[人工智能]Pytorch情感分析（task5）

数据集

从二分类的情感分析进阶到多分类情感分析，数据集采用TREC数据集,这个数据包括6个不同的问题类型。

导入数据

import os
import time
import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
from torch.units.data import Dataset, DataLoader
from sklearn.model_selection import train_test_split
from torchtext.legacy import data
from torchtext.legacy import datasets

SEED = 2021

torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True

TEXT = data.Field(tokenize = 'spacy',tokenizer_language = 'en_core_web_sm')
LABEL = data.LabelField()

train_data, test_data = datasets.TREC.splits(TEXT,  LABEL,  fine_grained=False)
train_data, valid_data = train_data.split(random_state = random.seed(SEED))

接下来根据数据集构建词汇表，数据集约3800个训练样本，词汇约为7500。

MAX_VOCAB_SIZE = 25_000

TEXT.build_vocab(train_data, 
                 max_size = MAX_VOCAB_SIZE, 
                 vectors = "glove.6B.100d", 
                 unk_init = torch.Tensor.normal_)

LABEL.build_vocab(train_data)

检查训练集中的标签类别，一共6个标签：

• HUM: 关于人类的问题
• ENTY：关于实体的问题的
• DESC：关于要求提供描述的问题
• NUM：关于答案为数字的问题
• LOC：关于答案是位置的问题
• ABBR：关于询问缩写的问题

设置迭代器

BATCH_SIZE = 64

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

train_iterator, valid_iterator, test_iterator = data.BucketIterator.splits(
    (train_data, valid_data, test_data),  batch_size = BATCH_SIZE,  device = device)

构建CNN模型

class CNN(nn.Module):
    def __init__(self, vocab_size, embedding_dim, n_filters, filter_sizes, output_dim, 
                 dropout, pad_idx):
        
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, embedding_dim)      
        self.convs = nn.ModuleList([
                                    nn.Conv2d(in_channels = 1, 
                                              out_channels = n_filters, 
                                              kernel_size = (fs, embedding_dim)) 
                                    for fs in filter_sizes
                                    ])
        
        self.fc = nn.Linear(len(filter_sizes) * n_filters, output_dim) 
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, text):
        text = text.permute(1, 0)
        embedded = self.embedding(text)
        embedded = embedded.unsqueeze(1)
        conved = [F.relu(conv(embedded)).squeeze(3) for conv in self.convs]
        pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]
        cat = self.dropout(torch.cat(pooled, dim = 1))
        return self.fc(cat)

设置CNN参数

INPUT_DIM = len(TEXT.vocab) #6个类别
EMBEDDING_DIM = 100
N_FILTERS = 100
FILTER_SIZES = [2,3,4]
OUTPUT_DIM = len(LABEL.vocab)
DROPOUT = 0.5
PAD_IDX = TEXT.vocab.stoi[TEXT.pad_token]

model = CNN(INPUT_DIM, EMBEDDING_DIM, N_FILTERS, FILTER_SIZES, OUTPUT_DIM, DROPOUT, PAD_IDX)

计算使用参数的量

def count_parameters(model):
    return sum(p.numel() for p in model.parameters() if p.requires_grad)

print(f'The model has {count_parameters(model):,} trainable parameters')

加载预训练embedding

pretrained_embeddings = TEXT.vocab.vectors
model.embedding.weight.data.copy_(pretrained_embeddings)

用0来初始化位置的权重和padding参数

UNK_IDX = TEXT.vocab.stoi[TEXT.unk_token]

model.embedding.weight.data[UNK_IDX] = torch.zeros(EMBEDDING_DIM)
model.embedding.weight.data[PAD_IDX] = torch.zeros(EMBEDDING_DIM)

构建优化器和损失函数

optimizer = optim.Adam(model.parameters())
criterion = nn.CrossEntropyLoss()

model = model.to(device)
criterion = criterion.to(device)

损失函数采用交叉熵损失
通常二分类采用BCEWithLogitsLoss，多分类采用CrossEntropyLoss

之前，我们有一个函数可以计算二进制标签情况下的准确度，我们说如果值超过 0.5，那么我们会假设它是正的。 在我们有C 个类（C > 2）的情况下，我们的模型输出一个C 维向量，其中每个元素的值是示例属于该类的置信度。

例如，在我们的标签中，我们有：‘HUM’ = 0、‘ENTY’ = 1、‘DESC’ = 2、‘NUM’ = 3、‘LOC’ = 4 和 ‘ABBR’ = 5。如果我们的输出 模型是这样的：[5.1, 0.3, 0.1, 2.1, 0.2, 0.6] 这意味着该模型确信该示例属于第 0 类：这是一个关于人类的问题，并且略微相信该示例属于该第3类：关于数字的问题。

我们通过执行 argmax 来获取批次中每个元素的预测最大值的索引，然后计算它与实际标签相等的次数来计算准确度。 然后我们对整个批次进行平均。

def categorical_accuracy(preds, y):
    """
    Returns accuracy per batch, i.e. if you get 8/10 right, this returns 0.8, NOT 8
    """
    top_pred = preds.argmax(1, keepdim = True)
    correct = top_pred.eq(y.view_as(top_pred)).sum()
    acc = correct.float() / y.shape[0]
    return acc

训练循环与之前类似，CrossEntropyLoss期望输入数据为 [batch size, n classes] ，标签为 [batch size] 。
标签默认需要是一个 LongTensor类型的数据，因为我们没有像以前那样将 dtype 设置为 FloatTensor。

def train(model, iterator, optimizer, criterion):
    
    epoch_loss = 0
    epoch_acc = 0
    model.train()
    
    for batch in iterator:    
        optimizer.zero_grad()
        predictions = model(batch.text) 
        loss = criterion(predictions, batch.label)
        acc = categorical_accuracy(predictions, batch.label)
        
        loss.backward()
        optimizer.step()
        epoch_loss += loss.item()
        epoch_acc += acc.item()
        
    return epoch_loss / len(iterator), epoch_acc / len(iterator)

def evaluate(model, iterator, criterion):
    
    epoch_loss = 0
    epoch_acc = 0
    model.eval()
    with torch.no_grad():
        for batch in iterator:
            predictions = model(batch.text)
            loss = criterion(predictions, batch.label)           
            acc = categorical_accuracy(predictions, batch.label)
            epoch_loss += loss.item()
            epoch_acc += acc.item()
        
    return epoch_loss / len(iterator), epoch_acc / len(iterator)

import time

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

main

EPOCHS = 5
best_valid_loss = float('inf')

for epoch in range(EPOCHS):

    start_time = time.time()
    train_loss, train_acc = train(model, train_iterator, optimizer, criterion)
    valid_loss, valid_acc = 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(), 'tut5-model.pt')
    
    print(f'Epoch: {epoch+1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s')
    print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%')
    print(f'\t Val. Loss: {valid_loss:.3f} |  Val. Acc: {valid_acc*100:.2f}%')

在测试集上运行

model.load_state_dict(torch.load('tut5-model.pt'))
test_loss, test_acc = evaluate(model, test_iterator, criterion)
print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc*100:.2f}%')

创建一个函数来预测给定问题的类别
使用argmax获得最高的预测类索引，使用这个索引和标签vocab来获得可读的标签。

import spacy
nlp = spacy.load('en_core_web_sm')

def predict_class(model, sentence, min_len = 4):
    model.eval()
    tokenized = [tok.text for tok in nlp.tokenizer(sentence)]
    if len(tokenized) < min_len:
        tokenized += ['<pad>'] * (min_len - len(tokenized))
    indexed = [TEXT.vocab.stoi[t] for t in tokenized]
    tensor = torch.LongTensor(indexed).to(device)
    tensor = tensor.unsqueeze(1)
    preds = model(tensor)
    max_preds = preds.argmax(dim = 1)
    return max_preds.item()

在随机的问题上进行尝试

参考链接:
https://github.com/datawhalechina/team-learning-nlp/blob/master/EmotionalAnalysis