Sample pipeline for text feature extraction and evaluation

The dataset used in this example is the 20 newsgroups dataset which will be automatically downloaded and then cached and reused for the document classification example.

You can adjust the number of categories by giving there name to the dataset loader or setting them to None to get the 20 of them.

Here is a sample output of a run on a quad-core machine:

Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
1427 documents
2 categories

Performing grid search...
pipeline: ['vect', 'tfidf', 'clf']
parameters:
{'clf__alpha': (1.0000000000000001e-05, 9.9999999999999995e-07),
 'clf__n_iter': (10, 50, 80),
 'clf__penalty': ('l2', 'elasticnet'),
 'tfidf__use_idf': (True, False),
 'vect__max_n': (1, 2),
 'vect__max_df': (0.5, 0.75, 1.0),
 'vect__max_features': (None, 5000, 10000, 50000)}
done in 1737.030s

Best score: 0.940
Best parameters set:
    clf__alpha: 9.9999999999999995e-07
    clf__n_iter: 50
    clf__penalty: 'elasticnet'
    tfidf__use_idf: True
    vect__max_n: 2
    vect__max_df: 0.75
    vect__max_features: 50000

Python source code: grid_search_text_feature_extraction.py

print __doc__

# Author: Olivier Grisel <olivier.grisel@ensta.org>
#         Peter Prettenhofer <peter.prettenhofer@gmail.com>
#         Mathieu Blondel <mathieu@mblondel.org>
# License: Simplified BSD

from pprint import pprint
from time import time
import logging

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.linear_model import SGDClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.pipeline import Pipeline

# 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

print "Loading 20 newsgroups dataset for categories:"
print categories

data = fetch_20newsgroups(subset='train', categories=categories)
print "%d documents" % len(data.filenames)
print "%d categories" % len(data.target_names)
print

###############################################################################
# define a pipeline combining a text feature extractor with a simple
# classifier
pipeline = Pipeline([
    ('vect', CountVectorizer()),
    ('tfidf', TfidfTransformer()),
    ('clf', SGDClassifier()),
])

parameters = {
# uncommenting more parameters will give better exploring power but will
# increase processing time in a combinatorial way
    'vect__max_df': (0.5, 0.75, 1.0),
#    'vect__max_features': (None, 5000, 10000, 50000),
    'vect__max_n': (1, 2),  # words or bigrams
#    'tfidf__use_idf': (True, False),
#    'tfidf__norm': ('l1', 'l2'),
    'clf__alpha': (0.00001, 0.000001),
    'clf__penalty': ('l2', 'elasticnet'),
#    'clf__n_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])