edxcourse2/wordcount1.py at master · benjaminDom/edxcourse2 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
# -*- coding: utf-8 -*-
"""
Created on Sat Nov 16 07:17:41 2019

@author: BenTemp
"""

import collections

mydict={}


file1=open('98-0.txt',encoding="utf8")
x=file1.read().lower()


x=x.replace('\n',' ')
x=x.replace(".","")
x=x.replace(",","")
x=x.replace("\"","")
x=x.replace("“","")


x=x.split(' ')

for i in x:
    i.strip()


for i in x:
    if i=='':
        x.remove(i)


file2=open('stopwords')
sw=file2.read().lower()
sw=sw.split("\n")


"""
use stop words
"""
"""
for i in x:
    if i in sw:
        x.remove(i)
"""

words=[]
for i in x:
    if i not in sw:
       words.append(i)

for i in words:
    if i in mydict:
        mydict[i]+=1
    else:
        mydict[i]=1


d =collections.Counter(mydict)

#print(d.most_common(10))
for word, count in d.most_common(20):
	print(word, ": ", count)


"""
for i in x:
    print(i)


if i in mydict:
        print('key found')

file2=open('stopwordstest.txt')
sw=file2.read()
sw=sw.split("\n")

if x[10] in sw:
    x.remove(x[10])


     import collections

d = collections.Counter(mydict)
#print(d.most_common(10))
for word, count in d.most_common(10):
	print(word, ": ", count)

 :  4377
the :  4338
a :  1663
I :  1446
his :  1080
Mr. :  602
The :  586
he :  579
to :  579
said :  570


k=1
for i in x:
    if i in sw:
        x.remove(i)
        if i=='the':
            print('removed the word="the" :',i,',',k,'times')
            k+=1


"""