Pushing the docs to 1.5/ for branch: 1.5.X, commit 70fdc843a4b8182d97a3508c1a426acc5e87e980

Author: sklearn-ci

1.5/.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: 2907958f5ac8f0a65d5062369d2dcd04
+config: d957078dbf4c58a2fce77ff0dd5a988d
 tags: 645f666f9bcd5a90fca523b33c5a78b7

1.5/_downloads/00ae629d652473137a3905a5e08ea815/plot_iris_dtc.py

@@ -66,7 +66,6 @@
             X[idx, 1],
             c=color,
             label=iris.target_names[i],
-            cmap=plt.cm.RdYlBu,
             edgecolor="black",
             s=15,
         )

1.5/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -63,6 +63,21 @@
 # means that the final logistic regression step contains the feature names of the input.
 clf[-1].feature_names_in_
 
+# %%
+# .. note:: If one uses the method `set_params`, the transformer will be
+#    replaced by a new one with the default output format.
+clf.set_params(standardscaler=StandardScaler())
+clf.fit(X_train, y_train)
+clf[-1].feature_names_in_
+
+# %%
+# To keep the intended behavior, use `set_output` on the new transformer
+# beforehand
+scaler = StandardScaler().set_output(transform="pandas")
+clf.set_params(standardscaler=scaler)
+clf.fit(X_train, y_train)
+clf[-1].feature_names_in_
+
 # %%
 # Next we load the titanic dataset to demonstrate `set_output` with
 # :class:`compose.ColumnTransformer` and heterogeneous data.

1.5/_downloads/1b3f17ff0f112d5b77cbdb90f1c17046/plot_set_output.py

@@ -16,7 +16,6 @@
 from itertools import cycle
 
 import matplotlib.pyplot as plt
-import numpy as np
 
 from sklearn import datasets
 from sklearn.linear_model import enet_path, lasso_path
@@ -49,41 +48,37 @@
 
 plt.figure(1)
 colors = cycle(["b", "r", "g", "c", "k"])
-neg_log_alphas_lasso = -np.log10(alphas_lasso)
-neg_log_alphas_enet = -np.log10(alphas_enet)
 for coef_l, coef_e, c in zip(coefs_lasso, coefs_enet, colors):
-    l1 = plt.plot(neg_log_alphas_lasso, coef_l, c=c)
-    l2 = plt.plot(neg_log_alphas_enet, coef_e, linestyle="--", c=c)
+    l1 = plt.semilogx(alphas_lasso, coef_l, c=c)
+    l2 = plt.semilogx(alphas_enet, coef_e, linestyle="--", c=c)
 
-plt.xlabel("-Log(alpha)")
+plt.xlabel("alpha")
 plt.ylabel("coefficients")
 plt.title("Lasso and Elastic-Net Paths")
-plt.legend((l1[-1], l2[-1]), ("Lasso", "Elastic-Net"), loc="lower left")
+plt.legend((l1[-1], l2[-1]), ("Lasso", "Elastic-Net"), loc="lower right")
 plt.axis("tight")
 
 
 plt.figure(2)
-neg_log_alphas_positive_lasso = -np.log10(alphas_positive_lasso)
 for coef_l, coef_pl, c in zip(coefs_lasso, coefs_positive_lasso, colors):
-    l1 = plt.plot(neg_log_alphas_lasso, coef_l, c=c)
-    l2 = plt.plot(neg_log_alphas_positive_lasso, coef_pl, linestyle="--", c=c)
+    l1 = plt.semilogy(alphas_lasso, coef_l, c=c)
+    l2 = plt.semilogy(alphas_positive_lasso, coef_pl, linestyle="--", c=c)
 
-plt.xlabel("-Log(alpha)")
+plt.xlabel("alpha")
 plt.ylabel("coefficients")
 plt.title("Lasso and positive Lasso")
-plt.legend((l1[-1], l2[-1]), ("Lasso", "positive Lasso"), loc="lower left")
+plt.legend((l1[-1], l2[-1]), ("Lasso", "positive Lasso"), loc="lower right")
 plt.axis("tight")
 
 
 plt.figure(3)
-neg_log_alphas_positive_enet = -np.log10(alphas_positive_enet)
 for coef_e, coef_pe, c in zip(coefs_enet, coefs_positive_enet, colors):
-    l1 = plt.plot(neg_log_alphas_enet, coef_e, c=c)
-    l2 = plt.plot(neg_log_alphas_positive_enet, coef_pe, linestyle="--", c=c)
+    l1 = plt.semilogx(alphas_enet, coef_e, c=c)
+    l2 = plt.semilogx(alphas_positive_enet, coef_pe, linestyle="--", c=c)
 
-plt.xlabel("-Log(alpha)")
+plt.xlabel("alpha")
 plt.ylabel("coefficients")
 plt.title("Elastic-Net and positive Elastic-Net")
-plt.legend((l1[-1], l2[-1]), ("Elastic-Net", "positive Elastic-Net"), loc="lower left")
+plt.legend((l1[-1], l2[-1]), ("Elastic-Net", "positive Elastic-Net"), loc="lower right")
 plt.axis("tight")
 plt.show()

1.5/_downloads/1f682002d8b68c290d9d03599368e83d/plot_lasso_coordinate_descent_path.py

@@ -51,7 +51,7 @@
       },
       "outputs": [],
       "source": [
-        "def plot_cv_indices(cv, X, y, group, ax, n_splits, lw=10):\n    \"\"\"Create a sample plot for indices of a cross-validation object.\"\"\"\n\n    # Generate the training/testing visualizations for each CV split\n    for ii, (tr, tt) in enumerate(cv.split(X=X, y=y, groups=group)):\n        # Fill in indices with the training/test groups\n        indices = np.array([np.nan] * len(X))\n        indices[tt] = 1\n        indices[tr] = 0\n\n        # Visualize the results\n        ax.scatter(\n            range(len(indices)),\n            [ii + 0.5] * len(indices),\n            c=indices,\n            marker=\"_\",\n            lw=lw,\n            cmap=cmap_cv,\n            vmin=-0.2,\n            vmax=1.2,\n        )\n\n    # Plot the data classes and groups at the end\n    ax.scatter(\n        range(len(X)), [ii + 1.5] * len(X), c=y, marker=\"_\", lw=lw, cmap=cmap_data\n    )\n\n    ax.scatter(\n        range(len(X)), [ii + 2.5] * len(X), c=group, marker=\"_\", lw=lw, cmap=cmap_data\n    )\n\n    # Formatting\n    yticklabels = list(range(n_splits)) + [\"class\", \"group\"]\n    ax.set(\n        yticks=np.arange(n_splits + 2) + 0.5,\n        yticklabels=yticklabels,\n        xlabel=\"Sample index\",\n        ylabel=\"CV iteration\",\n        ylim=[n_splits + 2.2, -0.2],\n        xlim=[0, 100],\n    )\n    ax.set_title(\"{}\".format(type(cv).__name__), fontsize=15)\n    return ax"
+        "def plot_cv_indices(cv, X, y, group, ax, n_splits, lw=10):\n    \"\"\"Create a sample plot for indices of a cross-validation object.\"\"\"\n    use_groups = \"Group\" in type(cv).__name__\n    groups = group if use_groups else None\n    # Generate the training/testing visualizations for each CV split\n    for ii, (tr, tt) in enumerate(cv.split(X=X, y=y, groups=groups)):\n        # Fill in indices with the training/test groups\n        indices = np.array([np.nan] * len(X))\n        indices[tt] = 1\n        indices[tr] = 0\n\n        # Visualize the results\n        ax.scatter(\n            range(len(indices)),\n            [ii + 0.5] * len(indices),\n            c=indices,\n            marker=\"_\",\n            lw=lw,\n            cmap=cmap_cv,\n            vmin=-0.2,\n            vmax=1.2,\n        )\n\n    # Plot the data classes and groups at the end\n    ax.scatter(\n        range(len(X)), [ii + 1.5] * len(X), c=y, marker=\"_\", lw=lw, cmap=cmap_data\n    )\n\n    ax.scatter(\n        range(len(X)), [ii + 2.5] * len(X), c=group, marker=\"_\", lw=lw, cmap=cmap_data\n    )\n\n    # Formatting\n    yticklabels = list(range(n_splits)) + [\"class\", \"group\"]\n    ax.set(\n        yticks=np.arange(n_splits + 2) + 0.5,\n        yticklabels=yticklabels,\n        xlabel=\"Sample index\",\n        ylabel=\"CV iteration\",\n        ylim=[n_splits + 2.2, -0.2],\n        xlim=[0, 100],\n    )\n    ax.set_title(\"{}\".format(type(cv).__name__), fontsize=15)\n    return ax"
       ]
     },
     {

1.5/_downloads/49cd91d05440a1c88b074430761aeb76/plot_cv_indices.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Tom Dupre la Tour <[email protected]>\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.multiclass import OneVsRestClassifier\n\n# make 3-class dataset for classification\ncenters = [[-5, 0], [0, 1.5], [5, -1]]\nX, y = make_blobs(n_samples=1000, centers=centers, random_state=40)\ntransformation = [[0.4, 0.2], [-0.4, 1.2]]\nX = np.dot(X, transformation)\n\nfor multi_class in (\"multinomial\", \"ovr\"):\n    clf = LogisticRegression(solver=\"sag\", max_iter=100, random_state=42)\n    if multi_class == \"ovr\":\n        clf = OneVsRestClassifier(clf)\n    clf.fit(X, y)\n\n    # print the training scores\n    print(\"training score : %.3f (%s)\" % (clf.score(X, y), multi_class))\n\n    _, ax = plt.subplots()\n    DecisionBoundaryDisplay.from_estimator(\n        clf, X, response_method=\"predict\", cmap=plt.cm.Paired, ax=ax\n    )\n    plt.title(\"Decision surface of LogisticRegression (%s)\" % multi_class)\n    plt.axis(\"tight\")\n\n    # Plot also the training points\n    colors = \"bry\"\n    for i, color in zip(clf.classes_, colors):\n        idx = np.where(y == i)\n        plt.scatter(\n            X[idx, 0], X[idx, 1], c=color, cmap=plt.cm.Paired, edgecolor=\"black\", s=20\n        )\n\n    # Plot the three one-against-all classifiers\n    xmin, xmax = plt.xlim()\n    ymin, ymax = plt.ylim()\n    if multi_class == \"ovr\":\n        coef = np.concatenate([est.coef_ for est in clf.estimators_])\n        intercept = np.concatenate([est.intercept_ for est in clf.estimators_])\n    else:\n        coef = clf.coef_\n        intercept = clf.intercept_\n\n    def plot_hyperplane(c, color):\n        def line(x0):\n            return (-(x0 * coef[c, 0]) - intercept[c]) / coef[c, 1]\n\n        plt.plot([xmin, xmax], [line(xmin), line(xmax)], ls=\"--\", color=color)\n\n    for i, color in zip(clf.classes_, colors):\n        plot_hyperplane(i, color)\n\nplt.show()"
+        "# Authors: Tom Dupre la Tour <[email protected]>\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.multiclass import OneVsRestClassifier\n\n# make 3-class dataset for classification\ncenters = [[-5, 0], [0, 1.5], [5, -1]]\nX, y = make_blobs(n_samples=1000, centers=centers, random_state=40)\ntransformation = [[0.4, 0.2], [-0.4, 1.2]]\nX = np.dot(X, transformation)\n\nfor multi_class in (\"multinomial\", \"ovr\"):\n    clf = LogisticRegression(solver=\"sag\", max_iter=100, random_state=42)\n    if multi_class == \"ovr\":\n        clf = OneVsRestClassifier(clf)\n    clf.fit(X, y)\n\n    # print the training scores\n    print(\"training score : %.3f (%s)\" % (clf.score(X, y), multi_class))\n\n    _, ax = plt.subplots()\n    DecisionBoundaryDisplay.from_estimator(\n        clf, X, response_method=\"predict\", cmap=plt.cm.Paired, ax=ax\n    )\n    plt.title(\"Decision surface of LogisticRegression (%s)\" % multi_class)\n    plt.axis(\"tight\")\n\n    # Plot also the training points\n    colors = \"bry\"\n    for i, color in zip(clf.classes_, colors):\n        idx = np.where(y == i)\n        plt.scatter(X[idx, 0], X[idx, 1], c=color, edgecolor=\"black\", s=20)\n\n    # Plot the three one-against-all classifiers\n    xmin, xmax = plt.xlim()\n    ymin, ymax = plt.ylim()\n    if multi_class == \"ovr\":\n        coef = np.concatenate([est.coef_ for est in clf.estimators_])\n        intercept = np.concatenate([est.intercept_ for est in clf.estimators_])\n    else:\n        coef = clf.coef_\n        intercept = clf.intercept_\n\n    def plot_hyperplane(c, color):\n        def line(x0):\n            return (-(x0 * coef[c, 0]) - intercept[c]) / coef[c, 1]\n\n        plt.plot([xmin, xmax], [line(xmin), line(xmax)], ls=\"--\", color=color)\n\n    for i, color in zip(clf.classes_, colors):\n        plot_hyperplane(i, color)\n\nplt.show()"
       ]
     }
   ],

1.5/_downloads/4c1663175b07cf9608b07331aa180eb7/plot_logistic_multinomial.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Alexandre Gramfort <[email protected]>\n# License: BSD 3 clause\n\nfrom itertools import cycle\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn import datasets\nfrom sklearn.linear_model import enet_path, lasso_path\n\nX, y = datasets.load_diabetes(return_X_y=True)\n\n\nX /= X.std(axis=0)  # Standardize data (easier to set the l1_ratio parameter)\n\n# Compute paths\n\neps = 5e-3  # the smaller it is the longer is the path\n\nprint(\"Computing regularization path using the lasso...\")\nalphas_lasso, coefs_lasso, _ = lasso_path(X, y, eps=eps)\n\nprint(\"Computing regularization path using the positive lasso...\")\nalphas_positive_lasso, coefs_positive_lasso, _ = lasso_path(\n    X, y, eps=eps, positive=True\n)\nprint(\"Computing regularization path using the elastic net...\")\nalphas_enet, coefs_enet, _ = enet_path(X, y, eps=eps, l1_ratio=0.8)\n\nprint(\"Computing regularization path using the positive elastic net...\")\nalphas_positive_enet, coefs_positive_enet, _ = enet_path(\n    X, y, eps=eps, l1_ratio=0.8, positive=True\n)\n\n# Display results\n\nplt.figure(1)\ncolors = cycle([\"b\", \"r\", \"g\", \"c\", \"k\"])\nneg_log_alphas_lasso = -np.log10(alphas_lasso)\nneg_log_alphas_enet = -np.log10(alphas_enet)\nfor coef_l, coef_e, c in zip(coefs_lasso, coefs_enet, colors):\n    l1 = plt.plot(neg_log_alphas_lasso, coef_l, c=c)\n    l2 = plt.plot(neg_log_alphas_enet, coef_e, linestyle=\"--\", c=c)\n\nplt.xlabel(\"-Log(alpha)\")\nplt.ylabel(\"coefficients\")\nplt.title(\"Lasso and Elastic-Net Paths\")\nplt.legend((l1[-1], l2[-1]), (\"Lasso\", \"Elastic-Net\"), loc=\"lower left\")\nplt.axis(\"tight\")\n\n\nplt.figure(2)\nneg_log_alphas_positive_lasso = -np.log10(alphas_positive_lasso)\nfor coef_l, coef_pl, c in zip(coefs_lasso, coefs_positive_lasso, colors):\n    l1 = plt.plot(neg_log_alphas_lasso, coef_l, c=c)\n    l2 = plt.plot(neg_log_alphas_positive_lasso, coef_pl, linestyle=\"--\", c=c)\n\nplt.xlabel(\"-Log(alpha)\")\nplt.ylabel(\"coefficients\")\nplt.title(\"Lasso and positive Lasso\")\nplt.legend((l1[-1], l2[-1]), (\"Lasso\", \"positive Lasso\"), loc=\"lower left\")\nplt.axis(\"tight\")\n\n\nplt.figure(3)\nneg_log_alphas_positive_enet = -np.log10(alphas_positive_enet)\nfor coef_e, coef_pe, c in zip(coefs_enet, coefs_positive_enet, colors):\n    l1 = plt.plot(neg_log_alphas_enet, coef_e, c=c)\n    l2 = plt.plot(neg_log_alphas_positive_enet, coef_pe, linestyle=\"--\", c=c)\n\nplt.xlabel(\"-Log(alpha)\")\nplt.ylabel(\"coefficients\")\nplt.title(\"Elastic-Net and positive Elastic-Net\")\nplt.legend((l1[-1], l2[-1]), (\"Elastic-Net\", \"positive Elastic-Net\"), loc=\"lower left\")\nplt.axis(\"tight\")\nplt.show()"
+        "# Author: Alexandre Gramfort <[email protected]>\n# License: BSD 3 clause\n\nfrom itertools import cycle\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.linear_model import enet_path, lasso_path\n\nX, y = datasets.load_diabetes(return_X_y=True)\n\n\nX /= X.std(axis=0)  # Standardize data (easier to set the l1_ratio parameter)\n\n# Compute paths\n\neps = 5e-3  # the smaller it is the longer is the path\n\nprint(\"Computing regularization path using the lasso...\")\nalphas_lasso, coefs_lasso, _ = lasso_path(X, y, eps=eps)\n\nprint(\"Computing regularization path using the positive lasso...\")\nalphas_positive_lasso, coefs_positive_lasso, _ = lasso_path(\n    X, y, eps=eps, positive=True\n)\nprint(\"Computing regularization path using the elastic net...\")\nalphas_enet, coefs_enet, _ = enet_path(X, y, eps=eps, l1_ratio=0.8)\n\nprint(\"Computing regularization path using the positive elastic net...\")\nalphas_positive_enet, coefs_positive_enet, _ = enet_path(\n    X, y, eps=eps, l1_ratio=0.8, positive=True\n)\n\n# Display results\n\nplt.figure(1)\ncolors = cycle([\"b\", \"r\", \"g\", \"c\", \"k\"])\nfor coef_l, coef_e, c in zip(coefs_lasso, coefs_enet, colors):\n    l1 = plt.semilogx(alphas_lasso, coef_l, c=c)\n    l2 = plt.semilogx(alphas_enet, coef_e, linestyle=\"--\", c=c)\n\nplt.xlabel(\"alpha\")\nplt.ylabel(\"coefficients\")\nplt.title(\"Lasso and Elastic-Net Paths\")\nplt.legend((l1[-1], l2[-1]), (\"Lasso\", \"Elastic-Net\"), loc=\"lower right\")\nplt.axis(\"tight\")\n\n\nplt.figure(2)\nfor coef_l, coef_pl, c in zip(coefs_lasso, coefs_positive_lasso, colors):\n    l1 = plt.semilogy(alphas_lasso, coef_l, c=c)\n    l2 = plt.semilogy(alphas_positive_lasso, coef_pl, linestyle=\"--\", c=c)\n\nplt.xlabel(\"alpha\")\nplt.ylabel(\"coefficients\")\nplt.title(\"Lasso and positive Lasso\")\nplt.legend((l1[-1], l2[-1]), (\"Lasso\", \"positive Lasso\"), loc=\"lower right\")\nplt.axis(\"tight\")\n\n\nplt.figure(3)\nfor coef_e, coef_pe, c in zip(coefs_enet, coefs_positive_enet, colors):\n    l1 = plt.semilogx(alphas_enet, coef_e, c=c)\n    l2 = plt.semilogx(alphas_positive_enet, coef_pe, linestyle=\"--\", c=c)\n\nplt.xlabel(\"alpha\")\nplt.ylabel(\"coefficients\")\nplt.title(\"Elastic-Net and positive Elastic-Net\")\nplt.legend((l1[-1], l2[-1]), (\"Elastic-Net\", \"positive Elastic-Net\"), loc=\"lower right\")\nplt.axis(\"tight\")\nplt.show()"
       ]
     }
   ],

1.5/_downloads/4c4c075dc14e39d30d982d0b2818ea95/plot_lasso_coordinate_descent_path.ipynb

@@ -9,7 +9,7 @@
 first transform it into a feature vector with length 64.
 
 See `here
-<https://archive.ics.uci.edu/ml/datasets/Pen-Based+Recognition+of+Handwritten+Digits>`_
+<https://archive.ics.uci.edu/dataset/81/pen+based+recognition+of+handwritten+digits>`_
 for more information about this dataset.
 
 """

1.5/_downloads/4ddbef459f3a80ccda29978b8cb0ef79/plot_digits_last_image.py

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# The Digit Dataset\n\nThis dataset is made up of 1797 8x8 images. Each image,\nlike the one shown below, is of a hand-written digit.\nIn order to utilize an 8x8 figure like this, we'd have to\nfirst transform it into a feature vector with length 64.\n\nSee [here](https://archive.ics.uci.edu/ml/datasets/Pen-Based+Recognition+of+Handwritten+Digits)\nfor more information about this dataset.\n"
+        "\n# The Digit Dataset\n\nThis dataset is made up of 1797 8x8 images. Each image,\nlike the one shown below, is of a hand-written digit.\nIn order to utilize an 8x8 figure like this, we'd have to\nfirst transform it into a feature vector with length 64.\n\nSee [here](https://archive.ics.uci.edu/dataset/81/pen+based+recognition+of+handwritten+digits)\nfor more information about this dataset.\n"
       ]
     },
     {

1.5/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -46,9 +46,7 @@
     colors = "bry"
     for i, color in zip(clf.classes_, colors):
         idx = np.where(y == i)
-        plt.scatter(
-            X[idx, 0], X[idx, 1], c=color, cmap=plt.cm.Paired, edgecolor="black", s=20
-        )
+        plt.scatter(X[idx, 0], X[idx, 1], c=color, edgecolor="black", s=20)
 
     # Plot the three one-against-all classifiers
     xmin, xmax = plt.xlim()