NLP项目实战——基于Bert模子的多情绪评论分类（附数据集和源码） - ToB企服应用市场:ToB评测及商务社交产业平台

content: 酒店还是非常的不错，我预定的是套间，服务非常好，随叫随到，结帐非常快。顺便提一句，这个酒店三楼是一个高级KTV，里面的服务小姐非常的漂亮，有机会去看看。
idtype: 2

复制代码

from transformers import BertTokenizer, BertForSequenceClassification
from datasets import load_dataset
import torch
from torch.utils.data import DataLoader
import numpy as np

复制代码

# 自定义数据集类，继承自torch.utils.data.Dataset
class CommentDataset(torch.utils.data.Dataset):
def __init__(self, encodings, labels):
self.encodings = encodings
self.labels = labels
def __getitem__(self, idx):
item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
item['labels'] = torch.tensor(self.labels[idx])
return item
def __len__(self):
return len(self.labels)
# 加载训练集数据
train_data = []
train_labels = []
with open('Dataset/train.txt', 'r', encoding='utf-8') as f:
for line in f.readlines():
text, label = line.split('\t')
train_data.append(text)
train_labels.append(int(label))
# 对训练集进行编码
tokenizer = BertTokenizer.from_pretrained('/root/model/bert-base-chinese')
train_encodings = tokenizer(train_data, truncation=True, padding=True)
train_dataset = CommentDataset(train_encodings, train_labels)
train_loader = DataLoader(train_dataset, batch_size=8, shuffle=True)
# 加载开发集数据
dev_data = []
dev_labels = []
with open('Dataset/dev.txt', 'r', encoding='utf-8') as f:
for line in f.readlines():
text, label = line.split('\t')
dev_data.append(text)
dev_labels.append(int(label))
# 对开发集进行编码
dev_encodings = tokenizer(dev_data, truncation=True, padding=True)
dev_dataset = CommentDataset(dev_encodings, dev_labels)
dev_loader = DataLoader(dev_dataset, batch_size=8)
# 加载测试集数据
test_data = []
test_labels = []
with open('Dataset/test.txt', 'r', encoding='utf-8') as f:
for line in f.readlines():
text, label = line.split('\t')
test_data.append(text)
test_labels.append(int(label))
# 对测试集进行编码
test_encodings = tokenizer(test_data, truncation=True, padding=True)
test_dataset = CommentDataset(test_encodings, test_labels)
test_loader = DataLoader(test_dataset, batch_size=8)

复制代码

# 加载预训练的Bert模型用于序列分类，这里假设是二分类（0和1代表不同情感倾向），可以根据实际调整num_labels
model = BertForSequenceClassification.from_pretrained('/root/model/bert-base-chinese', num_labels=len(idset))

复制代码

# 训练函数
def train():
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=1e-5)
epochs = 3 # 可以根据实际调整训练轮数
for epoch in range(epochs):
model.train()
for batch in train_loader:
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
labels = batch['labels'].to(device)
outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
loss = outputs.loss
loss.backward()
optimizer.step()
optimizer.zero_grad()
print(f'Epoch {epoch + 1} completed')
# 在开发集上验证
validate()
# 验证函数（在开发集上查看模型表现辅助调参）
def validate():
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.eval()
correct = 0
total = 0
with torch.no_grad():
for batch in dev_loader:
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
labels = batch['labels'].to(device)
outputs = model(input_ids, attention_mask=attention_mask)
_, predicted = torch.max(outputs.logits, dim=1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(f'Validation Accuracy: {correct / total}')
# 评估函数
def evaluate():
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.eval()
correct = 0
total = 0
with torch.no_grad():
for batch in test_loader:
input_ids = batch['input_ids'].to(device)
attention_mask = batch['attention_mask'].to(device)
labels = batch['labels'].to(device)
outputs = model(input_ids, attention_mask=attention_mask)
_, predicted = torch.max(outputs.logits, dim=1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(f'Test Accuracy: {correct / total}')
train()
evaluate()

复制代码

Epoch 1 completed
Validation Accuracy: 0.9435662345874171
Epoch 2 completed
Validation Accuracy: 0.9521024343977237
Epoch 3 completed
Validation Accuracy: 0.9524185899462535
Test Accuracy: 0.9485416172634574

复制代码

with open('Dataset/train.txt', 'r', encoding='utf-8') as f: train_data = f.read()with open('Dataset/dev.txt', 'r', encoding='utf-8') as f: eval_data = f.read() train_data = train_data.split('\n')eval_data = eval_data.split('\n')idset = set()for data in train_data: idset.add(data.split('\t')[-1])for data in eval_data: idset.add(data.split('\t')[-1])from transformers import BertTokenizer, BertForSequenceClassification
from datasets import load_dataset
import torch
from torch.utils.data import DataLoader
import numpy as np
# 自定义数据集类，继承自torch.utils.data.Dataset
class CommentDataset(torch.utils.data.Dataset):
def __init__(self, encodings, labels):
self.encodings = encodings
self.labels = labels
def __getitem__(self, idx):
item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
item['labels'] = torch.tensor(self.labels[idx])
return item
def __len__(self):
return len(self.labels)
# 加载训练集数据
train_data = []
train_labels = []
with open('Dataset/train.txt', 'r', encoding='utf-8') as f:
for line in f.readlines():
text, label = line.split('\t')
train_data.append(text)
train_labels.append(int(label))
# 对训练集进行编码
tokenizer = BertTokenizer.from_pretrained('/root/model/bert-base-chinese')
train_encodings = tokenizer(train_data, truncation=True, padding=True)
train_dataset = CommentDataset(train_encodings, train_labels)
train_loader = DataLoader(train_dataset, batch_size=8, shuffle=True)
# 加载开发集数据
dev_data = []
dev_labels = []
with open('Dataset/dev.txt', 'r', encoding='utf-8') as f:
for line in f.readlines():
text, label = line.split('\t')
dev_data.append(text)
dev_labels.append(int(label))
# 对开发集进行编码
dev_encodings = tokenizer(dev_data, truncation=True, padding=True)
dev_dataset = CommentDataset(dev_encodings, dev_labels)
dev_loader = DataLoader(dev_dataset, batch_size=8)
# 加载测试集数据
test_data = []
test_labels = []
with open('Dataset/test.txt', 'r', encoding='utf-8') as f:
for line in f.readlines():
text, label = line.split('\t')
test_data.append(text)
test_labels.append(int(label))
# 对测试集进行编码
test_encodings = tokenizer(test_data, truncation=True, padding=True)
test_dataset = CommentDataset(test_encodings, test_labels)
test_loader = DataLoader(test_dataset, batch_size=8)
# 加载预训练的Bert模型用于序列分类，这里假设是二分类（0和1代表不同情感倾向），可以根据实际调整num_labels
model = BertForSequenceClassification.from_pretrained('/root/model/bert-base-chinese', num_labels=len(idset))
# 训练函数def train(): device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model.to(device) optimizer = torch.optim.AdamW(model.parameters(), lr=1e-5) epochs = 3 # 可以根据实际调整训练轮数 for epoch in range(epochs): model.train() for batch in train_loader: input_ids = batch['input_ids'].to(device) attention_mask = batch['attention_mask'].to(device) labels = batch['labels'].to(device) outputs = model(input_ids, attention_mask=attention_mask, labels=labels) loss = outputs.loss loss.backward() optimizer.step() optimizer.zero_grad() print(f'Epoch {epoch + 1} completed') # 在开辟集上验证 validate()# 验证函数（在开辟集上查看模子体现辅助调参）def validate(): device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model.eval() correct = 0 total = 0 with torch.no_grad(): for batch in dev_loader: input_ids = batch['input_ids'].to(device) attention_mask = batch['attention_mask'].to(device) labels = batch['labels'].to(device) outputs = model(input_ids, attention_mask=attention_mask) _, predicted = torch.max(outputs.logits, dim=1) total += labels.size(0) correct += (predicted == labels).sum().item() print(f'Validation Accuracy: {correct / total}')# 评估函数def evaluate(): device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model.eval() correct = 0 total = 0 with torch.no_grad(): for batch in test_loader: input_ids = batch['input_ids'].to(device) attention_mask = batch['attention_mask'].to(device) labels = batch['labels'].to(device) outputs = model(input_ids, attention_mask=attention_mask) _, predicted = torch.max(outputs.logits, dim=1) total += labels.size(0) correct += (predicted == labels).sum().item() print(f'Test Accuracy: {correct / total}')if __name__ == "__main__": train() evaluate()

复制代码