Pushing the docs to dev/ for branch: main, commit 3a428086ddb4485f5c21af3b3378dd1f659448e5

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,43 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Olivier Grisel <[email protected]>\n#         Peter Prettenhofer <[email protected]>\n#         Mathieu Blondel <[email protected]>\n# License: BSD 3 clause\nfrom pprint import pprint\nfrom time import time\nimport logging\n\nfrom sklearn.datasets import fetch_20newsgroups\nfrom sklearn.feature_extraction.text import CountVectorizer\nfrom sklearn.feature_extraction.text import TfidfTransformer\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.pipeline import Pipeline\n\n# Display progress logs on stdout\nlogging.basicConfig(level=logging.INFO, format=\"%(asctime)s %(levelname)s %(message)s\")\n\n\n# #############################################################################\n# Load some categories from the training set\ncategories = [\n    \"alt.atheism\",\n    \"talk.religion.misc\",\n]\n# Uncomment the following to do the analysis on all the categories\n# categories = None\n\nprint(\"Loading 20 newsgroups dataset for categories:\")\nprint(categories)\n\ndata = fetch_20newsgroups(subset=\"train\", categories=categories)\nprint(\"%d documents\" % len(data.filenames))\nprint(\"%d categories\" % len(data.target_names))\nprint()\n\n# #############################################################################\n# Define a pipeline combining a text feature extractor with a simple\n# classifier\npipeline = Pipeline(\n    [\n        (\"vect\", CountVectorizer()),\n        (\"tfidf\", TfidfTransformer()),\n        (\"clf\", SGDClassifier()),\n    ]\n)\n\n# uncommenting more parameters will give better exploring power but will\n# increase processing time in a combinatorial way\nparameters = {\n    \"vect__max_df\": (0.5, 0.75, 1.0),\n    # 'vect__max_features': (None, 5000, 10000, 50000),\n    \"vect__ngram_range\": ((1, 1), (1, 2)),  # unigrams or bigrams\n    # 'tfidf__use_idf': (True, False),\n    # 'tfidf__norm': ('l1', 'l2'),\n    \"clf__max_iter\": (20,),\n    \"clf__alpha\": (0.00001, 0.000001),\n    \"clf__penalty\": (\"l2\", \"elasticnet\"),\n    # 'clf__max_iter': (10, 50, 80),\n}\n\nif __name__ == \"__main__\":\n    # multiprocessing requires the fork to happen in a __main__ protected\n    # block\n\n    # find the best parameters for both the feature extraction and the\n    # classifier\n    grid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1)\n\n    print(\"Performing grid search...\")\n    print(\"pipeline:\", [name for name, _ in pipeline.steps])\n    print(\"parameters:\")\n    pprint(parameters)\n    t0 = time()\n    grid_search.fit(data.data, data.target)\n    print(\"done in %0.3fs\" % (time() - t0))\n    print()\n\n    print(\"Best score: %0.3f\" % grid_search.best_score_)\n    print(\"Best parameters set:\")\n    best_parameters = grid_search.best_estimator_.get_params()\n    for param_name in sorted(parameters.keys()):\n        print(\"\\t%s: %r\" % (param_name, best_parameters[param_name]))"
+        "# Author: Olivier Grisel <[email protected]>\n#         Peter Prettenhofer <[email protected]>\n#         Mathieu Blondel <[email protected]>\n# License: BSD 3 clause"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data loading\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "from pprint import pprint\nfrom time import time\nimport logging\n\nfrom sklearn.datasets import fetch_20newsgroups\nfrom sklearn.feature_extraction.text import CountVectorizer\nfrom sklearn.feature_extraction.text import TfidfTransformer\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.pipeline import Pipeline\n\n# Display progress logs on stdout\nlogging.basicConfig(level=logging.INFO, format=\"%(asctime)s %(levelname)s %(message)s\")\n\n# Load some categories from the training set\ncategories = [\n    \"alt.atheism\",\n    \"talk.religion.misc\",\n]\n\n# Uncomment the following to do the analysis on all the categories\n# categories = None\n\nprint(\"Loading 20 newsgroups dataset for categories:\")\nprint(categories)\n\ndata = fetch_20newsgroups(subset=\"train\", categories=categories)\nprint(\"%d documents\" % len(data.filenames))\nprint(\"%d categories\" % len(data.target_names))\nprint()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Pipeline with hyperparameter tuning\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# Define a pipeline combining a text feature extractor with a simple classifier\npipeline = Pipeline(\n    [\n        (\"vect\", CountVectorizer()),\n        (\"tfidf\", TfidfTransformer()),\n        (\"clf\", SGDClassifier()),\n    ]\n)\n\n# Parameters to use for grid search. Uncommenting more parameters will give\n# better exploring power but will increase processing time in a combinatorial\n# way\nparameters = {\n    \"vect__max_df\": (0.5, 0.75, 1.0),\n    # 'vect__max_features': (None, 5000, 10000, 50000),\n    \"vect__ngram_range\": ((1, 1), (1, 2)),  # unigrams or bigrams\n    # 'tfidf__use_idf': (True, False),\n    # 'tfidf__norm': ('l1', 'l2'),\n    \"clf__max_iter\": (20,),\n    \"clf__alpha\": (0.00001, 0.000001),\n    \"clf__penalty\": (\"l2\", \"elasticnet\"),\n    # 'clf__max_iter': (10, 50, 80),\n}\n\n# Find the best parameters for both the feature extraction and the\n# classifier\ngrid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1)\n\nprint(\"Performing grid search...\")\nprint(\"pipeline:\", [name for name, _ in pipeline.steps])\nprint(\"parameters:\")\npprint(parameters)\nt0 = time()\ngrid_search.fit(data.data, data.target)\nprint(\"done in %0.3fs\" % (time() - t0))\nprint()\n\nprint(\"Best score: %0.3f\" % grid_search.best_score_)\nprint(\"Best parameters set:\")\nbest_parameters = grid_search.best_estimator_.get_params()\nfor param_name in sorted(parameters.keys()):\n    print(\"\\t%s: %r\" % (param_name, best_parameters[param_name]))"
       ]
     }
   ],

dev/_downloads/2686c9a8c33b1b0159cc05f207d65b4c/grid_search_text_feature_extraction.ipynb

@@ -45,6 +45,11 @@
 #         Peter Prettenhofer <[email protected]>
 #         Mathieu Blondel <[email protected]>
 # License: BSD 3 clause
+
+# %%
+# Data loading
+# ------------
+
 from pprint import pprint
 from time import time
 import logging
@@ -59,13 +64,12 @@
 # Display progress logs on stdout
 logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
 
-
-# #############################################################################
 # Load some categories from the training set
 categories = [
     "alt.atheism",
     "talk.religion.misc",
 ]
+
 # Uncomment the following to do the analysis on all the categories
 # categories = None
 
@@ -77,9 +81,11 @@
 print("%d categories" % len(data.target_names))
 print()
 
-# #############################################################################
-# Define a pipeline combining a text feature extractor with a simple
-# classifier
+# %%
+# Pipeline with hyperparameter tuning
+# -----------------------------------
+
+# Define a pipeline combining a text feature extractor with a simple classifier
 pipeline = Pipeline(
     [
         ("vect", CountVectorizer()),
@@ -88,8 +94,9 @@
     ]
 )
 
-# uncommenting more parameters will give better exploring power but will
-# increase processing time in a combinatorial way
+# Parameters to use for grid search. Uncommenting more parameters will give
+# better exploring power but will increase processing time in a combinatorial
+# way
 parameters = {
     "vect__max_df": (0.5, 0.75, 1.0),
     # 'vect__max_features': (None, 5000, 10000, 50000),
@@ -102,25 +109,21 @@
     # 'clf__max_iter': (10, 50, 80),
 }
 
-if __name__ == "__main__":
-    # multiprocessing requires the fork to happen in a __main__ protected
-    # block
-
-    # find the best parameters for both the feature extraction and the
-    # classifier
-    grid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1)
-
-    print("Performing grid search...")
-    print("pipeline:", [name for name, _ in pipeline.steps])
-    print("parameters:")
-    pprint(parameters)
-    t0 = time()
-    grid_search.fit(data.data, data.target)
-    print("done in %0.3fs" % (time() - t0))
-    print()
-
-    print("Best score: %0.3f" % grid_search.best_score_)
-    print("Best parameters set:")
-    best_parameters = grid_search.best_estimator_.get_params()
-    for param_name in sorted(parameters.keys()):
-        print("\t%s: %r" % (param_name, best_parameters[param_name]))
+# Find the best parameters for both the feature extraction and the
+# classifier
+grid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1)
+
+print("Performing grid search...")
+print("pipeline:", [name for name, _ in pipeline.steps])
+print("parameters:")
+pprint(parameters)
+t0 = time()
+grid_search.fit(data.data, data.target)
+print("done in %0.3fs" % (time() - t0))
+print()
+
+print("Best score: %0.3f" % grid_search.best_score_)
+print("Best parameters set:")
+best_parameters = grid_search.best_estimator_.get_params()
+for param_name in sorted(parameters.keys()):
+    print("\t%s: %r" % (param_name, best_parameters[param_name]))