Pushing the docs to dev/ for branch: main, commit 3ab6c8cf0cf6b8253d9e5a9d52908129fc147987

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: 5172073a9b8bdc3e0184c79c9994bbd9
+config: 88143eba9ec42ba5bbd89acd3533a3de
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/05ca8a4e90b4cc2acd69f9e24b4a1f3a/plot_classifier_chain_yeast.ipynb

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.model_selection import train_test_split\n\n# Load a multi-label dataset from https://www.openml.org/d/40597\nX, Y = fetch_openml(\"yeast\", version=4, return_X_y=True, parser=\"pandas\")\nY = Y == \"TRUE\"\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)"
+        "import matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.model_selection import train_test_split\n\n# Load a multi-label dataset from https://www.openml.org/d/40597\nX, Y = fetch_openml(\"yeast\", version=4, return_X_y=True)\nY = Y == \"TRUE\"\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)"
       ]
     },
     {

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -68,9 +68,7 @@
 # :class:`compose.ColumnTransformer` and heterogeneous data.
 from sklearn.datasets import fetch_openml
 
-X, y = fetch_openml(
-    "titanic", version=1, as_frame=True, return_X_y=True, parser="pandas"
-)
+X, y = fetch_openml("titanic", version=1, as_frame=True, return_X_y=True)
 X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y)
 
 # %%

dev/_downloads/1b3f17ff0f112d5b77cbdb90f1c17046/plot_set_output.py

@@ -36,7 +36,7 @@
 # in OpenML.
 from sklearn.datasets import fetch_openml
 
-co2 = fetch_openml(data_id=41187, as_frame=True, parser="pandas")
+co2 = fetch_openml(data_id=41187, as_frame=True)
 co2.frame.head()
 
 # %%

dev/_downloads/1b8827af01c9a70017a4739bcf2e21a8/plot_gpr_co2.py

@@ -22,7 +22,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.datasets import fetch_openml\n\nbikes = fetch_openml(\"Bike_Sharing_Demand\", version=2, as_frame=True, parser=\"pandas\")\n# Make an explicit copy to avoid \"SettingWithCopyWarning\" from pandas\nX, y = bikes.data.copy(), bikes.target\n\n# We use only a subset of the data to speed up the example.\nX = X.iloc[::5, :]\ny = y[::5]"
+        "from sklearn.datasets import fetch_openml\n\nbikes = fetch_openml(\"Bike_Sharing_Demand\", version=2, as_frame=True)\n# Make an explicit copy to avoid \"SettingWithCopyWarning\" from pandas\nX, y = bikes.data.copy(), bikes.target\n\n# We use only a subset of the data to speed up the example.\nX = X.iloc[::5, :]\ny = y[::5]"
       ]
     },
     {

dev/_downloads/21b82d82985712b5de6347f382c77c86/plot_partial_dependence.ipynb

@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "X, y = fetch_openml(\n    \"titanic\", version=1, as_frame=True, return_X_y=True, parser=\"pandas\"\n)\n\n# Alternatively X and y can be obtained directly from the frame attribute:\n# X = titanic.frame.drop('survived', axis=1)\n# y = titanic.frame['survived']"
+        "X, y = fetch_openml(\"titanic\", version=1, as_frame=True, return_X_y=True)\n\n# Alternatively X and y can be obtained directly from the frame attribute:\n# X = titanic.frame.drop('survived', axis=1)\n# y = titanic.frame['survived']"
       ]
     },
     {

dev/_downloads/26f110ad6cff1a8a7c58b1a00d8b8b5a/plot_column_transformer_mixed_types.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Arthur Mensch <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.utils import check_random_state\n\n# Turn down for faster convergence\nt0 = time.time()\ntrain_samples = 5000\n\n# Load data from https://www.openml.org/d/554\nX, y = fetch_openml(\n    \"mnist_784\", version=1, return_X_y=True, as_frame=False, parser=\"pandas\"\n)\n\nrandom_state = check_random_state(0)\npermutation = random_state.permutation(X.shape[0])\nX = X[permutation]\ny = y[permutation]\nX = X.reshape((X.shape[0], -1))\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, train_size=train_samples, test_size=10000\n)\n\nscaler = StandardScaler()\nX_train = scaler.fit_transform(X_train)\nX_test = scaler.transform(X_test)\n\n# Turn up tolerance for faster convergence\nclf = LogisticRegression(C=50.0 / train_samples, penalty=\"l1\", solver=\"saga\", tol=0.1)\nclf.fit(X_train, y_train)\nsparsity = np.mean(clf.coef_ == 0) * 100\nscore = clf.score(X_test, y_test)\n# print('Best C % .4f' % clf.C_)\nprint(\"Sparsity with L1 penalty: %.2f%%\" % sparsity)\nprint(\"Test score with L1 penalty: %.4f\" % score)\n\ncoef = clf.coef_.copy()\nplt.figure(figsize=(10, 5))\nscale = np.abs(coef).max()\nfor i in range(10):\n    l1_plot = plt.subplot(2, 5, i + 1)\n    l1_plot.imshow(\n        coef[i].reshape(28, 28),\n        interpolation=\"nearest\",\n        cmap=plt.cm.RdBu,\n        vmin=-scale,\n        vmax=scale,\n    )\n    l1_plot.set_xticks(())\n    l1_plot.set_yticks(())\n    l1_plot.set_xlabel(\"Class %i\" % i)\nplt.suptitle(\"Classification vector for...\")\n\nrun_time = time.time() - t0\nprint(\"Example run in %.3f s\" % run_time)\nplt.show()"
+        "# Author: Arthur Mensch <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.utils import check_random_state\n\n# Turn down for faster convergence\nt0 = time.time()\ntrain_samples = 5000\n\n# Load data from https://www.openml.org/d/554\nX, y = fetch_openml(\"mnist_784\", version=1, return_X_y=True, as_frame=False)\n\nrandom_state = check_random_state(0)\npermutation = random_state.permutation(X.shape[0])\nX = X[permutation]\ny = y[permutation]\nX = X.reshape((X.shape[0], -1))\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, train_size=train_samples, test_size=10000\n)\n\nscaler = StandardScaler()\nX_train = scaler.fit_transform(X_train)\nX_test = scaler.transform(X_test)\n\n# Turn up tolerance for faster convergence\nclf = LogisticRegression(C=50.0 / train_samples, penalty=\"l1\", solver=\"saga\", tol=0.1)\nclf.fit(X_train, y_train)\nsparsity = np.mean(clf.coef_ == 0) * 100\nscore = clf.score(X_test, y_test)\n# print('Best C % .4f' % clf.C_)\nprint(\"Sparsity with L1 penalty: %.2f%%\" % sparsity)\nprint(\"Test score with L1 penalty: %.4f\" % score)\n\ncoef = clf.coef_.copy()\nplt.figure(figsize=(10, 5))\nscale = np.abs(coef).max()\nfor i in range(10):\n    l1_plot = plt.subplot(2, 5, i + 1)\n    l1_plot.imshow(\n        coef[i].reshape(28, 28),\n        interpolation=\"nearest\",\n        cmap=plt.cm.RdBu,\n        vmin=-scale,\n        vmax=scale,\n    )\n    l1_plot.set_xticks(())\n    l1_plot.set_yticks(())\n    l1_plot.set_xlabel(\"Class %i\" % i)\nplt.suptitle(\"Classification vector for...\")\n\nrun_time = time.time() - t0\nprint(\"Example run in %.3f s\" % run_time)\nplt.show()"
       ]
     }
   ],

dev/_downloads/2a5eb3b98b9fe593b9bfeb548a54175d/plot_sparse_logistic_regression_mnist.ipynb

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.datasets import fetch_openml\n\ndf = fetch_openml(data_id=41214, as_frame=True, parser=\"pandas\").frame\ndf"
+        "from sklearn.datasets import fetch_openml\n\ndf = fetch_openml(data_id=41214, as_frame=True).frame\ndf"
       ]
     },
     {

dev/_downloads/2e4791a177381a6102b21e44083615c8/plot_poisson_regression_non_normal_loss.ipynb

@@ -37,7 +37,7 @@
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import MinMaxScaler
 
-X, y = fetch_openml(data_id=41082, as_frame=False, return_X_y=True, parser="pandas")
+X, y = fetch_openml(data_id=41082, as_frame=False, return_X_y=True)
 X = MinMaxScaler().fit_transform(X)
 
 # %%