def combine(src_path, save_path):
file_list_dict, file_name_list = util.get_objdict_list(src_path, ".txt")
for file_name, file_dict in file_list_dict.items():
r_dict = dict()
for place, num in file_dict.items():
p_place = place.split(" ")[0]
r_dict[p_place] = r_dict.get(p_place, 0) + num
util.save_dict_list(r_dict,save_path+file_name)
import re
import tool.util as util
key_list = util.get_key_list()
dict_dir = r"D:\semantic analysis\2016-10-09结果\词频1//"
for key in key_list:
print(key)
set_dict, file_name = util.get_objdict_list(dict_dir + key, ".txt")
date_list = util.get_file_list(dict_dir + key, ".txt")
pattern = re.compile(r"(\d*-\d*)-\d*")
month_array = pattern.findall(" ".join(date_list))
month_array = ["2010"]
util.create_directory(r"D:\semantic analysis\2016-10-12结果\2010年频数统计//" +
key)
# 循环查找月份
for month in month_array:
pattern = re.compile(r"(" + month + "-\d*-\d*)")
date_array = pattern.findall(" ".join(date_list))
print(date_array)
# 循环合并月份频数字典
r_dict = dict()
for file_date in date_array:
r_dict = util.union_dicts(set_dict[file_date + ".txt"], r_dict)
util.save_dict_list(
r_dict,
r"D:\semantic analysis\2016-10-12结果\2010年频数统计//" + key + ".txt")
import re
import tool.util as util
key_list = util.get_key_list2()
dict_dir = r"D:\semantic analysis\2016-10-09结果\词频1//"
r_dict = dict()
for key in key_list:
print(key)
set_dict = util.get_obj_list(dict_dir + key, ".txt")
for file_date in set_dict:
r_dict = util.union_dicts(file_date, r_dict)
util.save_dict_list(r_dict, r"D:\百度指数截屏//常用词总频率统计" + ".txt")
"2011-10-16",
"2012-02-16",
"2012-07-09",
"2012-11-19"]
]
py_list = ["zp","dd","sz","dr","ms","fh"]
date_list_list = [["2010-06-01",
"2011-01-21",
"2011-07-09",
"2011-11-21"]]
py_list = ["tc"]
root_path = r"D:\semantic analysis\用户信息\dict//"
i = 0
while i < len(py_list):
py = py_list[i]
date_list = date_list_list[i]
i += 1
for dd in date_list:
user_id_list = extract_user_id(py,dd)
place_list = []
place_dict = dict()
if user_id_list:
for user_id in user_id_list:
place = get_place(user_id)
if place:
place_list.append(place)
place_dict = dict((a, place_list.count(a)) for a in place_list)
util.create_directory(root_path+py)
util.save_dict_list(place_dict, root_path+py+"//"+dd+".txt")
import tool.util as util
# 从每个dict——txt文件里面统计词频率
dict_path = r"D:\semantic analysis\结果\去重频数//"
result_path = r"D:\semantic analysis\结果\去重频率//"
keyword_list = util.get_key_list2() + util.get_key_list()
for key in keyword_list:
print(key)
r_dict, file_name_list = util.get_objdict_list(dict_path + key, ".txt")
for (k, word_dict) in r_dict.items():
sum = 0
r_f_dict = {}
if key in word_dict:
word_dict.pop(key)
for word, value in word_dict.items():
sum += int(value)
for word, value in word_dict.items():
ratio = value / sum
r_f_dict[word] = ratio
util.create_directory(result_path + key + "//")
util.save_dict_list(r_f_dict, result_path + key + "//" + k)
# 统计所有关键词出现的文件数
def count_word(word_set, word_dict):
for word in word_set:
if word not in word_dict:
word_dict[word] = 1
else:
word_dict[word] = word_dict[word] + 1
def count_word_from_dict(new_dict, word_dict):
for word, v in new_dict.items():
if word not in word_dict:
word_dict[word] = 1
else:
word_dict[word] = word_dict[word] + 1
dir = r"D:\semantic analysis\2016-10-09结果\词频月//"
key_list = util.get_key_list()
for key in key_list:
os.chdir(dir+key)
print(key)
file_list = util.get_obj_list(dir+key,".txt")
r_word_dict = dict()
for file in file_list:
count_word_from_dict(file, r_word_dict)
util.save_dict_list(r_word_dict,r"D:\semantic analysis\2016-10-12结果\总频数月//"+key+".txt")