Pushing the docs to 1.3/ for branch: 1.3.X, commit 7f9bad99d6e0a3e8ddf92a7e5561245224dab102

Author: sklearn-ci

Diff for: 1.3/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 4f5caed29f0e06a89d4de5cb2447e013
+config: afc023663d94539ff18489a9370c996e
 tags: 645f666f9bcd5a90fca523b33c5a78b7

Diff for: 1.3/_downloads/006fc185672e58b056a5c134db26935c/plot_coin_segmentation.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Gael Varoquaux <[email protected]>\n#         Brian Cheung\n#         Andrew Knyazev <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\nfrom scipy.ndimage import gaussian_filter\nimport matplotlib.pyplot as plt\nfrom skimage.data import coins\nfrom skimage.transform import rescale\n\nfrom sklearn.feature_extraction import image\nfrom sklearn.cluster import spectral_clustering\n\n\n# load the coins as a numpy array\norig_coins = coins()\n\n# Resize it to 20% of the original size to speed up the processing\n# Applying a Gaussian filter for smoothing prior to down-scaling\n# reduces aliasing artifacts.\nsmoothened_coins = gaussian_filter(orig_coins, sigma=2)\nrescaled_coins = rescale(smoothened_coins, 0.2, mode=\"reflect\", anti_aliasing=False)\n\n# Convert the image into a graph with the value of the gradient on the\n# edges.\ngraph = image.img_to_graph(rescaled_coins)\n\n# Take a decreasing function of the gradient: an exponential\n# The smaller beta is, the more independent the segmentation is of the\n# actual image. For beta=1, the segmentation is close to a voronoi\nbeta = 10\neps = 1e-6\ngraph.data = np.exp(-beta * graph.data / graph.data.std()) + eps\n\n# The number of segmented regions to display needs to be chosen manually.\n# The current version of 'spectral_clustering' does not support determining\n# the number of good quality clusters automatically.\nn_regions = 26"
+        "# Author: Gael Varoquaux <[email protected]>\n#         Brian Cheung\n#         Andrew Knyazev <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom scipy.ndimage import gaussian_filter\nfrom skimage.data import coins\nfrom skimage.transform import rescale\n\nfrom sklearn.cluster import spectral_clustering\nfrom sklearn.feature_extraction import image\n\n# load the coins as a numpy array\norig_coins = coins()\n\n# Resize it to 20% of the original size to speed up the processing\n# Applying a Gaussian filter for smoothing prior to down-scaling\n# reduces aliasing artifacts.\nsmoothened_coins = gaussian_filter(orig_coins, sigma=2)\nrescaled_coins = rescale(smoothened_coins, 0.2, mode=\"reflect\", anti_aliasing=False)\n\n# Convert the image into a graph with the value of the gradient on the\n# edges.\ngraph = image.img_to_graph(rescaled_coins)\n\n# Take a decreasing function of the gradient: an exponential\n# The smaller beta is, the more independent the segmentation is of the\n# actual image. For beta=1, the segmentation is close to a voronoi\nbeta = 10\neps = 1e-6\ngraph.data = np.exp(-beta * graph.data / graph.data.std()) + eps\n\n# The number of segmented regions to display needs to be chosen manually.\n# The current version of 'spectral_clustering' does not support determining\n# the number of good quality clusters automatically.\nn_regions = 26"
       ]
     },
     {

Diff for: 1.3/_downloads/00ae629d652473137a3905a5e08ea815/plot_iris_dtc.py

@@ -23,13 +23,12 @@
 
 # %%
 # Display the decision functions of trees trained on all pairs of features.
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
 
 from sklearn.datasets import load_iris
-from sklearn.tree import DecisionTreeClassifier
 from sklearn.inspection import DecisionBoundaryDisplay
-
+from sklearn.tree import DecisionTreeClassifier
 
 # Parameters
 n_classes = 3

Diff for: 1.3/_downloads/010337852815f8103ac6cca38a812b3c/plot_roc_crossval.py

@@ -41,6 +41,7 @@
 # (`class_id=0`).
 
 import numpy as np
+
 from sklearn.datasets import load_iris
 
 iris = load_iris()
@@ -66,8 +67,7 @@
 import matplotlib.pyplot as plt
 
 from sklearn import svm
-from sklearn.metrics import auc
-from sklearn.metrics import RocCurveDisplay
+from sklearn.metrics import RocCurveDisplay, auc
 from sklearn.model_selection import StratifiedKFold
 
 n_splits = 6

Diff for: 1.3/_downloads/01fdc7c95204e4a420de7cd297711693/plot_feature_union.py

@@ -20,12 +20,12 @@
 #
 # License: BSD 3 clause
 
-from sklearn.pipeline import Pipeline, FeatureUnion
-from sklearn.model_selection import GridSearchCV
-from sklearn.svm import SVC
 from sklearn.datasets import load_iris
 from sklearn.decomposition import PCA
 from sklearn.feature_selection import SelectKBest
+from sklearn.model_selection import GridSearchCV
+from sklearn.pipeline import FeatureUnion, Pipeline
+from sklearn.svm import SVC
 
 iris = load_iris()
 

Diff for: 1.3/_downloads/02a1306a494b46cc56c930ceec6e8c4a/plot_species_kde.py

@@ -40,8 +40,9 @@
 #
 # License: BSD 3 clause
 
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+
 from sklearn.datasets import fetch_species_distributions
 from sklearn.neighbors import KernelDensity
 

Diff for: 1.3/_downloads/02a7bbce3c39c70d62d80e875968e5c6/plot_digits_kde_sampling.py

@@ -11,13 +11,13 @@
 
 """
 
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
 
 from sklearn.datasets import load_digits
-from sklearn.neighbors import KernelDensity
 from sklearn.decomposition import PCA
 from sklearn.model_selection import GridSearchCV
+from sklearn.neighbors import KernelDensity
 
 # load the data
 digits = load_digits()

Diff for: 1.3/_downloads/02d88d76c60b7397c8c6e221b31568dd/plot_grid_search_refit_callable.py

@@ -20,8 +20,8 @@
 
 # Author: Wenhao Zhang <[email protected]>
 
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
 
 from sklearn.datasets import load_digits
 from sklearn.decomposition import PCA

Diff for: 1.3/_downloads/02f111fb3dd79805b161e14c564184fc/plot_sgd_comparison.ipynb

@@ -15,7 +15,7 @@
       },
       "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]\n# Number of rounds to fit and evaluate an estimator.\nrounds = 10\nX, y = datasets.load_digits(return_X_y=True)\n\nclassifiers = [\n    (\"SGD\", SGDClassifier(max_iter=110)),\n    (\"ASGD\", SGDClassifier(max_iter=110, average=True)),\n    (\"Perceptron\", Perceptron(max_iter=110)),\n    (\n        \"Passive-Aggressive I\",\n        PassiveAggressiveClassifier(max_iter=110, loss=\"hinge\", C=1.0, tol=1e-4),\n    ),\n    (\n        \"Passive-Aggressive II\",\n        PassiveAggressiveClassifier(\n            max_iter=110, loss=\"squared_hinge\", C=1.0, tol=1e-4\n        ),\n    ),\n    (\n        \"SAG\",\n        LogisticRegression(max_iter=110, solver=\"sag\", tol=1e-1, C=1.0e4 / X.shape[0]),\n    ),\n]\n\nxx = 1.0 - 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 = train_test_split(\n                X, y, test_size=i, random_state=rng\n            )\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 matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn import datasets\nfrom sklearn.linear_model import (\n    LogisticRegression,\n    PassiveAggressiveClassifier,\n    Perceptron,\n    SGDClassifier,\n)\nfrom sklearn.model_selection import train_test_split\n\nheldout = [0.95, 0.90, 0.75, 0.50, 0.01]\n# Number of rounds to fit and evaluate an estimator.\nrounds = 10\nX, y = datasets.load_digits(return_X_y=True)\n\nclassifiers = [\n    (\"SGD\", SGDClassifier(max_iter=110)),\n    (\"ASGD\", SGDClassifier(max_iter=110, average=True)),\n    (\"Perceptron\", Perceptron(max_iter=110)),\n    (\n        \"Passive-Aggressive I\",\n        PassiveAggressiveClassifier(max_iter=110, loss=\"hinge\", C=1.0, tol=1e-4),\n    ),\n    (\n        \"Passive-Aggressive II\",\n        PassiveAggressiveClassifier(\n            max_iter=110, loss=\"squared_hinge\", C=1.0, tol=1e-4\n        ),\n    ),\n    (\n        \"SAG\",\n        LogisticRegression(max_iter=110, solver=\"sag\", tol=1e-1, C=1.0e4 / X.shape[0]),\n    ),\n]\n\nxx = 1.0 - 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 = train_test_split(\n                X, y, test_size=i, random_state=rng\n            )\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()"
       ]
     }
   ],

Diff for: 1.3/_downloads/036b9372e2e7802453cbb994da7a6786/plot_linearsvc_support_vectors.py

@@ -9,11 +9,12 @@
 
 """
 
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+
 from sklearn.datasets import make_blobs
-from sklearn.svm import LinearSVC
 from sklearn.inspection import DecisionBoundaryDisplay
+from sklearn.svm import LinearSVC
 
 X, y = make_blobs(n_samples=40, centers=2, random_state=0)
 

Diff for: 1.3/_downloads/0486bf9e537e44cedd2a236d034bcd90/plot_pcr_vs_pls.ipynb

@@ -22,7 +22,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.decomposition import PCA\n\nrng = np.random.RandomState(0)\nn_samples = 500\ncov = [[3, 3], [3, 4]]\nX = rng.multivariate_normal(mean=[0, 0], cov=cov, size=n_samples)\npca = PCA(n_components=2).fit(X)\n\n\nplt.scatter(X[:, 0], X[:, 1], alpha=0.3, label=\"samples\")\nfor i, (comp, var) in enumerate(zip(pca.components_, pca.explained_variance_)):\n    comp = comp * var  # scale component by its variance explanation power\n    plt.plot(\n        [0, comp[0]],\n        [0, comp[1]],\n        label=f\"Component {i}\",\n        linewidth=5,\n        color=f\"C{i + 2}\",\n    )\nplt.gca().set(\n    aspect=\"equal\",\n    title=\"2-dimensional dataset with principal components\",\n    xlabel=\"first feature\",\n    ylabel=\"second feature\",\n)\nplt.legend()\nplt.show()"
+        "import matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.decomposition import PCA\n\nrng = np.random.RandomState(0)\nn_samples = 500\ncov = [[3, 3], [3, 4]]\nX = rng.multivariate_normal(mean=[0, 0], cov=cov, size=n_samples)\npca = PCA(n_components=2).fit(X)\n\n\nplt.scatter(X[:, 0], X[:, 1], alpha=0.3, label=\"samples\")\nfor i, (comp, var) in enumerate(zip(pca.components_, pca.explained_variance_)):\n    comp = comp * var  # scale component by its variance explanation power\n    plt.plot(\n        [0, comp[0]],\n        [0, comp[1]],\n        label=f\"Component {i}\",\n        linewidth=5,\n        color=f\"C{i + 2}\",\n    )\nplt.gca().set(\n    aspect=\"equal\",\n    title=\"2-dimensional dataset with principal components\",\n    xlabel=\"first feature\",\n    ylabel=\"second feature\",\n)\nplt.legend()\nplt.show()"
       ]
     },
     {
@@ -58,7 +58,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.model_selection import train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.decomposition import PCA\nfrom sklearn.cross_decomposition import PLSRegression\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rng)\n\npcr = make_pipeline(StandardScaler(), PCA(n_components=1), LinearRegression())\npcr.fit(X_train, y_train)\npca = pcr.named_steps[\"pca\"]  # retrieve the PCA step of the pipeline\n\npls = PLSRegression(n_components=1)\npls.fit(X_train, y_train)\n\nfig, axes = plt.subplots(1, 2, figsize=(10, 3))\naxes[0].scatter(pca.transform(X_test), y_test, alpha=0.3, label=\"ground truth\")\naxes[0].scatter(\n    pca.transform(X_test), pcr.predict(X_test), alpha=0.3, label=\"predictions\"\n)\naxes[0].set(\n    xlabel=\"Projected data onto first PCA component\", ylabel=\"y\", title=\"PCR / PCA\"\n)\naxes[0].legend()\naxes[1].scatter(pls.transform(X_test), y_test, alpha=0.3, label=\"ground truth\")\naxes[1].scatter(\n    pls.transform(X_test), pls.predict(X_test), alpha=0.3, label=\"predictions\"\n)\naxes[1].set(xlabel=\"Projected data onto first PLS component\", ylabel=\"y\", title=\"PLS\")\naxes[1].legend()\nplt.tight_layout()\nplt.show()"
+        "from sklearn.cross_decomposition import PLSRegression\nfrom sklearn.decomposition import PCA\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rng)\n\npcr = make_pipeline(StandardScaler(), PCA(n_components=1), LinearRegression())\npcr.fit(X_train, y_train)\npca = pcr.named_steps[\"pca\"]  # retrieve the PCA step of the pipeline\n\npls = PLSRegression(n_components=1)\npls.fit(X_train, y_train)\n\nfig, axes = plt.subplots(1, 2, figsize=(10, 3))\naxes[0].scatter(pca.transform(X_test), y_test, alpha=0.3, label=\"ground truth\")\naxes[0].scatter(\n    pca.transform(X_test), pcr.predict(X_test), alpha=0.3, label=\"predictions\"\n)\naxes[0].set(\n    xlabel=\"Projected data onto first PCA component\", ylabel=\"y\", title=\"PCR / PCA\"\n)\naxes[0].legend()\naxes[1].scatter(pls.transform(X_test), y_test, alpha=0.3, label=\"ground truth\")\naxes[1].scatter(\n    pls.transform(X_test), pls.predict(X_test), alpha=0.3, label=\"predictions\"\n)\naxes[1].set(xlabel=\"Projected data onto first PLS component\", ylabel=\"y\", title=\"PLS\")\naxes[1].legend()\nplt.tight_layout()\nplt.show()"
       ]
     },
     {

Diff for: 1.3/_downloads/055e50ba9fa8c7dcf45dc8f1f32a0243/plot_nnls.py

@@ -9,8 +9,9 @@
 
 """
 
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+
 from sklearn.metrics import r2_score
 
 # %%

Diff for: 1.3/_downloads/055e8313e28f2f3b5fd508054dfe5fe0/plot_roc_crossval.ipynb

@@ -22,7 +22,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom sklearn.datasets import load_iris\n\niris = load_iris()\ntarget_names = iris.target_names\nX, y = iris.data, iris.target\nX, y = X[y != 2], y[y != 2]\nn_samples, n_features = X.shape"
+        "import numpy as np\n\nfrom sklearn.datasets import load_iris\n\niris = load_iris()\ntarget_names = iris.target_names\nX, y = iris.data, iris.target\nX, y = X[y != 2], y[y != 2]\nn_samples, n_features = X.shape"
       ]
     },
     {
@@ -58,7 +58,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nfrom sklearn import svm\nfrom sklearn.metrics import auc\nfrom sklearn.metrics import RocCurveDisplay\nfrom sklearn.model_selection import StratifiedKFold\n\nn_splits = 6\ncv = StratifiedKFold(n_splits=n_splits)\nclassifier = svm.SVC(kernel=\"linear\", probability=True, random_state=random_state)\n\ntprs = []\naucs = []\nmean_fpr = np.linspace(0, 1, 100)\n\nfig, ax = plt.subplots(figsize=(6, 6))\nfor fold, (train, test) in enumerate(cv.split(X, y)):\n    classifier.fit(X[train], y[train])\n    viz = RocCurveDisplay.from_estimator(\n        classifier,\n        X[test],\n        y[test],\n        name=f\"ROC fold {fold}\",\n        alpha=0.3,\n        lw=1,\n        ax=ax,\n        plot_chance_level=(fold == n_splits - 1),\n    )\n    interp_tpr = np.interp(mean_fpr, viz.fpr, viz.tpr)\n    interp_tpr[0] = 0.0\n    tprs.append(interp_tpr)\n    aucs.append(viz.roc_auc)\n\nmean_tpr = np.mean(tprs, axis=0)\nmean_tpr[-1] = 1.0\nmean_auc = auc(mean_fpr, mean_tpr)\nstd_auc = np.std(aucs)\nax.plot(\n    mean_fpr,\n    mean_tpr,\n    color=\"b\",\n    label=r\"Mean ROC (AUC = %0.2f $\\pm$ %0.2f)\" % (mean_auc, std_auc),\n    lw=2,\n    alpha=0.8,\n)\n\nstd_tpr = np.std(tprs, axis=0)\ntprs_upper = np.minimum(mean_tpr + std_tpr, 1)\ntprs_lower = np.maximum(mean_tpr - std_tpr, 0)\nax.fill_between(\n    mean_fpr,\n    tprs_lower,\n    tprs_upper,\n    color=\"grey\",\n    alpha=0.2,\n    label=r\"$\\pm$ 1 std. dev.\",\n)\n\nax.set(\n    xlim=[-0.05, 1.05],\n    ylim=[-0.05, 1.05],\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=f\"Mean ROC curve with variability\\n(Positive label '{target_names[1]}')\",\n)\nax.axis(\"square\")\nax.legend(loc=\"lower right\")\nplt.show()"
+        "import matplotlib.pyplot as plt\n\nfrom sklearn import svm\nfrom sklearn.metrics import RocCurveDisplay, auc\nfrom sklearn.model_selection import StratifiedKFold\n\nn_splits = 6\ncv = StratifiedKFold(n_splits=n_splits)\nclassifier = svm.SVC(kernel=\"linear\", probability=True, random_state=random_state)\n\ntprs = []\naucs = []\nmean_fpr = np.linspace(0, 1, 100)\n\nfig, ax = plt.subplots(figsize=(6, 6))\nfor fold, (train, test) in enumerate(cv.split(X, y)):\n    classifier.fit(X[train], y[train])\n    viz = RocCurveDisplay.from_estimator(\n        classifier,\n        X[test],\n        y[test],\n        name=f\"ROC fold {fold}\",\n        alpha=0.3,\n        lw=1,\n        ax=ax,\n        plot_chance_level=(fold == n_splits - 1),\n    )\n    interp_tpr = np.interp(mean_fpr, viz.fpr, viz.tpr)\n    interp_tpr[0] = 0.0\n    tprs.append(interp_tpr)\n    aucs.append(viz.roc_auc)\n\nmean_tpr = np.mean(tprs, axis=0)\nmean_tpr[-1] = 1.0\nmean_auc = auc(mean_fpr, mean_tpr)\nstd_auc = np.std(aucs)\nax.plot(\n    mean_fpr,\n    mean_tpr,\n    color=\"b\",\n    label=r\"Mean ROC (AUC = %0.2f $\\pm$ %0.2f)\" % (mean_auc, std_auc),\n    lw=2,\n    alpha=0.8,\n)\n\nstd_tpr = np.std(tprs, axis=0)\ntprs_upper = np.minimum(mean_tpr + std_tpr, 1)\ntprs_lower = np.maximum(mean_tpr - std_tpr, 0)\nax.fill_between(\n    mean_fpr,\n    tprs_lower,\n    tprs_upper,\n    color=\"grey\",\n    alpha=0.2,\n    label=r\"$\\pm$ 1 std. dev.\",\n)\n\nax.set(\n    xlim=[-0.05, 1.05],\n    ylim=[-0.05, 1.05],\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=f\"Mean ROC curve with variability\\n(Positive label '{target_names[1]}')\",\n)\nax.axis(\"square\")\nax.legend(loc=\"lower right\")\nplt.show()"
       ]
     }
   ],