if len(sys.argv) > 1 and sys.argv[1] != "":
source = sys.argv[1]
else:
source = IMDB_DATA_DEFAULT
print "Loading data from original source"
imdb = ImdbDataHandler(source=source)
(train_reviews, train_labels) = imdb.get_data(type=ImdbDataHandler.DATA_TRAIN, shuffle=True)
(test_reviews, test_labels) = imdb.get_data(type=ImdbDataHandler.DATA_TEST, shuffle=True)
# Simple bag of words with SGD
sgd = SGDTextClassifier(train_reviews, train_labels,
test_texts=test_reviews, test_labels=test_labels,
compute_features=True)
sgd.grid_search_cv(verbose=5, n_jobs=4)
test_error = sgd.get_test_error()
print "Test error in held out set: " + str(test_error)
print "=" * 20
# Now with bigrams too
sgd = SGDTextClassifier(train_reviews, train_labels, ngram_range=(1,2),
test_texts=test_reviews, test_labels=test_labels,
compute_features=True)
sgd.grid_search_cv(verbose=5, n_jobs=4)
test_error = sgd.get_test_error()
print "Test error in held out set: " + str(test_error)
print "=" * 20
# Simple bag of words with NB
nb = NaiveBayesClassifier(train_reviews, train_labels,
test_texts=test_reviews, test_labels=test_labels)
print "Loading data from original source"
imdb = ImdbDataHandler(source=source)
(train_reviews,
train_labels) = imdb.get_data(type=ImdbDataHandler.DATA_TRAIN,
shuffle=True)
(test_reviews, test_labels) = imdb.get_data(type=ImdbDataHandler.DATA_TEST,
shuffle=True)
# Simple bag of words with SGD
sgd = SGDTextClassifier(train_reviews,
train_labels,
test_texts=test_reviews,
test_labels=test_labels,
compute_features=True)
sgd.grid_search_cv(verbose=5, n_jobs=4)
test_error = sgd.get_test_error()
print "Test error in held out set: " + str(test_error)
print "=" * 20
# Now with bigrams too
sgd = SGDTextClassifier(train_reviews,
train_labels,
ngram_range=(1, 2),
test_texts=test_reviews,
test_labels=test_labels,
compute_features=True)
sgd.grid_search_cv(verbose=5, n_jobs=4)
test_error = sgd.get_test_error()
print "Test error in held out set: " + str(test_error)
print "=" * 20
