零基础入门NLP - 新闻文本分类(五、基于深度学习的文本分类2 - 2 - TextCNN)

TextCNN利用CNN（卷积神经网络）进行文本特征抽取，不同大小的卷积核分别抽取n-gram特征，卷积计算出的特征图经过MaxPooling保留最大的特征值，然后将拼接成一个向量作为文本的表示。

基于TextCNN原始论文的设定，分别采用了100个大小为2,3,4的卷积核，最后得到的文本向量大小为100*3=300维。

import logging
import random

import numpy as np
import torch

logging.basicConfig(level=logging.INFO, format='%(asctime)-15s %(levelname)s: %(message)s')

# set seed 
seed = 666
random.seed(seed)
np.random.seed(seed)
torch.cuda.manual_seed(seed)
torch.manual_seed(seed)

# set cuda
gpu = 0
use_cuda = gpu >= 0 and torch.cuda.is_available()
if use_cuda:
    torch.cuda.set_device(gpu)
    device = torch.device("cuda", gpu)
else:
    device = torch.device("cpu")
logging.info("Use cuda: %s, gpu id: %d.", use_cuda, gpu)

# split data to 10 fold
fold_num = 10
data_file = '../data/train_set.csv'
import pandas as pd


def all_data2fold(fold_num, num=10000):
    fold_data = []
    f = pd.read_csv(data_file, sep='\t', encoding='UTF-8')
    texts = f['text'].tolist()[:num]
    labels = f['label'].tolist()[:num]

    total = len(labels)

    index = list(range(total))
    np.random.shuffle(index)

    all_texts = []
    all_labels = []
    for i in index:
        all_texts.append(texts[i])
        all_labels.append(labels[i])

    label2id = {
   }
    for i in range(total):
        label = str(all_labels[i])
        if label not in label2id:
            label2id[label] = [i]
        else:
            label2id[label].append(i)

    all_index = [[] for _ in range(fold_num)]
    for label, data in label2id.items():
        # print(label, len(data))
        batch_size = int(len(data) / fold_num)
        other = len(data) - batch_size * fold_num
        for i in range(fold_num):
            cur_batch_size = batch_size + 1 if i < other else batch_size
            # print(cur_batch_size)
            batch_data = [data[i * batch_size + b] for b in range(cur_batch_size)]
            all_index[i].extend(batch_data)

    batch_size = int(total / fold_num)
    other_texts = []
    other_labels = []
    other_num = 0
    start = 0
    for fold in range(fold_num):
        num = len(all_index[fold])
        texts = [all_texts[i] for i in all_index[fold]]
        labels = [all_labels[i] for i in all_index[fold]]

        if num > batch_size:
            fold_texts = texts[:batch_size]
            other_texts.extend(texts[batch_size:])
            fold_labels = labels[:batch_size]
            other_labels.extend(labels[batch_size:])
            other_num += num - batch_size
        elif num < batch_size:
            end = start + batch_size - num
            fold_texts = texts + other_texts[start: end]
            fold_labels = labels + other_labels[start: end]
            start = end
        else:
            fold_texts = texts
            fold_labels = labels

        assert batch_size == len(fold_labels)

        # shuffle
        index = list(range(batch_size))
        np.random.shuffle(index)

        shuffle_fold_texts = []
        shuffle_fold_labels = []
        for i in index:
            shuffle_fold_texts.append(fold_texts[i])
            shuffle_fold_labels.append(fold_labels[i])

        data = {
   'label': shuffle_fold_labels, 'text': shuffle_fold_texts}
        fold_data.append(data)

    logging.info("Fold lens %s", str([len(data['label']) for data in fold_data]))

    return fold_data


fold_data = all_data2fold(10)

# build train, dev, test data
fold_id = 9

# dev
dev_data = fold_data[fold_id]

# train
train_texts = []
train_labels = []
for i in range(0, fold_id):
    data = fold_data[i]
    train_texts.extend(data['text'])
    train_labels.extend(data['label'])

train_data = {
   'label': train_labels, 'text': train_texts}

# test
test_data_file = '../data/test_a.csv'
f = pd.read_csv(test_data_file, sep='\t', encoding='UTF-8')
texts = f['text'].tolist()
test_data = {
   'label': [0] * len(texts), 'text': texts}

# build vocab
from collections import Counter
from transformers import BasicTokenizer

basic_tokenizer = BasicTokenizer()


class Vocab():
    def __init__(self, train_data):
        self.min_count = 5
        self.pad = 0
        self.unk = 1
        self._id2word = ['[PAD]', '[UNK]']
        self._id2extword = ['[PAD]', '[UNK]']

        self._id2label = []
        self.target_names = []

        self.build_vocab(train_data)

        reverse = lambda x: dict(zip(x, range(len(x))))
        self._word2id = reverse(self._id2word)
        self._label2id = reverse(self._id2label)

        logging.info("Build vocab: words %d, labels %d." % (self.word_size, self.label_size))

    def build_vocab(self, data):
        self.word_counter = Counter()

        for text in data['text']:
            words = text.split()
            for word in words:
                self.word_counter[word] += 1

        for word, count in self.word_counter.most_common():
            if count >= self.min_count:
                self._id2word.append(word)

        label2name = {
   0