def __get_next_rule__(self, tokens, instances):
best_pattern = []
best_match_count = -1
best_score = float('-inf')
un_matched_instances = []
_, ys = zip(*instances)
improved = True
while improved:
improved = False
current_best_pattern = best_pattern[:]
insertion_indices = range(len(current_best_pattern) + 1)
for token in tokens:
for insertion_index in insertion_indices:
new_pattern = best_pattern[:insertion_index] + [token] + best_pattern[insertion_index:]
new_rule = Rule(new_pattern)
un_matched = []
predictions = []
match_count = 0
for x, y in instances:
if new_rule.matches(x):
match_count += 1
predictions.append(self.positive_label)
else:
predictions.append(0)
un_matched.append((x, y))
score = self.rule_score_fn(ys, predictions)
if score >= best_score and match_count >= self.min_positive_rules_covered:
# If tied, always prefer ones that match more instances
if score == best_score and match_count <= best_match_count:
continue
current_best_pattern = new_pattern
best_match_count = match_count
best_score = score
improved = True
un_matched_instances = un_matched
pass # End for
pass # End for
best_pattern = current_best_pattern
pass
if len(best_pattern) == 0:
return None, None, None
best_rule = Rule(best_pattern)
print "\tNew rule added: {0}\n\t\tRule Score: {1}\n\t\tMatches: {2}".format(best_rule, best_score,
best_match_count)
""" Compute remaining tokens """
un_matched_positives, un_matched_negatives = self.__partition_by_class__(un_matched_instances)
positive_doc_freq = compute_document_frequency(un_matched_positives)
remaining_tokens = self.__above_doc_freq__(positive_doc_freq, self.min_positive_rules_covered)
return best_rule, un_matched_instances, remaining_tokens
def __get_next_rule__(self, tokens, instances):
best_pattern = []
best_match_count = -1
best_score = float('-inf')
un_matched_instances = []
_, ys = zip(*instances)
improved = True
while improved:
improved = False
current_best_pattern = best_pattern[:]
insertion_indices = range(len(current_best_pattern) + 1)
for token in tokens:
for insertion_index in insertion_indices:
new_pattern = best_pattern[:insertion_index] + [
token
] + best_pattern[insertion_index:]
new_rule = Rule(new_pattern)
un_matched = []
predictions = []
match_count = 0
for x, y in instances:
if new_rule.matches(x):
match_count += 1
predictions.append(self.positive_label)
else:
predictions.append(0)
un_matched.append((x, y))
score = self.rule_score_fn(ys, predictions)
if score >= best_score and match_count >= self.min_positive_rules_covered:
# If tied, always prefer ones that match more instances
if score == best_score and match_count <= best_match_count:
continue
current_best_pattern = new_pattern
best_match_count = match_count
best_score = score
improved = True
un_matched_instances = un_matched
pass # End for
pass # End for
best_pattern = current_best_pattern
pass
if len(best_pattern) == 0:
return None, None, None
best_rule = Rule(best_pattern)
print "\tNew rule added: {0}\n\t\tRule Score: {1}\n\t\tMatches: {2}".format(
best_rule, best_score, best_match_count)
""" Compute remaining tokens """
un_matched_positives, un_matched_negatives = self.__partition_by_class__(
un_matched_instances)
positive_doc_freq = compute_document_frequency(un_matched_positives)
remaining_tokens = self.__above_doc_freq__(
positive_doc_freq, self.min_positive_rules_covered)
return best_rule, un_matched_instances, remaining_tokens
