第N3周：Pytorch文本分类入门

🍨 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 | 接辅导、项目定制

本周任务:

文本分类流程图：

需要的环境：

数据集：

TextClassificationModel模型介绍：

模型结构

模型结构图：

实现代码：

报错：

结果：

本周任务:

了解文本分类的基本流程
学习常用数据清洗方法
学习如何使用jieba实现英文分词
学习如何构建文本向量

文本分类流程图：

需要的环境：

pytorch
torchtext库
portalocker库
torchdata

数据集：

AG News数据集是一个用于文本分类任务的广泛使用的数据集，特别是在新闻文章分类领域。该数据集由4类新闻文章组成，每类包含不同主题的新闻，具体类别如下：

World（世界新闻）
Sports（体育新闻）
Business（商业新闻）
Sci/Tech（科学和技术新闻）

torchtext.datasets.AG_NEWS()类加载的数据集是一个列表，其中每个条目都是一个元组(label, text) ，包含以下两个元素:

text：一条新闻文章的文本内容。
label：新闻文章所属的类别(一个整数，从1到4，分别对应世界、科技、体育和商业)

TextClassificationModel模型介绍：

TextClassificationModel 是一个用于文本分类任务的简单神经网络模型，通常包括一个嵌入层和一个线性层。

首先对文本进行嵌入，然后对句子嵌入之后的结果进行均值聚合。

模型结构

嵌入层 (EmbeddingBag)：
- 该层用于将输入的文本数据转化为稠密的向量表示。EmbeddingBag 比 Embedding 更高效，因为它在计算时结合了嵌入和平均/加权操作，这对于处理变长的输入特别有用。
线性层 (Linear)：
- 该层接收来自嵌入层的输出，并将其映射到输出类别。输出类别的数量与分类任务中的类别数量一致。

模型结构图：

实现代码：

import  torch
import torch.nn as nn
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warningsimport torch
torch.utils.data.datapipes.utils.common.DILL_AVAILABLE = torch.utils._import_utils.dill_available()warnings.filterwarnings("ignore")
#win10
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")from torchtext.datasets import AG_NEWS
train_iter = AG_NEWS(split='train')#加载 AG News 数据集from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator#返回分词器
tokenizer = get_tokenizer('basic_english')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>"])#设置默认索引
print(vocab(['here', 'is', 'an', 'example']))text_pipeline = lambda x: vocab(tokenizer(x))
label_pipeline = lambda x: int(x) - 1
print(text_pipeline('here is an example '))
print(label_pipeline('10'))from torch.utils.data import DataLoaderdef collate_batch(batch):label_list,text_list,offsets =[],[],[0]for(_label,_text)in batch:#标签列表label_list.append(label_pipeline(_label))#文本列表processed_text =torch.tensor(text_pipeline(_text),dtype=torch.int64)text_list.append(processed_text)#偏移量，即语句的总词汇量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)#返回维度dim中输入元素的累计和return label_list.to(device),text_list.to(device),offsets.to(device)
#数据加载器
dataloader =DataLoader(train_iter,batch_size=8,shuffle   =False,collate_fn=collate_batch)from torch import nn
class TextClassificationModel(nn.Module):def __init__(self,vocab_size,embed_dim,num_class):super(TextClassificationModel,self).__init__()self.embedding =nn.EmbeddingBag(vocab_size,#词典大小embed_dim,#嵌入的维度sparse=False)#self.fc =nn.Linear(embed_dim,num_class)self.init_weights()def init_weights(self):initrange =0.5self.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)num_class = len(set([label for(label,text)in train_iter]))
vocab_size = len(vocab)
em_size = 64
model = TextClassificationModel(vocab_size,em_size,num_class).to(device)import time
def train(dataloader):model.train()  #切换为训练模式total_acc,train_loss,total_count =0,0,0log_interval =500start_time   =time.time()for idx,(label,text,offsets) in enumerate(dataloader):predicted_label =model(text,offsets)optimizer.zero_grad()#grad属性归零loss =criterion(predicted_label,label)#计算网络输出和真实值之间的差距，labe1为真实值loss.backward()#反向传播optimizer.step()  #每一步自动更新#记录acc与losstotal_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_timeprint('|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 =0,0,0start_time =time.time()def evaluate(dataloader):model.eval()  #切换为测试模式total_acc,train_loss,total_count =0,0,0with torch.no_grad():for idx,(label,text,offsets)in enumerate(dataloader):predicted_label =model(text,offsets)loss = criterion(predicted_label,label)  #计算loss值#记录测试数据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_countfrom torch.utils.data.dataset import random_split
from torchtext.data.functional import to_map_style_dataset
#超参数
EPOCHS=10 #epoch
LR=5  #学习率
BATCH_SIZE=64 #batch size for training
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 =Nonetrain_iter,test_iter =AG_NEWS()#加载数据
train_dataset =to_map_style_dataset(train_iter)
test_dataset =to_map_style_dataset(test_iter)
num_train=int(len(train_dataset)*0.95)split_train_,split_valid_=random_split(train_dataset,[num_train,len(train_dataset)-num_train])
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)
test_dataloader=DataLoader(test_dataset,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)if total_accu is not None and total_accu >val_acc:scheduler.step()else:total_accu =val_accprint('-'*69)print('|epoch {:1d}|time:{:4.2f}s|''valid_acc {:4.3f}valid_loss {:4.3f}'.format(epoch,time.time()-epoch_start_time,val_acc,val_loss))print('-'*69)print('Checking the results of test dataset.')
test_acc,test_loss =evaluate(test_dataloader)
print('test accuracy {:8.3f}'.format(test_acc))

报错：

ImportError: cannot import name 'DILL_AVAILABLE' from 'torch.utils.data.datapipes.utils.common' (D:\miniconda\envs\nlp_pytorch\lib\site-packages\torch\utils\data\datapipes\utils\common.py)

解决：torchdata pytorch2.3 报错-CSDN博客

import torch
torch.utils.data.datapipes.utils.common.DILL_AVAILABLE = torch.utils._import_utils.dill_available()

tps://github.com/pytorch/pytorch/pull/122616

结果：

[475, 21, 30, 5297]
[475, 21, 30, 5297]
9
|epoch 1| 500/1782batches|train_acc 0.719train_loss 0.01115
|epoch 1|1000/1782batches|train_acc 0.867train_loss 0.00620
|epoch 1|1500/1782batches|train_acc 0.882train_loss 0.00550
---------------------------------------------------------------------
|epoch 1|time:8.96s|valid_acc 0.898valid_loss 0.005
---------------------------------------------------------------------
|epoch 2| 500/1782batches|train_acc 0.903train_loss 0.00459
|epoch 2|1000/1782batches|train_acc 0.905train_loss 0.00440
|epoch 2|1500/1782batches|train_acc 0.907train_loss 0.00436
---------------------------------------------------------------------
|epoch 2|time:8.14s|valid_acc 0.884valid_loss 0.005
---------------------------------------------------------------------
|epoch 3| 500/1782batches|train_acc 0.925train_loss 0.00351
|epoch 3|1000/1782batches|train_acc 0.929train_loss 0.00339
|epoch 3|1500/1782batches|train_acc 0.928train_loss 0.00343
---------------------------------------------------------------------
|epoch 3|time:7.56s|valid_acc 0.912valid_loss 0.004
---------------------------------------------------------------------
|epoch 4| 500/1782batches|train_acc 0.930train_loss 0.00333
|epoch 4|1000/1782batches|train_acc 0.932train_loss 0.00327
|epoch 4|1500/1782batches|train_acc 0.931train_loss 0.00331
---------------------------------------------------------------------
|epoch 4|time:7.80s|valid_acc 0.913valid_loss 0.004
---------------------------------------------------------------------
|epoch 5| 500/1782batches|train_acc 0.933train_loss 0.00322
|epoch 5|1000/1782batches|train_acc 0.930train_loss 0.00330
|epoch 5|1500/1782batches|train_acc 0.934train_loss 0.00320
---------------------------------------------------------------------
|epoch 5|time:8.47s|valid_acc 0.914valid_loss 0.004
---------------------------------------------------------------------
|epoch 6| 500/1782batches|train_acc 0.937train_loss 0.00309
|epoch 6|1000/1782batches|train_acc 0.933train_loss 0.00324
|epoch 6|1500/1782batches|train_acc 0.932train_loss 0.00315
---------------------------------------------------------------------
|epoch 6|time:8.37s|valid_acc 0.912valid_loss 0.004
---------------------------------------------------------------------
|epoch 7| 500/1782batches|train_acc 0.936train_loss 0.00308
|epoch 7|1000/1782batches|train_acc 0.938train_loss 0.00298
|epoch 7|1500/1782batches|train_acc 0.934train_loss 0.00314
---------------------------------------------------------------------
|epoch 7|time:8.38s|valid_acc 0.914valid_loss 0.004
---------------------------------------------------------------------
|epoch 8| 500/1782batches|train_acc 0.938train_loss 0.00302
|epoch 8|1000/1782batches|train_acc 0.937train_loss 0.00306
|epoch 8|1500/1782batches|train_acc 0.934train_loss 0.00308
---------------------------------------------------------------------
|epoch 8|time:8.26s|valid_acc 0.915valid_loss 0.004
---------------------------------------------------------------------
|epoch 9| 500/1782batches|train_acc 0.939train_loss 0.00297
|epoch 9|1000/1782batches|train_acc 0.935train_loss 0.00316
|epoch 9|1500/1782batches|train_acc 0.934train_loss 0.00313
---------------------------------------------------------------------
|epoch 9|time:8.27s|valid_acc 0.915valid_loss 0.004
---------------------------------------------------------------------
|epoch 10| 500/1782batches|train_acc 0.935train_loss 0.00308
|epoch 10|1000/1782batches|train_acc 0.938train_loss 0.00301
|epoch 10|1500/1782batches|train_acc 0.936train_loss 0.00308
---------------------------------------------------------------------
|epoch 10|time:8.08s|valid_acc 0.915valid_loss 0.004
---------------------------------------------------------------------
Checking the results of test dataset.
test accuracy    0.908