Deep Learning Note 35 读取机器翻译数据集

import os
import torch
from d2l import torch as d2l

d2l.DATA_HUB['fra-eng'] = (d2l.DATA_URL + 'fra-eng.zip',
                           '94646ad1522d915e7b0f9296181140edcf86a4f5')

def read_data_nmt():
    """载入翻译数据集"""
    data_dir = d2l.download_extract('fra-eng')
    with open(os.path.join(data_dir, 'fra.txt'), 'r',
              encoding='utf-8') as f:
        return f.read()

raw_text = read_data_nmt()
print(raw_text[:75])

# 几个预处理步骤
def preprocess_nmt(text):
    def no_space(char, prev_char):
        return char in set(',.!?') and prev_char != ' '

    # 用空格替换不间断空格
    # 用小写字母替换大写字母

    text = text.replace('\u202f', ' ').replace('\xa0', ' ').lower()

    # 在单词和标点符号之间插入空格
    out = [' ' + char if i > 0 and no_space(char, text[i - 1]) else char
           for i, char in enumerate(text)]

    return ''.join(out)

text = preprocess_nmt(raw_text)
print(text[:80])

# 词元化
def tokenize_nmt(text, num_examples=None):
    source, target = [], []
    for i, line in enumerate(text.split('\n')):
        if num_examples and i > num_examples:
            break
        parts = line.split('\t')
        if len(parts) == 2:
            source.append(parts[0].split(' '))
            target.append(parts[1].split(' '))
    return source, target

source, target = tokenize_nmt(text)
print(source[:6])
print(target[:6])

# 词汇表
src_vocab = d2l.Vocab(source, min_freq=2,
                      reserved_tokens=['', '', ''])
print(len(src_vocab))

# 加载数据集
def truncate_pad(line, num_steps, padding_token):
    """截断或填充文本序列"""
    if len(line) > num_steps:
        return line[:num_steps]  # 截断
    return line + [padding_token] * (num_steps - len(line))

print(truncate_pad(src_vocab[source[0]], 10, src_vocab['']))

def build_array_nmt(lines, vocab, num_steps):
    """将机器翻译的文本序列转换成小批量"""
    lines = [vocab[l] for l in lines]
    lines = [l + [vocab['']] for l in lines]
    array = torch.tensor([truncate_pad(l, num_steps, vocab['']) for l in lines])
    valid_len = (array != vocab['']).type(torch.int32).sum(1)
    # 计算有效序列长度
    # 给定一个数组和一个字典，其中字典包含一个''键，其对应的值用于表示填充符号。
    # 函数作用是计算数组中每个元素不等于''符号的连续元素的数量，即有效序列的长度。
    return array, valid_len

# 训练模型
def load_data_nmt(batch_size, num_steps, num_examples=600):
    """返回翻译数据集的迭代器和词表"""
    text = preprocess_nmt(read_data_nmt())
    source, target = tokenize_nmt(text, num_examples)
    src_vocab = d2l.Vocab(source, min_freq=2,
                          reserved_tokens=['', '', ''])
    tgt_vocab = d2l.Vocab(target, min_freq=2,
                          reserved_tokens=['', '', ''])
    src_array, src_valid_len = build_array_nmt(source, src_vocab, num_steps)
    tgt_array, tgt_valid_len = build_array_nmt(target, tgt_vocab, num_steps)
    data_arrays = (src_array, src_valid_len, tgt_array, tgt_valid_len)
    data_iter = d2l.load_array(data_arrays, batch_size)
    return data_iter, src_vocab, tgt_vocab