目录
引言:
1.所有文件展示:
1.中文停用词数据(hit_stopwords.txt)来源于:
2.其中data数据集为chinese_text_cnn-master.zip提取出的文件。点击链接进入github,点击Code、Download ZIP即可下载。
2.安装依赖库:
3.数据预处理(data_set.py):
train.txt-去除停用词后的训练集文件:
test.txt -去除停用词后的测试集文件:
4. 模型训练以及保存(main.py)
1.LSTM模型搭建:
2.main.py代价展示 :
3.模型保存
4.训练结果
5.LSTM模型测试(test.py)
1.测试结果:
2.测试结果:
6.完整代码展示:
1.data_set.py
2.mian.py
3.test.py
引言:
在当今数字化时代,人们在社交媒体、评论平台以及各类在线交流中产生了海量的文本数据。这些数据蕴含着丰富的情感信息,从而成为了深入理解用户态度、市场趋势,甚至社会情绪的宝贵资源。自然语言处理(NLP)的发展为我们提供了强大的工具,使得对文本情感进行分析成为可能。在这个领域中,长短时记忆网络(LSTM)凭借其能够捕捉文本序列中长距离依赖关系的能力,成为了情感分析任务中的一项重要技术。
本篇博客将手把手地教你如何使用LSTM网络实现中文文本情感分析。我们将从数据预处理开始,逐步构建一个端到端的情感分析模型。通过详细的步骤和示例代码,深入了解如何处理中文文本数据、构建LSTM模型、进行训练和评估。
1.所有文件展示:
1.中文停用词数据(hit_stopwords.txt)来源于:
项目目录预览 - stopwords - GitCode
2.其中data数据集为chinese_text_cnn-master.zip提取出的文件。点击链接进入github,点击Code、Download ZIP即可下载。
2.安装依赖库:
pip install torch # 搭建LSTM模型
pip install gensim # 中文文本词向量转换
pip install numpy # 数据清洗、预处理
pip install pandas
3.数据预处理(data_set.py):
# -*- coding: utf-8 -*-
# @Time : 2023/11/15 10:52
# @Author :Muzi
# @File : data_set.py
# @Software: PyCharm
import pandas as pd
import jieba
# 数据读取
def load_tsv(file_path):
data = pd.read_csv(file_path, sep='\t')
data_x = data.iloc[:, -1]
data_y = data.iloc[:, 1]
return data_x, data_y
train_x, train_y = load_tsv("./data/train.tsv")
test_x, test_y = load_tsv("./data/test.tsv")
train_x=[list(jieba.cut(x)) for x in train_x]
test_x=[list(jieba.cut(x)) for x in test_x]
with open('./hit_stopwords.txt','r',encoding='UTF8') as f:
stop_words=[word.strip() for word in f.readlines()]
print('Successfully')
def drop_stopword(datas):
for data in datas:
for word in data:
if word in stop_words:
data.remove(word)
return datas
def save_data(datax,path):
with open(path, 'w', encoding="UTF8") as f:
for lines in datax:
for i, line in enumerate(lines):
f.write(str(line))
# 如果不是最后一行,就添加一个逗号
if i != len(lines) - 1:
f.write(',')
f.write('\n')
if __name__ == '__main':
train_x=drop_stopword(train_x)
test_x=drop_stopword(test_x)
save_data(train_x,'./train.txt')
save_data(test_x,'./test.txt')
print('Successfully')
train.txt-去除停用词后的训练集文件:
test.txt -去除停用词后的测试集文件:
4. 模型训练以及保存(main.py)
1.LSTM模型搭建:
不同的数据集应该有不同的分类标准,我这里用到的数据模型属于二分类问题
# 定义LSTM模型
class LSTMModel(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(LSTMModel, self).__init__()
self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, x):
lstm_out, _ = self.lstm(x)
output = self.fc(lstm_out[:, -1, :]) # 取序列的最后一个输出
return output
# 定义模型
input_size = word2vec_model.vector_size
hidden_size = 50 # 你可以根据需要调整隐藏层大小
output_size = 2 # 输出的大小,根据你的任务而定
model = LSTMModel(input_size, hidden_size, output_size)
# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss() # 交叉熵损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.0002)
2.main.py代价展示 :
# -*- coding: utf-8 -*-
# @Time : 2023/11/13 20:31
# @Author :Muzi
# @File : mian.py.py
# @Software: PyCharm
import pandas as pd
import torch
from torch import nn
import jieba
from gensim.models import Word2Vec
import numpy as np
from data_set import load_tsv
from torch.utils.data import DataLoader, TensorDataset
# 数据读取
def load_txt(path):
with open(path,'r',encoding='utf-8') as f:
data=[[line.strip()] for line in f.readlines()]
return data
train_x=load_txt('train.txt')
test_x=load_txt('test.txt')
train=train_x+test_x
X_all=[i for x in train for i in x]
_, train_y = load_tsv("./data/train.tsv")
_, test_y = load_tsv("./data/test.tsv")
# 训练Word2Vec模型
word2vec_model = Word2Vec(sentences=X_all, vector_size=100, window=5, min_count=1, workers=4)
# 将文本转换为Word2Vec向量表示
def text_to_vector(text):
vector = [word2vec_model.wv[word] for word in text if word in word2vec_model.wv]
return sum(vector) / len(vector) if vector else [0] * word2vec_model.vector_size
X_train_w2v = [[text_to_vector(text)] for line in train_x for text in line]
X_test_w2v = [[text_to_vector(text)] for line in test_x for text in line]
# 将词向量转换为PyTorch张量
X_train_array = np.array(X_train_w2v, dtype=np.float32)
X_train_tensor = torch.Tensor(X_train_array)
X_test_array = np.array(X_test_w2v, dtype=np.float32)
X_test_tensor = torch.Tensor(X_test_array)
#使用DataLoader打包文件
train_dataset = TensorDataset(X_train_tensor, torch.LongTensor(train_y))
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_dataset = TensorDataset(X_test_tensor,torch.LongTensor(test_y))
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=True)
# 定义LSTM模型
class LSTMModel(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(LSTMModel, self).__init__()
self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, x):
lstm_out, _ = self.lstm(x)
output = self.fc(lstm_out[:, -1, :]) # 取序列的最后一个输出
return output
# 定义模型
input_size = word2vec_model.vector_size
hidden_size = 50 # 你可以根据需要调整隐藏层大小
output_size = 2 # 输出的大小,根据你的任务而定
model = LSTMModel(input_size, hidden_size, output_size)
# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss() # 交叉熵损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.0002)
if __name__ == "__main__":
# 训练模型
num_epochs = 10
log_interval = 100 # 每隔100个批次输出一次日志
loss_min=100
for epoch in range(num_epochs):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
outputs = model(data)
loss = criterion(outputs, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch_idx % log_interval == 0:
print('Epoch [{}/{}], Batch [{}/{}], Loss: {:.4f}'.format(
epoch + 1, num_epochs, batch_idx, len(train_loader), loss.item()))
# 保存最佳模型
if loss.item()<loss_min:
loss_min=loss.item()
torch.save(model, 'model.pth')
# 模型评估
with torch.no_grad():
model.eval()
correct = 0
total = 0
for data, target in test_loader:
outputs = model(data)
_, predicted = torch.max(outputs.data, 1)
total += target.size(0)
correct += (predicted == target).sum().item()
accuracy = correct / total
print('Test Accuracy: {:.2%}'.format(accuracy))
3.模型保存
# 保存最佳模型
if loss.item()<loss_min:
loss_min=loss.item()
torch.save(model, 'model.pth')
4.训练结果
5.LSTM模型测试(test.py)
# -*- coding: utf-8 -*-
# @Time : 2023/11/15 15:53
# @Author :Muzi
# @File : test.py.py
# @Software: PyCharm
import torch
import jieba
from torch import nn
from gensim.models import Word2Vec
import numpy as np
class LSTMModel(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(LSTMModel, self).__init__()
self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, x):
lstm_out, _ = self.lstm(x)
output = self.fc(lstm_out[:, -1, :]) # 取序列的最后一个输出
return output
# 数据读取
def load_txt(path):
with open(path,'r',encoding='utf-8') as f:
data=[[line.strip()] for line in f.readlines()]
return data
#去停用词
def drop_stopword(datas):
# 假设你有一个函数用于预处理文本数据
with open('./hit_stopwords.txt', 'r', encoding='UTF8') as f:
stop_words = [word.strip() for word in f.readlines()]
datas=[x for x in datas if x not in stop_words]
return datas
def preprocess_text(text):
text=list(jieba.cut(text))
text=drop_stopword(text)
return text
# 将文本转换为Word2Vec向量表示
def text_to_vector(text):
train_x = load_txt('train.txt')
test_x = load_txt('test.txt')
train = train_x + test_x
X_all = [i for x in train for i in x]
# 训练Word2Vec模型
word2vec_model = Word2Vec(sentences=X_all, vector_size=100, window=5, min_count=1, workers=4)
vector = [word2vec_model.wv[word] for word in text if word in word2vec_model.wv]
return sum(vector) / len(vector) if vector else [0] * word2vec_model.vector_size
if __name__ == '__main__':
# input_text = "这个车完全就是垃圾,又热又耗油"
input_text = "这个车我开了好几年,还是不错的"
label = {1: "正面情绪", 0: "负面情绪"}
model = torch.load('model.pth')
# 预处理输入数据
input_data = preprocess_text(input_text)
# 确保输入词向量与模型维度和数据类型相同
input_data=[[text_to_vector(input_data)]]
input_arry= np.array(input_data, dtype=np.float32)
input_tensor = torch.Tensor(input_arry)
# 将输入数据传入模型
with torch.no_grad():
output = model(input_tensor)
predicted_class = label[torch.argmax(output).item()]
print(f"predicted_text:{input_text}")
print(f"模型预测的类别: {predicted_class}")
1.测试结果:
2.测试结果:
6.完整代码展示:
1.data_set.py
import pandas as pd
import jieba
# 数据读取
def load_tsv(file_path):
data = pd.read_csv(file_path, sep='\t')
data_x = data.iloc[:, -1]
data_y = data.iloc[:, 1]
return data_x, data_y
with open('./hit_stopwords.txt','r',encoding='UTF8') as f:
stop_words=[word.strip() for word in f.readlines()]
print('Successfully')
def drop_stopword(datas):
for data in datas:
for word in data:
if word in stop_words:
data.remove(word)
return datas
def save_data(datax,path):
with open(path, 'w', encoding="UTF8") as f:
for lines in datax:
for i, line in enumerate(lines):
f.write(str(line))
# 如果不是最后一行,就添加一个逗号
if i != len(lines) - 1:
f.write(',')
f.write('\n')
if __name__ == '__main':
train_x, train_y = load_tsv("./data/train.tsv")
test_x, test_y = load_tsv("./data/test.tsv")
train_x = [list(jieba.cut(x)) for x in train_x]
test_x = [list(jieba.cut(x)) for x in test_x]
train_x=drop_stopword(train_x)
test_x=drop_stopword(test_x)
save_data(train_x,'./train.txt')
save_data(test_x,'./test.txt')
print('Successfully')
2.mian.py
import pandas as pd
import torch
from torch import nn
import jieba
from gensim.models import Word2Vec
import numpy as np
from data_set import load_tsv
from torch.utils.data import DataLoader, TensorDataset
# 数据读取
def load_txt(path):
with open(path,'r',encoding='utf-8') as f:
data=[[line.strip()] for line in f.readlines()]
return data
train_x=load_txt('train.txt')
test_x=load_txt('test.txt')
train=train_x+test_x
X_all=[i for x in train for i in x]
_, train_y = load_tsv("./data/train.tsv")
_, test_y = load_tsv("./data/test.tsv")
# 训练Word2Vec模型
word2vec_model = Word2Vec(sentences=X_all, vector_size=100, window=5, min_count=1, workers=4)
# 将文本转换为Word2Vec向量表示
def text_to_vector(text):
vector = [word2vec_model.wv[word] for word in text if word in word2vec_model.wv]
return sum(vector) / len(vector) if vector else [0] * word2vec_model.vector_size
X_train_w2v = [[text_to_vector(text)] for line in train_x for text in line]
X_test_w2v = [[text_to_vector(text)] for line in test_x for text in line]
# 将词向量转换为PyTorch张量
X_train_array = np.array(X_train_w2v, dtype=np.float32)
X_train_tensor = torch.Tensor(X_train_array)
X_test_array = np.array(X_test_w2v, dtype=np.float32)
X_test_tensor = torch.Tensor(X_test_array)
#使用DataLoader打包文件
train_dataset = TensorDataset(X_train_tensor, torch.LongTensor(train_y))
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_dataset = TensorDataset(X_test_tensor,torch.LongTensor(test_y))
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=True)
# 定义LSTM模型
class LSTMModel(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(LSTMModel, self).__init__()
self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, x):
lstm_out, _ = self.lstm(x)
output = self.fc(lstm_out[:, -1, :]) # 取序列的最后一个输出
return output
# 定义模型
input_size = word2vec_model.vector_size
hidden_size = 50 # 你可以根据需要调整隐藏层大小
output_size = 2 # 输出的大小,根据你的任务而定
model = LSTMModel(input_size, hidden_size, output_size)
# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss() # 交叉熵损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.0002)
if __name__ == "__main__":
# 训练模型
num_epochs = 10
log_interval = 100 # 每隔100个批次输出一次日志
loss_min=100
for epoch in range(num_epochs):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
outputs = model(data)
loss = criterion(outputs, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch_idx % log_interval == 0:
print('Epoch [{}/{}], Batch [{}/{}], Loss: {:.4f}'.format(
epoch + 1, num_epochs, batch_idx, len(train_loader), loss.item()))
# 保存最佳模型
if loss.item()<loss_min:
loss_min=loss.item()
torch.save(model, 'model.pth')
# 模型评估
with torch.no_grad():
model.eval()
correct = 0
total = 0
for data, target in test_loader:
outputs = model(data)
_, predicted = torch.max(outputs.data, 1)
total += target.size(0)
correct += (predicted == target).sum().item()
accuracy = correct / total
print('Test Accuracy: {:.2%}'.format(accuracy))
3.test.py
import torch
import jieba
from torch import nn
from gensim.models import Word2Vec
import numpy as np
class LSTMModel(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(LSTMModel, self).__init__()
self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, x):
lstm_out, _ = self.lstm(x)
output = self.fc(lstm_out[:, -1, :]) # 取序列的最后一个输出
return output
# 数据读取
def load_txt(path):
with open(path,'r',encoding='utf-8') as f:
data=[[line.strip()] for line in f.readlines()]
return data
#去停用词
def drop_stopword(datas):
# 假设你有一个函数用于预处理文本数据
with open('./hit_stopwords.txt', 'r', encoding='UTF8') as f:
stop_words = [word.strip() for word in f.readlines()]
datas=[x for x in datas if x not in stop_words]
return datas
def preprocess_text(text):
text=list(jieba.cut(text))
text=drop_stopword(text)
return text
# 将文本转换为Word2Vec向量表示
def text_to_vector(text):
train_x = load_txt('train.txt')
test_x = load_txt('test.txt')
train = train_x + test_x
X_all = [i for x in train for i in x]
# 训练Word2Vec模型
word2vec_model = Word2Vec(sentences=X_all, vector_size=100, window=5, min_count=1, workers=4)
vector = [word2vec_model.wv[word] for word in text if word in word2vec_model.wv]
return sum(vector) / len(vector) if vector else [0] * word2vec_model.vector_size
if __name__ == '__main__':
input_text = "这个车完全就是垃圾,又热又耗油"
# input_text = "这个车我开了好几年,还是不错的"
label = {1: "正面情绪", 0: "负面情绪"}
model = torch.load('model.pth')
# 预处理输入数据
input_data = preprocess_text(input_text)
# 确保输入词向量与模型维度和数据类型相同
input_data=[[text_to_vector(input_data)]]
input_arry= np.array(input_data, dtype=np.float32)
input_tensor = torch.Tensor(input_arry)
# 将输入数据传入模型
with torch.no_grad():
output = model(input_tensor)
# 这里只一个简单的示例
predicted_class = label[torch.argmax(output).item()]
print(f"predicted_text:{input_text}")
print(f"模型预测的类别: {predicted_class}")