def main():
# 设置结果保存的目录
result_dir = r'D:\semantic analysis\2016-10-05结果\html标记分句2//'
txt_dir = r"D:\semantic analysis\2016-10-05结果\新词分句//"
set_dir = r"D:\semantic analysis\2016-10-05结果\新词//"
k_list = util.get_key_list()
for key in k_list:
print(key)
# 文件目录
file_list = sorted(util.get_file_list(txt_dir + key, ".txt"))
# 集合目录
set_list = sorted(util.get_file_list(set_dir + key, ".pkl"))
util.create_directory(result_dir + "新词//" + key + "//")
i = 0
while i < len(file_list):
s_list = util.get_list_from_file(txt_dir + key + "//" +
set_list[i][0:-4] + ".txt")
new_word_list = util.get_nw(set_dir + key + "//" + set_list[i])
# 过滤相同的语句，防止重复计算
s_list = list(set(s_list))
w_list = remark(s_list, new_word_list, key)
html_name = file_list[i][:-4] + '.html'
util.save_file(result_dir + "新词//" + key + "//" + html_name,
w_list)
i += 1
def main():
k_list = util.get_key_list()
jieba.set_dictionary("D:\semantic analysis\分词\词库\导出结果\dict1.txt")
jieba.initialize()
for key in k_list:
print(key)
file_list = util.get_file_list(
'D://semantic analysis//analyze_data//fc//' + key, ".txt")
# 建立目录
mk_dir('./w')
mk_dir('./p')
for n_file in file_list:
s_list = util.get_list_from_file(n_file)
# 过滤相同的语句，防止重复计算
print(len(s_list))
s_list = list(set(s_list))
print(len(s_list))
wg = nx.Graph()
pg = nx.Graph()
for sentence in s_list:
# 创建整句话的网络
ll = util.input_filer(sentence)
wg = add_s2g(wg, ' '.join(ll))
# 只创建关键词所在的分句的网络
for ss in ll:
if (key in ss):
pg = add_s2g(pg, ss)
pkl_name = n_file[:-4] + '.pkl'
util.save_nw(pg, './/p//' + pkl_name)
util.save_nw(wg, './/w//' + pkl_name)
print(n_file)
print(
time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time())))
with open('record.txt', 'a', encoding='utf-8') as rf:
rf.write(n_file + '\n')
def main():
# 设置结果保存的目录
result_dir = r'D:\semantic analysis\新纯文本\1新词分句//'
txt_dir = r"D:\semantic analysis\新纯文本\1新词//"
k_list = util.get_key_list()
for key in k_list:
print(key)
# 文件目录
file_list = util.get_file_list(txt_dir + key, ".txt")
# 建立目录
# mk_dir(result_dir+"新词整句//"+key)
mk_dir(result_dir + key)
for file in file_list:
s_list = util.get_list_from_file(txt_dir + key + "//" + file)
# 过滤相同的语句，防止重复计算
# s_list = list(set(s_list))
w_list, p_list = extract_sentence(s_list, key)
util.save_file(result_dir + key + "//" + file, p_list, True)
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")
# 相互比例
if mode == 1:
r1, r2 = com_function(copy.deepcopy(g1), copy.deepcopy(g2))
result_list.append(nw_list[ii + lap][0:-4] + "\t" + str(r1))
result_list.append((nw_list[ii][0:-4] + "\t" + str(r2)))
# 一对一
elif mode == 0:
result_list = com_function(copy.deepcopy(g1),
copy.deepcopy(g2))
util.save_file(
result_dir + key + "//" + nw_list[ii + lap][0:-4] + ".txt",
result_list)
# n对一
elif mode == 2:
r1 = com_function(copy.deepcopy(g1), copy.deepcopy(g2), type)
result_list.append(nw_list[ii + lap][0:-4] + "\t" + str(r1))
ii -= lap
if mode != 0:
result_list.reverse()
util.save_file(result_dir + key + ".txt", result_list)
key_list = util.get_key_list() + util.get_key_list2()
pkl_dir = r"D:\semantic analysis\新结果\去虚词去单字\合成共现网络\{0}\p//"
# pkl_dir = r"D:\semantic analysis\新结果\合并图\{0}//"
result_dir = r"D:\semantic analysis\新结果\去虚词去单字\半年间边变化率//"
# result_dir = r"D:\semantic analysis\新结果\合并图\扯淡//"
loop_compare(cal_existed_edges_ratio, key_list, pkl_dir, result_dir, 2, 5)
# loop_compare(same_node_degree, key_list, pkl_dir, result_dir, 0)