def kfold_average_score(learner, files, dirs, k=5, min_word_len=2, min_freq=10, feature_size=160, weight='tfidf', sw=True):
scores = [0] * k
kfold = KFold(files, dirs, k)
for ii in range(k):
train_X, train_Y, test_X, test_Y = kfold.kth(ii)
features = Features(train_X, train_Y, min_word_len, min_freq, feature_size, sw)
x = []
for f_name in train_X:
x.append(features.get_x_vector(f_name, weight))
learner.fit(x, features.y_transform(train_Y))
x = []
for f_name in test_X:
x.append(features.get_x_vector(f_name, weight))
scores[ii] = f1_score(features.y_transform(test_Y), learner.predict(x).tolist())
return mean(scores)
if __name__ == '__main__':
parser = argparse.ArgumentParser("Read in data directory")
parser.add_argument('data_dir')
print('Reading Data Path')
files, dirs = fe.get_file_name_and_path(parser.parse_args().data_dir)
print('Spliting Train-Test Set ')
train_x, train_y, test_x, test_y = train_test_split(files, dirs, 0.25)
learner = svm.SVC(kernel='rbf', C=1)
features = Features(train_x, train_y, 3, 0, 160)
x = []
for f_name in train_x:
x.append(features.get_x_vector(f_name, 'tfidf'))
learner.fit(x, features.y_transform(train_y))
x=[]
for f_name in test_x:
x.append(features.get_x_vector(f_name, 'tfidf'))
print('Score:', f1_score(features.y_transform(test_y), learner.predict(x).tolist()))
# print('Test if "TFIDF" is better than "TF"')
# print('TF:', kfold_average_score(learner, train_x, train_y, weight='tf',feature_size=2))
# print('TFIDF:', kfold_average_score(learner, train_x, train_y, weight='tfidf',feature_size=2))
# #
# #
# print('Test which min length of word is best')
# lst = []
# for i in range(10):
# lst.append(kfold_average_score(learner, files, dirs, k=5, min_word_len=i))
