Pushing the docs to dev/ for branch: master, commit e3fe559a870cbe52bbdd23fd1c74f07ec83052f5

Author: sklearn-ci

dev/_downloads/18771ded92de7c896426232db4ecc24e/plot_sgd_weighted_samples.py

@@ -27,14 +27,14 @@
             cmap=plt.cm.bone, edgecolor='black')
 
 # fit the unweighted model
-clf = linear_model.SGDClassifier(alpha=0.01, max_iter=100, tol=1e-3)
+clf = linear_model.SGDClassifier(alpha=0.01, max_iter=100)
 clf.fit(X, y)
 Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
 Z = Z.reshape(xx.shape)
 no_weights = plt.contour(xx, yy, Z, levels=[0], linestyles=['solid'])
 
 # fit the weighted model
-clf = linear_model.SGDClassifier(alpha=0.01, max_iter=100, tol=1e-3)
+clf = linear_model.SGDClassifier(alpha=0.01, max_iter=100)
 clf.fit(X, y, sample_weight=sample_weight)
 Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
 Z = Z.reshape(xx.shape)

dev/_downloads/1abc4484d4183963e2039c8c679497eb/plot_sgd_comparison.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Rob Zinkov <rob at zinkov dot com>\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import datasets\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import SGDClassifier, Perceptron\nfrom sklearn.linear_model import PassiveAggressiveClassifier\nfrom sklearn.linear_model import LogisticRegression\n\nheldout = [0.95, 0.90, 0.75, 0.50, 0.01]\nrounds = 20\nX, y = datasets.load_digits(return_X_y=True)\n\nclassifiers = [\n    (\"SGD\", SGDClassifier(max_iter=100, tol=1e-3)),\n    (\"ASGD\", SGDClassifier(average=True, max_iter=1000, tol=1e-3)),\n    (\"Perceptron\", Perceptron(tol=1e-3)),\n    (\"Passive-Aggressive I\", PassiveAggressiveClassifier(loss='hinge',\n                                                         C=1.0, tol=1e-4)),\n    (\"Passive-Aggressive II\", PassiveAggressiveClassifier(loss='squared_hinge',\n                                                          C=1.0, tol=1e-4)),\n    (\"SAG\", LogisticRegression(solver='sag', tol=1e-1, C=1.e4 / X.shape[0]))\n]\n\nxx = 1. - np.array(heldout)\n\nfor name, clf in classifiers:\n    print(\"training %s\" % name)\n    rng = np.random.RandomState(42)\n    yy = []\n    for i in heldout:\n        yy_ = []\n        for r in range(rounds):\n            X_train, X_test, y_train, y_test = \\\n                train_test_split(X, y, test_size=i, random_state=rng)\n            clf.fit(X_train, y_train)\n            y_pred = clf.predict(X_test)\n            yy_.append(1 - np.mean(y_pred == y_test))\n        yy.append(np.mean(yy_))\n    plt.plot(xx, yy, label=name)\n\nplt.legend(loc=\"upper right\")\nplt.xlabel(\"Proportion train\")\nplt.ylabel(\"Test Error Rate\")\nplt.show()"
+        "# Author: Rob Zinkov <rob at zinkov dot com>\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import datasets\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import SGDClassifier, Perceptron\nfrom sklearn.linear_model import PassiveAggressiveClassifier\nfrom sklearn.linear_model import LogisticRegression\n\nheldout = [0.95, 0.90, 0.75, 0.50, 0.01]\nrounds = 20\nX, y = datasets.load_digits(return_X_y=True)\n\nclassifiers = [\n    (\"SGD\", SGDClassifier(max_iter=100)),\n    (\"ASGD\", SGDClassifier(average=True, max_iter=1000)),\n    (\"Perceptron\", Perceptron(tol=1e-3)),\n    (\"Passive-Aggressive I\", PassiveAggressiveClassifier(loss='hinge',\n                                                         C=1.0, tol=1e-4)),\n    (\"Passive-Aggressive II\", PassiveAggressiveClassifier(loss='squared_hinge',\n                                                          C=1.0, tol=1e-4)),\n    (\"SAG\", LogisticRegression(solver='sag', tol=1e-1, C=1.e4 / X.shape[0]))\n]\n\nxx = 1. - np.array(heldout)\n\nfor name, clf in classifiers:\n    print(\"training %s\" % name)\n    rng = np.random.RandomState(42)\n    yy = []\n    for i in heldout:\n        yy_ = []\n        for r in range(rounds):\n            X_train, X_test, y_train, y_test = \\\n                train_test_split(X, y, test_size=i, random_state=rng)\n            clf.fit(X_train, y_train)\n            y_pred = clf.predict(X_test)\n            yy_.append(1 - np.mean(y_pred == y_test))\n        yy.append(np.mean(yy_))\n    plt.plot(xx, yy, label=name)\n\nplt.legend(loc=\"upper right\")\nplt.xlabel(\"Proportion train\")\nplt.ylabel(\"Test Error Rate\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/275c1a8902428a3a52b079bb6f13591a/plot_sgd_separating_hyperplane.py

@@ -19,7 +19,7 @@
 
 # fit the model
 clf = SGDClassifier(loss="hinge", alpha=0.01, max_iter=200,
-                    fit_intercept=True, tol=1e-3)
+                    fit_intercept=True)
 clf.fit(X, Y)
 
 # plot the line, the points, and the nearest vectors to the plane

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -24,8 +24,8 @@
 X, y = datasets.load_digits(return_X_y=True)
 
 classifiers = [
-    ("SGD", SGDClassifier(max_iter=100, tol=1e-3)),
-    ("ASGD", SGDClassifier(average=True, max_iter=1000, tol=1e-3)),
+    ("SGD", SGDClassifier(max_iter=100)),
+    ("ASGD", SGDClassifier(average=True, max_iter=1000)),
     ("Perceptron", Perceptron(tol=1e-3)),
     ("Passive-Aggressive I", PassiveAggressiveClassifier(loss='hinge',
                                                          C=1.0, tol=1e-4)),

dev/_downloads/3650884f0a646ba96d2e47df0a6fb935/plot_sgd_comparison.py

@@ -87,7 +87,7 @@
 pipeline = Pipeline([
     ('vect', CountVectorizer()),
     ('tfidf', TfidfTransformer()),
-    ('clf', SGDClassifier(tol=1e-3)),
+    ('clf', SGDClassifier()),
 ])
 
 # uncommenting more parameters will give better exploring power but will

dev/_downloads/4339c826f9873f4c9ebbcaf331f57b9d/grid_search_text_feature_extraction.py

@@ -38,7 +38,7 @@
 
 h = .02  # step size in the mesh
 
-clf = SGDClassifier(alpha=0.001, max_iter=100, tol=1e-3).fit(X, y)
+clf = SGDClassifier(alpha=0.001, max_iter=100).fit(X, y)
 
 # create a mesh to plot in
 x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1

dev/_downloads/4452f13fc6e1f6bc2280af49e5c4afde/plot_sgd_iris.py

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import linear_model\n\n# we create 20 points\nnp.random.seed(0)\nX = np.r_[np.random.randn(10, 2) + [1, 1], np.random.randn(10, 2)]\ny = [1] * 10 + [-1] * 10\nsample_weight = 100 * np.abs(np.random.randn(20))\n# and assign a bigger weight to the last 10 samples\nsample_weight[:10] *= 10\n\n# plot the weighted data points\nxx, yy = np.meshgrid(np.linspace(-4, 5, 500), np.linspace(-4, 5, 500))\nplt.figure()\nplt.scatter(X[:, 0], X[:, 1], c=y, s=sample_weight, alpha=0.9,\n            cmap=plt.cm.bone, edgecolor='black')\n\n# fit the unweighted model\nclf = linear_model.SGDClassifier(alpha=0.01, max_iter=100, tol=1e-3)\nclf.fit(X, y)\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\nno_weights = plt.contour(xx, yy, Z, levels=[0], linestyles=['solid'])\n\n# fit the weighted model\nclf = linear_model.SGDClassifier(alpha=0.01, max_iter=100, tol=1e-3)\nclf.fit(X, y, sample_weight=sample_weight)\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\nsamples_weights = plt.contour(xx, yy, Z, levels=[0], linestyles=['dashed'])\n\nplt.legend([no_weights.collections[0], samples_weights.collections[0]],\n           [\"no weights\", \"with weights\"], loc=\"lower left\")\n\nplt.xticks(())\nplt.yticks(())\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import linear_model\n\n# we create 20 points\nnp.random.seed(0)\nX = np.r_[np.random.randn(10, 2) + [1, 1], np.random.randn(10, 2)]\ny = [1] * 10 + [-1] * 10\nsample_weight = 100 * np.abs(np.random.randn(20))\n# and assign a bigger weight to the last 10 samples\nsample_weight[:10] *= 10\n\n# plot the weighted data points\nxx, yy = np.meshgrid(np.linspace(-4, 5, 500), np.linspace(-4, 5, 500))\nplt.figure()\nplt.scatter(X[:, 0], X[:, 1], c=y, s=sample_weight, alpha=0.9,\n            cmap=plt.cm.bone, edgecolor='black')\n\n# fit the unweighted model\nclf = linear_model.SGDClassifier(alpha=0.01, max_iter=100)\nclf.fit(X, y)\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\nno_weights = plt.contour(xx, yy, Z, levels=[0], linestyles=['solid'])\n\n# fit the weighted model\nclf = linear_model.SGDClassifier(alpha=0.01, max_iter=100)\nclf.fit(X, y, sample_weight=sample_weight)\nZ = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\nZ = Z.reshape(xx.shape)\nsamples_weights = plt.contour(xx, yy, Z, levels=[0], linestyles=['dashed'])\n\nplt.legend([no_weights.collections[0], samples_weights.collections[0]],\n           [\"no weights\", \"with weights\"], loc=\"lower left\")\n\nplt.xticks(())\nplt.yticks(())\nplt.show()"
       ]
     }
   ],

dev/_downloads/4aaaf51a640f112464b83039979cb0fe/plot_sgd_weighted_samples.ipynb

@@ -224,6 +224,6 @@ def centrality_scores(X, alpha=0.85, max_iter=100, tol=1e-10):
 
 print("Computing principal eigenvector score using a power iteration method")
 t0 = time()
-scores = centrality_scores(X, max_iter=100, tol=1e-10)
+scores = centrality_scores(X, max_iter=100)
 print("done in %0.3fs" % (time() - t0))
 pprint([names[i] for i in np.abs(scores).argsort()[-10:]])

dev/_downloads/637afdd681404c733540858401aadf5c/wikipedia_principal_eigenvector.py

@@ -207,7 +207,7 @@ def progress(blocknum, bs, size):
 
 # Here are some classifiers that support the `partial_fit` method
 partial_fit_classifiers = {
-    'SGD': SGDClassifier(max_iter=5, tol=1e-3),
+    'SGD': SGDClassifier(max_iter=5),
     'Perceptron': Perceptron(tol=1e-3),
     'NB Multinomial': MultinomialNB(alpha=0.01),
     'Passive-Aggressive': PassiveAggressiveClassifier(tol=1e-3),