def generate_labels():
fp = FileProcessor(testing_data_filepath, ' ')
rows = fp.parse_input_file()
expected = []
for row in rows:
expected.append(row[0])
if fp.generate_output(labels_output_filepath, expected):
return True
def test_logistic_regression(w):
if not generate_labels():
return
fp = FileProcessor(testing_data_filepath, ' ')
rows = fp.parse_input_file()
output = []
expected = []
labels = get_labels()
for row in rows:
expected.append(row[0])
row = row[1:]
sum_val = w[0]
for feature in row:
feature_id = int(feature.split(':')[0])
sum_val += w[feature_id]
if sigmoid(sum_val) >= 0.5:
output.append(labels[0])
else:
output.append(labels[1])
if fp.generate_output(output_filepath, output):
print 'Successfully generated predictions.lr'
def get_vocabulary_size():
fp = FileProcessor(vocabulary_filepath, ' ')
lines = fp.parse_input_file()
return len(lines)
def get_labels():
fp = FileProcessor(labels_filepath, ' ')
lines = fp.parse_input_file()
return [float(lines[0][1]), float(lines[1][1])]
def learn_logistic_regression():
fp = FileProcessor(training_data_filepath, ' ')
training_corpus = fp.parse_input_file()
return learn_lr_classifier(training_corpus)