for clf, name in ((RidgeClassifier(tol=1e-1), "Ridge Classifier"),
(KNeighborsClassifier(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))
class L1LinearSVC(LinearSVC):
for clf, name in ((RidgeClassifier(tol=1e-1), "Ridge Classifier"),
(KNeighborsClassifier(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))
class L1LinearSVC(LinearSVC):
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__analyzer__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),
}
def find_best_sgd(**params):
parameters = {
'alpha': [0.0001, 0.0005, 0.001],
'rho': [0.80, 0.85, 0.95],
}
return GridSearchCV(SGDClassifier(**params), parameters)