N4中文分类

news2024/11/16 23:40:23

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊# 前言

前言

上周学习了英文文本分类，这次进行中文分类实战。

1. 数据读取

import pandas as pd
train_data = pd.read_csv('train.csv',sep='\t',header=None)
print(train_data.head())

读取包含训练数据的 CSV 文件。数据被存储在 train_data 中，并输出前几行进行检查。

2. 自定义数据迭代器

def coustom_data_iter(texts, labels):
    for x, y in zip(texts, labels):
        yield x, y

train_iter = coustom_data_iter(train_data[0].values[:], train_data[1].values[:])

定义了一个生成器函数 coustom_data_iter，用于迭代文本和标签。

3. 词汇表构建与文本处理

from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator
import jieba

tokenizer = jieba.lcut

def yield_tokens(data_iter):
    for text, _ in data_iter:
        yield tokenizer(text)

vocab = build_vocab_from_iterator(yield_tokens(train_iter), specials=["<unk>"])
vocab.set_default_index(vocab["<unk>"])

使用 Jieba 分词器对文本进行分词，然后从分词结果中构建词汇表 vocab。<unk> 表示未知词。

4. 数据加载与批处理

from torch.utils.data import DataLoader

def collate_batch(batch):
    label_list, text_list, offsets = [], [], [0]

    for (_text, _label) in batch:
        label_list.append(label_pipeline(_label))

        processed_text = torch.tensor(text_pipeline(_text), dtype=torch.int64)
        text_list.append(processed_text)

        offsets.append(processed_text.size(0))

    label_list = torch.tensor(label_list, dtype=torch.int64)
    text_list = torch.cat(text_list)
    offsets = torch.tensor(offsets[:-1]).cumsum(dim=0)

    return text_list.to(device), label_list.to(device), offsets.to(device)

dataloader = DataLoader(train_iter, batch_size=8, shuffle=False, collate_fn=collate_batch)

定义了一个批处理函数 collate_batch，用于将文本和标签转换成适合模型输入的格式，并创建数据加载器 dataloader。

5. 模型定义

class TextClassificationModel(nn.Module):

    def __init__(self, vocab_size, embed_dim, num_class):
        super(TextClassificationModel, self).__init__()

        self.embedding = nn.EmbeddingBag(vocab_size, embed_dim, sparse=False)
        self.fc = nn.Linear(embed_dim, num_class)
        self.init_weights()

    def init_weights(self):
        initrange = 0.5
        self.embedding.weight.data.uniform_(-initrange, initrange)
        self.fc.weight.data.uniform_(-initrange, initrange)
        self.fc.bias.data.zero_()

    def forward(self, text, offsets):
        embedded = self.embedding(text, offsets)
        return self.fc(embedded)

一个简单的文本分类模型，包含嵌入层 nn.EmbeddingBag 和全连接层 nn.Linear。

6. 训练与评估函数

def train(dataloader):
    model.train()
    total_acc, train_loss, total_count = 0, 0, 0
    log_interval = 50
    start_time = time.time()

    for idx, (text, label, offsets) in enumerate(dataloader):

        predicted_label = model(text, offsets)

        optimizer.zero_grad()
        loss = criterion(predicted_label, label)
        loss.backward()
        torch.nn.utils.clip_grad_norm_(model.parameters(), 0.1)
        optimizer.step()

        total_acc += (predicted_label.argmax(1) == label).sum().item()
        train_loss += loss.item()
        total_count += label.size(0)

        if idx % log_interval == 0 and idx > 0:
            elapsed = time.time() - start_time
            print('| epoch {:1d}|{:4d}/{:4d} batches'
                  '| train_acc {:4.3f} train_loss{:4.5f}'.format(epoch, idx, len(dataloader),
                                                                 total_acc / total_count, train_loss / total_count))
            total_acc, train_loss, total_count = 0, 0, 0
            start_time = time.time()

def evaluate(dataloader):
    model.eval()
    total_acc, train_loss, total_count = 0, 0, 0

    with torch.no_grad():
        for idx, (text, label, offsets) in enumerate(dataloader):
            predicted_label = model(text, offsets)

            loss = criterion(predicted_label, label)

            total_acc += (predicted_label.argmax(1) == label).sum().item()
            train_loss += loss.item()
            total_count += label.size(0)

    return total_acc / total_count, train_loss / total_count

这部分代码定义了训练函数 train 和评估函数 evaluate。训练函数执行模型的前向和后向传播以及参数更新，而评估函数用于在验证数据集上评估模型性能。

7. 数据集划分与训练

from torch.utils.data.dataset import random_split
from torchtext.data.functional import to_map_style_dataset

EPOCHS = 10
LR = 5
BATCH_SIZE = 64

criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=LR)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.1)
total_accu = None

train_iter = coustom_data_iter(train_data[0].values[:], train_data[1].values[:])
train_dataset = to_map_style_dataset(train_iter)

split_train_, split_valid_ = random_split(train_dataset,
                                          [int(len(train_dataset) * 0.8), int(len(train_dataset) * 0.2)])

train_dataloader = DataLoader(split_train_, batch_size=BATCH_SIZE,
                              shuffle=True, collate_fn=collate_batch)
valid_dataloader = DataLoader(split_valid_, batch_size=BATCH_SIZE,
                              shuffle=True, collate_fn=collate_batch)
for epoch in range(1, EPOCHS + 1):
    epoch_start_time = time.time()
    train(train_dataloader)
    val_acc, val_loss = evaluate(valid_dataloader)

    lr = optimizer.state_dict()['param_groups'][0]['lr']

    if total_accu is not None and total_accu > val_acc:
        scheduler.step()
    else:
        total_accu = val_acc
    print('-' * 69)
    print('|epoch {:1d} |time: {:4.2f}s | '
          'valid_acc{:4.3f} valid_loss{:4.3f} | lr{:4.6f}'.format(epoch,
                                                                  time.time() - epoch_start_time,
                                                                  val_acc, val_loss, lr))
    print('-' * 69)

将数据集分为训练集和验证集，并创建对应的数据加载器。然后进行模型训练和验证，使用调度器根据验证集的表现调整学习率。

8. 模型预测

def predict(text, text_pipeline):
    with torch.no_grad():
        text = torch.tensor(text_pipeline(text))
        output = model(text, torch.tensor([0]))
        return output.argmax(1).item()

ex_text_str = "还有双鸭山到淮阴的汽车票吗13号的"

model = model.to("cpu")
print("该文本的类别是：%s" % label_name[predict(ex_text_str, text_pipeline)])