Pushing the docs to dev/ for branch: master, commit 7896b215628e50ced758571c80d7a564351be40e

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Alexandre Gramfort <[email protected]>\n#         Jan Hendrik Metzen <[email protected]>\n# License: BSD Style.\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.svm import LinearSVC\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import (brier_score_loss, precision_score, recall_score,\n                             f1_score)\nfrom sklearn.calibration import CalibratedClassifierCV, calibration_curve\nfrom sklearn.model_selection import train_test_split\n\n\n# Create dataset of classification task with many redundant and few\n# informative features\nX, y = datasets.make_classification(n_samples=100000, n_features=20,\n                                    n_informative=2, n_redundant=10,\n                                    random_state=42)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.99,\n                                                    random_state=42)\n\n\ndef plot_calibration_curve(est, name, fig_index):\n    \"\"\"Plot calibration curve for est w/o and with calibration. \"\"\"\n    # Calibrated with isotonic calibration\n    isotonic = CalibratedClassifierCV(est, cv=2, method='isotonic')\n\n    # Calibrated with sigmoid calibration\n    sigmoid = CalibratedClassifierCV(est, cv=2, method='sigmoid')\n\n    # Logistic regression with no calibration as baseline\n    lr = LogisticRegression(C=1., solver='lbfgs')\n\n    fig = plt.figure(fig_index, figsize=(10, 10))\n    ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)\n    ax2 = plt.subplot2grid((3, 1), (2, 0))\n\n    ax1.plot([0, 1], [0, 1], \"k:\", label=\"Perfectly calibrated\")\n    for clf, name in [(lr, 'Logistic'),\n                      (est, name),\n                      (isotonic, name + ' + Isotonic'),\n                      (sigmoid, name + ' + Sigmoid')]:\n        clf.fit(X_train, y_train)\n        y_pred = clf.predict(X_test)\n        if hasattr(clf, \"predict_proba\"):\n            prob_pos = clf.predict_proba(X_test)[:, 1]\n        else:  # use decision function\n            prob_pos = clf.decision_function(X_test)\n            prob_pos = \\\n                (prob_pos - prob_pos.min()) / (prob_pos.max() - prob_pos.min())\n\n        clf_score = brier_score_loss(y_test, prob_pos, pos_label=y.max())\n        print(\"%s:\" % name)\n        print(\"\\tBrier: %1.3f\" % (clf_score))\n        print(\"\\tPrecision: %1.3f\" % precision_score(y_test, y_pred))\n        print(\"\\tRecall: %1.3f\" % recall_score(y_test, y_pred))\n        print(\"\\tF1: %1.3f\\n\" % f1_score(y_test, y_pred))\n\n        fraction_of_positives, mean_predicted_value = \\\n            calibration_curve(y_test, prob_pos, n_bins=10)\n\n        ax1.plot(mean_predicted_value, fraction_of_positives, \"s-\",\n                 label=\"%s (%1.3f)\" % (name, clf_score))\n\n        ax2.hist(prob_pos, range=(0, 1), bins=10, label=name,\n                 histtype=\"step\", lw=2)\n\n    ax1.set_ylabel(\"Fraction of positives\")\n    ax1.set_ylim([-0.05, 1.05])\n    ax1.legend(loc=\"lower right\")\n    ax1.set_title('Calibration plots  (reliability curve)')\n\n    ax2.set_xlabel(\"Mean predicted value\")\n    ax2.set_ylabel(\"Count\")\n    ax2.legend(loc=\"upper center\", ncol=2)\n\n    plt.tight_layout()\n\n# Plot calibration curve for Gaussian Naive Bayes\nplot_calibration_curve(GaussianNB(), \"Naive Bayes\", 1)\n\n# Plot calibration curve for Linear SVC\nplot_calibration_curve(LinearSVC(max_iter=10000), \"SVC\", 2)\n\nplt.show()"
+        "print(__doc__)\n\n# Author: Alexandre Gramfort <[email protected]>\n#         Jan Hendrik Metzen <[email protected]>\n# License: BSD Style.\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.svm import LinearSVC\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import (brier_score_loss, precision_score, recall_score,\n                             f1_score)\nfrom sklearn.calibration import CalibratedClassifierCV, calibration_curve\nfrom sklearn.model_selection import train_test_split\n\n\n# Create dataset of classification task with many redundant and few\n# informative features\nX, y = datasets.make_classification(n_samples=100000, n_features=20,\n                                    n_informative=2, n_redundant=10,\n                                    random_state=42)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.99,\n                                                    random_state=42)\n\n\ndef plot_calibration_curve(est, name, fig_index):\n    \"\"\"Plot calibration curve for est w/o and with calibration. \"\"\"\n    # Calibrated with isotonic calibration\n    isotonic = CalibratedClassifierCV(est, cv=2, method='isotonic')\n\n    # Calibrated with sigmoid calibration\n    sigmoid = CalibratedClassifierCV(est, cv=2, method='sigmoid')\n\n    # Logistic regression with no calibration as baseline\n    lr = LogisticRegression(C=1.)\n\n    fig = plt.figure(fig_index, figsize=(10, 10))\n    ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)\n    ax2 = plt.subplot2grid((3, 1), (2, 0))\n\n    ax1.plot([0, 1], [0, 1], \"k:\", label=\"Perfectly calibrated\")\n    for clf, name in [(lr, 'Logistic'),\n                      (est, name),\n                      (isotonic, name + ' + Isotonic'),\n                      (sigmoid, name + ' + Sigmoid')]:\n        clf.fit(X_train, y_train)\n        y_pred = clf.predict(X_test)\n        if hasattr(clf, \"predict_proba\"):\n            prob_pos = clf.predict_proba(X_test)[:, 1]\n        else:  # use decision function\n            prob_pos = clf.decision_function(X_test)\n            prob_pos = \\\n                (prob_pos - prob_pos.min()) / (prob_pos.max() - prob_pos.min())\n\n        clf_score = brier_score_loss(y_test, prob_pos, pos_label=y.max())\n        print(\"%s:\" % name)\n        print(\"\\tBrier: %1.3f\" % (clf_score))\n        print(\"\\tPrecision: %1.3f\" % precision_score(y_test, y_pred))\n        print(\"\\tRecall: %1.3f\" % recall_score(y_test, y_pred))\n        print(\"\\tF1: %1.3f\\n\" % f1_score(y_test, y_pred))\n\n        fraction_of_positives, mean_predicted_value = \\\n            calibration_curve(y_test, prob_pos, n_bins=10)\n\n        ax1.plot(mean_predicted_value, fraction_of_positives, \"s-\",\n                 label=\"%s (%1.3f)\" % (name, clf_score))\n\n        ax2.hist(prob_pos, range=(0, 1), bins=10, label=name,\n                 histtype=\"step\", lw=2)\n\n    ax1.set_ylabel(\"Fraction of positives\")\n    ax1.set_ylim([-0.05, 1.05])\n    ax1.legend(loc=\"lower right\")\n    ax1.set_title('Calibration plots  (reliability curve)')\n\n    ax2.set_xlabel(\"Mean predicted value\")\n    ax2.set_ylabel(\"Count\")\n    ax2.legend(loc=\"upper center\", ncol=2)\n\n    plt.tight_layout()\n\n# Plot calibration curve for Gaussian Naive Bayes\nplot_calibration_curve(GaussianNB(), \"Naive Bayes\", 1)\n\n# Plot calibration curve for Linear SVC\nplot_calibration_curve(LinearSVC(max_iter=10000), \"SVC\", 2)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -78,7 +78,7 @@ def plot_calibration_curve(est, name, fig_index):
     sigmoid = CalibratedClassifierCV(est, cv=2, method='sigmoid')
 
     # Logistic regression with no calibration as baseline
-    lr = LogisticRegression(C=1., solver='lbfgs')
+    lr = LogisticRegression(C=1.)
 
     fig = plt.figure(fig_index, figsize=(10, 10))
     ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)

dev/_downloads/plot_calibration_curve.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Adam Kleczewski\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.multioutput import ClassifierChain\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.multiclass import OneVsRestClassifier\nfrom sklearn.metrics import jaccard_score\nfrom sklearn.linear_model import LogisticRegression\n\nprint(__doc__)\n\n# Load a multi-label dataset from https://www.openml.org/d/40597\nX, Y = fetch_openml('yeast', version=4, return_X_y=True)\nY = Y == 'TRUE'\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.2,\n                                                    random_state=0)\n\n# Fit an independent logistic regression model for each class using the\n# OneVsRestClassifier wrapper.\nbase_lr = LogisticRegression(solver='lbfgs')\novr = OneVsRestClassifier(base_lr)\novr.fit(X_train, Y_train)\nY_pred_ovr = ovr.predict(X_test)\novr_jaccard_score = jaccard_score(Y_test, Y_pred_ovr, average='samples')\n\n# Fit an ensemble of logistic regression classifier chains and take the\n# take the average prediction of all the chains.\nchains = [ClassifierChain(base_lr, order='random', random_state=i)\n          for i in range(10)]\nfor chain in chains:\n    chain.fit(X_train, Y_train)\n\nY_pred_chains = np.array([chain.predict(X_test) for chain in\n                          chains])\nchain_jaccard_scores = [jaccard_score(Y_test, Y_pred_chain >= .5,\n                                      average='samples')\n                        for Y_pred_chain in Y_pred_chains]\n\nY_pred_ensemble = Y_pred_chains.mean(axis=0)\nensemble_jaccard_score = jaccard_score(Y_test,\n                                       Y_pred_ensemble >= .5,\n                                       average='samples')\n\nmodel_scores = [ovr_jaccard_score] + chain_jaccard_scores\nmodel_scores.append(ensemble_jaccard_score)\n\nmodel_names = ('Independent',\n               'Chain 1',\n               'Chain 2',\n               'Chain 3',\n               'Chain 4',\n               'Chain 5',\n               'Chain 6',\n               'Chain 7',\n               'Chain 8',\n               'Chain 9',\n               'Chain 10',\n               'Ensemble')\n\nx_pos = np.arange(len(model_names))\n\n# Plot the Jaccard similarity scores for the independent model, each of the\n# chains, and the ensemble (note that the vertical axis on this plot does\n# not begin at 0).\n\nfig, ax = plt.subplots(figsize=(7, 4))\nax.grid(True)\nax.set_title('Classifier Chain Ensemble Performance Comparison')\nax.set_xticks(x_pos)\nax.set_xticklabels(model_names, rotation='vertical')\nax.set_ylabel('Jaccard Similarity Score')\nax.set_ylim([min(model_scores) * .9, max(model_scores) * 1.1])\ncolors = ['r'] + ['b'] * len(chain_jaccard_scores) + ['g']\nax.bar(x_pos, model_scores, alpha=0.5, color=colors)\nplt.tight_layout()\nplt.show()"
+        "# Author: Adam Kleczewski\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.multioutput import ClassifierChain\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.multiclass import OneVsRestClassifier\nfrom sklearn.metrics import jaccard_score\nfrom sklearn.linear_model import LogisticRegression\n\nprint(__doc__)\n\n# Load a multi-label dataset from https://www.openml.org/d/40597\nX, Y = fetch_openml('yeast', version=4, return_X_y=True)\nY = Y == 'TRUE'\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.2,\n                                                    random_state=0)\n\n# Fit an independent logistic regression model for each class using the\n# OneVsRestClassifier wrapper.\nbase_lr = LogisticRegression()\novr = OneVsRestClassifier(base_lr)\novr.fit(X_train, Y_train)\nY_pred_ovr = ovr.predict(X_test)\novr_jaccard_score = jaccard_score(Y_test, Y_pred_ovr, average='samples')\n\n# Fit an ensemble of logistic regression classifier chains and take the\n# take the average prediction of all the chains.\nchains = [ClassifierChain(base_lr, order='random', random_state=i)\n          for i in range(10)]\nfor chain in chains:\n    chain.fit(X_train, Y_train)\n\nY_pred_chains = np.array([chain.predict(X_test) for chain in\n                          chains])\nchain_jaccard_scores = [jaccard_score(Y_test, Y_pred_chain >= .5,\n                                      average='samples')\n                        for Y_pred_chain in Y_pred_chains]\n\nY_pred_ensemble = Y_pred_chains.mean(axis=0)\nensemble_jaccard_score = jaccard_score(Y_test,\n                                       Y_pred_ensemble >= .5,\n                                       average='samples')\n\nmodel_scores = [ovr_jaccard_score] + chain_jaccard_scores\nmodel_scores.append(ensemble_jaccard_score)\n\nmodel_names = ('Independent',\n               'Chain 1',\n               'Chain 2',\n               'Chain 3',\n               'Chain 4',\n               'Chain 5',\n               'Chain 6',\n               'Chain 7',\n               'Chain 8',\n               'Chain 9',\n               'Chain 10',\n               'Ensemble')\n\nx_pos = np.arange(len(model_names))\n\n# Plot the Jaccard similarity scores for the independent model, each of the\n# chains, and the ensemble (note that the vertical axis on this plot does\n# not begin at 0).\n\nfig, ax = plt.subplots(figsize=(7, 4))\nax.grid(True)\nax.set_title('Classifier Chain Ensemble Performance Comparison')\nax.set_xticks(x_pos)\nax.set_xticklabels(model_names, rotation='vertical')\nax.set_ylabel('Jaccard Similarity Score')\nax.set_ylim([min(model_scores) * .9, max(model_scores) * 1.1])\ncolors = ['r'] + ['b'] * len(chain_jaccard_scores) + ['g']\nax.bar(x_pos, model_scores, alpha=0.5, color=colors)\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_calibration_curve.py

@@ -54,7 +54,7 @@
 
 # Fit an independent logistic regression model for each class using the
 # OneVsRestClassifier wrapper.
-base_lr = LogisticRegression(solver='lbfgs')
+base_lr = LogisticRegression()
 ovr = OneVsRestClassifier(base_lr)
 ovr.fit(X_train, Y_train)
 Y_pred_ovr = ovr.predict(X_test)

dev/_downloads/plot_classifier_chain_yeast.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Pedro Morales <[email protected]>\n#\n# License: BSD 3 clause\n\nimport pandas as pd\nimport numpy as np\n\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split, GridSearchCV\n\nnp.random.seed(0)\n\n# Read data from Titanic dataset.\ntitanic_url = ('https://raw.githubusercontent.com/amueller/'\n               'scipy-2017-sklearn/091d371/notebooks/datasets/titanic3.csv')\ndata = pd.read_csv(titanic_url)\n\n# We will train our classifier with the following features:\n# Numeric Features:\n# - age: float.\n# - fare: float.\n# Categorical Features:\n# - embarked: categories encoded as strings {'C', 'S', 'Q'}.\n# - sex: categories encoded as strings {'female', 'male'}.\n# - pclass: ordinal integers {1, 2, 3}.\n\n# We create the preprocessing pipelines for both numeric and categorical data.\nnumeric_features = ['age', 'fare']\nnumeric_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='median')),\n    ('scaler', StandardScaler())])\n\ncategorical_features = ['embarked', 'sex', 'pclass']\ncategorical_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),\n    ('onehot', OneHotEncoder(handle_unknown='ignore'))])\n\npreprocessor = ColumnTransformer(\n    transformers=[\n        ('num', numeric_transformer, numeric_features),\n        ('cat', categorical_transformer, categorical_features)])\n\n# Append classifier to preprocessing pipeline.\n# Now we have a full prediction pipeline.\nclf = Pipeline(steps=[('preprocessor', preprocessor),\n                      ('classifier', LogisticRegression(solver='lbfgs'))])\n\nX = data.drop('survived', axis=1)\ny = data['survived']\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n\nclf.fit(X_train, y_train)\nprint(\"model score: %.3f\" % clf.score(X_test, y_test))"
+        "# Author: Pedro Morales <[email protected]>\n#\n# License: BSD 3 clause\n\nimport pandas as pd\nimport numpy as np\n\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split, GridSearchCV\n\nnp.random.seed(0)\n\n# Read data from Titanic dataset.\ntitanic_url = ('https://raw.githubusercontent.com/amueller/'\n               'scipy-2017-sklearn/091d371/notebooks/datasets/titanic3.csv')\ndata = pd.read_csv(titanic_url)\n\n# We will train our classifier with the following features:\n# Numeric Features:\n# - age: float.\n# - fare: float.\n# Categorical Features:\n# - embarked: categories encoded as strings {'C', 'S', 'Q'}.\n# - sex: categories encoded as strings {'female', 'male'}.\n# - pclass: ordinal integers {1, 2, 3}.\n\n# We create the preprocessing pipelines for both numeric and categorical data.\nnumeric_features = ['age', 'fare']\nnumeric_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='median')),\n    ('scaler', StandardScaler())])\n\ncategorical_features = ['embarked', 'sex', 'pclass']\ncategorical_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),\n    ('onehot', OneHotEncoder(handle_unknown='ignore'))])\n\npreprocessor = ColumnTransformer(\n    transformers=[\n        ('num', numeric_transformer, numeric_features),\n        ('cat', categorical_transformer, categorical_features)])\n\n# Append classifier to preprocessing pipeline.\n# Now we have a full prediction pipeline.\nclf = Pipeline(steps=[('preprocessor', preprocessor),\n                      ('classifier', LogisticRegression())])\n\nX = data.drop('survived', axis=1)\ny = data['survived']\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n\nclf.fit(X_train, y_train)\nprint(\"model score: %.3f\" % clf.score(X_test, y_test))"
       ]
     },
     {

dev/_downloads/plot_classifier_chain_yeast.py

@@ -69,7 +69,7 @@
 # Append classifier to preprocessing pipeline.
 # Now we have a full prediction pipeline.
 clf = Pipeline(steps=[('preprocessor', preprocessor),
-                      ('classifier', LogisticRegression(solver='lbfgs'))])
+                      ('classifier', LogisticRegression())])
 
 X = data.drop('survived', axis=1)
 y = data['survived']