Commitf601d5b

committed

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

1 parent54df66d commitf601d5bCopy full SHA for f601d5b

File tree

1,319 files changed

+5785

-5780

lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

1,319 files changed

+5785

-5780

lines changed

`‎dev/.buildinfo`

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`	`1`	`# Sphinx build info version 1`
`2`	`2`	`# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.`
`3`		`-config:64552944cc0ffe4efdd50963e6027564`
	`3`	`+config:a0f54c044cc4c39c7016296a66a9f00f`
`4`	`4`	`tags: 645f666f9bcd5a90fca523b33c5a78b7`

`‎dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip`

3 Bytes

Binary file not shown.

`‎dev/_downloads/15dc6d7a809edf988a7328336a25faec/plot_column_transformer.ipynb`

Lines changed: 2 additions & 2 deletions

Original file line number	Diff line number	Diff line change
`@@ -15,7 +15,7 @@`
`15`	`15`	`},`
`16`	`16`	`"outputs": [],`
`17`	`17`	`"source": [`
`18`		-"# Author: Matt Terry <matt.terry@gmail.com>\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 importTruncatedSVD\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"
	`18`	+"# Author: Matt Terry <matt.terry@gmail.com>\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 importPCA\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"
`19`	`19`	`]`
`20`	`20`	`},`
`21`	`21`	`{`
`@@ -105,7 +105,7 @@`
`105`	`105`	`},`
`106`	`106`	`"outputs": [],`
`107`	`107`	`"source": [`
`108`		- "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)"
	`108`	+ "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)"
`109`	`109`	`]`
`110`	`110`	`},`
`111`	`111`	`{`

`‎dev/_downloads/3e8abcbcde21489054beb05cb87da525/plot_column_transformer.py`

Lines changed: 2 additions & 2 deletions

Original file line number	Diff line number	Diff line change
`@@ -26,7 +26,7 @@`
`26`	`26`
`27`	`27`	`fromsklearn.composeimportColumnTransformer`
`28`	`28`	`fromsklearn.datasetsimportfetch_20newsgroups`
`29`		`-fromsklearn.decompositionimportTruncatedSVD`
	`29`	`+fromsklearn.decompositionimportPCA`
`30`	`30`	`fromsklearn.feature_extractionimportDictVectorizer`
`31`	`31`	`fromsklearn.feature_extraction.textimportTfidfVectorizer`
`32`	`32`	`fromsklearn.metricsimportclassification_report`
`@@ -141,7 +141,7 @@ def text_stats(posts):`
`141`	`141`	`Pipeline(`
`142`	`142`	`[`
`143`	`143`	`("tfidf",TfidfVectorizer()),`
`144`		`- ("best",TruncatedSVD(n_components=50)),`
	`144`	`+ ("best",PCA(n_components=50,svd_solver="arpack")),`
`145`	`145`	`]`
`146`	`146`	`),`
`147`	`147`	`1,`