更新加入LSTM的推特文本情感分类

最新推荐文章于 2024-03-07 15:43:35 发布

jianshanzhange

最新推荐文章于 2024-03-07 15:43:35 发布

阅读量340

点赞数

文章标签： pytorch

本文链接：https://blog.csdn.net/jianshanzhange/article/details/113246449

版权

import torch
import torchtext
import torch.nn as nn
import torch.nn.functional as F
from torchtext.vocab import GloVe
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import re
from sklearn.model_selection import train_test_split
import time

start=time.time()

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

#读取文件
data = pd.read_csv('D:/pycharmworkspace/ISLR-master/Tweets.csv')

#取指定的两列
data = data[['airline_sentiment','text']]

#去掉重复值
data.drop_duplicates(inplace=True)

#返回每一种类型的数量
data.airline_sentiment.value_counts()
#print(data.airline_sentiment.value_counts())

#在数据后面新建名字为review的一列数据 #neutral编号为0 positive编号为1 negative编号为2 取前一部分
data['review'] = pd.factorize(data.airline_sentiment)[0]

#删除airline_sentiment这一列数据
del data['airline_sentiment']

#保留规则 保留A-Z a-z 加号是按原来句子样式表达
token = re.compile('[A-Za-z]+|[!?,.()]')

def reg_text(text):