def prepare(text):
"""this will take a text as input, and put the letters in order of most frequent
"""
text = text.lower()
text = [i for i in text if i in alpha]
text = "".join(text)
out = [i[0] for i in frequency.top(frequency.letters(text))]
return out
out_put(leader[0])
return leader[0]
# 下面才是真正的入口
# with open(wen_dang, 'r', encoding='utf-8') as f:
with open(wen_dang, 'r', encoding='gbk') as f:
target_words = f.readlines()
need_pop = " "
def me_replace(str11):
return "".join(str11.split(need_pop))
topx = frequency.top(target_words, medal=int(1/threshold))
for me_item in topx:
need_pop = the_long_the_better(me_item, True)
# 每找出一个最长的词组，就把这个词组从文件中删掉。
if need_pop:
target_words = list(map(me_replace, target_words))
print(datetime.now() - start)
print(out_put_list)
# topx = frequency.top(wen_dang, "", medal=int(1 / threshold))
# print(datetime.now() - start)
# for me_item in topx:
# the_long_the_better(me_item, False)
#
# print(out_put_list)
