Pushing the docs to dev/ for branch: master, commit acb810647233e40839203ac553429e8663169702

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n\n# Author: Issam H. Laradji\n# License: BSD 3 clause\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom matplotlib.colors import ListedColormap\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.datasets import make_moons, make_circles, make_classification\nfrom sklearn.neural_network import MLPClassifier\n\nh = .02  # step size in the mesh\n\nalphas = np.logspace(-5, 3, 5)\nnames = []\nfor i in alphas:\n    names.append('alpha ' + str(i))\n\nclassifiers = []\nfor i in alphas:\n    classifiers.append(MLPClassifier(alpha=i, random_state=1))\n\nX, y = make_classification(n_features=2, n_redundant=0, n_informative=2,\n                           random_state=0, n_clusters_per_class=1)\nrng = np.random.RandomState(2)\nX += 2 * rng.uniform(size=X.shape)\nlinearly_separable = (X, y)\n\ndatasets = [make_moons(noise=0.3, random_state=0),\n            make_circles(noise=0.2, factor=0.5, random_state=1),\n            linearly_separable]\n\nfigure = plt.figure(figsize=(17, 9))\ni = 1\n# iterate over datasets\nfor X, y in datasets:\n    # preprocess dataset, split into training and test part\n    X = StandardScaler().fit_transform(X)\n    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)\n\n    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5\n    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n                         np.arange(y_min, y_max, h))\n\n    # just plot the dataset first\n    cm = plt.cm.RdBu\n    cm_bright = ListedColormap(['#FF0000', '#0000FF'])\n    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n    # Plot the training points\n    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)\n    # and testing points\n    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)\n    ax.set_xlim(xx.min(), xx.max())\n    ax.set_ylim(yy.min(), yy.max())\n    ax.set_xticks(())\n    ax.set_yticks(())\n    i += 1\n\n    # iterate over classifiers\n    for name, clf in zip(names, classifiers):\n        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n        clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n\n        # Plot the decision boundary. For that, we will assign a color to each\n        # point in the mesh [x_min, x_max]x[y_min, y_max].\n        if hasattr(clf, \"decision_function\"):\n            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\n        else:\n            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]\n\n        # Put the result into a color plot\n        Z = Z.reshape(xx.shape)\n        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)\n\n        # Plot also the training points\n        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,\n                   edgecolors='black', s=25)\n        # and testing points\n        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,\n                   alpha=0.6, edgecolors='black', s=25)\n\n        ax.set_xlim(xx.min(), xx.max())\n        ax.set_ylim(yy.min(), yy.max())\n        ax.set_xticks(())\n        ax.set_yticks(())\n        ax.set_title(name)\n        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),\n                size=15, horizontalalignment='right')\n        i += 1\n\nfigure.subplots_adjust(left=.02, right=.98)\nplt.show()"
+        "print(__doc__)\n\n\n# Author: Issam H. Laradji\n# License: BSD 3 clause\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom matplotlib.colors import ListedColormap\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.datasets import make_moons, make_circles, make_classification\nfrom sklearn.neural_network import MLPClassifier\n\nh = .02  # step size in the mesh\n\nalphas = np.logspace(-5, 3, 5)\nnames = ['alpha ' + str(i) for i in alphas]\n\nclassifiers = []\nfor i in alphas:\n    classifiers.append(MLPClassifier(alpha=i, random_state=1))\n\nX, y = make_classification(n_features=2, n_redundant=0, n_informative=2,\n                           random_state=0, n_clusters_per_class=1)\nrng = np.random.RandomState(2)\nX += 2 * rng.uniform(size=X.shape)\nlinearly_separable = (X, y)\n\ndatasets = [make_moons(noise=0.3, random_state=0),\n            make_circles(noise=0.2, factor=0.5, random_state=1),\n            linearly_separable]\n\nfigure = plt.figure(figsize=(17, 9))\ni = 1\n# iterate over datasets\nfor X, y in datasets:\n    # preprocess dataset, split into training and test part\n    X = StandardScaler().fit_transform(X)\n    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)\n\n    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5\n    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n                         np.arange(y_min, y_max, h))\n\n    # just plot the dataset first\n    cm = plt.cm.RdBu\n    cm_bright = ListedColormap(['#FF0000', '#0000FF'])\n    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n    # Plot the training points\n    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)\n    # and testing points\n    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)\n    ax.set_xlim(xx.min(), xx.max())\n    ax.set_ylim(yy.min(), yy.max())\n    ax.set_xticks(())\n    ax.set_yticks(())\n    i += 1\n\n    # iterate over classifiers\n    for name, clf in zip(names, classifiers):\n        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n        clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n\n        # Plot the decision boundary. For that, we will assign a color to each\n        # point in the mesh [x_min, x_max]x[y_min, y_max].\n        if hasattr(clf, \"decision_function\"):\n            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\n        else:\n            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]\n\n        # Put the result into a color plot\n        Z = Z.reshape(xx.shape)\n        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)\n\n        # Plot also the training points\n        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,\n                   edgecolors='black', s=25)\n        # and testing points\n        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,\n                   alpha=0.6, edgecolors='black', s=25)\n\n        ax.set_xlim(xx.min(), xx.max())\n        ax.set_ylim(yy.min(), yy.max())\n        ax.set_xticks(())\n        ax.set_yticks(())\n        ax.set_title(name)\n        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),\n                size=15, horizontalalignment='right')\n        i += 1\n\nfigure.subplots_adjust(left=.02, right=.98)\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -32,9 +32,7 @@
 h = .02  # step size in the mesh
 
 alphas = np.logspace(-5, 3, 5)
-names = []
-for i in alphas:
-    names.append('alpha ' + str(i))
+names = ['alpha ' + str(i) for i in alphas]
 
 classifiers = []
 for i in alphas:

dev/_downloads/plot_mlp_alpha.ipynb

@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "def plot_accuracy(x, y, x_legend):\n    \"\"\"Plot accuracy as a function of x.\"\"\"\n    x = np.array(x)\n    y = np.array(y)\n    plt.title('Classification accuracy as a function of %s' % x_legend)\n    plt.xlabel('%s' % x_legend)\n    plt.ylabel('Accuracy')\n    plt.grid(True)\n    plt.plot(x, y)\n\n\nrcParams['legend.fontsize'] = 10\ncls_names = list(sorted(cls_stats.keys()))\n\n# Plot accuracy evolution\nplt.figure()\nfor _, stats in sorted(cls_stats.items()):\n    # Plot accuracy evolution with #examples\n    accuracy, n_examples = zip(*stats['accuracy_history'])\n    plot_accuracy(n_examples, accuracy, \"training examples (#)\")\n    ax = plt.gca()\n    ax.set_ylim((0.8, 1))\nplt.legend(cls_names, loc='best')\n\nplt.figure()\nfor _, stats in sorted(cls_stats.items()):\n    # Plot accuracy evolution with runtime\n    accuracy, runtime = zip(*stats['runtime_history'])\n    plot_accuracy(runtime, accuracy, 'runtime (s)')\n    ax = plt.gca()\n    ax.set_ylim((0.8, 1))\nplt.legend(cls_names, loc='best')\n\n# Plot fitting times\nplt.figure()\nfig = plt.gcf()\ncls_runtime = []\nfor cls_name, stats in sorted(cls_stats.items()):\n    cls_runtime.append(stats['total_fit_time'])\n\ncls_runtime.append(total_vect_time)\ncls_names.append('Vectorization')\nbar_colors = ['b', 'g', 'r', 'c', 'm', 'y']\n\nax = plt.subplot(111)\nrectangles = plt.bar(range(len(cls_names)), cls_runtime, width=0.5,\n                     color=bar_colors)\n\nax.set_xticks(np.linspace(0, len(cls_names) - 1, len(cls_names)))\nax.set_xticklabels(cls_names, fontsize=10)\nymax = max(cls_runtime) * 1.2\nax.set_ylim((0, ymax))\nax.set_ylabel('runtime (s)')\nax.set_title('Training Times')\n\n\ndef autolabel(rectangles):\n    \"\"\"attach some text vi autolabel on rectangles.\"\"\"\n    for rect in rectangles:\n        height = rect.get_height()\n        ax.text(rect.get_x() + rect.get_width() / 2.,\n                1.05 * height, '%.4f' % height,\n                ha='center', va='bottom')\n        plt.setp(plt.xticks()[1], rotation=30)\n\n\nautolabel(rectangles)\nplt.tight_layout()\nplt.show()\n\n# Plot prediction times\nplt.figure()\ncls_runtime = []\ncls_names = list(sorted(cls_stats.keys()))\nfor cls_name, stats in sorted(cls_stats.items()):\n    cls_runtime.append(stats['prediction_time'])\ncls_runtime.append(parsing_time)\ncls_names.append('Read/Parse\\n+Feat.Extr.')\ncls_runtime.append(vectorizing_time)\ncls_names.append('Hashing\\n+Vect.')\n\nax = plt.subplot(111)\nrectangles = plt.bar(range(len(cls_names)), cls_runtime, width=0.5,\n                     color=bar_colors)\n\nax.set_xticks(np.linspace(0, len(cls_names) - 1, len(cls_names)))\nax.set_xticklabels(cls_names, fontsize=8)\nplt.setp(plt.xticks()[1], rotation=30)\nymax = max(cls_runtime) * 1.2\nax.set_ylim((0, ymax))\nax.set_ylabel('runtime (s)')\nax.set_title('Prediction Times (%d instances)' % n_test_documents)\nautolabel(rectangles)\nplt.tight_layout()\nplt.show()"
+        "def plot_accuracy(x, y, x_legend):\n    \"\"\"Plot accuracy as a function of x.\"\"\"\n    x = np.array(x)\n    y = np.array(y)\n    plt.title('Classification accuracy as a function of %s' % x_legend)\n    plt.xlabel('%s' % x_legend)\n    plt.ylabel('Accuracy')\n    plt.grid(True)\n    plt.plot(x, y)\n\n\nrcParams['legend.fontsize'] = 10\ncls_names = list(sorted(cls_stats.keys()))\n\n# Plot accuracy evolution\nplt.figure()\nfor _, stats in sorted(cls_stats.items()):\n    # Plot accuracy evolution with #examples\n    accuracy, n_examples = zip(*stats['accuracy_history'])\n    plot_accuracy(n_examples, accuracy, \"training examples (#)\")\n    ax = plt.gca()\n    ax.set_ylim((0.8, 1))\nplt.legend(cls_names, loc='best')\n\nplt.figure()\nfor _, stats in sorted(cls_stats.items()):\n    # Plot accuracy evolution with runtime\n    accuracy, runtime = zip(*stats['runtime_history'])\n    plot_accuracy(runtime, accuracy, 'runtime (s)')\n    ax = plt.gca()\n    ax.set_ylim((0.8, 1))\nplt.legend(cls_names, loc='best')\n\n# Plot fitting times\nplt.figure()\nfig = plt.gcf()\ncls_runtime = [stats['total_fit_time']\n               for cls_name, stats in sorted(cls_stats.items())]\n\ncls_runtime.append(total_vect_time)\ncls_names.append('Vectorization')\nbar_colors = ['b', 'g', 'r', 'c', 'm', 'y']\n\nax = plt.subplot(111)\nrectangles = plt.bar(range(len(cls_names)), cls_runtime, width=0.5,\n                     color=bar_colors)\n\nax.set_xticks(np.linspace(0, len(cls_names) - 1, len(cls_names)))\nax.set_xticklabels(cls_names, fontsize=10)\nymax = max(cls_runtime) * 1.2\nax.set_ylim((0, ymax))\nax.set_ylabel('runtime (s)')\nax.set_title('Training Times')\n\n\ndef autolabel(rectangles):\n    \"\"\"attach some text vi autolabel on rectangles.\"\"\"\n    for rect in rectangles:\n        height = rect.get_height()\n        ax.text(rect.get_x() + rect.get_width() / 2.,\n                1.05 * height, '%.4f' % height,\n                ha='center', va='bottom')\n        plt.setp(plt.xticks()[1], rotation=30)\n\n\nautolabel(rectangles)\nplt.tight_layout()\nplt.show()\n\n# Plot prediction times\nplt.figure()\ncls_runtime = []\ncls_names = list(sorted(cls_stats.keys()))\nfor cls_name, stats in sorted(cls_stats.items()):\n    cls_runtime.append(stats['prediction_time'])\ncls_runtime.append(parsing_time)\ncls_names.append('Read/Parse\\n+Feat.Extr.')\ncls_runtime.append(vectorizing_time)\ncls_names.append('Hashing\\n+Vect.')\n\nax = plt.subplot(111)\nrectangles = plt.bar(range(len(cls_names)), cls_runtime, width=0.5,\n                     color=bar_colors)\n\nax.set_xticks(np.linspace(0, len(cls_names) - 1, len(cls_names)))\nax.set_xticklabels(cls_names, fontsize=8)\nplt.setp(plt.xticks()[1], rotation=30)\nymax = max(cls_runtime) * 1.2\nax.set_ylim((0, ymax))\nax.set_ylabel('runtime (s)')\nax.set_title('Prediction Times (%d instances)' % n_test_documents)\nautolabel(rectangles)\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_mlp_alpha.py

@@ -359,9 +359,8 @@ def plot_accuracy(x, y, x_legend):
 # Plot fitting times
 plt.figure()
 fig = plt.gcf()
-cls_runtime = []
-for cls_name, stats in sorted(cls_stats.items()):
-    cls_runtime.append(stats['total_fit_time'])
+cls_runtime = [stats['total_fit_time']
+               for cls_name, stats in sorted(cls_stats.items())]
 
 cls_runtime.append(total_vect_time)
 cls_names.append('Vectorization')