NERTaggingUsingStanford/ReadFileAndShuffle.py at master · pratikbhatia199/NERTaggingUsingStanford · 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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
from babel.localedata import exists

__author__ = 'pratik'
from __builtin__ import open
import random
import os
import sys
import csv

list_sentences = []
list_values = []
list_train_data = []
list_test_data = []


print "This program should read a file and shuffle it"


def read_file_and_populate_list_sentences():
    index = 0
    with open("./train-v2.iob") as file:
        sentence = []
        for line in file:
            print index
            list_line = line.strip().split()
            print list_line
            print len(list_line)
            if len(list_line)>0:
                sentence.append(list_line)
                if list_line[0] == '.':
                    list_sentences.append(sentence)
                    sentence = []
            index+=1

    for line in list_sentences:
        print line
    print index
    print len(list_sentences)

def shuffle_array():
    print list_sentences[0]
    random.shuffle(list_sentences)
    print list_sentences[0]

def split_training_test():
    test_length = int(0.30*len(list_sentences))

    test_data = list_sentences[:test_length]
    print len(test_data)
    train_data = list_sentences[test_length:]
    print len(train_data)
    return (test_data, train_data)


def write_test_file(list_test_data):
    if not os.path.exists('./test'):
        os.makedirs('./test')

    f = open('./test/testing_file_with_tags.tsv', 'w')
    try:

        # for i in range(10):
        #     writer.writerow( (i+1, chr(ord('a') + i), '08/%02d/07' % (i+1)) )
        for list_sentence in list_test_data:
            for word_tag in list_sentence:
                print word_tag[0], word_tag[1]
                f.write(str(word_tag[0]+'\t'+'\t'+word_tag[1]+'\n'))
    finally:
        f.close()

    f = open('./test/testing_file_without_tags.tsv', 'w')
    try:
        for list_sentence in list_test_data:
            for word_tag in list_sentence:
                print word_tag[0]
                f.write(word_tag[0]+'\n')
    finally:
        f.close()

    print open('./test/testing_file_without_tags.tsv', 'r').read()

def write_train_file(list_train_data):
    if not os.path.exists('./train'):
        os.makedirs('./train')

    f = open('./train/train_data.tsv', 'w')
    try:

        # for i in range(10):
        #     writer.writerow( (i+1, chr(ord('a') + i), '08/%02d/07' % (i+1)) )
        for list_sentence in list_train_data:
            for word_tag in list_sentence:
                print word_tag[0], word_tag[1]
                f.write(str(word_tag[0]+'\t'+word_tag[1]+'\n'))
    finally:
        f.close()


def partition(lst, n):
    q, r = divmod(len(lst), n)
    indices = [q*i + min(i, r) for i in xrange(n+1)]
    return [lst[indices[i]:indices[i+1]] for i in xrange(n)]


def create_partitions_for_crossvalidation(list_train_data):
    list_partitions = []
    list_index_values = partition(range(0, len(list_train_data)), 7)
    if not os.path.exists('./train'):
        os.makedirs('./train')
    i = 1
    print "List train data", len(list_train_data)
    for list_partition_index in list_index_values:
        print i, len(list_partition_index)
        print list_partition_index[0], list_partition_index[len(list_partition_index)-1]


        print list_train_data[list_partition_index[0]], list_train_data[list_partition_index[len(list_partition_index)-1]]

        f = open('./train/train_partition_'+str(i)+'.tsv', 'w')
        try:
            writer = csv.writer(f)
            for sentence_index in list_partition_index:
                for word in list_train_data[sentence_index]:
                    print i, sentence_index, word
                    f.write(str(word[0]+'\t'+word[1]+'\n'))
        finally:
            f.close()

        i += 1

def create_crossvalidation_sets():
    if not os.path.exists('./cross_validation'):
        os.makedirs('./cross_validation')
    for i in range(1,8):
        list_train_cv = []
        list_test_cv = []
        print type(list_test_cv)
        print type(list_test_cv)
        if not os.path.exists('./cross_validation/cv_set_'+str(i)):
            os.makedirs('./cross_validation/cv_set_'+str(i))
        for j in range(1,8):
            if i == j:
                with open('./train/train_partition_'+str(i)+'.tsv', 'r') as file:
                    for line in file:
                        list_test_cv.append(line)

                with open('./cross_validation/cv_set_'+str(i)+'/test.tsv', 'w') as test_file:
                    for line in list_test_cv:
                        list_line = line.strip().split('\t')
                        test_file.write(str(list_line[0]+'\t'+'\t'+list_line[1]+'\n'))


            else:
                with open('./train/train_partition_'+str(j)+'.tsv', 'r') as file:
                    for line in file:
                        list_train_cv.append(line)

        with open('./cross_validation/cv_set_'+str(i)+'/train.tsv', 'w') as train_file:
            for line in list_train_cv:
                train_file.write(line)


def main():
    read_file_and_populate_list_sentences()
    shuffle_array()
    list_test_data, list_train_data = split_training_test()
    write_test_file(list_test_data)
    write_train_file(list_train_data)
    create_partitions_for_crossvalidation(list_train_data)
    create_crossvalidation_sets()
main()