-
Notifications
You must be signed in to change notification settings - Fork 1
/
data_helpers.py
212 lines (188 loc) · 7.58 KB
/
data_helpers.py
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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
import numpy as np
import re
import itertools
from collections import Counter
import os
from bs4 import BeautifulSoup
# from gensim.models import word2vec
def clean_str(string):
"""
Tokenization/string cleaning for all datasets except for SST.
Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
"""
string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
string = re.sub(r"\'s", " \'s", string)
string = re.sub(r"\'ve", " \'ve", string)
string = re.sub(r"n\'t", " n\'t", string)
string = re.sub(r"\'re", " \'re", string)
string = re.sub(r"\'d", " \'d", string)
string = re.sub(r"\'ll", " \'ll", string)
string = re.sub(r",", " , ", string)
string = re.sub(r"!", " ! ", string)
string = re.sub(r"\(", " \( ", string)
string = re.sub(r"\)", " \) ", string)
string = re.sub(r"\?", " \? ", string)
string = re.sub(r"\s{2,}", " ", string)
return string.strip().lower()
def load_data_and_labels():
"""
Loads MR polarity data from files, splits the data into words and generates labels.
Returns split sentences and labels.
"""
# Load data from files
pos_path = "./data/rt-polaritydata/rt-polarity.pos"
neg_path = "./data/rt-polaritydata/rt-polarity.neg"
if not os.path.exists(pos_path):
os.system("git clone https://github.com/dennybritz/cnn-text-classification-tf.git")
os.system('mv cnn-text-classification-tf/data .')
os.system('rm -rf cnn-text-classification-tf')
positive_examples = list(open(pos_path,encoding="utf-8").readlines())
positive_examples = [s.strip() for s in positive_examples]
negative_examples = list(open(neg_path,encoding="utf-8").readlines())
negative_examples = [s.strip() for s in negative_examples]
# Split by words
x_text = positive_examples + negative_examples
x_text = [clean_str(sent) for sent in x_text]
x_text = [s.split(" ") for s in x_text]
# Generate labels
positive_labels = [1 for _ in positive_examples]
negative_labels = [0 for _ in negative_examples]
y = np.concatenate([positive_labels, negative_labels], 0)
return [x_text, y]
def pad_sentences(sentences, padding_word="</s>"):
"""
Pads all sentences to the same length. The length is defined by the longest sentence.
Returns padded sentences.
"""
sequence_length = max(len(x) for x in sentences)
padded_sentences = []
for i in range(len(sentences)):
sentence = sentences[i]
num_padding = sequence_length - len(sentence)
new_sentence = sentence + [padding_word] * num_padding
padded_sentences.append(new_sentence)
return padded_sentences
def build_vocab(sentences):
"""
Builds a vocabulary mapping from word to index based on the sentences.
Returns vocabulary mapping and inverse vocabulary mapping.
"""
# Build vocabulary
word_counts = Counter(itertools.chain(*sentences))
# Mapping from index to word
vocabulary_inv = [x[0] for x in word_counts.most_common()]
# Mapping from word to index
vocabulary = {x: i for i, x in enumerate(vocabulary_inv)}
return [vocabulary, vocabulary_inv]
def build_input_data(sentences, labels, vocabulary):
"""
Maps sentencs and labels to vectors based on a vocabulary.
"""
x = np.array([[vocabulary[word] for word in sentence] for sentence in sentences])
y = np.array(labels)
return [x, y]
def build_input_data_with_word2vec(sentences, labels, word2vec):
"""Map sentences and labels to vectors based on a pretrained word2vec"""
x_vec = []
for sent in sentences:
vec = []
for word in sent:
if word in word2vec:
vec.append(word2vec[word])
else:
vec.append(word2vec['</s>'])
x_vec.append(vec)
x_vec = np.array(x_vec)
y_vec = np.array(labels)
return [x_vec, y_vec]
def load_data_with_word2vec(word2vec):
"""
Loads and preprocessed data for the MR dataset.
Returns input vectors, labels, vocabulary, and inverse vocabulary.
"""
# Load and preprocess data
sentences, labels = load_data_and_labels()
sentences_padded = pad_sentences(sentences)
# vocabulary, vocabulary_inv = build_vocab(sentences_padded)
return build_input_data_with_word2vec(sentences_padded, labels, word2vec)
def load_data():
"""
Loads and preprocessed data for the MR dataset.
Returns input vectors, labels, vocabulary, and inverse vocabulary.
"""
# Load and preprocess data
sentences, labels = load_data_and_labels()
sentences_padded = pad_sentences(sentences)
vocabulary, vocabulary_inv = build_vocab(sentences_padded)
x, y = build_input_data(sentences_padded, labels, vocabulary)
return [x, y, vocabulary, vocabulary_inv]
def batch_iter(data, batch_size, num_epochs):
"""
Generates a batch iterator for a dataset.
"""
data = np.array(data)
data_size = len(data)
num_batches_per_epoch = int(len(data)/batch_size) + 1
for epoch in range(num_epochs):
# Shuffle the data at each epoch
shuffle_indices = np.random.permutation(np.arange(data_size))
shuffled_data = data[shuffle_indices]
for batch_num in range(num_batches_per_epoch):
start_index = batch_num * batch_size
end_index = min((batch_num + 1) * batch_size, data_size)
yield shuffled_data[start_index:end_index]
def load_pretrained_word2vec(infile):
if isinstance(infile, str):
infile = open(infile)
word2vec = {}
for idx, line in enumerate(infile):
if idx == 0:
vocab_size, dim = line.strip().split()
else:
tks = line.strip().split()
word2vec[tks[0]] = map(float, tks[1:])
return word2vec
def load_google_word2vec(path):
model = word2vec.Word2Vec.load_word2vec_format(path, binary=True)
return model
def review_to_wordlist(review):
'''
把IMDB的评论转成词序列
参考:http://blog.csdn.net/longxinchen_ml/article/details/50629613
'''
# 去掉HTML标签,拿到内容
review_text = BeautifulSoup(review, "html.parser").get_text()
# 用正则表达式取出符合规范的部分
string = re.sub("[^a-zA-Z]"," ", review_text)
string = re.sub(r"\'s", " \'s", string)
string = re.sub(r"\'ve", " \'ve", string)
string = re.sub(r"n\'t", " n\'t", string)
string = re.sub(r"\'re", " \'re", string)
string = re.sub(r"\'d", " \'d", string)
string = re.sub(r"\'ll", " \'ll", string)
string = re.sub(r",", " , ", string)
string = re.sub(r"!", " ! ", string)
string = re.sub(r"\(", " \( ", string)
string = re.sub(r"\)", " \) ", string)
string = re.sub(r"\?", " \? ", string)
string = re.sub(r"\s{2,}", " ", string)
# 小写化所有的词,并转成词list
words = string.lower().split()
# 返回words
return words