當前位置:成語大全網 - 新華字典 - 用Python統計詞頻

用Python統計詞頻

def statistics(astr):

# astr.replace("\n", "")

slist = list(astr.split("\t"))

alist = []

[alist.append(i) for i in slist if i not in alist]

alist[-1] = alist[-1].replace("\n", "")

return alist

if __name__ == "__main__":

code_doc = {}

with open("test_data.txt", "r", encoding='utf-8') as fs:

for ln in fs.readlines():

l = statistics(ln)

for t in l:

if t not in code_doc:

code_doc.setdefault(t, 1)

else:

code_doc[t] += 1

for keys in code_doc.keys():

print(keys + ' ' + str(code_doc[keys]))