Pushing the docs to dev/ for branch: main, commit ae2ccbf69a7dbc8398bd9c8443ff265f8f687a13

Author: sklearn-ci

dev/.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: f1c77509c248640c80fa34f784c7d838
+config: d13a003d9102e8060d36407acfd1a1c6
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -76,7 +76,9 @@
     i += 1
     # transform the dataset with KBinsDiscretizer
     for strategy in strategies:
-        enc = KBinsDiscretizer(n_bins=4, encode="ordinal", strategy=strategy)
+        enc = KBinsDiscretizer(
+            n_bins=4, encode="ordinal", strategy=strategy, subsample=200_000
+        )
         enc.fit(X)
         grid_encoded = enc.transform(grid)
 

dev/_downloads/43e84df0b93ff974da370e8da900f2ee/plot_discretization_strategies.py

@@ -89,7 +89,7 @@
 X, y = load_iris(return_X_y=True)
 estimators = [
     ("rf", RandomForestClassifier(n_estimators=10, random_state=42)),
-    ("svr", make_pipeline(StandardScaler(), LinearSVC(random_state=42))),
+    ("svr", make_pipeline(StandardScaler(), LinearSVC(dual="auto", random_state=42))),
 ]
 clf = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())
 X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)

dev/_downloads/50040ae12dd16e7d2e79135d7793c17e/plot_release_highlights_0_22_0.py

@@ -77,7 +77,11 @@
 
 n_bins = 8
 encoder = KBinsDiscretizer(
-    n_bins=n_bins, encode="ordinal", strategy="uniform", random_state=0
+    n_bins=n_bins,
+    encode="ordinal",
+    strategy="uniform",
+    random_state=0,
+    subsample=200_000,
 )
 compressed_raccoon_uniform = encoder.fit_transform(raccoon_face.reshape(-1, 1)).reshape(
     raccoon_face.shape
@@ -122,7 +126,11 @@
 # find a more optimal mapping.
 
 encoder = KBinsDiscretizer(
-    n_bins=n_bins, encode="ordinal", strategy="kmeans", random_state=0
+    n_bins=n_bins,
+    encode="ordinal",
+    strategy="kmeans",
+    random_state=0,
+    subsample=200_000,
 )
 compressed_raccoon_kmeans = encoder.fit_transform(raccoon_face.reshape(-1, 1)).reshape(
     raccoon_face.shape

dev/_downloads/5bb71b0b2052531cacf3736b4d2b3a92/plot_face_compress.py

@@ -58,8 +58,8 @@
 from sklearn.linear_model import ARDRegression, BayesianRidge, LinearRegression
 
 olr = LinearRegression().fit(X, y)
-brr = BayesianRidge(compute_score=True, n_iter=30).fit(X, y)
-ard = ARDRegression(compute_score=True, n_iter=30).fit(X, y)
+brr = BayesianRidge(compute_score=True, max_iter=30).fit(X, y)
+ard = ARDRegression(compute_score=True, max_iter=30).fit(X, y)
 df = pd.DataFrame(
     {
         "Weights of true generative process": true_weights,
@@ -117,7 +117,7 @@
 
 # %%
 # Indeed, both models minimize the log-likelihood up to an arbitrary cutoff
-# defined by the `n_iter` parameter.
+# defined by the `max_iter` parameter.
 #
 # Bayesian regressions with polynomial feature expansion
 # ======================================================

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Tom Dupr\u00e9 la Tour\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.preprocessing import KBinsDiscretizer\n\nstrategies = [\"uniform\", \"quantile\", \"kmeans\"]\n\nn_samples = 200\ncenters_0 = np.array([[0, 0], [0, 5], [2, 4], [8, 8]])\ncenters_1 = np.array([[0, 0], [3, 1]])\n\n# construct the datasets\nrandom_state = 42\nX_list = [\n    np.random.RandomState(random_state).uniform(-3, 3, size=(n_samples, 2)),\n    make_blobs(\n        n_samples=[\n            n_samples // 10,\n            n_samples * 4 // 10,\n            n_samples // 10,\n            n_samples * 4 // 10,\n        ],\n        cluster_std=0.5,\n        centers=centers_0,\n        random_state=random_state,\n    )[0],\n    make_blobs(\n        n_samples=[n_samples // 5, n_samples * 4 // 5],\n        cluster_std=0.5,\n        centers=centers_1,\n        random_state=random_state,\n    )[0],\n]\n\nfigure = plt.figure(figsize=(14, 9))\ni = 1\nfor ds_cnt, X in enumerate(X_list):\n    ax = plt.subplot(len(X_list), len(strategies) + 1, i)\n    ax.scatter(X[:, 0], X[:, 1], edgecolors=\"k\")\n    if ds_cnt == 0:\n        ax.set_title(\"Input data\", size=14)\n\n    xx, yy = np.meshgrid(\n        np.linspace(X[:, 0].min(), X[:, 0].max(), 300),\n        np.linspace(X[:, 1].min(), X[:, 1].max(), 300),\n    )\n    grid = np.c_[xx.ravel(), yy.ravel()]\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\n    i += 1\n    # transform the dataset with KBinsDiscretizer\n    for strategy in strategies:\n        enc = KBinsDiscretizer(n_bins=4, encode=\"ordinal\", strategy=strategy)\n        enc.fit(X)\n        grid_encoded = enc.transform(grid)\n\n        ax = plt.subplot(len(X_list), len(strategies) + 1, i)\n\n        # horizontal stripes\n        horizontal = grid_encoded[:, 0].reshape(xx.shape)\n        ax.contourf(xx, yy, horizontal, alpha=0.5)\n        # vertical stripes\n        vertical = grid_encoded[:, 1].reshape(xx.shape)\n        ax.contourf(xx, yy, vertical, alpha=0.5)\n\n        ax.scatter(X[:, 0], X[:, 1], edgecolors=\"k\")\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        if ds_cnt == 0:\n            ax.set_title(\"strategy='%s'\" % (strategy,), size=14)\n\n        i += 1\n\nplt.tight_layout()\nplt.show()"
+        "# Author: Tom Dupr\u00e9 la Tour\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.preprocessing import KBinsDiscretizer\n\nstrategies = [\"uniform\", \"quantile\", \"kmeans\"]\n\nn_samples = 200\ncenters_0 = np.array([[0, 0], [0, 5], [2, 4], [8, 8]])\ncenters_1 = np.array([[0, 0], [3, 1]])\n\n# construct the datasets\nrandom_state = 42\nX_list = [\n    np.random.RandomState(random_state).uniform(-3, 3, size=(n_samples, 2)),\n    make_blobs(\n        n_samples=[\n            n_samples // 10,\n            n_samples * 4 // 10,\n            n_samples // 10,\n            n_samples * 4 // 10,\n        ],\n        cluster_std=0.5,\n        centers=centers_0,\n        random_state=random_state,\n    )[0],\n    make_blobs(\n        n_samples=[n_samples // 5, n_samples * 4 // 5],\n        cluster_std=0.5,\n        centers=centers_1,\n        random_state=random_state,\n    )[0],\n]\n\nfigure = plt.figure(figsize=(14, 9))\ni = 1\nfor ds_cnt, X in enumerate(X_list):\n    ax = plt.subplot(len(X_list), len(strategies) + 1, i)\n    ax.scatter(X[:, 0], X[:, 1], edgecolors=\"k\")\n    if ds_cnt == 0:\n        ax.set_title(\"Input data\", size=14)\n\n    xx, yy = np.meshgrid(\n        np.linspace(X[:, 0].min(), X[:, 0].max(), 300),\n        np.linspace(X[:, 1].min(), X[:, 1].max(), 300),\n    )\n    grid = np.c_[xx.ravel(), yy.ravel()]\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\n    i += 1\n    # transform the dataset with KBinsDiscretizer\n    for strategy in strategies:\n        enc = KBinsDiscretizer(\n            n_bins=4, encode=\"ordinal\", strategy=strategy, subsample=200_000\n        )\n        enc.fit(X)\n        grid_encoded = enc.transform(grid)\n\n        ax = plt.subplot(len(X_list), len(strategies) + 1, i)\n\n        # horizontal stripes\n        horizontal = grid_encoded[:, 0].reshape(xx.shape)\n        ax.contourf(xx, yy, horizontal, alpha=0.5)\n        # vertical stripes\n        vertical = grid_encoded[:, 1].reshape(xx.shape)\n        ax.contourf(xx, yy, vertical, alpha=0.5)\n\n        ax.scatter(X[:, 0], X[:, 1], edgecolors=\"k\")\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        if ds_cnt == 0:\n            ax.set_title(\"strategy='%s'\" % (strategy,), size=14)\n\n        i += 1\n\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/892d774326b523935a603b8700193195/plot_ard.py

@@ -51,7 +51,7 @@
       },
       "outputs": [],
       "source": [
-        "import pandas as pd\n\nfrom sklearn.linear_model import ARDRegression, BayesianRidge, LinearRegression\n\nolr = LinearRegression().fit(X, y)\nbrr = BayesianRidge(compute_score=True, n_iter=30).fit(X, y)\nard = ARDRegression(compute_score=True, n_iter=30).fit(X, y)\ndf = pd.DataFrame(\n    {\n        \"Weights of true generative process\": true_weights,\n        \"ARDRegression\": ard.coef_,\n        \"BayesianRidge\": brr.coef_,\n        \"LinearRegression\": olr.coef_,\n    }\n)"
+        "import pandas as pd\n\nfrom sklearn.linear_model import ARDRegression, BayesianRidge, LinearRegression\n\nolr = LinearRegression().fit(X, y)\nbrr = BayesianRidge(compute_score=True, max_iter=30).fit(X, y)\nard = ARDRegression(compute_score=True, max_iter=30).fit(X, y)\ndf = pd.DataFrame(\n    {\n        \"Weights of true generative process\": true_weights,\n        \"ARDRegression\": ard.coef_,\n        \"BayesianRidge\": brr.coef_,\n        \"LinearRegression\": olr.coef_,\n    }\n)"
       ]
     },
     {
@@ -101,7 +101,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Indeed, both models minimize the log-likelihood up to an arbitrary cutoff\ndefined by the `n_iter` parameter.\n\n## Bayesian regressions with polynomial feature expansion\nGenerate synthetic dataset\n--------------------------\nWe create a target that is a non-linear function of the input feature.\nNoise following a standard uniform distribution is added.\n\n"
+        "Indeed, both models minimize the log-likelihood up to an arbitrary cutoff\ndefined by the `max_iter` parameter.\n\n## Bayesian regressions with polynomial feature expansion\nGenerate synthetic dataset\n--------------------------\nWe create a target that is a non-linear function of the input feature.\nNoise following a standard uniform distribution is added.\n\n"
       ]
     },
     {

dev/_downloads/adc9be3b7acc279025dad9ee4ce92038/plot_discretization_strategies.ipynb

@@ -40,7 +40,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.datasets import load_iris\nfrom sklearn.ensemble import StackingClassifier\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import LinearSVC\n\nX, y = load_iris(return_X_y=True)\nestimators = [\n    (\"rf\", RandomForestClassifier(n_estimators=10, random_state=42)),\n    (\"svr\", make_pipeline(StandardScaler(), LinearSVC(random_state=42))),\n]\nclf = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())\nX_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)\nclf.fit(X_train, y_train).score(X_test, y_test)"
+        "from sklearn.datasets import load_iris\nfrom sklearn.ensemble import StackingClassifier\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import LinearSVC\n\nX, y = load_iris(return_X_y=True)\nestimators = [\n    (\"rf\", RandomForestClassifier(n_estimators=10, random_state=42)),\n    (\"svr\", make_pipeline(StandardScaler(), LinearSVC(dual=\"auto\", random_state=42))),\n]\nclf = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())\nX_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)\nclf.fit(X_train, y_train).score(X_test, y_test)"
       ]
     },
     {