目录
1.案例介绍
或者数据存在百度网盘中:glove.6B.50d.txt_免费高速下载|百度网盘-分享无限制 (baidu.com)
提取码:p1ua
关于文本分类(情感分析)的英文数据集汇总:(2条消息) 关于文本分类(情感分析)的英文数据集汇总_饭饭童鞋的博客-CSDN博客_英文文本分类数据集
2.思路分析
3.准备数据集
3.1 基础Dataset的准备
import jieba
from keras.datasets import imdb#情感文本分类数据集
import torch,os,re
from torch.utils.data import DataLoader,Dataset
def tokenlize(content):
re.sub('<.*?>',' ',content)#将特殊字符替换成空格
fileters=["\.",":",'\t','\n','\x97','\x96','#','$','%','&']#删去这些字符
content=re.sub('|'.join(fileters),' ',content)
tokens=[i.strip() for i in content.split()]
return tokens
class ImdbDataset(Dataset):
def __init__(self,train=True):
self.train_data_path=r'D:\各种编译器的代码\pythonProject12\机器学习\NLP自然语言处理\datas\IMDB文本情感分类数据集\aclImdb\train'
self.test_data_path=r'D:\各种编译器的代码\pythonProject12\机器学习\NLP自然语言处理\datas\IMDB文本情感分类数据集\aclImdb\test'
data_path=self.train_data_path if train else self.test_data_path
#1.把所有的文件名放入列表
temp_data_path=[os.path.join(data_path,'pos'),os.path.join(data_path,'neg')]#不需要\符号了 两个文件夹
self.total_file_path=[]#所有评论文件的path
for path in temp_data_path:
file_name_list=os.listdir(path)
file_path_list=[os.path.join(path,i) for i in file_name_list if i.endswith('.txt')]#当前文件夹中所有的文件名字
self.total_file_path.extend(file_path_list)#正例 负例文件名字都在
def __getitem__(self, index):
file_path=self.total_file_path[index]
#获取label
label_str=file_path.split("\\")[-2]
label=0 if label_str=='neg' else 1#文本类型数字化
#获取内容
tokens=tokenlize(open(file_path,'r',encoding='utf8').read())
return tokens,label
def __len__(self):
return len(self.total_file_path)
def collate_fn(batch):
"""
:param batch:([tokens,label],[tokens,label]...)
:return:
"""
content,label=zip(*batch)
return content,label
def get_dataloader(train=True):
imdb_dataset=ImdbDataset(train)
data_loader=DataLoader(imdb_dataset,batch_size=2,shuffle=True,collate_fn=collate_fn)
return data_loader
if __name__ == '__main__':
for idx,(input,target) in enumerate(get_dataloader()):
print(idx)
print(input)
print(target)
break
3.2 文本序列化
"""
实现的是:构建字典,实现方法把句子转化为数字序列和其翻转
"""
class Word2Sequence:
UNK_TAG='UNK'#不常见的单词 标记
PAD_TAG="PAD"#padding填充,即测试集中遇到新单词 标记
UNK=0
PAD=1
def __init__(self):
self.dict={
self.UNK_TAG:self.UNK,
self.PAD_TAG:self.PAD
}
self.count={}#统计词频
def fit(self,sentence):
"""
把单个句子保存到dict中
:param sentence:[word1,word2,word3,...]
:return:
"""
for word in sentence:
self.count[word]=self.count.get(word,0)+1
def build_vocab(self,min=5,max=None,max_features=None):
"""
生成词典
:param min:最小出现的次数
:param max:最大出现的次数
:param max_features:一共保留多少个词语
:return:
"""
#删除count中词频小于min的word
if min is not None:
self.count={word:value for word,value in self.count.items() if value>min}
#删除count中词频大于max的word
if max is not None:
self.count={word:value for word,value in self.count.items() if value<max}
#限制保留的词语数
if max_features is not None:
temp=sorted(self.count.items(),key=lambda x:x[-1],reverse=True)[:max_features]#降序,按照values值
self.count=dict(temp)#转换为字典
for word in self.count:
self.dict[word]=len(self.dict)
#得到一个翻转的字典
self.inverse_dict=dict(zip(self.dict.values(),self.dict.keys()))
def transform(self,sentence,max_len=None):
"""
把句子转化为数字序列
:param sentence:[word1,word2,...]
:param max_len:int,对句子进行填充或裁剪裁剪
:return:
"""
if max_len is not None:
if max_len>len(sentence):#填充
sentence=sentence+[self.PAD_TAG]*(max_len-len(sentence))
elif max_len<len(sentence):#裁剪
sentence=sentence[:max_len]
return [self.dict.get(word,self.UNK) for word in sentence]
def inverse_transform(self,indices):
"""
把序列转化为句子
:param indices:[1,2,3,4,...]
:return:
"""
return [self.inverse_dict.get(idx) for idx in indices]
if __name__ == '__main__':
ws=Word2Sequence()
ws.fit(['我', '是', '谁'])
ws.fit(['我', '是', '我'])
ws.build_vocab(min=0)
print(ws.dict)
ret=ws.transform(['我','爱','北京'],max_len=10)
print(ret)
ret=ws.inverse_transform(ret)
print(ret)
4.构建模型
'''
定义模型
'''
import torch
import torch.nn as nn
from lib import ws,max_len
import torch.nn.functional as F
from torch.optim import Adam
from dataset import get_dataloader
class MyModel(nn.Module):
def __init__(self):
super(MyModel,self).__init__()
self.embedding=nn.Embedding(len(ws),100)
self.fc=nn.Linear(max_len*100,2)
def forward(self,*input):
"""
:param input:[batch_size,max_len]
:return:
"""
x=self.embedding(input)#进行embedding操作,形状:[batch_size,max_len,100]
x=x.view([-1,max_len*100])
out=self.fc(x)
return F.log_softmax(out,dim=-1)
model=MyModel()
optimizer=Adam(model.parameters(),lr=0.001)
def train(epoch):
for idx,(input,target) in enumerate(get_dataloader(train=True)):
optimizer.zero_grad()#梯度归0
output=model(input)
loss=F.nll_loss(output,target)
loss.backward()
optimizer.step()
print(loss.item())
if __name__ == '__main__':
for i in range(1):
train(i)