TextCNN处理多标签文本分类任务

思路：

设置一个列表，对应标签位置的值置为1，其他位置的值置为0

TextCNN最后一层需要加上一个sigmoid层，把值锁定在0-1之间

损失函数采用二元交叉熵损失函数

一般采用macro平均这一衡量指标

然后就是数据处理的时候需要变化，最主要的就是标签形式有所改变已经不是一个单一的标量了

代码实现如下：

models/TextCNN.py

 

# models/TextCNN.py
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np

class Config(object):

    """配置参数"""
    def __init__(self, dataset, embedding):
        self.model_name = 'TextCNN'
        self.train_path = dataset + '/data/train.txt'                                # 训练集
        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
        self.test_path = dataset + '/data/test.txt'                                  # 测试集
        self.class_list = ["动力", "价格", "内饰", "配置", "安全性", "外观", "操控", "油耗", "空间", "舒适性"]  # 类别名单
        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
        self.log_path = dataset + '/log/' + self.model_name
        self.embedding_pretrained = torch.tensor(
            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
            if embedding != 'random' else None                                       # 预训练词向量
        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')   # 设备

        self.dropout = 0.5                                              # 随机失活
        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
        self.num_classes = len(self.class_list)                         # 类别数
        self.n_vocab = 0                                                # 词表大小，在运行时赋值
        self.num_epochs = 20                                            # epoch数
        self.batch_size = 8                                            # mini-batch大小
        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
        self.learning_rate = 0.5*1e-3                                       # 学习率
        self.embed = self.embedding_pretrained.size(1)\
            if self.embedding_pretrained is not None else 300           # 字向量维度
        self.filter_sizes = (2, 3, 4)                                   # 卷积核尺寸
        self.num_filters = 256                                          # 卷积核数量(channels数)

class Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.convs = nn.ModuleList(
            [nn.Conv2d(1, config.num_filters, (k, config.embed)) for k in config.filter_sizes])
        self.dropout = nn.Dropout(config.dropout)
        self.fc = nn.Linear(config.num_filters * len(config.filter_sizes), config.num_classes)

    def conv_and_pool(self, x, conv):
        x = F.relu(conv(x)).squeeze(3)
        x = F.max_pool1d(x, x.size(2)).squeeze(2)
        return x

    def forward(self, x):
        out = self.embedding(x[0])
        out = out.unsqueeze(1)
        out = torch.cat([self.conv_and_pool(out, conv) for conv in self.convs], 1)
        out = self.dropout(out)
        out = self.fc(out)
        out = torch.sigmoid(out)  # 使用sigmoid激活函数用于多标签分类
        return out

utils.py

# utils.py
import os
import torch
import numpy as np
import pickle as pkl
from tqdm import tqdm
import time
from datetime import timedelta

MAX_VOCAB_SIZE = 10000  # 词表长度限制
UNK, PAD = '<UNK>', '<PAD>'

def build_vocab(file_path, tokenizer, max_size, min_freq):
    vocab_dic = {}
    with open(file_path, 'r', encoding='UTF-8') as f:
        for line in tqdm(f):
            lin = line.strip()
            if not lin:
                continue
            content = lin.split('\t')[0]
            for word in tokenizer(content):
                vocab_dic[word] = vocab_dic.get(word, 0) + 1
        vocab_list = sorted([_ for _ in vocab_dic.items() if _[1] >= min_freq], key=lambda x: x[1], reverse=True)[:max_size]
        vocab_dic = {word_count[0]: idx for idx, word_count in enumerate(vocab_list)}
        vocab_dic.update({UNK: len(vocab_dic), PAD: len(vocab_dic) + 1})
    return vocab_dic

def build_dataset(config, ues_word):
    if ues_word:
        tokenizer = lambda x: x.split(' ')
    else:
        tokenizer = lambda x: [y for y in x]

    def load_dataset(path, pad_size=32):
        contents = []
        with open(path, 'r', encoding='UTF-8') as f:
            for line in tqdm(f):
                lin = line.strip()
                if not lin:
                    continue
                parts = lin.split('\t')
                content = parts[0]
                labels = parts[1:]
                words_line = []
                token = tokenizer(content)
                seq_len = len(token)
                if pad_size:
                    if len(token) < pad_size:
                        token.extend([PAD] * (pad_size - len(token)))
                    else:
                        token = token[:pad_size]
                        seq_len = pad_size
                for word in token:
                    words_line.append(vocab.get(word, vocab.get(UNK)))
                label_vector = [0] * len(config.class_list)
                for label in labels:
                    label_name = label.split('#')[0]  # 提取标签名称
                    label_index = config.class_list.index(label_name)  # 查找标签索引
                    label_vector[label_index] = 1
                contents.append((words_line, label_vector, seq_len))
        return contents

    if os.path.exists(config.vocab_path):
        vocab = pkl.load(open(config.vocab_path, 'rb'))
    else:
        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(vocab, open(config.vocab_path, 'wb'))
    print(f"Vocab size: {len(vocab)}")

    train = load_dataset(config.train_path, config.pad_size)
    dev = load_dataset(config.dev_path, config.pad_size)
    test = load_dataset(config.test_path, config.pad_size)
    return vocab, train, dev, test

class DatasetIterater(object):
    def __init__(self, batches, batch_size, device):
        self.batch_size = batch_size
        self.batches = batches
        self.n_batches = len(batches) // batch_size
        self.residue = False
        if len(batches) % self.n_batches != 0:
            self.residue = True
        self.index = 0
        self.device = device

    def _to_tensor(self, datas):
        x = torch.LongTensor([_[0] for _ in datas]).to(self.device)
        y = torch.FloatTensor([_[1] for _ in datas]).to(self.device)
        seq_len = torch.LongTensor([_[2] for _ in datas]).to(self.device)
        return (x, seq_len), y

    def __next__(self):
        if self.residue and self.index == self.n_batches:
            batches = self.batches[self.index * self.batch_size: len(self.batches)]
            self.index += 1
            batches = self._to_tensor(batches)
            return batches
        elif self.index >= self.n_batches:
            self.index = 0
            raise StopIteration
        else:
            batches = self.batches[self.index * self.batch_size: (self.index + 1) * self.batch_size]
            self.index += 1
            batches = self._to_tensor(batches)
            return batches

    def __iter__(self):
        return self

    def __len__(self):
        if self.residue:
            return self.n_batches + 1
        else:
            return self.n_batches

def build_iterator(dataset, config):
    iter = DatasetIterater(dataset, config.batch_size, config.device)
    return iter

def get_time_dif(start_time):
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))

if __name__ == "__main__":
    '''提取预训练词向量'''
    train_dir = "./CarData/data/train.txt"
    vocab_dir = "./CarData/data/vocab.pkl"
    pretrain_dir = "./CarData/data/sgns.sogou.char"
    emb_dim = 300
    filename_trimmed_dir = "./CarData/data/embedding_CarData.npz"
    if os.path.exists(vocab_dir):
        word_to_id = pkl.load(open(vocab_dir, 'rb'))
    else:
        tokenizer = lambda x: x.split(' ')
        word_to_id = build_vocab(train_dir, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
        pkl.dump(word_to_id, open(vocab_dir, 'wb'))

    embeddings = np.random.rand(len(word_to_id), emb_dim)
    with open(pretrain_dir, "r", encoding='UTF-8') as f:
        for i, line in enumerate(f.readlines()):
            if i == 0:  # 若第一行是标题，则跳过
                continue
            lin = line.strip().split(" ")
            if lin[0] in word_to_id:
                idx = word_to_id[lin[0]]
                emb = [float(x) for x in lin[1:301]]
                embeddings[idx] = np.asarray(emb, dtype='float32')
    np.savez_compressed(filename_trimmed_dir, embeddings=embeddings)

train_eval.py

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from sklearn import metrics
import time
from utils import get_time_dif
from tensorboardX import SummaryWriter

def init_network(model, method='xavier', exclude='embedding', seed=123):
    for name, w in model.named_parameters():
        if exclude not in name:
            if 'weight' in name:
                if method == 'xavier':
                    nn.init.xavier_normal_(w)
                elif method == 'kaiming':
                    nn.init.kaiming_normal_(w)
                else:
                    nn.init.normal_(w)
            elif 'bias' in name:
                nn.init.constant_(w, 0)

def train(config, model, train_iter, dev_iter, test_iter):
    start_time = time.time()
    model.train()
    optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate)
    total_batch = 0
    dev_best_loss = float('inf')
    last_improve = 0
    flag = False
    writer = SummaryWriter(log_dir=config.log_path + '/' + time.strftime('%m-%d_%H.%M', time.localtime()))
    criterion = nn.BCELoss()

    for epoch in range(config.num_epochs):
        print('Epoch [{}/{}]'.format(epoch + 1, config.num_epochs))
        for i, (trains, labels) in enumerate(train_iter):
            outputs = model(trains)
            model.zero_grad()
            loss = criterion(outputs, labels.float())
            loss.backward()
            optimizer.step()
            if total_batch % 100 == 0:
                true = labels.data.cpu().numpy()
                predic = torch.round(outputs).detach().cpu().numpy()

                # 计算训练集的宏平均准确率
                per_label_acc = []
                for j in range(config.num_classes):
                    per_label_acc.append(metrics.accuracy_score(true[:, j], predic[:, j]))
                train_acc = np.mean(per_label_acc)

                dev_acc, dev_loss = evaluate(config, model, dev_iter)
                if dev_loss < dev_best_loss:
                    dev_best_loss = dev_loss
                    torch.save(model.state_dict(), config.save_path)
                    improve = '*'
                    last_improve = total_batch
                else:
                    improve = ''
                time_dif = get_time_dif(start_time)
                msg = 'Iter: {0:>6},  Train Loss: {1:>5.2},  Train Acc: {2:>6.2%},  Val Loss: {3:>5.2},  Val Acc: {4:>6.2%},  Time: {5} {6}'
                print(msg.format(total_batch, loss.item(), train_acc, dev_loss, dev_acc, time_dif, improve))
                writer.add_scalar("loss/train", loss.item(), total_batch)
                writer.add_scalar("loss/dev", dev_loss, total_batch)
                writer.add_scalar("acc/train", train_acc, total_batch)
                writer.add_scalar("acc/dev", dev_acc, total_batch)
                model.train()
            total_batch += 1
            if total_batch - last_improve > config.require_improvement:
                print("No optimization for a long time, auto-stopping...")
                flag = True
                break
        if flag:
            break
    writer.close()
    test(config, model, test_iter)

def evaluate(config, model, data_iter, test=False):
    model.eval()
    loss_total = 0
    predict_all = np.array([], dtype=int).reshape(0, config.num_classes)
    labels_all = np.array([], dtype=int).reshape(0, config.num_classes)
    criterion = nn.BCELoss()

    with torch.no_grad():
        for texts, labels in data_iter:
            outputs = model(texts)
            loss = criterion(outputs, labels.float())
            loss_total += loss
            labels = labels.data.cpu().numpy()
            predic = torch.round(outputs).detach().cpu().numpy()
            labels_all = np.concatenate((labels_all, labels), axis=0)
            predict_all = np.concatenate((predict_all, predic), axis=0)

    # 计算宏平均准确率
    per_label_acc = []
    for i in range(config.num_classes):
        per_label_acc.append(metrics.accuracy_score(labels_all[:, i], predict_all[:, i]))
    acc = np.mean(per_label_acc)

    if test:
        precision = metrics.precision_score(labels_all, predict_all, average='macro')
        recall = metrics.recall_score(labels_all, predict_all, average='macro')
        f1 = metrics.f1_score(labels_all, predict_all, average='macro')
        report = metrics.classification_report(labels_all, predict_all, target_names=config.class_list, digits=4)
        confusion = metrics.multilabel_confusion_matrix(labels_all, predict_all)
        return acc, loss_total / len(data_iter), report, confusion, precision, recall, f1
    return acc, loss_total / len(data_iter)

def test(config, model, test_iter):
    model.load_state_dict(torch.load(config.save_path))
    model.eval()
    start_time = time.time()
    test_acc, test_loss, test_report, test_confusion, precision, recall, f1 = evaluate(config, model, test_iter, test=True)
    msg = 'Test Loss: {0:>5.2},  Test Acc: {1:>6.2%}'
    print(msg.format(test_loss, test_acc))
    print("Precision, Recall and F1-Score...")
    print(test_report)
    print(f"Precision: {precision:.4f}, Recall: {recall:.4f}, F1-Score: {f1:.4f}")
    print("Confusion Matrix...")
    print(test_confusion)
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)

run.py

# run.py
import time
import torch
import numpy as np
from train_eval import train, init_network
from importlib import import_module
import argparse

parser = argparse.ArgumentParser(description='Chinese-Multi-label-Text-Classification')
parser.add_argument('--model', type=str, required=True, help='choose a model: TextCNN, TextRNN, FastText, TextRCNN, TextRNN_Att, DPCNN, Transformer')
parser.add_argument('--embedding', default='pre_trained', type=str, help='random or pre_trained')
parser.add_argument('--word', default=False, type=bool, help='True for word, False for char')
args = parser.parse_args()

if __name__ == '__main__':
    dataset = 'CarData'  # 替换为新数据集的名称

    embedding = 'embedding_CarData.npz'
    if args.embedding == 'random':
        embedding = 'random'
    model_name = args.model
    from utils import build_dataset, build_iterator, get_time_dif

    x = import_module('models.' + model_name)
    config = x.Config(dataset, embedding)
    np.random.seed(1)
    torch.manual_seed(1)
    torch.cuda.manual_seed_all(1)
    torch.backends.cudnn.deterministic = True

    start_time = time.time()
    print("Loading data...")
    vocab, train_data, dev_data, test_data = build_dataset(config, True)
    train_iter = build_iterator(train_data, config)
    dev_iter = build_iterator(dev_data, config)
    test_iter = build_iterator(test_data, config)
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)

    config.n_vocab = len(vocab)
    model = x.Model(config).to(config.device)
    if model_name != 'Transformer':
        init_network(model)
    print(model.parameters)
    train(config, model, train_iter, dev_iter, test_iter)