from __future__ import print_function
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.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
print(__doc__)
# 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()),
])
# 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),
'vect__ngram_range': ((1, 1), (1, 2)), # unigrams 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]))输出：
None
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
857 documents
2 categories
Performing grid search...
pipeline: ['vect', 'tfidf', 'clf']
parameters:
{'clf__alpha': (1e-05, 1e-06),
'clf__penalty': ('l2', 'elasticnet'),
'vect__max_df': (0.5, 0.75, 1.0),
'vect__ngram_range': ((1, 1), (1, 2))}
Fitting 3 folds for each of 24 candidates, totalling 72 fits
None
None
Loading 20 newsgroups dataset for categories:
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
['alt.atheism', 'talk.religion.misc']
None
None
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
None
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
None
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
None
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
None
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc']
857 documents
2 categories
857 documents
2 categories
857 documents
2 categories
857 documents
857 documents
2 categories
2 categories
857 documents
2 categories
857 documents
2 categories
857 documents
2 categories
D:\F\Anaconda3\lib\site-packages\sklearn\feature_extraction\text.py:1059: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
.......
if hasattr(X, 'dtype') and np.issubdtype(X.dtype, np.float):
done in 16.886s
Best score: 0.943
Best parameters set:
clf__alpha: 1e-05
clf__penalty: 'elasticnet'
vect__max_df: 0.75
vect__ngram_range: (1, 2)