pytorch学习7-情感分类

PyTorch模型和TorchText再来做情感分析(检测一段文字的情感是正面的还是负面的)。我们会使用IMDb 数据集，即电影评论。

1.准备数据

TorchText中的一个重要概念是Field。Field决定了你的数据会被怎样处理。在我们的情感分类任务中，我们所需要接触到的数据有文本字符串和两种情感，“pos"或者"neg”。
Field的参数制定了数据会被怎样处理。
我们使用TEXT field来定义如何处理电影评论，使用LABEL field来处理两个情感类别。
我们的TEXT field带有tokenize=‘spacy’，这表示我们会用spaCy tokenizer来tokenize英文句子。如果我们不特别声明tokenize这个参数，那么默认的分词方法是使用空格。
安装spaCy
pip install -U spacy
python -m spacy download en
LABEL由LabelField定义。这是一种特别的用来处理label的Field。我们后面会解释dtype。
更多关于Fields，参见https://github.com/pytorch/text/blob/master/torchtext/data/field.py
和之前一样，我们会设定random seeds使实验可以复现。

import torch
import numpy as np
from torchtext import data
import random

SEED = 1234

torch.manual_seed(SEED)
np.random.seed(SEED)
random.seed(SEED)
torch.cuda.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False

TEXT = data.Field(tokenize='spacy')
LABEL = data.LabelField(dtype=torch.float)

TorchText支持很多常见的自然语言处理数据集。
下面的代码会自动下载IMDb数据集，然后分成train/test两个torchtext.datasets类别。数据被前面的Fields处理。IMDb数据集一共有50000电影评论，每个评论都被标注为正面的或负面的。

from torchtext import datasets
train_data,test_data = datasets.IMDB.splits(TEXT,LABEL)

查看每个数据split有多少条数据。

print(f'Number of training examples: {len(train_data)}')
print(f'Number of testing examples: {len(test_data)}')

查看一个example。

print(vars(train_data.examples[0]))

由于我们现在只有train/test这两个分类，所以我们需要创建一个新的validation set。我们可以使用.split()创建新的分类。
默认的数据分割是 70、30，如果我们声明split_ratio，可以改变split之间的比例，split_ratio=0.8表示80%的数据是训练集，20%是验证集。
我们还声明random_state这个参数，确保我们每次分割的数据集都是一样的。

import random
train_data, valid_data = train_data.split(random_state=random.seed(SEED))

检查一下现在每个部分有多少条数据。

print(f'Number of training examples: {len(train_data)}')
print(f'Number of validation examples: {len(valid_data)}')
print(f'Number of testing examples: {len(test_data)}')

下一步我们需要创建 vocabulary 。vocabulary 就是把每个单词一一映射到一个数字。
我们使用最常见的25k个单词来构建我们的单词表，用max_size这个参数可以做到这一点。
所有其他的单词都用来表示。

TEXT.build_vocab(train_data, max_size=25000, vectors="glove.6B.100d", unk_init=torch.Tensor.normal_)
LABEL.build_vocab(train_data)

print(f"Unique tokens in TEXT vocabulary: {len(TEXT.vocab)}")
print(f"Unique tokens in LABEL vocabulary: {len(LABEL.vocab)}"

当我们把句子传进模型的时候，我们是按照一个个 batch 穿进去的，也就是说，我们一次传入了好几个句子，而且每个batch中的句子必须是相同的长度。为了确保句子的长度相同，TorchText会把短的句子pad到和最长的句子等长。
下面我们来看看训练数据集中最常见的单词

print(TEXT.vocab.freqs.most_common(20))

我们可以直接用 stoi(string to int) 或者 itos (int to string) 来查看我们的单词表。

print(TEXT.vocab.itos[:10])

查看labels。

print(LABEL.vocab.stoi)

最后一步数据的准备是创建iterators。每个itartion都会返回一个batch的examples。
我们会使用BucketIterator。BucketIterator会把长度差不多的句子放到同一个batch中，确保每个batch中不出现太多的padding。
严格来说，我们这份notebook中的模型代码都有一个问题，也就是我们把也当做了模型的输入进行训练。更好的做法是在模型中把由产生的输出给消除掉。在这节课中我们简单处理，直接把也用作模型输入了。由于数量不多，模型的效果也不差。
如果我们有GPU，还可以指定每个iteration返回的tensor都在GPU上。

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)

2.构建Word Averaging模型

我们首先介绍一个简单的Word Averaging模型。这个模型非常简单，我们把每个单词都通过Embedding层投射成word embedding vector，然后把一句话中的所有word vector做个平均，就是整个句子的vector表示了。接下来把这个sentence vector传入一个Linear层，做分类即可。
我们使用avg_pool2d来做average pooling。我们的目标是把sentence length那个维度平均成1，然后保留embedding这个维度。
avg_pool2d的kernel size是 (embedded.shape[1], 1)，所以句子长度的那个维度会被压扁。

import torch.nn as nn
import torch.nn.functional as F

class WordAVGModel(nn.Module):
    def __init__(self,vocab_size,embedding_dim,output_dim,pad_idx):
        super().__init__()
        self.embedding = nn.Embedding(vocab_size,embedding_dim,padding_idx=pad_idx)
        self.fc = nn.Linear(embedding_dim,output_dim)
    def forward(self,text):
        embedded = self.embedding(text)  # [sent len, batch size, emb dim]
        embedded = embedded.permute(1,0,2) # [batch size, sent len, emb dim]
        pooled = F.avg_pool2d(embedded,(embedded.shape[1],1)).squeeze(1) # [batch size, embedding_dim]
        return self.fc(pooled) #[batch size,1]

INPUT_DIM = len(TEXT.vocab)
EMBEDDING_DIM = 100
OUTPUT_DIM = 1
PAD_IDX = TEXT.vocab.stoi[TEXT.pad_token]

model = WordAVGModel(INPUT_DIM, EMBEDDING_DIM, OUTPUT_DIM, PAD_IDX)

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')

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

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)

3.训练模型

import torch.optim as optim
optimizer = optim.Adam(model.parameters())
criterion = nn.BCEWithLogitsLoss()
model = model.to(device)
criterion = criterion.to(device)

计算预测的准确率

def binary_accuracy(preds, y):
    """
    Returns accuracy per batch, i.e. if you get 8/10 right, this returns 0.8, NOT 8
    """

    #round predictions to the closest integer
    rounded_preds = torch.round(torch.sigmoid(preds))
    correct = (rounded_preds == y).float() #convert into float for division 
    acc = correct.sum()/len(correct)
    return acc

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).squeeze(1)
        loss = criterion(predictions, batch.label)
        acc = binary_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).squeeze(1)
            loss = criterion(predictions, batch.label)
            acc = binary_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

N_EPOCHS = 10

best_valid_loss = float('inf')

for epoch in range(N_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(), 'wordavg-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}%')

4.进行预测

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

def predict_sentiment(sentence):
    tokenized = [tok.text for tok in nlp.tokenizer(sentence)]
    indexed = [TEXT.vocab.stoi[t] for t in tokenized]
    tensor = torch.LongTensor(indexed).to(device)
    tensor = tensor.unsqueeze(1)
    prediction = torch.sigmoid(model(tensor))
    return prediction.item()

predict_sentiment("This film is terrible")

predict_sentiment("This film is great")

5.RNN模型

下面我们尝试把模型换成一个recurrent neural network (RNN)。RNN经常会被用来encode一个sequence

我们使用最后一个hidden state hT 来表示整个句子。
然后我们把 hT 通过一个线性变换 f ，然后用来预测句子的情感。

class RNN(nn.Module):
    def __init__(self, vocab_size, embedding_dim, hidden_dim, output_dim, 
                 n_layers, bidirectional, dropout, pad_idx):
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, embedding_dim, padding_idx=pad_idx)
        self.rnn = nn.LSTM(embedding_dim, hidden_dim, num_layers=n_layers, 
                           bidirectional=bidirectional, dropout=dropout)
        self.fc = nn.Linear(hidden_dim*2, output_dim)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, text):
        embedded = self.dropout(self.embedding(text)) #[sent len, batch size, emb dim]
        output, (hidden, cell) = self.rnn(embedded)
        #output = [sent len, batch size, hid dim * num directions]
        #hidden = [num layers * num directions, batch size, hid dim]
        #cell = [num layers * num directions, batch size, hid dim]
        
        #concat the final forward (hidden[-2,:,:]) and backward (hidden[-1,:,:]) hidden layers
        #and apply dropout
        hidden = self.dropout(torch.cat((hidden[-2,:,:], hidden[-1,:,:]), dim=1)) # [batch size, hid dim * num directions]
        return self.fc(hidden.squeeze(0))

INPUT_DIM = len(TEXT.vocab)
EMBEDDING_DIM = 100
HIDDEN_DIM = 256
OUTPUT_DIM = 1
N_LAYERS = 2
BIDIRECTIONAL = True
DROPOUT = 0.5
PAD_IDX = TEXT.vocab.stoi[TEXT.pad_token]

model = RNN(INPUT_DIM, EMBEDDING_DIM, HIDDEN_DIM, OUTPUT_DIM, 
            N_LAYERS, BIDIRECTIONAL, DROPOUT, PAD_IDX)

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

model.embedding.weight.data.copy_(pretrained_embeddings)
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)

print(model.embedding.weight.data)

6.训练RNN模型

optimizer = optim.Adam(model.parameters())
model = model.to(device)

N_EPOCHS = 5
best_valid_loss = float('inf')
for epoch in range(N_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(), 'lstm-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}%')

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

7.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, padding_idx=pad_idx)
        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) # [batch size, sent len]
        embedded = self.embedding(text) # [batch size, sent len, emb dim]
        embedded = embedded.unsqueeze(1) # [batch size, 1, sent len, emb dim]
        conved = [F.relu(conv(embedded)).squeeze(3) for conv in self.convs]
            
        #conv_n = [batch size, n_filters, sent len - filter_sizes[n]]
        
        pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]
        
        #pooled_n = [batch size, n_filters]
        
        cat = self.dropout(torch.cat(pooled, dim=1))

        #cat = [batch size, n_filters * len(filter_sizes)]
            
        return self.fc(cat)

INPUT_DIM = len(TEXT.vocab)
EMBEDDING_DIM = 100
N_FILTERS = 100
FILTER_SIZES = [3,4,5]
OUTPUT_DIM = 1
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)
model.embedding.weight.data.copy_(pretrained_embeddings)
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)
model = model.to(device)

optimizer = optim.Adam(model.parameters())
criterion = nn.BCEWithLogitsLoss()
criterion = criterion.to(device)

N_EPOCHS = 5

best_valid_loss = float('inf')

for epoch in range(N_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(), 'CNN-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}%')

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