sentimentcode/chunkreview.py at master · summersunshine1/sentimentcode · 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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
# -*- coding:utf-8 -*-
from nltk.tokenize import StanfordTokenizer
import nltk
from nltk import *
import codecs
from nltk.stem import WordNetLemmatizer

def readfile(filepath):
    file_object = codecs.open(filepath,'r','utf-8')
    try:
        all_text = file_object.read()
    finally:
        file_object.close()
    return all_text

linenoun = []

def traverse(t):
    try:
        t.label()
    except AttributeError:
        return linenoun
    else:
        if t.label()=='NP':
            onenp =[]
            arr = t.leaves()
            for a in arr:
                temp = a.split('/')
                onenp.append(temp[0])
            linenoun.append(onenp)
            for child in t:
                 traverse(child)
        else:
            for child in t:
                traverse(child)

def chunk(filepath):
    all_text = readfile(filepath)
    tokenizer = StanfordTokenizer()
    wordnet_lemmatizer = WordNetLemmatizer()
    arr = tokenizer.tokenize(all_text)
    grammar = "NP: {<JJ>*<NN>+}"
    cp = nltk.RegexpParser(grammar)
    res = []
    for line in arr:
        ar = line.split()
        newarr = []
        for i in ar:
            a = wordnet_lemmatizer.lemmatize(i)
            newarr.append(a)
        list = nltk.pos_tag(newarr)
        if len(list)==0:
            continue
        result = cp.parse(list)
        if len(result)==0:
            continue
        res.append(str(result))
    return res

def getsymbol(file_path):
    file_object = codecs.open(file_path,'r','utf-8')
    try:
        alltext = file_object.read()
        symbols = alltext.split()
    finally:
        file_object.close()
    return symbols

def create_txt(file_path, content):
    if os.path.exists(file_path):
        os.remove(file_path)
    f=codecs.open(file_path,'w','utf-8')
    for x in content:
        for y in x:
            for z in y:
                f.write(z)
                f.write(' ')
            f.write('\n')
    f.close()


def write_lines(file_path, lines):
    if os.path.exists(file_path):
        os.remove(file_path)
    f=codecs.open(file_path,'w','utf-8')
    for line in lines:
        f.write(line)
        f.write('\n')
    f.close()

def isspace(line):
    l = len(line)
    re = ''
    for i in range(l):
        re+=' '
    if re==line:
        return True
    return False


res = chunk("F:/course/sentimentcode/feature/data/corpuswithoutstop")
nounarr = []
for r in res:
    tree=Tree.fromstring(r)
    traverse(tree)
    if len(linenoun) == 0:
        continue
    nounarr.append(linenoun)
    linenoun = []#linenoun.clear() clear memory data
symbols = getsymbol('F:/course/sentimentcode/feature/symbol.txt')

nounpath = 'F:/course/sentimentcode/feature/data/noun'
create_txt(nounpath, nounarr)
file_object = codecs.open(nounpath,'r','utf-8')
newlines = []
try:
    lines = file_object.readlines()
    for line in lines:
        line = line.replace('\n','')
        for symbol in symbols:
            if symbol in line:
                line = line.replace(symbol,' ')
                if len(line) == 0:
                    break
        if not len(line) == 0 and not isspace(line):
            newlines.append(line)
finally:
    file_object.close()
newnounpath = 'F:/course/sentimentcode/feature/data/newnoun'
write_lines(newnounpath,newlines)