Pushing the docs to dev/ for branch: main, commit b32e5c7ab3535694f3c9fc98ec0e2e3ed03cf923

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: 0c8082022f005208422aa7a8498ba762
+config: f16a8334a27fd41e7952661bdfaa6ad3
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/02d88d76c60b7397c8c6e221b31568dd/plot_grid_search_refit_callable.py

@@ -81,7 +81,7 @@ def best_low_complexity(cv_results):
 pipe = Pipeline(
     [
         ("reduce_dim", PCA(random_state=42)),
-        ("classify", LinearSVC(random_state=42, C=0.01)),
+        ("classify", LinearSVC(random_state=42, C=0.01, dual="auto")),
     ]
 )
 

dev/_downloads/036b9372e2e7802453cbb994da7a6786/plot_linearsvc_support_vectors.py

@@ -20,7 +20,7 @@
 plt.figure(figsize=(10, 5))
 for i, C in enumerate([1, 100]):
     # "hinge" is the standard SVM loss
-    clf = LinearSVC(C=C, loss="hinge", random_state=42).fit(X, y)
+    clf = LinearSVC(C=C, loss="hinge", random_state=42, dual="auto").fit(X, y)
     # obtain the support vectors through the decision function
     decision_function = clf.decision_function(X)
     # we can also calculate the decision function manually

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -40,7 +40,7 @@
       },
       "outputs": [],
       "source": [
-        "n_samples = len(digits.data)\ndata = digits.data / 16.0\ndata -= data.mean(axis=0)\n\n# We learn the digits on the first half of the digits\ndata_train, targets_train = (data[: n_samples // 2], digits.target[: n_samples // 2])\n\n\n# Now predict the value of the digit on the second half:\ndata_test, targets_test = (data[n_samples // 2 :], digits.target[n_samples // 2 :])\n# data_test = scaler.transform(data_test)\n\n# Create a classifier: a support vector classifier\nkernel_svm = svm.SVC(gamma=0.2)\nlinear_svm = svm.LinearSVC()\n\n# create pipeline from kernel approximation\n# and linear svm\nfeature_map_fourier = RBFSampler(gamma=0.2, random_state=1)\nfeature_map_nystroem = Nystroem(gamma=0.2, random_state=1)\nfourier_approx_svm = pipeline.Pipeline(\n    [(\"feature_map\", feature_map_fourier), (\"svm\", svm.LinearSVC())]\n)\n\nnystroem_approx_svm = pipeline.Pipeline(\n    [(\"feature_map\", feature_map_nystroem), (\"svm\", svm.LinearSVC())]\n)\n\n# fit and predict using linear and kernel svm:\n\nkernel_svm_time = time()\nkernel_svm.fit(data_train, targets_train)\nkernel_svm_score = kernel_svm.score(data_test, targets_test)\nkernel_svm_time = time() - kernel_svm_time\n\nlinear_svm_time = time()\nlinear_svm.fit(data_train, targets_train)\nlinear_svm_score = linear_svm.score(data_test, targets_test)\nlinear_svm_time = time() - linear_svm_time\n\nsample_sizes = 30 * np.arange(1, 10)\nfourier_scores = []\nnystroem_scores = []\nfourier_times = []\nnystroem_times = []\n\nfor D in sample_sizes:\n    fourier_approx_svm.set_params(feature_map__n_components=D)\n    nystroem_approx_svm.set_params(feature_map__n_components=D)\n    start = time()\n    nystroem_approx_svm.fit(data_train, targets_train)\n    nystroem_times.append(time() - start)\n\n    start = time()\n    fourier_approx_svm.fit(data_train, targets_train)\n    fourier_times.append(time() - start)\n\n    fourier_score = fourier_approx_svm.score(data_test, targets_test)\n    nystroem_score = nystroem_approx_svm.score(data_test, targets_test)\n    nystroem_scores.append(nystroem_score)\n    fourier_scores.append(fourier_score)\n\n# plot the results:\nplt.figure(figsize=(16, 4))\naccuracy = plt.subplot(121)\n# second y axis for timings\ntimescale = plt.subplot(122)\n\naccuracy.plot(sample_sizes, nystroem_scores, label=\"Nystroem approx. kernel\")\ntimescale.plot(sample_sizes, nystroem_times, \"--\", label=\"Nystroem approx. kernel\")\n\naccuracy.plot(sample_sizes, fourier_scores, label=\"Fourier approx. kernel\")\ntimescale.plot(sample_sizes, fourier_times, \"--\", label=\"Fourier approx. kernel\")\n\n# horizontal lines for exact rbf and linear kernels:\naccuracy.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [linear_svm_score, linear_svm_score],\n    label=\"linear svm\",\n)\ntimescale.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [linear_svm_time, linear_svm_time],\n    \"--\",\n    label=\"linear svm\",\n)\n\naccuracy.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [kernel_svm_score, kernel_svm_score],\n    label=\"rbf svm\",\n)\ntimescale.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [kernel_svm_time, kernel_svm_time],\n    \"--\",\n    label=\"rbf svm\",\n)\n\n# vertical line for dataset dimensionality = 64\naccuracy.plot([64, 64], [0.7, 1], label=\"n_features\")\n\n# legends and labels\naccuracy.set_title(\"Classification accuracy\")\ntimescale.set_title(\"Training times\")\naccuracy.set_xlim(sample_sizes[0], sample_sizes[-1])\naccuracy.set_xticks(())\naccuracy.set_ylim(np.min(fourier_scores), 1)\ntimescale.set_xlabel(\"Sampling steps = transformed feature dimension\")\naccuracy.set_ylabel(\"Classification accuracy\")\ntimescale.set_ylabel(\"Training time in seconds\")\naccuracy.legend(loc=\"best\")\ntimescale.legend(loc=\"best\")\nplt.tight_layout()\nplt.show()"
+        "n_samples = len(digits.data)\ndata = digits.data / 16.0\ndata -= data.mean(axis=0)\n\n# We learn the digits on the first half of the digits\ndata_train, targets_train = (data[: n_samples // 2], digits.target[: n_samples // 2])\n\n\n# Now predict the value of the digit on the second half:\ndata_test, targets_test = (data[n_samples // 2 :], digits.target[n_samples // 2 :])\n# data_test = scaler.transform(data_test)\n\n# Create a classifier: a support vector classifier\nkernel_svm = svm.SVC(gamma=0.2)\nlinear_svm = svm.LinearSVC(dual=\"auto\")\n\n# create pipeline from kernel approximation\n# and linear svm\nfeature_map_fourier = RBFSampler(gamma=0.2, random_state=1)\nfeature_map_nystroem = Nystroem(gamma=0.2, random_state=1)\nfourier_approx_svm = pipeline.Pipeline(\n    [(\"feature_map\", feature_map_fourier), (\"svm\", svm.LinearSVC(dual=\"auto\"))]\n)\n\nnystroem_approx_svm = pipeline.Pipeline(\n    [(\"feature_map\", feature_map_nystroem), (\"svm\", svm.LinearSVC(dual=\"auto\"))]\n)\n\n# fit and predict using linear and kernel svm:\n\nkernel_svm_time = time()\nkernel_svm.fit(data_train, targets_train)\nkernel_svm_score = kernel_svm.score(data_test, targets_test)\nkernel_svm_time = time() - kernel_svm_time\n\nlinear_svm_time = time()\nlinear_svm.fit(data_train, targets_train)\nlinear_svm_score = linear_svm.score(data_test, targets_test)\nlinear_svm_time = time() - linear_svm_time\n\nsample_sizes = 30 * np.arange(1, 10)\nfourier_scores = []\nnystroem_scores = []\nfourier_times = []\nnystroem_times = []\n\nfor D in sample_sizes:\n    fourier_approx_svm.set_params(feature_map__n_components=D)\n    nystroem_approx_svm.set_params(feature_map__n_components=D)\n    start = time()\n    nystroem_approx_svm.fit(data_train, targets_train)\n    nystroem_times.append(time() - start)\n\n    start = time()\n    fourier_approx_svm.fit(data_train, targets_train)\n    fourier_times.append(time() - start)\n\n    fourier_score = fourier_approx_svm.score(data_test, targets_test)\n    nystroem_score = nystroem_approx_svm.score(data_test, targets_test)\n    nystroem_scores.append(nystroem_score)\n    fourier_scores.append(fourier_score)\n\n# plot the results:\nplt.figure(figsize=(16, 4))\naccuracy = plt.subplot(121)\n# second y axis for timings\ntimescale = plt.subplot(122)\n\naccuracy.plot(sample_sizes, nystroem_scores, label=\"Nystroem approx. kernel\")\ntimescale.plot(sample_sizes, nystroem_times, \"--\", label=\"Nystroem approx. kernel\")\n\naccuracy.plot(sample_sizes, fourier_scores, label=\"Fourier approx. kernel\")\ntimescale.plot(sample_sizes, fourier_times, \"--\", label=\"Fourier approx. kernel\")\n\n# horizontal lines for exact rbf and linear kernels:\naccuracy.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [linear_svm_score, linear_svm_score],\n    label=\"linear svm\",\n)\ntimescale.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [linear_svm_time, linear_svm_time],\n    \"--\",\n    label=\"linear svm\",\n)\n\naccuracy.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [kernel_svm_score, kernel_svm_score],\n    label=\"rbf svm\",\n)\ntimescale.plot(\n    [sample_sizes[0], sample_sizes[-1]],\n    [kernel_svm_time, kernel_svm_time],\n    \"--\",\n    label=\"rbf svm\",\n)\n\n# vertical line for dataset dimensionality = 64\naccuracy.plot([64, 64], [0.7, 1], label=\"n_features\")\n\n# legends and labels\naccuracy.set_title(\"Classification accuracy\")\ntimescale.set_title(\"Training times\")\naccuracy.set_xlim(sample_sizes[0], sample_sizes[-1])\naccuracy.set_xticks(())\naccuracy.set_ylim(np.min(fourier_scores), 1)\ntimescale.set_xlabel(\"Sampling steps = transformed feature dimension\")\naccuracy.set_ylabel(\"Classification accuracy\")\ntimescale.set_ylabel(\"Training time in seconds\")\naccuracy.legend(loc=\"best\")\ntimescale.legend(loc=\"best\")\nplt.tight_layout()\nplt.show()"
       ]
     },
     {

dev/_downloads/083d8568c199bebbc1a847fc6c917e9e/plot_kernel_approximation.ipynb

@@ -40,7 +40,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.ensemble import RandomForestClassifier\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.svm import LinearSVC\n\nclassifiers = {\n    \"Linear SVM\": make_pipeline(StandardScaler(), LinearSVC(C=0.025)),\n    \"Random Forest\": RandomForestClassifier(\n        max_depth=5, n_estimators=10, max_features=1\n    ),\n}"
+        "from sklearn.ensemble import RandomForestClassifier\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.svm import LinearSVC\n\nclassifiers = {\n    \"Linear SVM\": make_pipeline(StandardScaler(), LinearSVC(C=0.025, dual=\"auto\")),\n    \"Random Forest\": RandomForestClassifier(\n        max_depth=5, n_estimators=10, max_features=1\n    ),\n}"
       ]
     },
     {

dev/_downloads/10bb40e21b74618cdeed618ff1eae595/plot_det.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import make_blobs\nfrom sklearn.svm import LinearSVC\nfrom sklearn.inspection import DecisionBoundaryDisplay\n\nX, y = make_blobs(n_samples=40, centers=2, random_state=0)\n\nplt.figure(figsize=(10, 5))\nfor i, C in enumerate([1, 100]):\n    # \"hinge\" is the standard SVM loss\n    clf = LinearSVC(C=C, loss=\"hinge\", random_state=42).fit(X, y)\n    # obtain the support vectors through the decision function\n    decision_function = clf.decision_function(X)\n    # we can also calculate the decision function manually\n    # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]\n    # The support vectors are the samples that lie within the margin\n    # boundaries, whose size is conventionally constrained to 1\n    support_vector_indices = np.where(np.abs(decision_function) <= 1 + 1e-15)[0]\n    support_vectors = X[support_vector_indices]\n\n    plt.subplot(1, 2, i + 1)\n    plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)\n    ax = plt.gca()\n    DecisionBoundaryDisplay.from_estimator(\n        clf,\n        X,\n        ax=ax,\n        grid_resolution=50,\n        plot_method=\"contour\",\n        colors=\"k\",\n        levels=[-1, 0, 1],\n        alpha=0.5,\n        linestyles=[\"--\", \"-\", \"--\"],\n    )\n    plt.scatter(\n        support_vectors[:, 0],\n        support_vectors[:, 1],\n        s=100,\n        linewidth=1,\n        facecolors=\"none\",\n        edgecolors=\"k\",\n    )\n    plt.title(\"C=\" + str(C))\nplt.tight_layout()\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import make_blobs\nfrom sklearn.svm import LinearSVC\nfrom sklearn.inspection import DecisionBoundaryDisplay\n\nX, y = make_blobs(n_samples=40, centers=2, random_state=0)\n\nplt.figure(figsize=(10, 5))\nfor i, C in enumerate([1, 100]):\n    # \"hinge\" is the standard SVM loss\n    clf = LinearSVC(C=C, loss=\"hinge\", random_state=42, dual=\"auto\").fit(X, y)\n    # obtain the support vectors through the decision function\n    decision_function = clf.decision_function(X)\n    # we can also calculate the decision function manually\n    # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]\n    # The support vectors are the samples that lie within the margin\n    # boundaries, whose size is conventionally constrained to 1\n    support_vector_indices = np.where(np.abs(decision_function) <= 1 + 1e-15)[0]\n    support_vectors = X[support_vector_indices]\n\n    plt.subplot(1, 2, i + 1)\n    plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)\n    ax = plt.gca()\n    DecisionBoundaryDisplay.from_estimator(\n        clf,\n        X,\n        ax=ax,\n        grid_resolution=50,\n        plot_method=\"contour\",\n        colors=\"k\",\n        levels=[-1, 0, 1],\n        alpha=0.5,\n        linestyles=[\"--\", \"-\", \"--\"],\n    )\n    plt.scatter(\n        support_vectors[:, 0],\n        support_vectors[:, 1],\n        s=100,\n        linewidth=1,\n        facecolors=\"none\",\n        edgecolors=\"k\",\n    )\n    plt.title(\"C=\" + str(C))\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/12a392e818ac5fa47dd91461855f3f77/plot_linearsvc_support_vectors.ipynb

@@ -50,7 +50,7 @@
 C = 1.0  # SVM regularization parameter
 models = (
     svm.SVC(kernel="linear", C=C),
-    svm.LinearSVC(C=C, max_iter=10000),
+    svm.LinearSVC(C=C, max_iter=10000, dual="auto"),
     svm.SVC(kernel="rbf", gamma=0.7, C=C),
     svm.SVC(kernel="poly", degree=3, gamma="auto", C=C),
 )

dev/_downloads/4186bc506946013950b224b06f827118/plot_iris_svc.py

@@ -40,7 +40,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.feature_selection import SelectKBest, f_classif\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.svm import LinearSVC\n\nanova_filter = SelectKBest(f_classif, k=3)\nclf = LinearSVC()\nanova_svm = make_pipeline(anova_filter, clf)\nanova_svm.fit(X_train, y_train)"
+        "from sklearn.feature_selection import SelectKBest, f_classif\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.svm import LinearSVC\n\nanova_filter = SelectKBest(f_classif, k=3)\nclf = LinearSVC(dual=\"auto\")\nanova_svm = make_pipeline(anova_filter, clf)\nanova_svm.fit(X_train, y_train)"
       ]
     },
     {

dev/_downloads/51e6f272e94e3b63cfd48c4b41fbaa10/plot_feature_selection_pipeline.ipynb

@@ -46,7 +46,7 @@
 from sklearn.svm import LinearSVC
 
 anova_filter = SelectKBest(f_classif, k=3)
-clf = LinearSVC()
+clf = LinearSVC(dual="auto")
 anova_svm = make_pipeline(anova_filter, clf)
 anova_svm.fit(X_train, y_train)