Pushing the docs to dev/ for branch: main, commit 3e127a3d5cb9ff89fcf61260c4d082663695fec4

Author: sklearn-ci

dev/_downloads/00ae629d652473137a3905a5e08ea815/plot_iris_dtc.py

@@ -15,6 +15,9 @@
 We also show the tree structure of a model built on all of the features.
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # %%
 # First load the copy of the Iris dataset shipped with scikit-learn:
 from sklearn.datasets import load_iris

dev/_downloads/010337852815f8103ac6cca38a812b3c/plot_roc_crossval.py

@@ -27,6 +27,9 @@
     generalize the metrics for multiclass classifiers.
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # %%
 # Load and prepare data
 # =====================

dev/_downloads/02a7bbce3c39c70d62d80e875968e5c6/plot_digits_kde_sampling.py

@@ -11,6 +11,9 @@
 
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 import matplotlib.pyplot as plt
 import numpy as np
 

dev/_downloads/02d88d76c60b7397c8c6e221b31568dd/plot_grid_search_refit_callable.py

@@ -18,7 +18,8 @@
 
 """
 
-# Author: Wenhao Zhang <[email protected]>
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.pyplot as plt
 import numpy as np

dev/_downloads/036b9372e2e7802453cbb994da7a6786/plot_linearsvc_support_vectors.py

@@ -9,6 +9,9 @@
 
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 import matplotlib.pyplot as plt
 import numpy as np
 

dev/_downloads/0486bf9e537e44cedd2a236d034bcd90/plot_pcr_vs_pls.ipynb

@@ -7,6 +7,17 @@
         "\n# Principal Component Regression vs Partial Least Squares Regression\n\nThis example compares [Principal Component Regression](https://en.wikipedia.org/wiki/Principal_component_regression) (PCR) and\n[Partial Least Squares Regression](https://en.wikipedia.org/wiki/Partial_least_squares_regression) (PLS) on a\ntoy dataset. Our goal is to illustrate how PLS can outperform PCR when the\ntarget is strongly correlated with some directions in the data that have a\nlow variance.\n\nPCR is a regressor composed of two steps: first,\n:class:`~sklearn.decomposition.PCA` is applied to the training data, possibly\nperforming dimensionality reduction; then, a regressor (e.g. a linear\nregressor) is trained on the transformed samples. In\n:class:`~sklearn.decomposition.PCA`, the transformation is purely\nunsupervised, meaning that no information about the targets is used. As a\nresult, PCR may perform poorly in some datasets where the target is strongly\ncorrelated with *directions* that have low variance. Indeed, the\ndimensionality reduction of PCA projects the data into a lower dimensional\nspace where the variance of the projected data is greedily maximized along\neach axis. Despite them having the most predictive power on the target, the\ndirections with a lower variance will be dropped, and the final regressor\nwill not be able to leverage them.\n\nPLS is both a transformer and a regressor, and it is quite similar to PCR: it\nalso applies a dimensionality reduction to the samples before applying a\nlinear regressor to the transformed data. The main difference with PCR is\nthat the PLS transformation is supervised. Therefore, as we will see in this\nexample, it does not suffer from the issue we just mentioned.\n"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

dev/_downloads/055e50ba9fa8c7dcf45dc8f1f32a0243/plot_nnls.py

@@ -9,6 +9,9 @@
 
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 import matplotlib.pyplot as plt
 import numpy as np
 

dev/_downloads/055e8313e28f2f3b5fd508054dfe5fe0/plot_roc_crossval.ipynb

@@ -7,6 +7,17 @@
         "\n# Receiver Operating Characteristic (ROC) with cross validation\n\nThis example presents how to estimate and visualize the variance of the Receiver\nOperating Characteristic (ROC) metric using cross-validation.\n\nROC curves typically feature true positive rate (TPR) on the Y axis, and false\npositive rate (FPR) on the X axis. This means that the top left corner of the\nplot is the \"ideal\" point - a FPR of zero, and a TPR of one. This is not very\nrealistic, but it does mean that a larger Area Under the Curve (AUC) is usually\nbetter. The \"steepness\" of ROC curves is also important, since it is ideal to\nmaximize the TPR while minimizing the FPR.\n\nThis example shows the ROC response of different datasets, created from K-fold\ncross-validation. Taking all of these curves, it is possible to calculate the\nmean AUC, and see the variance of the curve when the\ntraining set is split into different subsets. This roughly shows how the\nclassifier output is affected by changes in the training data, and how different\nthe splits generated by K-fold cross-validation are from one another.\n\n<div class=\"alert alert-info\"><h4>Note</h4><p>See `sphx_glr_auto_examples_model_selection_plot_roc.py` for a\n    complement of the present example explaining the averaging strategies to\n    generalize the metrics for multiclass classifiers.</p></div>\n"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

dev/_downloads/061854726c268bcdae5cd1c330cf8c75/plot_sgd_penalties.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nimport numpy as np\n\nl1_color = \"navy\"\nl2_color = \"c\"\nelastic_net_color = \"darkorange\"\n\nline = np.linspace(-1.5, 1.5, 1001)\nxx, yy = np.meshgrid(line, line)\n\nl2 = xx**2 + yy**2\nl1 = np.abs(xx) + np.abs(yy)\nrho = 0.5\nelastic_net = rho * l1 + (1 - rho) * l2\n\nplt.figure(figsize=(10, 10), dpi=100)\nax = plt.gca()\n\nelastic_net_contour = plt.contour(\n    xx, yy, elastic_net, levels=[1], colors=elastic_net_color\n)\nl2_contour = plt.contour(xx, yy, l2, levels=[1], colors=l2_color)\nl1_contour = plt.contour(xx, yy, l1, levels=[1], colors=l1_color)\nax.set_aspect(\"equal\")\nax.spines[\"left\"].set_position(\"center\")\nax.spines[\"right\"].set_color(\"none\")\nax.spines[\"bottom\"].set_position(\"center\")\nax.spines[\"top\"].set_color(\"none\")\n\nplt.clabel(\n    elastic_net_contour,\n    inline=1,\n    fontsize=18,\n    fmt={1.0: \"elastic-net\"},\n    manual=[(-1, -1)],\n)\nplt.clabel(l2_contour, inline=1, fontsize=18, fmt={1.0: \"L2\"}, manual=[(-1, -1)])\nplt.clabel(l1_contour, inline=1, fontsize=18, fmt={1.0: \"L1\"}, manual=[(-1, -1)])\n\nplt.tight_layout()\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nl1_color = \"navy\"\nl2_color = \"c\"\nelastic_net_color = \"darkorange\"\n\nline = np.linspace(-1.5, 1.5, 1001)\nxx, yy = np.meshgrid(line, line)\n\nl2 = xx**2 + yy**2\nl1 = np.abs(xx) + np.abs(yy)\nrho = 0.5\nelastic_net = rho * l1 + (1 - rho) * l2\n\nplt.figure(figsize=(10, 10), dpi=100)\nax = plt.gca()\n\nelastic_net_contour = plt.contour(\n    xx, yy, elastic_net, levels=[1], colors=elastic_net_color\n)\nl2_contour = plt.contour(xx, yy, l2, levels=[1], colors=l2_color)\nl1_contour = plt.contour(xx, yy, l1, levels=[1], colors=l1_color)\nax.set_aspect(\"equal\")\nax.spines[\"left\"].set_position(\"center\")\nax.spines[\"right\"].set_color(\"none\")\nax.spines[\"bottom\"].set_position(\"center\")\nax.spines[\"top\"].set_color(\"none\")\n\nplt.clabel(\n    elastic_net_contour,\n    inline=1,\n    fontsize=18,\n    fmt={1.0: \"elastic-net\"},\n    manual=[(-1, -1)],\n)\nplt.clabel(l2_contour, inline=1, fontsize=18, fmt={1.0: \"L2\"}, manual=[(-1, -1)])\nplt.clabel(l1_contour, inline=1, fontsize=18, fmt={1.0: \"L1\"}, manual=[(-1, -1)])\n\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/067cd5d39b097d2c49dd98f563dac13a/plot_iterative_imputer_variants_comparison.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.ensemble import RandomForestRegressor\n\n# To use this experimental feature, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa\nfrom sklearn.impute import IterativeImputer, SimpleImputer\nfrom sklearn.kernel_approximation import Nystroem\nfrom sklearn.linear_model import BayesianRidge, Ridge\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.pipeline import make_pipeline\n\nN_SPLITS = 5\n\nrng = np.random.RandomState(0)\n\nX_full, y_full = fetch_california_housing(return_X_y=True)\n# ~2k samples is enough for the purpose of the example.\n# Remove the following two lines for a slower run with different error bars.\nX_full = X_full[::10]\ny_full = y_full[::10]\nn_samples, n_features = X_full.shape\n\n# Estimate the score on the entire dataset, with no missing values\nbr_estimator = BayesianRidge()\nscore_full_data = pd.DataFrame(\n    cross_val_score(\n        br_estimator, X_full, y_full, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    ),\n    columns=[\"Full Data\"],\n)\n\n# Add a single missing value to each row\nX_missing = X_full.copy()\ny_missing = y_full\nmissing_samples = np.arange(n_samples)\nmissing_features = rng.choice(n_features, n_samples, replace=True)\nX_missing[missing_samples, missing_features] = np.nan\n\n# Estimate the score after imputation (mean and median strategies)\nscore_simple_imputer = pd.DataFrame()\nfor strategy in (\"mean\", \"median\"):\n    estimator = make_pipeline(\n        SimpleImputer(missing_values=np.nan, strategy=strategy), br_estimator\n    )\n    score_simple_imputer[strategy] = cross_val_score(\n        estimator, X_missing, y_missing, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\n# Estimate the score after iterative imputation of the missing values\n# with different estimators\nestimators = [\n    BayesianRidge(),\n    RandomForestRegressor(\n        # We tuned the hyperparameters of the RandomForestRegressor to get a good\n        # enough predictive performance for a restricted execution time.\n        n_estimators=4,\n        max_depth=10,\n        bootstrap=True,\n        max_samples=0.5,\n        n_jobs=2,\n        random_state=0,\n    ),\n    make_pipeline(\n        Nystroem(kernel=\"polynomial\", degree=2, random_state=0), Ridge(alpha=1e3)\n    ),\n    KNeighborsRegressor(n_neighbors=15),\n]\nscore_iterative_imputer = pd.DataFrame()\n# iterative imputer is sensible to the tolerance and\n# dependent on the estimator used internally.\n# we tuned the tolerance to keep this example run with limited computational\n# resources while not changing the results too much compared to keeping the\n# stricter default value for the tolerance parameter.\ntolerances = (1e-3, 1e-1, 1e-1, 1e-2)\nfor impute_estimator, tol in zip(estimators, tolerances):\n    estimator = make_pipeline(\n        IterativeImputer(\n            random_state=0, estimator=impute_estimator, max_iter=25, tol=tol\n        ),\n        br_estimator,\n    )\n    score_iterative_imputer[impute_estimator.__class__.__name__] = cross_val_score(\n        estimator, X_missing, y_missing, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\nscores = pd.concat(\n    [score_full_data, score_simple_imputer, score_iterative_imputer],\n    keys=[\"Original\", \"SimpleImputer\", \"IterativeImputer\"],\n    axis=1,\n)\n\n# plot california housing results\nfig, ax = plt.subplots(figsize=(13, 6))\nmeans = -scores.mean()\nerrors = scores.std()\nmeans.plot.barh(xerr=errors, ax=ax)\nax.set_title(\"California Housing Regression with Different Imputation Methods\")\nax.set_xlabel(\"MSE (smaller is better)\")\nax.set_yticks(np.arange(means.shape[0]))\nax.set_yticklabels([\" w/ \".join(label) for label in means.index.tolist()])\nplt.tight_layout(pad=1)\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.ensemble import RandomForestRegressor\n\n# To use this experimental feature, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa\nfrom sklearn.impute import IterativeImputer, SimpleImputer\nfrom sklearn.kernel_approximation import Nystroem\nfrom sklearn.linear_model import BayesianRidge, Ridge\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.pipeline import make_pipeline\n\nN_SPLITS = 5\n\nrng = np.random.RandomState(0)\n\nX_full, y_full = fetch_california_housing(return_X_y=True)\n# ~2k samples is enough for the purpose of the example.\n# Remove the following two lines for a slower run with different error bars.\nX_full = X_full[::10]\ny_full = y_full[::10]\nn_samples, n_features = X_full.shape\n\n# Estimate the score on the entire dataset, with no missing values\nbr_estimator = BayesianRidge()\nscore_full_data = pd.DataFrame(\n    cross_val_score(\n        br_estimator, X_full, y_full, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    ),\n    columns=[\"Full Data\"],\n)\n\n# Add a single missing value to each row\nX_missing = X_full.copy()\ny_missing = y_full\nmissing_samples = np.arange(n_samples)\nmissing_features = rng.choice(n_features, n_samples, replace=True)\nX_missing[missing_samples, missing_features] = np.nan\n\n# Estimate the score after imputation (mean and median strategies)\nscore_simple_imputer = pd.DataFrame()\nfor strategy in (\"mean\", \"median\"):\n    estimator = make_pipeline(\n        SimpleImputer(missing_values=np.nan, strategy=strategy), br_estimator\n    )\n    score_simple_imputer[strategy] = cross_val_score(\n        estimator, X_missing, y_missing, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\n# Estimate the score after iterative imputation of the missing values\n# with different estimators\nestimators = [\n    BayesianRidge(),\n    RandomForestRegressor(\n        # We tuned the hyperparameters of the RandomForestRegressor to get a good\n        # enough predictive performance for a restricted execution time.\n        n_estimators=4,\n        max_depth=10,\n        bootstrap=True,\n        max_samples=0.5,\n        n_jobs=2,\n        random_state=0,\n    ),\n    make_pipeline(\n        Nystroem(kernel=\"polynomial\", degree=2, random_state=0), Ridge(alpha=1e3)\n    ),\n    KNeighborsRegressor(n_neighbors=15),\n]\nscore_iterative_imputer = pd.DataFrame()\n# iterative imputer is sensible to the tolerance and\n# dependent on the estimator used internally.\n# we tuned the tolerance to keep this example run with limited computational\n# resources while not changing the results too much compared to keeping the\n# stricter default value for the tolerance parameter.\ntolerances = (1e-3, 1e-1, 1e-1, 1e-2)\nfor impute_estimator, tol in zip(estimators, tolerances):\n    estimator = make_pipeline(\n        IterativeImputer(\n            random_state=0, estimator=impute_estimator, max_iter=25, tol=tol\n        ),\n        br_estimator,\n    )\n    score_iterative_imputer[impute_estimator.__class__.__name__] = cross_val_score(\n        estimator, X_missing, y_missing, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\nscores = pd.concat(\n    [score_full_data, score_simple_imputer, score_iterative_imputer],\n    keys=[\"Original\", \"SimpleImputer\", \"IterativeImputer\"],\n    axis=1,\n)\n\n# plot california housing results\nfig, ax = plt.subplots(figsize=(13, 6))\nmeans = -scores.mean()\nerrors = scores.std()\nmeans.plot.barh(xerr=errors, ax=ax)\nax.set_title(\"California Housing Regression with Different Imputation Methods\")\nax.set_xlabel(\"MSE (smaller is better)\")\nax.set_yticks(np.arange(means.shape[0]))\nax.set_yticklabels([\" w/ \".join(label) for label in means.index.tolist()])\nplt.tight_layout(pad=1)\nplt.show()"
       ]
     }
   ],

dev/_downloads/06d58c7fb0650278c0e3ea127bff7167/plot_lof_outlier_detection.py

@@ -22,6 +22,9 @@
 
 """
 
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
 # %%
 # Generate data with outliers
 # ---------------------------

dev/_downloads/06ffeb4f0ded6447302acd5a712f8490/plot_nearest_centroid.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nimport numpy as np\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn import datasets\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.neighbors import NearestCentroid\n\n# import some data to play with\niris = datasets.load_iris()\n# we only take the first two features. We could avoid this ugly\n# slicing by using a two-dim dataset\nX = iris.data[:, :2]\ny = iris.target\n\n# Create color maps\ncmap_light = ListedColormap([\"orange\", \"cyan\", \"cornflowerblue\"])\ncmap_bold = ListedColormap([\"darkorange\", \"c\", \"darkblue\"])\n\nfor shrinkage in [None, 0.2]:\n    # we create an instance of Nearest Centroid Classifier and fit the data.\n    clf = NearestCentroid(shrink_threshold=shrinkage)\n    clf.fit(X, y)\n    y_pred = clf.predict(X)\n    print(shrinkage, np.mean(y == y_pred))\n\n    _, ax = plt.subplots()\n    DecisionBoundaryDisplay.from_estimator(\n        clf, X, cmap=cmap_light, ax=ax, response_method=\"predict\"\n    )\n\n    # Plot also the training points\n    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor=\"k\", s=20)\n    plt.title(\"3-Class classification (shrink_threshold=%r)\" % shrinkage)\n    plt.axis(\"tight\")\n\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn import datasets\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.neighbors import NearestCentroid\n\n# import some data to play with\niris = datasets.load_iris()\n# we only take the first two features. We could avoid this ugly\n# slicing by using a two-dim dataset\nX = iris.data[:, :2]\ny = iris.target\n\n# Create color maps\ncmap_light = ListedColormap([\"orange\", \"cyan\", \"cornflowerblue\"])\ncmap_bold = ListedColormap([\"darkorange\", \"c\", \"darkblue\"])\n\nfor shrinkage in [None, 0.2]:\n    # we create an instance of Nearest Centroid Classifier and fit the data.\n    clf = NearestCentroid(shrink_threshold=shrinkage)\n    clf.fit(X, y)\n    y_pred = clf.predict(X)\n    print(shrinkage, np.mean(y == y_pred))\n\n    _, ax = plt.subplots()\n    DecisionBoundaryDisplay.from_estimator(\n        clf, X, cmap=cmap_light, ax=ax, response_method=\"predict\"\n    )\n\n    # Plot also the training points\n    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor=\"k\", s=20)\n    plt.title(\"3-Class classification (shrink_threshold=%r)\" % shrinkage)\n    plt.axis(\"tight\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -7,6 +7,17 @@
         "\n# Compare cross decomposition methods\n\nSimple usage of various cross decomposition algorithms:\n\n- PLSCanonical\n- PLSRegression, with multivariate response, a.k.a. PLS2\n- PLSRegression, with univariate response, a.k.a. PLS1\n- CCA\n\nGiven 2 multivariate covarying two-dimensional datasets, X, and Y,\nPLS extracts the 'directions of covariance', i.e. the components of each\ndatasets that explain the most shared variance between both datasets.\nThis is apparent on the **scatterplot matrix** display: components 1 in\ndataset X and dataset Y are maximally correlated (points lie around the\nfirst diagonal). This is also true for components 2 in both dataset,\nhowever, the correlation across datasets for different components is\nweak: the point cloud is very spherical.\n"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},