print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
assert sp.issparse(X_train)
y_train = news_train.target
print "Training a linear classifier..."
parameters = {
'loss': 'hinge',
'penalty': 'l2',
'n_iter': 50,
'alpha': 0.00001,
'fit_intercept': True,
}
print "parameters:", parameters
t0 = time()
clf = SGDClassifier(**parameters).fit(X_train, y_train)
print "done in %fs" % (time() - t0)
print "Percentage of non zeros coef: %f" % (np.mean(clf.coef_ != 0) * 100)
print "Loading 20 newsgroups test set... "
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
print "done in %fs" % (time() - t0)
print "Predicting the labels of the test set..."
print "%d documents" % len(news_test.filenames)
print "%d categories" % len(news_test.target_names)
print "Extracting features from the dataset using the same vectorizer"
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in news_test.filenames))
return score, train_time, test_time
for clf, name in ((RidgeClassifier(tol=1e-1), "Ridge Classifier"),
(NeighborsClassifier(n_neighbors=10), "kNN")):
print 80*'='
print name
results = benchmark(clf)
for penalty in ["l2", "l1"]:
print 80 * '='
print "%s penalty" % penalty.upper()
# Train Liblinear model
liblinear_results = benchmark(LinearSVC(loss='l2', penalty=penalty, C=1000,
dual=False, tol=1e-3))
# Train SGD model
sgd_results = benchmark(SGDClassifier(alpha=.0001, n_iter=50,
penalty=penalty))
# Train SGD with Elastic Net penalty
print 80 * '='
print "Elastic-Net penalty"
sgd_results = benchmark(SGDClassifier(alpha=.0001, n_iter=50,
penalty="elasticnet"))
# Train sparse Naive Bayes classifiers
print 80 * '='
print "Naive Bayes"
mnnb_results = benchmark(MultinomialNB(alpha=.01))
bnb_result = benchmark(BernoulliNB(alpha=.01))
print "Loading 20 newsgroups dataset for categories:"
print categories
data = load_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__analyzer__max_n': (1, 2), # words or bigrams
# 'tfidf__use_idf': (True, False),
'clf__alpha': (0.00001, 0.000001),
'clf__penalty': ('l2', 'elasticnet'),
# 'clf__n_iter': (10, 50, 80),
}
# find the best parameters for both the feature extraction and the
if print_cm:
print "confusion matrix:"
print metrics.confusion_matrix(y_test, pred)
print
return score, train_time, test_time
for clf, name in ((RidgeClassifier(), "Ridge Classifier"), ):
print 80 * '='
print name
results = benchmark(clf)
for penalty in ["l2", "l1"]:
print 80 * '='
print "%s penalty" % penalty.upper()
# Train Liblinear model
liblinear_results = benchmark(
LinearSVC(loss='l2', penalty=penalty, C=1000, dual=False, tol=1e-3))
# Train SGD model
sgd_results = benchmark(
SGDClassifier(alpha=.0001, n_iter=50, penalty=penalty))
# Train SGD with Elastic Net penalty
print 80 * '='
print "Elastic-Net penalty"
sgd_results = benchmark(
SGDClassifier(alpha=.0001, n_iter=50, penalty="elasticnet"))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
assert sp.issparse(X_train)
y_train = news_train.target
print "Training a linear classifier..."
parameters = {
'loss': 'hinge',
'penalty': 'l2',
'n_iter': 50,
'alpha': 0.00001,
'fit_intercept': True,
}
print "parameters:", parameters
t0 = time()
clf = SGDClassifier(**parameters).fit(X_train, y_train)
print "done in %fs" % (time() - t0)
print "Percentage of non zeros coef: %f" % (np.mean(clf.coef_ != 0) * 100)
print "Loading 20 newsgroups test set... "
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
print "done in %fs" % (time() - t0)
print "Predicting the labels of the test set..."
print "%d documents" % len(news_test.filenames)
print "%d categories" % len(news_test.target_names)
print "Extracting features from the dataset using the same vectorizer"
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in news_test.filenames))