nltp APP-分析买家评论的评分-高频词：二维关系

# -*- coding: utf-8 -*-
from nltk  import *

# TO FIX : No such file or directory
os.chdir(r‘E:\zpy‘)

f = open(‘reviews_text_lt_3.txt‘, ‘r‘)
f_r = f.read()
strList = f_r.split(‘ ‘)
fdist1 = FreqDist(strList)
#总的词数
print fdist1
#表达式 keys()为我们提供了文本中所有不同类型的链表
vocabulary1 = fdist1.keys()
#通过切片看看这个链表的前 50 项
res0_50 =vocabulary1[:50]
print res0_50

C:\>python E:\zpy\wltp.py
<FreqDist with 16789 samples and 180043 outcomes>
[‘‘, ‘raining‘, ‘disappointing.It‘, ‘uncomfortable...‘, "lot‘s", ‘uv.\nSo,‘, ‘yellow‘, ‘Seller‘, ‘four‘, ‘vaporizers.I‘, ‘Does‘, ‘completely!!‘, ‘hanging‘, ‘Monday,‘, ‘asap!!This‘, ‘Until‘, ‘instead.The‘, ‘malfunctioned.‘, ‘Lately‘, ‘looking‘, ‘LAST‘, ‘eligible‘, ‘electricity‘, ‘DISAPPOINTED‘, ‘oneWorks‘, ‘powdery‘, ‘unanswered‘, ‘also.‘, ‘refun
‘sooooo‘, ‘foul‘, ‘on\nafter‘, ‘fingers.‘, ‘advice:‘, ‘fingers,‘, ‘advice?‘, ‘each),‘, ‘month.I‘]

C:\>

SELECT
    amz_review_text
FROM
    amz_reviews_grab_us
WHERE
    amz_review_rating < 3
LIMIT 3000;