task5：多类型情感分析_多分类情感分析综述

在本次学习中，我们将对具有 6 个类的数据集执行分类
可使用jupyter notebook运行！！！

import torch
from torchtext.legacy import data
from torchtext.legacy import datasets
import random

SEED = 1234
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))
# 建立词汇表
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)
# 建立迭代器
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)
# 模型的建立
import torch.nn as nn
import torch.nn.functional as F
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 = [sent len, batch size]        
        text = text.permute(1, 0)                
        #text = [batch size, sent len]
        embedded = self.embedding(text)   
        #embedded = [batch size, sent len, emb dim]
        embedded = embedded.unsqueeze(1)
        #embedded = [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)
# 模型参数设置
INPUT_DIM = len(TEXT.vocab)
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)
# 加载预训练模型
pretrained_embeddings = TEXT.vocab.vectors
model.embedding.weight.data.copy_(pretrained_embeddings)
# 用0初始化未知的权重和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)
# 设置loss
import torch.optim as optim
optimizer = optim.Adam(model.parameters())
criterion = nn.CrossEntropyLoss()
model = model.to(device)
criterion = criterion.to(device)
# 计算精确度
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
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)

# 评价
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)

# 时间统计
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

# 训练模型
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(), '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}%')

# 测试模型
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}%')



1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160