python3结巴分词分行拆分统计词频

python3 和 python2 的语法差异应该是最蛋疼的事情了

dict本来就是没有顺序的吧

把dict转换成list

再去排序就会比较好了

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import jieba
import csv


def dict2list(dic:dict):
     # 将字典转化为列表
    keys = dic.keys()
    vals = dic.values()
    lst = [(key, val) for key, val in zip(keys, vals)]
    return lst


csv_reader = csv.reader(open('/Users/dear_jinx/Desktop/zz.csv', 'U'))
dic = []

for row in csv_reader:
    # seg_list = jieba.cut_for_search(row[4])
    seg_list = jieba.cut(row[4])
    for x in seg_list:
        dic.append(x)

word = {}

for i in dic:
    if i not in word:
        word[i] = 1
    else:
        word[i] += 1

list = sorted(dict2list(word), key=lambda x: x[1], reverse=False)

for x in list:
    print(x)

# for item in word.items():
#     print(item)

# print("/".join(dic))

上面的方法太繁琐了，并且分词的效果也不好，会出现一些符号的统计。

这里我们只在列表里面加入那些长度大于等于2的词

并且用counter去做统计

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import jieba
import csv
from collections import Counter


def dict2list(dic:dict):
     # 将字典转化为列表
    keys = dic.keys()
    vals = dic.values()
    lst = [(key, val) for key, val in zip(keys, vals)]
    return lst


csv_reader = csv.reader(open('/Users/dear_jinx/Desktop/zz.csv', 'U'))
dic = []

for row in csv_reader:
    # seg_list = jieba.cut_for_search(row[4])
    seg_list = jieba.cut(row[4])
    for x in seg_list:
        if len(x) >= 2:
            dic.append(x)

c = Counter(dic).most_common(20)
print(c)