Datawhale AI 夏令营 第二期 NLP方向 Task2 学习笔记

上期task1链接:

http://t.csdnimg.cn/VJhcX

概要:

本次Task2采用的是Seq2Seq模型,代码实现过程主要分为配置环境,数据预处理,模型训练,翻译质量评价

一.配置环境

使用以下指令安装所需库

!pip install torchtext
!pip install jieba
!pip install sacrebleu

安装spacy
https://github.com/explosion/spacy-models/releases，下载压缩包后，上传到dataset目录，

随后使用

!pip install -U pip setuptools wheel -i https://pypi.tuna.tsinghua.edu.cn/simple
!pip install -U 'spacy[cuda12x]' -i https://pypi.tuna.tsinghua.edu.cn/simple
!pip install ./dataset/en_core_web_trf-3.7.3-py3-none-any.whl

随后在代码中导入库

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.nn.utils import clip_grad_norm_
from torchtext.data.metrics import bleu_score
from torch.utils.data import Dataset, DataLoader
from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator
from typing import List, Tuple
import jieba
import random
from torch.nn.utils.rnn import pad_sequence
import sacrebleu
import time
import math

二.数据预处理

1.定义提词器

# 定义tokenizer
en_tokenizer = get_tokenizer('spacy', language='en_core_web_trf')
zh_tokenizer = lambda x: list(jieba.cut(x))  # 使用jieba分词

2.读取数据函数

# 读取数据函数
def read_data(file_path: str) -> List[str]:
    with open(file_path, 'r', encoding='utf-8') as f:
        return [line.strip() for line in f]

3.构建词汇表

# 构建词汇表
def build_vocab(data: List[Tuple[List[str], List[str]]]):
    en_vocab = build_vocab_from_iterator(
        (en for en, _ in data),
        specials=['<unk>', '<pad>', '<bos>', '<eos>']
    )
    zh_vocab = build_vocab_from_iterator(
        (zh for _, zh in data),
        specials=['<unk>', '<pad>', '<bos>', '<eos>']
    )
    en_vocab.set_default_index(en_vocab['<unk>'])
    zh_vocab.set_default_index(zh_vocab['<unk>'])
    return en_vocab, zh_vocab

 4.翻译数据集

class TranslationDataset(Dataset):
    def __init__(self, data: List[Tuple[List[str], List[str]]], en_vocab, zh_vocab):
        self.data = data
        self.en_vocab = en_vocab
        self.zh_vocab = zh_vocab
 
    def __len__(self):
        return len(self.data)
 
    def __getitem__(self, idx):
        en, zh = self.data[idx]
        en_indices = [self.en_vocab['<bos>']] + [self.en_vocab[token] for token in en] + [self.en_vocab['<eos>']]
        zh_indices = [self.zh_vocab['<bos>']] + [self.zh_vocab[token] for token in zh] + [self.zh_vocab['<eos>']]
        return en_indices, zh_indices

 5.检测是否为空

def collate_fn(batch):
    en_batch, zh_batch = [], []
    for en_item, zh_item in batch:
        if en_item and zh_item:  # 确保两个序列都不为空
            # print("都不为空")
            en_batch.append(torch.tensor(en_item))
            zh_batch.append(torch.tensor(zh_item))
        else:
            print("存在为空")
    if not en_batch or not zh_batch:  # 如果整个批次为空，返回空张量
        return torch.tensor([]), torch.tensor([])
    
    # src_sequences = [item[0] for item in batch]
    # trg_sequences = [item[1] for item in batch]
    
    en_batch = nn.utils.rnn.pad_sequence(en_batch, batch_first=True, padding_value=en_vocab['<pad>'])
    zh_batch = nn.utils.rnn.pad_sequence(zh_batch, batch_first=True, padding_value=zh_vocab['<pad>'])
 
    # en_batch = pad_sequence(en_batch, batch_first=True, padding_value=en_vocab['<pad>'])
    # zh_batch = pad_sequence(zh_batch, batch_first=True, padding_value=zh_vocab['<pad>'])
    
    return en_batch, zh_batch

6.数据加载函数

# 数据加载函数
def load_data(train_path: str, dev_en_path: str, dev_zh_path: str, test_en_path: str):
    # 读取训练数据
    train_data = read_data(train_path)
    train_en, train_zh = zip(*(line.split('\t') for line in train_data))
    
    # 读取开发集和测试集
    dev_en = read_data(dev_en_path)
    dev_zh = read_data(dev_zh_path)
    test_en = read_data(test_en_path)
 
    # 预处理数据
    train_processed = preprocess_data(train_en, train_zh)
    dev_processed = preprocess_data(dev_en, dev_zh)
    test_processed = [(en_tokenizer(en.lower())[:MAX_LENGTH], []) for en in test_en if en.strip()]
 
    # 构建词汇表
    global en_vocab, zh_vocab
    en_vocab, zh_vocab = build_vocab(train_processed)
 
    # 创建数据集
    train_dataset = TranslationDataset(train_processed, en_vocab, zh_vocab)
    dev_dataset = TranslationDataset(dev_processed, en_vocab, zh_vocab)
    test_dataset = TranslationDataset(test_processed, en_vocab, zh_vocab)
    
    from torch.utils.data import Subset
 

 注意这里的N是你要训练的数据集大小,

假如你要训练所有数据集

请注释掉  
    N = 20000
    indices = list(range(N))
    train_dataset = Subset(train_dataset, indices)

 # 假设你有10000个样本，你只想用前1000个样本进行测试
    #indices = list(range(N))
    #train_dataset = Subset(train_dataset, indices)
    
     #设置样本数量为5000
    N = 20000
    # 创建一个包含前5000个样本的索引列表
    indices = list(range(N))
    # 使用这些索引来创建一个新的数据集，它只包含前5000个样本
    train_dataset = Subset(train_dataset, indices)
 
    # 创建数据加载器
    train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_fn, drop_last=True)
    dev_loader = DataLoader(dev_dataset, batch_size=BATCH_SIZE, collate_fn=collate_fn, drop_last=True)
    test_loader = DataLoader(test_dataset, batch_size=1, collate_fn=collate_fn, drop_last=True)
 
    return train_loader, dev_loader, test_loader, en_vocab, zh_vocab

三.模型构建 

1.编码器

class Encoder(nn.Module):
    def __init__(self, input_dim, emb_dim, hid_dim, n_layers, dropout):
        super().__init__()
        self.hid_dim = hid_dim
        self.n_layers = n_layers
        
        self.embedding = nn.Embedding(input_dim, emb_dim)
        self.gru = nn.GRU(emb_dim, hid_dim, n_layers, dropout=dropout, batch_first=True)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, src):
        # src = [batch size, src len]
        embedded = self.dropout(self.embedding(src))
        # embedded = [batch size, src len, emb dim]
        
        outputs, hidden = self.gru(embedded)
        # outputs = [batch size, src len, hid dim * n directions]
        # hidden = [n layers * n directions, batch size, hid dim]
        
        return outputs, hidden

2.注意力机制

Attention机制允许模型在解码时“关注”源句子中的不同部分。这使得翻译更加准确，尤其是对于长句子。

class Attention(nn.Module):
    def __init__(self, hid_dim):
        super().__init__()
        self.attn = nn.Linear(hid_dim * 2, hid_dim)
        self.v = nn.Linear(hid_dim, 1, bias=False)
        
    def forward(self, hidden, encoder_outputs):
        # hidden = [1, batch size, hid dim]
        # encoder_outputs = [batch size, src len, hid dim]
        
        batch_size = encoder_outputs.shape[0]
        src_len = encoder_outputs.shape[1]
        
        hidden = hidden.repeat(src_len, 1, 1).transpose(0, 1)
        # hidden = [batch size, src len, hid dim]
        
        energy = torch.tanh(self.attn(torch.cat((hidden, encoder_outputs), dim=2)))
        # energy = [batch size, src len, hid dim]
        
        attention = self.v(energy).squeeze(2)
        # attention = [batch size, src len]
        
        return F.softmax(attention, dim=1)

 3.解码器

class Decoder(nn.Module):
    def __init__(self, output_dim, emb_dim, hid_dim, n_layers, dropout, attention):
        super().__init__()
        self.output_dim = output_dim
        self.hid_dim = hid_dim
        self.n_layers = n_layers
        self.attention = attention
        
        self.embedding = nn.Embedding(output_dim, emb_dim)
        self.gru = nn.GRU(hid_dim + emb_dim, hid_dim, n_layers, dropout=dropout, batch_first=True)
        self.fc_out = nn.Linear(hid_dim * 2 + emb_dim, output_dim)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, input, hidden, encoder_outputs):
        # input = [batch size, 1]
        # hidden = [n layers, batch size, hid dim]
        # encoder_outputs = [batch size, src len, hid dim]
        
        input = input.unsqueeze(1)
        embedded = self.dropout(self.embedding(input))
        # embedded = [batch size, 1, emb dim]
        
        a = self.attention(hidden[-1:], encoder_outputs)
        # a = [batch size, src len]
        
        a = a.unsqueeze(1)
        # a = [batch size, 1, src len]
        
        weighted = torch.bmm(a, encoder_outputs)
        # weighted = [batch size, 1, hid dim]
        
        rnn_input = torch.cat((embedded, weighted), dim=2)
        # rnn_input = [batch size, 1, emb dim + hid dim]
        
        output, hidden = self.gru(rnn_input, hidden)
        # output = [batch size, 1, hid dim]
        # hidden = [n layers, batch size, hid dim]
        
        embedded = embedded.squeeze(1)
        output = output.squeeze(1)
        weighted = weighted.squeeze(1)
        
        prediction = self.fc_out(torch.cat((output, weighted, embedded), dim=1))
        # prediction = [batch size, output dim]
        
        return prediction, hidden

4.Seq2Seq模型

 
 
class Seq2Seq(nn.Module):
    def __init__(self, encoder, decoder, device):
        super().__init__()
        self.encoder = encoder
        self.decoder = decoder
        self.device = device
        
    def forward(self, src, trg, teacher_forcing_ratio=0.5):
        # src = [batch size, src len]
        # trg = [batch size, trg len]
        
        batch_size = src.shape[0]
        trg_len = trg.shape[1]
        trg_vocab_size = self.decoder.output_dim
        
        outputs = torch.zeros(batch_size, trg_len, trg_vocab_size).to(self.device)
        encoder_outputs, hidden = self.encoder(src)
        
        input = trg[:, 0]
        
        for t in range(1, trg_len):
            output, hidden = self.decoder(input, hidden, encoder_outputs)
            outputs[:, t] = output
            teacher_force = random.random() < teacher_forcing_ratio
            top1 = output.argmax(1)
            input = trg[:, t] if teacher_force else top1
        
        return outputs

5.初始化模型函数 

# 初始化模型
def initialize_model(input_dim, output_dim, emb_dim, hid_dim, n_layers, dropout, device):
    attn = Attention(hid_dim)
    enc = Encoder(input_dim, emb_dim, hid_dim, n_layers, dropout)
    dec = Decoder(output_dim, emb_dim, hid_dim, n_layers, dropout, attn)
    model = Seq2Seq(enc, dec, device).to(device)
    return model

四.训练 

 1.定义优化器

# 定义优化器
def initialize_optimizer(model, learning_rate=0.001):
    return optim.Adam(model.parameters(), lr=learning_rate)

2.运行时间计算函数

# 运行时间
def epoch_time(start_time, end_time):
    elapsed_time = end_time - start_time
    elapsed_mins = int(elapsed_time / 60)
    elapsed_secs = int(elapsed_time - (elapsed_mins * 60))
    return elapsed_mins, elapsed_secs

 3.训练函数

def train(model, iterator, optimizer, criterion, clip):
    model.train()
    epoch_loss = 0
    
    for i, batch in enumerate(iterator):
        #print(f"Training batch {i}")
        src, trg = batch
        #print(f"Source shape before: {src.shape}, Target shape before: {trg.shape}")
        if src.numel() == 0 or trg.numel() == 0:
            #print("Empty batch detected, skipping...")
            continue  # 跳过空的批次
        
        src, trg = src.to(DEVICE), trg.to(DEVICE)
        
        optimizer.zero_grad()
        output = model(src, trg)
        
        output_dim = output.shape[-1]
        output = output[:, 1:].contiguous().view(-1, output_dim)
        trg = trg[:, 1:].contiguous().view(-1)
        
        loss = criterion(output, trg)
        loss.backward()
        
        clip_grad_norm_(model.parameters(), clip)
        optimizer.step()
        
        epoch_loss += loss.item()
 
    print(f"Average loss for this epoch: {epoch_loss / len(iterator)}")
    return epoch_loss / len(iterator)

4.评估函数

def evaluate(model, iterator, criterion):
    model.eval()
    epoch_loss = 0
    with torch.no_grad():
        for i, batch in enumerate(iterator):
            #print(f"Evaluating batch {i}")
            src, trg = batch
            if src.numel() == 0 or trg.numel() == 0:
                continue  # 跳过空批次
            
            src, trg = src.to(DEVICE), trg.to(DEVICE)
            
            output = model(src, trg, 0)  # 关闭 teacher forcing
            
            output_dim = output.shape[-1]
            output = output[:, 1:].contiguous().view(-1, output_dim)
            trg = trg[:, 1:].contiguous().view(-1)
            
            loss = criterion(output, trg)
            epoch_loss += loss.item()
        
    return epoch_loss / len(iterator)

5.翻译函数 

# 翻译函数
def translate_sentence(sentence, src_vocab, trg_vocab, model, device, max_length=50):
    model.eval()
    #print(sentence)        # 打印sentence的内容
    if isinstance(sentence, str):
        #tokens = [token.lower() for token in en_tokenizer(sentence)]
        tokens = [token for token in en_tokenizer(sentence)]
    else:
        #tokens = [token.lower() for token in sentence]
        tokens = [str(token) for token in sentence]
        
    tokens = ['<bos>'] + tokens + ['<eos>']
    src_indexes = [src_vocab[token] for token in tokens]
    src_tensor = torch.LongTensor(src_indexes).unsqueeze(0).to(device)
    
    with torch.no_grad():
        encoder_outputs, hidden = model.encoder(src_tensor)
    
    trg_indexes = [trg_vocab['<bos>']]
    for i in range(max_length):
        trg_tensor = torch.LongTensor([trg_indexes[-1]]).to(device)
        
        with torch.no_grad():
            output, hidden = model.decoder(trg_tensor, hidden, encoder_outputs)
        
        pred_token = output.argmax(1).item()
        trg_indexes.append(pred_token)
        
        if pred_token == trg_vocab['<eos>']:
            break
    
    trg_tokens = [trg_vocab.get_itos()[i] for i in trg_indexes]
    return trg_tokens[1:-1]  # 移除 <bos> 和 <eos>

 6.计算BLEU分数

def calculate_bleu(dev_loader, src_vocab, trg_vocab, model, device):
    translated_sentences = []
    references = []
 
    for src, trg in dev_loader:
        src = src.to(device)
        translation = translate_sentence(src, src_vocab, trg_vocab, model, device)
        # 将翻译结果转换为字符串
        translated_sentences.append(' '.join(translation))
 
        # 将每个参考翻译转换为字符串，并添加到references列表中
        for t in trg:
            ref_str = ' '.join([trg_vocab.get_itos()[idx] for idx in t.tolist() if idx not in [trg_vocab['<bos>'], trg_vocab['<eos>'], trg_vocab['<pad>']]])
            references.append(ref_str)
 
    print("translated_sentences",translated_sentences[:2])
    print("references:",references[6:8])
    # 使用`sacrebleu`计算BLEU分数
    # 注意：sacrebleu要求references是一个列表的列表，其中每个子列表包含一个或多个参考翻译
    bleu = sacrebleu.corpus_bleu(translated_sentences, [references])
 
    # 打印BLEU分数
    return bleu.score

7.主循环训练

# 主训练循环
def train_model(model, train_iterator, valid_iterator, optimizer, criterion, N_EPOCHS=10, CLIP=1):
    best_valid_loss = float('inf')
    
    for epoch in range(N_EPOCHS):
        start_time = time.time()
        
        #print(f"Starting Epoch {epoch + 1}")
        train_loss = train(model, train_iterator, optimizer, criterion, CLIP)
        valid_loss = evaluate(model, valid_iterator, criterion)
        
        end_time = time.time()
        epoch_mins, epoch_secs = epoch_time(start_time, end_time)
        
        if valid_loss < best_valid_loss:
            best_valid_loss = valid_loss
            torch.save(model.state_dict(), './model/best-model_test.pt')
        
        print(f'Epoch: {epoch+1:02} | Time: {epoch_mins}m {epoch_secs}s')
        print(f'\tTrain Loss: {train_loss:.3f} | Train PPL: {math.exp(train_loss):7.3f}')
        print(f'\t Val. Loss: {valid_loss:.3f} |  Val. PPL: {math.exp(valid_loss):7.3f}')

 8.训练的循环函数

# 主训练循环
def train_model(model, train_iterator, valid_iterator, optimizer, criterion, N_EPOCHS=10, CLIP=1):
    best_valid_loss = float('inf')
    
    for epoch in range(N_EPOCHS):
        start_time = time.time()
        
        #print(f"Starting Epoch {epoch + 1}")
        train_loss = train(model, train_iterator, optimizer, criterion, CLIP)
        valid_loss = evaluate(model, valid_iterator, criterion)
        
        end_time = time.time()
        epoch_mins, epoch_secs = epoch_time(start_time, end_time)
        
        if valid_loss < best_valid_loss:
            best_valid_loss = valid_loss
            torch.save(model.state_dict(), './model/best-model_test.pt')
        
        print(f'Epoch: {epoch+1:02} | Time: {epoch_mins}m {epoch_secs}s')
        print(f'\tTrain Loss: {train_loss:.3f} | Train PPL: {math.exp(train_loss):7.3f}')
        print(f'\t Val. Loss: {valid_loss:.3f} |  Val. PPL: {math.exp(valid_loss):7.3f}')

 9.主体1

统计并打印出数据集大小,包括分类后

# 定义常量
MAX_LENGTH = 100  # 最大句子长度
BATCH_SIZE = 32
DEVICE = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
N = 10000   # 采样训练集的数量
 
train_path = './dataset/train.txt'
dev_en_path = './dataset/dev_en.txt'
dev_zh_path = './dataset/dev_zh.txt'
test_en_path = './dataset/test_en.txt'
 
train_loader, dev_loader, test_loader, en_vocab, zh_vocab = load_data(
    train_path, dev_en_path, dev_zh_path, test_en_path
)
 
 
print(f"英语词汇表大小: {len(en_vocab)}")
print(f"中文词汇表大小: {len(zh_vocab)}")
print(f"训练集大小: {len(train_loader.dataset)}")
print(f"开发集大小: {len(dev_loader.dataset)}")
print(f"测试集大小: {len(test_loader.dataset)}")

10主函数

注意这里的N_EPOCHS是训练轮数,如果你要调整训练轮数就修改N_EPOCHS的大小

if __name__ == '__main__':
    
    N_EPOCHS = 3
    CLIP=1
    # 模型参数
    INPUT_DIM = len(en_vocab)
    OUTPUT_DIM = len(zh_vocab)
    EMB_DIM = 128
    HID_DIM = 256
    N_LAYERS = 2
    DROPOUT = 0.5
    
    # 初始化模型
    model = initialize_model(INPUT_DIM, OUTPUT_DIM, EMB_DIM, HID_DIM, N_LAYERS, DROPOUT, DEVICE)
    print(f'The model has {sum(p.numel() for p in model.parameters() if p.requires_grad):,} trainable parameters')
 
    # 定义损失函数
    criterion = nn.CrossEntropyLoss(ignore_index=zh_vocab['<pad>'])
    # 初始化优化器
    optimizer = initialize_optimizer(model)
 
    # 训练模型
    train_model(model, train_loader, dev_loader, optimizer, criterion, N_EPOCHS, CLIP)

 五.在开发集上评价

注意这里要自己手动建立一个文件名是model的文件夹

否则会中断报错

# 加载最佳模型
model.load_state_dict(torch.load('./model/best-model_test.pt'))
 
# 计算BLEU分数
bleu_score = calculate_bleu(dev_loader, en_vocab, zh_vocab, model, DEVICE)
print(f'BLEU score = {bleu_score*100:.2f}')

六.在测评集上进行翻译 

# 加载最佳模型
#model.load_state_dict(torch.load('../model/best-model_test.pt'))
#%%
with open('./results/submit_test.txt', 'w') as f:
    translated_sentences = []
    for batch in test_loader:  # 遍历所有数据
        src, _ = batch
        src = src.to(DEVICE)
        translated = translate_sentence(src[0], en_vocab, zh_vocab, model, DEVICE)  #翻译结果
        #print(translated)
        results = "".join(translated)
        f.write(results + '\n')  # 将结果写入文件

七.结论

本baseline由于模型泛化能力太弱,在验证集,测试集效果不好,得分也远低于task1的得分,

每跑一轮Val.PPL基本都在上升,最后结果基本都是重复某些文字翻译

 翻译结果如图

 

得分如图