearn.decomposition import PCA\nfrom sklearn.feature_selection import SelectKBest\n\niris = load_iris()\n\nX, y = iris.data, iris.target\n\n# This dataset is way too high-dimensional. Better do PCA:\npca = PCA(n_components=2)\n\n# Maybe some original features where good, too?\nselection = SelectKBest(k=1)\n\n# Build estimator from PCA and Univariate selection:\n\ncombined_features = FeatureUnion([(\"pca\", pca), (\"univ_select\", selection)])\n\n# Use combined features to transform dataset:\nX_features = combined_features.fit(X, y).transform(X)\nprint(\"Combined space has\", X_features.shape[1], \"features\")\n\nsvm = SVC(kernel=\"linear\")\n\n# Do grid search over k, n_components and C:\n\npipeline = Pipeline([(\"features\", combined_features), (\"svm\", svm)])\n\nparam_grid = dict(features__pca__n_components=[1, 2, 3],\n                  features__univ_select__k=[1, 2],\n                  svm__C=[0.1, 1, 10])\n\ngrid_search = GridSearchCV(pipeline, param_grid=param_grid, verbose=10)\ngrid_search.fit(X, y)\nprint(grid_search.best_estimator_)"
+        "# Author: Andreas Mueller <[email protected]>\n#\n# License: BSD 3 clause\n\nfrom sklearn.pipeline import Pipeline, FeatureUnion\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.svm import SVC\nfrom sklearn.datasets import load_iris\nfrom sklearn.decomposition import PCA\nfrom sklearn.feature_selection import SelectKBest\n\niris = load_iris()\n\nX, y = iris.data, iris.target\n\n# This dataset is way too high-dimensional. Better do PCA:\npca = PCA(n_components=2)\n\n# Maybe some original features were good, too?\nselection = SelectKBest(k=1)\n\n# Build estimator from PCA and Univariate selection:\n\ncombined_features = FeatureUnion([(\"pca\", pca), (\"univ_select\", selection)])\n\n# Use combined features to transform dataset:\nX_features = combined_features.fit(X, y).transform(X)\nprint(\"Combined space has\", X_features.shape[1], \"features\")\n\nsvm = SVC(kernel=\"linear\")\n\n# Do grid search over k, n_components and C:\n\npipeline = Pipeline([(\"features\", combined_features), (\"svm\", svm)])\n\nparam_grid = dict(features__pca__n_components=[1, 2, 3],\n                  features__univ_select__k=[1, 2],\n                  svm__C=[0.1, 1, 10])\n\ngrid_search = GridSearchCV(pipeline, param_grid=param_grid, verbose=10)\ngrid_search.fit(X, y)\nprint(grid_search.best_estimator_)"
       ]
     }
   ],