def _get_working_year_words(self, year_convert_file=None):
year_list = TextHelper.get_years_pattern(self.raw_position)
if len(year_list) == 0:
default_year_requirement = "[0]"
self.new_words_list.append(default_year_requirement)
year_list = [default_year_requirement]
elif year_convert_file is not None:
year_convert_dict = StoreHelper.load_data(year_convert_file, {})
year_list = [
year_convert_dict[item] for item in year_list
if item in year_convert_dict
]
return DictHelper.dict_from_count_list(year_list)
def print_label(label, index_list, cluster_number=None):
if cluster_number is None:
label_dict = DictHelper.dict_from_count_list(label)
print("\t".join([str(i) for i in label]))
print(label_dict)
print("max cluster number: %i" % max(label_dict))
print("min cluster number: %i" % min(label_dict))
position_tag = {}
for i in range(len(label)):
DictHelper.append_dic_key(position_tag, label[i],
int(index_list[i]))
for key, value in position_tag.items():
print("%s: %s" % (key, value))
StoreHelper.store_data(position_tag, 'position_tag.dat')
StoreHelper.save_file(position_tag, 'position_tag.txt')
else:
length = len(label)
clusters = [[str(j) for j in range(length) if label[j] == i]
for i in range(cluster_number)]
for i in range(len(clusters)):
print("Cluster %i has %i position, position: %s" %
(i, len(clusters[i]), str(clusters[i])))
def get_frequency_dict(content):
words_list = []
for line in content.splitlines():
words_list.extend(
SegmentHelper.lemmatization(SegmentHelper.segment_text(line)))
return DictHelper.dict_from_count_list(words_list)
def convert_2(self, probability_dict):
year_phase_list = self._get_working_year_words()
phrase_list = self._remove_conjunction_segment(probability_dict)
phrase_list.extend(year_phase_list)
return DictHelper.dict_from_count_list(phrase_list)
def __init__(self, raw_position, word_list=[]):
self.raw_position = raw_position.lower()
self.word_list = word_list
self.phrase_dict = DictHelper.dict_from_count_list(self.word_list)
self.new_words_list = []
