def __init__(self, idf_path, stop_words_path="", r_hd=0):
self.tf_idf_hd = tf_idf(idf_path, stop_words_path)
self.repeat = 0
self.not_repeat = 1
if not r_hd:
self.r_hd = redis.Redis()
self.word_key_pre = "pub_word:"
self.title_id_pre = "pub_title_id:"
self.time_limit = 259200
self.pub_title_id_key = "incr:pub_title_id"
self.r_hd.flushdb()
def __init__(self, idf_path, stop_words_path = "", r_hd = 0):
self.tf_idf_hd = tf_idf(idf_path, stop_words_path)
self.repeat = 0
self.not_repeat = 1
if not r_hd:
self.r_hd = redis.Redis()
self.word_key_pre = "pub_word:"
self.title_id_pre = "pub_title_id:"
self.time_limit = 259200
self.pub_title_id_key = "incr:pub_title_id"
self.r_hd.flushdb()
def __init__(self, idf_path, stop_words_path="", uid_overtime_path=""):
self.uid_overtime_dic = self.gen_uid_overtime_dic(uid_overtime_path)
self.tf_idf_hd = tf_idf(idf_path, stop_words_path)
self.repeat = 0
self.not_repeat = 1
#如果title中topN小于此值则将结果判断相似度
self.sim_judge_limit = 3
self.r_hd = redis.Redis()
self.word_key_pre = "main_word:"
self.title_id_pre = "main_title_id:"
self.uid_pre = "main_tid_uid:"
self.time_stamp_pre = "main_time_stamp:"
self.time_limit = 259200
self.uid_overtime_default = self.time_limit
self.main_title_id_key = "incr:main_title_id"
self.r_hd.flushdb()
def __init__(self, idf_path, stop_words_path = "", uid_overtime_path = ""):
self.uid_overtime_dic = self.gen_uid_overtime_dic(uid_overtime_path)
self.tf_idf_hd = tf_idf(idf_path, stop_words_path)
self.repeat = 0
self.not_repeat = 1
#如果title中topN小于此值则将结果判断相似度
self.sim_judge_limit = 3
self.r_hd = redis.Redis()
self.word_key_pre = "main_word:"
self.title_id_pre = "main_title_id:"
self.uid_pre = "main_tid_uid:"
self.time_stamp_pre = "main_time_stamp:"
self.time_limit = 259200
self.uid_overtime_default = self.time_limit
self.main_title_id_key = "incr:main_title_id"
self.r_hd.flushdb()
ret = flter.filter(s, id_set)
print ret
time.sleep(2)
#raw_input(">>")
s = "a, b, c, d, f"
id_set = set([2, 3, 4, 5])
ret = flter.filter(s, id_set)
print ret
cov.stop() #分析结束
cov.save() #将覆盖率结果保存到数据文件
if 0:
tf_idf_hd = tf_idf("idf.txt", "stopwords.txt")
s = "a, b, c, d, e, f, 1, 2, 3"
print tf_idf_hd.get_top_n_tf_idf(s)
if 0:
main_flter = main_repeat_filter("idf.txt", "stopwords.txt")
main_flter.insert_s_to_redis('abc',
['main_word:a', 'main_word:b', 'main_word:c'],
set([10, 20, 30]))
if 0:
pub_flter = pub_repeat_filter("idf.txt", "stopwords.txt")
title = "广西一官员获刑十年未坐一天牢 法院称系监外执行"
ret = flter.filter(s, id_set)
print ret
time.sleep(2)
#raw_input(">>")
s = "a, b, c, d, f"
id_set = set([2, 3, 4, 5])
ret = flter.filter(s, id_set)
print ret
cov.stop() #分析结束
cov.save() #将覆盖率结果保存到数据文件
if 0:
tf_idf_hd = tf_idf("idf.txt", "stopwords.txt")
s = "a, b, c, d, e, f, 1, 2, 3"
print tf_idf_hd.get_top_n_tf_idf(s)
if 0:
main_flter = main_repeat_filter("idf.txt", "stopwords.txt")
main_flter.insert_s_to_redis('abc', ['main_word:a', 'main_word:b', 'main_word:c'], set([10, 20, 30]))
if 0:
pub_flter = pub_repeat_filter("idf.txt", "stopwords.txt")
title = "广西一官员获刑十年未坐一天牢 法院称系监外执行"
ret = pub_flter.filter(title)
