Pushing the docs to dev/ for branch: master, commit a8efe008767c9398ee375140e99d581559319bef

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Robert McGibbon, Joel Nothman, Guillaume Lemaitre\n\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', 'passthrough'),\n    ('classify', LinearSVC(dual=False, max_iter=10000))\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, 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\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', 'passthrough'),\n    ('classify', LinearSVC(dual=False, max_iter=10000))\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, n_jobs=1, param_grid=param_grid)\nX, y = load_digits(return_X_y=True)\ngrid.fit(X, y)\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 joblib import Memory\nfrom shutil import rmtree\n\n# Create a temporary folder to store the transformers of the pipeline\n___location = 'cachedir'\nmemory = Memory(___location=___location, verbose=10)\ncached_pipe = Pipeline([('reduce_dim', PCA()),\n                        ('classify', LinearSVC(dual=False, max_iter=10000))],\n                       memory=memory)\n\n# This time, a cached pipeline will be used within the grid search\ngrid = GridSearchCV(cached_pipe, n_jobs=1, param_grid=param_grid)\ndigits = load_digits()\ngrid.fit(digits.data, digits.target)\n\n# Delete the temporary cache before exiting\nmemory.clear(warn=False)\nrmtree(___location)"
+        "from joblib import Memory\nfrom shutil import rmtree\n\n# Create a temporary folder to store the transformers of the pipeline\n___location = 'cachedir'\nmemory = Memory(___location=___location, verbose=10)\ncached_pipe = Pipeline([('reduce_dim', PCA()),\n                        ('classify', LinearSVC(dual=False, max_iter=10000))],\n                       memory=memory)\n\n# This time, a cached pipeline will be used within the grid search\n\n\n# Delete the temporary cache before exiting\nmemory.clear(warn=False)\nrmtree(___location)"
       ]
     },
     {

dev/_downloads/auto_examples_python.zip

@@ -64,8 +64,8 @@
 reducer_labels = ['PCA', 'NMF', 'KBest(chi2)']
 
 grid = GridSearchCV(pipe, n_jobs=1, param_grid=param_grid)
-digits = load_digits()
-grid.fit(digits.data, digits.target)
+X, y = load_digits(return_X_y=True)
+grid.fit(X, y)
 
 mean_scores = np.array(grid.cv_results_['mean_test_score'])
 # scores are in the order of param_grid iteration, which is alphabetical
@@ -113,9 +113,7 @@
                        memory=memory)
 
 # This time, a cached pipeline will be used within the grid search
-grid = GridSearchCV(cached_pipe, n_jobs=1, param_grid=param_grid)
-digits = load_digits()
-grid.fit(digits.data, digits.target)
+
 
 # Delete the temporary cache before exiting
 memory.clear(warn=False)

dev/_downloads/plot_compare_reduction.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n\nimport numpy as np\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn import datasets, svm\n\ndigits = datasets.load_digits()\nX = digits.data\ny = digits.target\n\nsvc = svm.SVC(kernel='linear')\nC_s = np.logspace(-10, 0, 10)\n\nscores = list()\nscores_std = list()\nfor C in C_s:\n    svc.C = C\n    this_scores = cross_val_score(svc, X, y, n_jobs=1)\n    scores.append(np.mean(this_scores))\n    scores_std.append(np.std(this_scores))\n\n# Do the plotting\nimport matplotlib.pyplot as plt\nplt.figure()\nplt.semilogx(C_s, scores)\nplt.semilogx(C_s, np.array(scores) + np.array(scores_std), 'b--')\nplt.semilogx(C_s, np.array(scores) - np.array(scores_std), 'b--')\nlocs, labels = plt.yticks()\nplt.yticks(locs, list(map(lambda x: \"%g\" % x, locs)))\nplt.ylabel('CV score')\nplt.xlabel('Parameter C')\nplt.ylim(0, 1.1)\nplt.show()"
+        "print(__doc__)\n\n\nimport numpy as np\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn import datasets, svm\n\nX, y = datasets.load_digits(return_X_y=True)\n\nsvc = svm.SVC(kernel='linear')\nC_s = np.logspace(-10, 0, 10)\n\nscores = list()\nscores_std = list()\nfor C in C_s:\n    svc.C = C\n    this_scores = cross_val_score(svc, X, y, n_jobs=1)\n    scores.append(np.mean(this_scores))\n    scores_std.append(np.std(this_scores))\n\n# Do the plotting\nimport matplotlib.pyplot as plt\nplt.figure()\nplt.semilogx(C_s, scores)\nplt.semilogx(C_s, np.array(scores) + np.array(scores_std), 'b--')\nplt.semilogx(C_s, np.array(scores) - np.array(scores_std), 'b--')\nlocs, labels = plt.yticks()\nplt.yticks(locs, list(map(lambda x: \"%g\" % x, locs)))\nplt.ylabel('CV score')\nplt.xlabel('Parameter C')\nplt.ylim(0, 1.1)\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_compare_reduction.py

@@ -15,9 +15,7 @@
 from sklearn.model_selection import cross_val_score
 from sklearn import datasets, svm
 
-digits = datasets.load_digits()
-X = digits.data
-y = digits.target
+X, y = datasets.load_digits(return_X_y=True)
 
 svc = svm.SVC(kernel='linear')
 C_s = np.logspace(-10, 0, 10)

dev/_downloads/plot_cv_digits.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nfrom sklearn import datasets, neighbors, linear_model\n\ndigits = datasets.load_digits()\nX_digits = digits.data / digits.data.max()\ny_digits = digits.target\n\nn_samples = len(X_digits)\n\nX_train = X_digits[:int(.9 * n_samples)]\ny_train = y_digits[:int(.9 * n_samples)]\nX_test = X_digits[int(.9 * n_samples):]\ny_test = y_digits[int(.9 * n_samples):]\n\nknn = neighbors.KNeighborsClassifier()\nlogistic = linear_model.LogisticRegression(max_iter=1000)\n\nprint('KNN score: %f' % knn.fit(X_train, y_train).score(X_test, y_test))\nprint('LogisticRegression score: %f'\n      % logistic.fit(X_train, y_train).score(X_test, y_test))"
+        "print(__doc__)\n\nfrom sklearn import datasets, neighbors, linear_model\n\nX_digits, y_digits = datasets.load_digits(return_X_y=True)\nX_digits = X_digits / X_digits.max()\n\nn_samples = len(X_digits)\n\nX_train = X_digits[:int(.9 * n_samples)]\ny_train = y_digits[:int(.9 * n_samples)]\nX_test = X_digits[int(.9 * n_samples):]\ny_test = y_digits[int(.9 * n_samples):]\n\nknn = neighbors.KNeighborsClassifier()\nlogistic = linear_model.LogisticRegression(max_iter=1000)\n\nprint('KNN score: %f' % knn.fit(X_train, y_train).score(X_test, y_test))\nprint('LogisticRegression score: %f'\n      % logistic.fit(X_train, y_train).score(X_test, y_test))"
       ]
     }
   ],

dev/_downloads/plot_cv_digits.py

@@ -14,9 +14,8 @@
 
 from sklearn import datasets, neighbors, linear_model
 
-digits = datasets.load_digits()
-X_digits = digits.data / digits.data.max()
-y_digits = digits.target
+X_digits, y_digits = datasets.load_digits(return_X_y=True)
+X_digits = X_digits / X_digits.max()
 
 n_samples = len(X_digits)
 

dev/_downloads/plot_digits_classification_exercise.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Gael Varoquaux\n# License: BSD 3 clause (C) INRIA 2014\n\nprint(__doc__)\nfrom time import time\n\nimport numpy as np\nfrom scipy import ndimage\nfrom matplotlib import pyplot as plt\n\nfrom sklearn import manifold, datasets\n\ndigits = datasets.load_digits(n_class=10)\nX = digits.data\ny = digits.target\nn_samples, n_features = X.shape\n\nnp.random.seed(0)\n\ndef nudge_images(X, y):\n    # Having a larger dataset shows more clearly the behavior of the\n    # methods, but we multiply the size of the dataset only by 2, as the\n    # cost of the hierarchical clustering methods are strongly\n    # super-linear in n_samples\n    shift = lambda x: ndimage.shift(x.reshape((8, 8)),\n                                  .3 * np.random.normal(size=2),\n                                  mode='constant',\n                                  ).ravel()\n    X = np.concatenate([X, np.apply_along_axis(shift, 1, X)])\n    Y = np.concatenate([y, y], axis=0)\n    return X, Y\n\n\nX, y = nudge_images(X, y)\n\n\n#----------------------------------------------------------------------\n# Visualize the clustering\ndef plot_clustering(X_red, labels, title=None):\n    x_min, x_max = np.min(X_red, axis=0), np.max(X_red, axis=0)\n    X_red = (X_red - x_min) / (x_max - x_min)\n\n    plt.figure(figsize=(6, 4))\n    for i in range(X_red.shape[0]):\n        plt.text(X_red[i, 0], X_red[i, 1], str(y[i]),\n                 color=plt.cm.nipy_spectral(labels[i] / 10.),\n                 fontdict={'weight': 'bold', 'size': 9})\n\n    plt.xticks([])\n    plt.yticks([])\n    if title is not None:\n        plt.title(title, size=17)\n    plt.axis('off')\n    plt.tight_layout(rect=[0, 0.03, 1, 0.95])\n\n#----------------------------------------------------------------------\n# 2D embedding of the digits dataset\nprint(\"Computing embedding\")\nX_red = manifold.SpectralEmbedding(n_components=2).fit_transform(X)\nprint(\"Done.\")\n\nfrom sklearn.cluster import AgglomerativeClustering\n\nfor linkage in ('ward', 'average', 'complete', 'single'):\n    clustering = AgglomerativeClustering(linkage=linkage, n_clusters=10)\n    t0 = time()\n    clustering.fit(X_red)\n    print(\"%s :\\t%.2fs\" % (linkage, time() - t0))\n\n    plot_clustering(X_red, clustering.labels_, \"%s linkage\" % linkage)\n\n\nplt.show()"
+        "# Authors: Gael Varoquaux\n# License: BSD 3 clause (C) INRIA 2014\n\nprint(__doc__)\nfrom time import time\n\nimport numpy as np\nfrom scipy import ndimage\nfrom matplotlib import pyplot as plt\n\nfrom sklearn import manifold, datasets\n\nX, y = datasets.load_digits(return_X_y=True)\nn_samples, n_features = X.shape\n\nnp.random.seed(0)\n\ndef nudge_images(X, y):\n    # Having a larger dataset shows more clearly the behavior of the\n    # methods, but we multiply the size of the dataset only by 2, as the\n    # cost of the hierarchical clustering methods are strongly\n    # super-linear in n_samples\n    shift = lambda x: ndimage.shift(x.reshape((8, 8)),\n                                  .3 * np.random.normal(size=2),\n                                  mode='constant',\n                                  ).ravel()\n    X = np.concatenate([X, np.apply_along_axis(shift, 1, X)])\n    Y = np.concatenate([y, y], axis=0)\n    return X, Y\n\n\nX, y = nudge_images(X, y)\n\n\n#----------------------------------------------------------------------\n# Visualize the clustering\ndef plot_clustering(X_red, labels, title=None):\n    x_min, x_max = np.min(X_red, axis=0), np.max(X_red, axis=0)\n    X_red = (X_red - x_min) / (x_max - x_min)\n\n    plt.figure(figsize=(6, 4))\n    for i in range(X_red.shape[0]):\n        plt.text(X_red[i, 0], X_red[i, 1], str(y[i]),\n                 color=plt.cm.nipy_spectral(labels[i] / 10.),\n                 fontdict={'weight': 'bold', 'size': 9})\n\n    plt.xticks([])\n    plt.yticks([])\n    if title is not None:\n        plt.title(title, size=17)\n    plt.axis('off')\n    plt.tight_layout(rect=[0, 0.03, 1, 0.95])\n\n#----------------------------------------------------------------------\n# 2D embedding of the digits dataset\nprint(\"Computing embedding\")\nX_red = manifold.SpectralEmbedding(n_components=2).fit_transform(X)\nprint(\"Done.\")\n\nfrom sklearn.cluster import AgglomerativeClustering\n\nfor linkage in ('ward', 'average', 'complete', 'single'):\n    clustering = AgglomerativeClustering(linkage=linkage, n_clusters=10)\n    t0 = time()\n    clustering.fit(X_red)\n    print(\"%s :\\t%.2fs\" % (linkage, time() - t0))\n\n    plot_clustering(X_red, clustering.labels_, \"%s linkage\" % linkage)\n\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_digits_classification_exercise.py

@@ -30,9 +30,7 @@
 
 from sklearn import manifold, datasets
 
-digits = datasets.load_digits(n_class=10)
-X = digits.data
-y = digits.target
+X, y = datasets.load_digits(return_X_y=True)
 n_samples, n_features = X.shape
 
 np.random.seed(0)