def ConvertRawWordsToOrder(self, rawwords, nrange, ordertype="abs"):
Analyzer = base_analyzer()
WordRanker = ranker()
Converter = word_convert()
num_words = Converter.splitwords_bylen(rawwords, nrange)
for len_word in num_words:
num_words[len_word] = WordRanker.rank_words(num_words[len_word],
reverse=True)
#num_words[len_word] = WordRanker.rank_tulple(num_words[len_word], reverse=True)
PrimeWords = [word[0] for word in num_words[nrange]]
PrimeOrders = {}
for i in range(len(PrimeWords)):
PrimeOrders[PrimeWords[i]] = i
OrderWords = {}
OrderWords[nrange] = PrimeOrders
start_time = time.time()
for i in range(1, nrange):
if ordertype == 'abs':
OrderWords[i] = self.ConvertWordToNumOrder(
[word[0] for word in num_words[i]], PrimeWords, rawwords)
elif ordertype == 'Set':
OrderWords[i] = self.ConvertwordToCntOrder(
num_words[i], num_words[nrange])
else:
OrderWords[i] = Converter.convert_word_order(
[word[0] for word in num_words[i]], PrimeWords)
OrderWords = self.convert_order_to_raw(OrderWords)
return OrderWords
def infer_words_by_ve(self, data_path, r_way, h, combine, model, v_way, T,
r):
if type(data_path) == 'str':
datas = read_datas(data_path, r_way)
else:
datas = read_multity_dirs(data_path, r_way)
datas = get_puredatas(datas)
ABtest_now = ABtest()
datas = datas[0:int(len(datas) * ABtest_now.ratio)]
#messages = add_tail(datas, h) # change
messages = datas
message_splitter = splitter()
message_split = message_splitter.split_by_ve(messages, h, combine,
model, v_way, T, r)
t_now = time.strftime("%Y-%m-%d %H:%m:%s", time.localtime(time.time()))
m_logger = get_logger(log_path + '/messge_splited_log' + t_now,
'msg_split')
for message in message_split:
m_logger.error(message)
T_word_convert = word_convert()
words_prim = T_word_convert.convert_words_byloc(message_split)
p_logger = get_logger(log_path + '/p_log' + t_now, 'word_count')
for key in words_prim:
p_logger.error(key + str(words_prim[key].content))
words_count = T_word_convert.get_words_count(words_prim)
t_ranker = ranker()
words_rank = t_ranker.rank_dic(words_count, True)
return words_rank
def GetCorresOrder(self, WordChilds, WordVoc):
WordDic = {}
for Child in WordChilds:
WordDic[Child] = WordVoc[Child]
OrderWords = ranker().rank_dic(WordDic)
TotalNum = sum([item[1] for item in OrderWords])
Lo = 0
TempSum = 0
while (TempSum < TotalNum / 2):
TempSum = TempSum + OrderWords[Lo][1]
Lo = Lo + 1
return Lo
def __init__(self):
super().__init__
self.rank = ranker()
self.analysist = base_analyzer()
def __init__(self):
self.analyer = base_analyzer()
self.convert = Converter()
self.ranker = ranker()