def load_weibo(uid_weibo):
ts = time.time()
domain_dict, domain_count = load_train()
end = time.time()
print '%s' % (end - ts)
len_dict = dict()
total = 0
for k, v in domain_dict.items():
len_dict[k] = len(v)
total = total + len(v)
sw = load_scws()
black = load_black_words()
result_data = dict()
ts = time.time()
for k, v in uid_weibo.items():
words = sw.participle(v)
domain_p = start_p(name_list)
word_list = dict()
for word in words:
if (word[1] in cx_dict) and 3 < len(
word[0]) < 30 and (word[0] not in black) and (
word[0] not in single_word_whitelist
) and (word[0] not in word_list): #选择分词结果的名词、动词、形容词，并去掉单个词
if word_list.has_key(word[0]):
word_list[word[0]] = word_list[word[0]] + 1
else:
word_list[word[0]] = 1
for d_k in domain_p.keys():
start = time.time()
domain_p[d_k] = com_p(word_list, domain_dict[d_k],
domain_count[d_k], len_dict[d_k],
total) #计算文档属于每一个类的概率
end_time = time.time()
print '%s' % (end_time - start)
result_data[k] = domain_p
end = time.time()
print '%s takes %s...' % (k, end - ts)
ts = end
return result_data
def load_weibo(uid_weibo):
ts = time.time()
domain_dict,domain_count = load_train()
end = time.time()
print '%s' % (end-ts)
len_dict = dict()
total = 0
for k,v in domain_dict.items():
len_dict[k] = len(v)
total = total + len(v)
sw = load_scws()
black = load_black_words()
result_data = dict()
ts = time.time()
for k,v in uid_weibo.items():
words = sw.participle(v)
domain_p = start_p(name_list)
word_list = dict()
for word in words:
if (word[1] in cx_dict) and 3 < len(word[0]) < 30 and (word[0] not in black) and (word[0] not in single_word_whitelist) and (word[0] not in word_list):#选择分词结果的名词、动词、形容词，并去掉单个词
if word_list.has_key(word[0]):
word_list[word[0]] = word_list[word[0]] + 1
else:
word_list[word[0]] = 1
for d_k in domain_p.keys():
start = time.time()
domain_p[d_k] = com_p(word_list,domain_dict[d_k],domain_count[d_k],len_dict[d_k],total)#计算文档属于每一个类的概率
end_time = time.time()
print '%s' % (end_time-start)
result_data[k] = domain_p
end = time.time()
print '%s takes %s...' % (k,end-ts)
ts = end
return result_data
def read_csv(domain_dict,domain_count,d_time):
sw = load_scws()
black = load_black_words()
text = ''
word_dict = dict()
reader = csv.reader(file('./add_dict/%s_new.csv'% d_time, 'rb'))
for line in reader:
#line = line[0].strip('\xef\xbb\xbf')
#line = line.strip('\n')
text = text + ',' + line
#print text.encode('utf-8')
words = sw.participle(text)
for word in words:
if (word[1] in cx_dict) and (3 < len(word[0]) < 30 or word[0] in single_word_whitelist) and (word[0] not in black):#选择分词结果的名词、动词、形容词，并去掉单个词
if domain_dict.has_key(str(word[0])):
domain_dict[str(word[0])] = domain_dict[str(word[0])] + 1
else:
domain_dict[str(word[0])] = 1
domain_count = domain_count + 1
return domain_dict,domain_count
def read_csv(domain_dict, domain_count, d_time):
sw = load_scws()
black = load_black_words()
text = ''
word_dict = dict()
reader = csv.reader(file('./add_dict/%s_new.csv' % d_time, 'rb'))
for line in reader:
#line = line[0].strip('\xef\xbb\xbf')
#line = line.strip('\n')
text = text + ',' + line
#print text.encode('utf-8')
words = sw.participle(text)
for word in words:
if (word[1] in cx_dict) and (3 < len(
word[0]) < 30 or word[0] in single_word_whitelist) and (
word[0] not in black): #选择分词结果的名词、动词、形容词，并去掉单个词
if domain_dict.has_key(str(word[0])):
domain_dict[str(word[0])] = domain_dict[str(word[0])] + 1
else:
domain_dict[str(word[0])] = 1
domain_count = domain_count + 1
return domain_dict, domain_count
# -*- coding: UTF-8 -*-
import os
import time
import re
import scws
import csv
import sys
import json
from textrank4zh import TextRank4Keyword, TextRank4Sentence
from config import load_scws,load_black_words,re_cut
black = load_black_words()
tr4w = TextRank4Keyword()
def get_keyword(w_text, n_gram, n_count):
tr4w.analyze(text=w_text, lower=True, window=n_gram)
word_list = dict()
k_dict = tr4w.get_keywords(n_count, word_min_len=2)
for item in k_dict:
if item.word.encode('utf-8').isdigit() or item.word.encode('utf-8') in black:
continue
word_list[item.word.encode('utf-8')] = item.weight
return word_list
def get_weibo_single(text,n_gram=2,n_count=3):
'''
针对单条微博提取关键词，但是效率比较低
输入数据：
