def process_one_log(self, input_log, repo_info_topics):
input_log = PreprocessManager.remove_non_ascii(input_log)
# TODO : Do we need repo info?
#repo_info_topics = PreprocessManager.remove_non_ascii(repo_info_topics)
# Find the length
# TODO : All the scores which are dependent on the length are not unbiased if not normalized! Check that
length = len(PreprocessManager.get_raw_tokenized_text(input_log))
# Find structural integrity.
self.grammar_tool.enable_spellchecking()
problematic_matches = self.grammar_tool.check(input_log)
corrected_text = gc.correct(input_log, problematic_matches)
degree_of_match = fuzz.ratio(input_log, corrected_text)
structural_integrity_score = degree_of_match * (length - len(problematic_matches))
# Check if topic is relevant
# This is still in testing phase and not sure if it has a good impact on the final results.
# Might be totally useless at times.
sframe_data_for_topics = gl.SArray([PreprocessManager.get_word_counts(input_log)])
# Add Associations here TODO: Make it proper
associations = gl.SFrame({'word': ['fix', 'issue', 'implement', 'modify', 'changed', 'bug', 'error'],
'topic': [0, 0, 0, 0, 0, 0, 0]})
topic_model = gl.topic_model.create(sframe_data_for_topics, associations=associations)
# TODO : Add here the match with the description. Is that useful? Maybe Future work?
#pred = topic_model.predict(sframe_data_for_topics, output_type='probability')
topics = topic_model.get_topics()
# The final score is the sum of all the topic 0 scores! As they were used in associations. Gives us relevance of being a commit message!
topic_relevance_score = 0
for i in xrange(0, len(topics)):
curr = topics[i]
topic_id = curr['topic']
score_val = curr['score']
if topic_id == 0:
topic_relevance_score += score_val
topic_relevance_score *= 100
#print topics, topic_relevance_score
# Check how much positivity
log_dict = dict()
log_dict['text'] = input_log
positivity = self.senti_checker.predict_row(log_dict)
positivity_score = 100 * positivity
#print positivity_score
# Spelling Goodness
self.spell_master.set_text(input_log)
error_words = list()
for err in self.spell_master:
error_words.append(err.word)
spelling_integrity_score = length - len(error_words)
#return all
return length, structural_integrity_score, topic_relevance_score, positivity_score, spelling_integrity_score
