-
Notifications
You must be signed in to change notification settings - Fork 6
/
load_data.py
162 lines (127 loc) · 5.08 KB
/
load_data.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
from io import open
import unicodedata
import string
import re
import numpy as np
import torch
from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
MAX_LENGTH = 10
SOS_token = 0
EOS_token = 1
eng_prefixes = (
"i am ", "i m ",
"he is", "he s ",
"she is", "she s ",
"you are", "you re ",
"we are", "we re ",
"they are", "they re "
)
class Lang:
def __init__(self, name):
self.name = name
self.word2index = {}
self.word2count = {}
self.index2word = { SOS_token: "SOS", EOS_token: "EOS"}
self.n_words = 2 # Count SOS and EOS
def addSentence(self, sentence):
for word in sentence.split(' '):
self.addWord(word)
def addWord(self, word):
if word not in self.word2index:
self.word2index[word] = self.n_words
self.word2count[word] = 1
self.index2word[self.n_words] = word
self.n_words += 1
else:
self.word2count[word] += 1
def filterPair(p):
return len(p[0].split(' ')) < MAX_LENGTH and \
len(p[1].split(' ')) < MAX_LENGTH and \
p[1].startswith(eng_prefixes)
def filterPairs(pairs):
return [pair for pair in pairs if filterPair(pair)]
# Turn a Unicode string to plain ASCII, thanks to
# https://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
)
# Lowercase, trim, and remove non-letter characters
def normalizeString(s):
s = unicodeToAscii(s.lower().strip())
s = re.sub(r"([.!?])", r" \1", s)
s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
return s
# To read the data file we will split the file into lines, and then split
# lines into pairs. The files are all English → Other Language, so if we
# want to translate from Other Language → English I added the ``reverse``
# flag to reverse the pairs.
def readLangs(lang1, lang2, reverse=False):
print("Reading lines...")
# Read the file and split into lines
lines = open('data/%s-%s.txt' % (lang1, lang2), encoding='utf-8').\
read().strip().split('\n')
# Split every line into pairs and normalize
pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]
# Reverse pairs, make Lang instances
if reverse:
pairs = [list(reversed(p)) for p in pairs]
input_lang = Lang(lang2)
output_lang = Lang(lang1)
else:
input_lang = Lang(lang1)
output_lang = Lang(lang2)
return input_lang, output_lang, pairs
######################################################################
# The full process for preparing the data is:
#
# - Read text file and split into lines, split lines into pairs
# - Normalize text, filter by length and content
# - Make word lists from sentences in pairs
#
def prepareData(lang1, lang2, reverse=False):
input_lang, output_lang, pairs = readLangs(lang1, lang2, reverse)
print("Read %s sentence pairs" % len(pairs))
pairs = filterPairs(pairs)
print("Trimmed to %s sentence pairs" % len(pairs))
print("Counting words...")
for pair in pairs:
input_lang.addSentence(pair[0])
output_lang.addSentence(pair[1])
print("Counted words:")
print(input_lang.name, input_lang.n_words)
print(output_lang.name, output_lang.n_words)
return input_lang, output_lang, pairs
def indexesFromSentence(lang, sentence):
return [lang.word2index[word] for word in sentence.split(' ')]
def tensorFromSentence(lang, sentence):
indexes = indexesFromSentence(lang, sentence)
indexes.append(EOS_token)
return torch.tensor(indexes, dtype=torch.long, device=device).view(-1, 1)
def tensorsFromPair(pair):
input_tensor = tensorFromSentence(input_lang, pair[0])
target_tensor = tensorFromSentence(output_lang, pair[1])
return (input_tensor, target_tensor)
def get_dataloader(batch_size):
input_lang, output_lang, pairs = prepareData('eng', 'fra', True)
n = len(pairs)
input_ids = np.zeros((n, MAX_LENGTH), dtype=np.int32)
input_mask = np.zeros((n, MAX_LENGTH), dtype=np.int32)
target_ids = np.zeros((n, MAX_LENGTH), dtype=np.int32)
target_mask = np.zeros((n, MAX_LENGTH), dtype=np.int32)
for idx, (inp, tgt) in enumerate(pairs):
inp_ids = indexesFromSentence(input_lang, inp)
tgt_ids = indexesFromSentence(output_lang, tgt)
input_ids[idx, :len(inp_ids)] = inp_ids
input_mask[idx, :len(inp_ids)] = 1
target_ids[idx, :len(tgt_ids)] = tgt_ids
target_mask[idx, :len(tgt_ids)] = 1
train_data = TensorDataset(torch.LongTensor(input_ids).to(device),
torch.LongTensor(input_mask).to(device),
torch.LongTensor(target_ids).to(device),
torch.LongTensor(target_mask).to(device))
train_sampler = RandomSampler(train_data)
train_dataloader = DataLoader(train_data, sampler=train_sampler, batch_size=batch_size)
return input_lang, output_lang, train_dataloader