Pushing the docs to dev/ for branch: main, commit 2d9fa48aafa8e43304b7fd2b0cb76eabc48806ef

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: 64552944cc0ffe4efdd50963e6027564
+config: a0f54c044cc4c39c7016296a66a9f00f
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Matt Terry <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\n\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.datasets import fetch_20newsgroups\nfrom sklearn.decomposition import TruncatedSVD\nfrom sklearn.feature_extraction import DictVectorizer\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.metrics import classification_report\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import FunctionTransformer\nfrom sklearn.svm import LinearSVC"
+        "# Author: Matt Terry <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\n\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.datasets import fetch_20newsgroups\nfrom sklearn.decomposition import PCA\nfrom sklearn.feature_extraction import DictVectorizer\nfrom sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.metrics import classification_report\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import FunctionTransformer\nfrom sklearn.svm import LinearSVC"
       ]
     },
     {
@@ -105,7 +105,7 @@
       },
       "outputs": [],
       "source": [
-        "pipeline = Pipeline(\n    [\n        # Extract subject & body\n        (\"subjectbody\", subject_body_transformer),\n        # Use ColumnTransformer to combine the subject and body features\n        (\n            \"union\",\n            ColumnTransformer(\n                [\n                    # bag-of-words for subject (col 0)\n                    (\"subject\", TfidfVectorizer(min_df=50), 0),\n                    # bag-of-words with decomposition for body (col 1)\n                    (\n                        \"body_bow\",\n                        Pipeline(\n                            [\n                                (\"tfidf\", TfidfVectorizer()),\n                                (\"best\", TruncatedSVD(n_components=50)),\n                            ]\n                        ),\n                        1,\n                    ),\n                    # Pipeline for pulling text stats from post's body\n                    (\n                        \"body_stats\",\n                        Pipeline(\n                            [\n                                (\n                                    \"stats\",\n                                    text_stats_transformer,\n                                ),  # returns a list of dicts\n                                (\n                                    \"vect\",\n                                    DictVectorizer(),\n                                ),  # list of dicts -> feature matrix\n                            ]\n                        ),\n                        1,\n                    ),\n                ],\n                # weight above ColumnTransformer features\n                transformer_weights={\n                    \"subject\": 0.8,\n                    \"body_bow\": 0.5,\n                    \"body_stats\": 1.0,\n                },\n            ),\n        ),\n        # Use a SVC classifier on the combined features\n        (\"svc\", LinearSVC(dual=False)),\n    ],\n    verbose=True,\n)"
+        "pipeline = Pipeline(\n    [\n        # Extract subject & body\n        (\"subjectbody\", subject_body_transformer),\n        # Use ColumnTransformer to combine the subject and body features\n        (\n            \"union\",\n            ColumnTransformer(\n                [\n                    # bag-of-words for subject (col 0)\n                    (\"subject\", TfidfVectorizer(min_df=50), 0),\n                    # bag-of-words with decomposition for body (col 1)\n                    (\n                        \"body_bow\",\n                        Pipeline(\n                            [\n                                (\"tfidf\", TfidfVectorizer()),\n                                (\"best\", PCA(n_components=50, svd_solver=\"arpack\")),\n                            ]\n                        ),\n                        1,\n                    ),\n                    # Pipeline for pulling text stats from post's body\n                    (\n                        \"body_stats\",\n                        Pipeline(\n                            [\n                                (\n                                    \"stats\",\n                                    text_stats_transformer,\n                                ),  # returns a list of dicts\n                                (\n                                    \"vect\",\n                                    DictVectorizer(),\n                                ),  # list of dicts -> feature matrix\n                            ]\n                        ),\n                        1,\n                    ),\n                ],\n                # weight above ColumnTransformer features\n                transformer_weights={\n                    \"subject\": 0.8,\n                    \"body_bow\": 0.5,\n                    \"body_stats\": 1.0,\n                },\n            ),\n        ),\n        # Use a SVC classifier on the combined features\n        (\"svc\", LinearSVC(dual=False)),\n    ],\n    verbose=True,\n)"
       ]
     },
     {

dev/_downloads/15dc6d7a809edf988a7328336a25faec/plot_column_transformer.ipynb

@@ -26,7 +26,7 @@
 
 from sklearn.compose import ColumnTransformer
 from sklearn.datasets import fetch_20newsgroups
-from sklearn.decomposition import TruncatedSVD
+from sklearn.decomposition import PCA
 from sklearn.feature_extraction import DictVectorizer
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics import classification_report
@@ -141,7 +141,7 @@ def text_stats(posts):
                         Pipeline(
                             [
                                 ("tfidf", TfidfVectorizer()),
-                                ("best", TruncatedSVD(n_components=50)),
+                                ("best", PCA(n_components=50, svd_solver="arpack")),
                             ]
                         ),
                         1,