- 介绍
首先需要指出的是，代码是从李宏毅老师的课程中下载的，并不是我自己码的。这篇文章主要是在原代码中加了一些讲解和注释，以及将繁体字改成了简体字。
我们需要处理的问题是将Twitter上的文字评论分为正面和负面。具体的要求如下：
我们使用到的模型如下所示：
其中，word embedding是将词语转换为向量，以便于后续放入LSTM中进行训练。在下面的代码中，作者选用的是word2vec模型（Skip-gram、CBOW等）完成这个转换。具体的算法大家可以在CSDN或者B站搜索大佬们的文章来学习。
; 1. 下载数据
path_prefix = './'
!gdown --id '1lz0Wtwxsh5YCPdqQ3E3l_nbfJT1N13V8' --output data.zip
!unzip data.zip
!ls
import warnings
warnings.filterwarnings('ignore')
- 读入数据
因为数据的格式并不是一般的格式，所以需要写一个自己的读取函数
import torch
import numpy as np
import pandas as pd
import torch.optim as optim
import torch.nn.functional as F
def load_training_data(path='training_label.txt'):
if 'training_label' in path:
with open(path, 'r') as f:
lines = f.readlines()
lines = [line.strip('\n').split(' ') for line in lines]
x = [line[2:] for line in lines]
y = [line[0] for line in lines]
return x, y
else:
with open(path, 'r') as f:
lines = f.readlines()
x = [line.strip('\n').split(' ') for line in lines]
return x
def load_testing_data(path='testing_data'):
with open(path, 'r') as f:
lines = f.readlines()
X = ["".join(line.strip('\n').split(",")[1:]).strip() for line in lines[1:]]
X = [sen.split(' ') for sen in X]
return X
def evaluation(outputs, labels):
outputs[outputs>=0.5] = 1
outputs[outputs<0.5] = 0
correct = torch.sum(torch.eq(outputs, labels)).item()
return correct
- 定义word2vec模型
word2vec模型可以将词语转换为向量，并且能很神奇地保留词语的相似度等性质。具体的算法流程可以在csdn、知乎或者B站上搜索大佬们的文章。我们在这里使用word2vec是为了后续将文字转换为向量，以便于输入相应的神经网络来学习。（神经网络只认数字不认英文的嘛）
import os
import numpy as np
import pandas as pd
import argparse
from gensim.models import word2vec
def train_word2vec(x):
model = word2vec.Word2Vec(x, size=250, window=5, min_count=5, workers=12, iter=10, sg=1)
return model
if __name__ == "__main__":
print("loading training data ...")
train_x, y = load_training_data('training_label.txt')
train_x_no_label = load_training_data('training_nolabel.txt')
print("loading testing data ...")
test_x = load_testing_data('testing_data.txt')
model = train_word2vec(train_x + train_x_no_label + test_x)
print("saving model ...")
model.save(os.path.join(path_prefix, 'w2v_all.model'))
- 定义数据预处理类
因为我们要面对的是文本数据，所以必须要进行数据预处理。为了后续的操作方便，作者在这里将其封装成了一个类。具体包括：
- 把之前训练好的word2vec模型读进来，保存训练好的embedding（这个embedding包含了训练word2vec模型时使用的各个参数）
- 把”PAD”或”UNK”加进embedding_matrix
- 制作embedding_matrix
- 将输入的句子的长度变成一致的，方便后续输入神经网络中
- 实现word2indx，把句子里面的字变成相对应的index
- 将label转为tensor格式
from torch import nn
from gensim.models import Word2Vec
class Preprocess():
def __init__(self, sentences, sen_len, w2v_path="./w2v.model"):
self.w2v_path = w2v_path
self.sentences = sentences
self.sen_len = sen_len
self.idx2word = []
self.word2idx = {}
self.embedding_matrix = []
def get_w2v_model(self):
self.embedding = Word2Vec.load(self.w2v_path)
self.embedding_dim = self.embedding.vector_size
def add_embedding(self, word):
vector = torch.empty(1, self.embedding_dim)
torch.nn.init.uniform_(vector)
self.word2idx[word] = len(self.word2idx)
self.idx2word.append(word)
self.embedding_matrix = torch.cat([self.embedding_matrix, vector], 0)
def make_embedding(self, load=True):
print("Get embedding ...")
if load:
print("loading word to vec model ...")
self.get_w2v_model()
else:
raise NotImplementedError
for i, word in enumerate(self.embedding.wv.vocab):
print('get words #{}'.format(i+1), end='\r')
self.word2idx[word] = len(self.word2idx)
self.idx2word.append(word)
self.embedding_matrix.append(self.embedding[word])
print('')
self.embedding_matrix = torch.tensor(self.embedding_matrix)
self.add_embedding("")
self.add_embedding("")
print("total words: {}".format(len(self.embedding_matrix)))
return self.embedding_matrix
def pad_sequence(self, sentence):
if len(sentence) > self.sen_len:
sentence = sentence[:self.sen_len]
else:
pad_len = self.sen_len - len(sentence)
for _ in range(pad_len):
sentence.append(self.word2idx[""])
assert len(sentence) == self.sen_len
return sentence
def sentence_word2idx(self):
sentence_list = []
for i, sen in enumerate(self.sentences):
print('sentence count #{}'.format(i+1), end='\r')
sentence_idx = []
for word in sen:
if (word in self.word2idx.keys()):
sentence_idx.append(self.word2idx[word])
else:
sentence_idx.append(self.word2idx[""])
sentence_idx = self.pad_sequence(sentence_idx)
sentence_list.append(sentence_idx)
return torch.LongTensor(sentence_list)
def labels_to_tensor(self, y):
y = [int(label) for label in y]
return torch.LongTensor(y)
- 制作Dataset
这一步相对比较简单，只是做了Dataset类
import torch
from torch.utils import data
class TwitterDataset(data.Dataset):
"""
Expected data shape like:(data_num, data_len)
Data can be a list of numpy array or a list of lists
input data shape : (data_num, seq_len, feature_dim)
__len__ will return the number of data
"""
def __init__(self, X, y):
self.data = X
self.label = y
def __getitem__(self, idx):
if self.label is None: return self.data[idx]
return self.data[idx], self.label[idx]
def __len__(self):
return len(self.data)
- 建立模型
建立我们之后要使用的LSTM模型，主要包括三块：
- embedding layer
- LSTM
- 全连接神经网络
embedding layer可以理解为将我们的文字进行编码，以使得LSTM可以看得懂，具体用到的方法就是word2vec模型。
LSTM模型主要需要输入：
- input_size: 输入特征维数，即每一行输入元素的个数
- hidden_size: 隐藏层状态的维数，即隐藏层节点的个数，这个和单层感知器的结构是类似的。
- num_layers: LSTM 堆叠的层数，默认值是1层，如果设置为2，第二个LSTM接收第一个LSTM的计算结果。
- batch_first: 输入输出的第一维是否为 batch_size，默认值 False。因为 Torch 中，人们习惯使用Torch中带有的dataset，dataloader向神经网络模型连续输入数据，这里面就有一个 batch_size 的参数，表示一次输入多少个数据。 在 LSTM 模型中，输入数据必须是一批数据，为了区分LSTM中的批量数据和dataloader中的批量数据是否相同意义，LSTM 模型就通过这个参数的设定来区分。
- dropout: 默认值0。是否在除最后一个 RNN 层外的其他 RNN 层后面加 dropout 层。
- bidirectional: 是否是双向 RNN，默认为：false，若为 true，则：num_directions=2，否则为1。
全连接神经网络主要是为了将LSTM的输出和最终的预测进行一下转换。
import torch
from torch import nn
class LSTM_Net(nn.Module):
def __init__(self, embedding, embedding_dim, hidden_dim, num_layers, dropout=0.5, fix_embedding=True):
super(LSTM_Net, self).__init__()
self.embedding = torch.nn.Embedding(embedding.size(0),embedding.size(1))
self.embedding.weight = torch.nn.Parameter(embedding)
self.embedding.weight.requires_grad = False if fix_embedding else True
self.embedding_dim = embedding.size(1)
self.hidden_dim = hidden_dim
self.num_layers = num_layers
self.dropout = dropout
self.lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers=num_layers, batch_first=True)
self.classifier = nn.Sequential( nn.Dropout(dropout),
nn.Linear(hidden_dim, 1),
nn.Sigmoid() )
def forward(self, inputs):
inputs = self.embedding(inputs)
x, _ = self.lstm(inputs, None)
x = x[:, -1, :]
x = self.classifier(x)
return x
- 定义模型训练函数
这个训练的过程跟之间的训练较为相似。注释给的很详细，可以通过注释理解一下。
import torch
from torch import nn
import torch.optim as optim
import torch.nn.functional as F
def training(batch_size, n_epoch, lr, model_dir, train, valid, model, device):
total = sum(p.numel() for p in model.parameters())
trainable = sum(p.numel() for p in model.parameters() if p.requires_grad)
print('\nstart training, parameter total:{}, trainable:{}\n'.format(total, trainable))
model.train()
criterion = nn.BCELoss()
t_batch = len(train)
v_batch = len(valid)
optimizer = optim.Adam(model.parameters(), lr=lr)
total_loss, total_acc, best_acc = 0, 0, 0
for epoch in range(n_epoch):
total_loss, total_acc = 0, 0
for i, (inputs, labels) in enumerate(train):
inputs = inputs.to(device, dtype=torch.long)
labels = labels.to(device, dtype=torch.float)
optimizer.zero_grad()
outputs = model(inputs)
outputs = outputs.squeeze()
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
correct = evaluation(outputs, labels)
total_acc += (correct / batch_size)
total_loss += loss.item()
print('[ Epoch{}: {}/{} ] loss:{:.3f} acc:{:.3f} '.format(
epoch+1, i+1, t_batch, loss.item(), correct*100/batch_size), end='\r')
print('\nTrain | Loss:{:.5f} Acc: {:.3f}'.format(total_loss/t_batch, total_acc/t_batch*100))
model.eval()
with torch.no_grad():
total_loss, total_acc = 0, 0
for i, (inputs, labels) in enumerate(valid):
inputs = inputs.to(device, dtype=torch.long)
labels = labels.to(device, dtype=torch.float)
outputs = model(inputs)
outputs = outputs.squeeze()
loss = criterion(outputs, labels)
correct = evaluation(outputs, labels)
total_acc += (correct / batch_size)
total_loss += loss.item()
print("Valid | Loss:{:.5f} Acc: {:.3f} ".format(total_loss/v_batch, total_acc/v_batch*100))
if total_acc > best_acc:
best_acc = total_acc
torch.save(model, "{}/ckpt.model".format(model_dir))
print('saving model with acc {:.3f}'.format(total_acc/v_batch*100))
print('-----------------------------------------------')
model.train()
8.定义模型测试函数
import torch
from torch import nn
import torch.optim as optim
import torch.nn.functional as F
def testing(batch_size, test_loader, model, device):
model.eval()
ret_output = []
with torch.no_grad():
for i, inputs in enumerate(test_loader):
inputs = inputs.to(device, dtype=torch.long)
outputs = model(inputs)
outputs = outputs.squeeze()
outputs[outputs>=0.5] = 1
outputs[outputs<0.5] = 0
ret_output += outputs.int().tolist()
return ret_output
-
调用之前的各个函数开始训练
-
整理好各个data的路径
- 定义句子长度、要不要固定embedding、batch大小、要训练的轮数epoch、learning rate的值、model的资料保存路径
- 读入数据
- input和labels做预处理
- 制作一个model的对象
- 把data分为training data和validation data(将一部分training data拿去当做validation data)
- 把data做成dataset供dataloader取用
- 把data 转成 batch of tensors
- 开始训练
import os
import torch
import argparse
import numpy as np
from torch import nn
from gensim.models import word2vec
from sklearn.model_selection import train_test_split
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
train_with_label = os.path.join(path_prefix, 'training_label.txt')
train_no_label = os.path.join(path_prefix, 'training_nolabel.txt')
testing_data = os.path.join(path_prefix, 'testing_data.txt')
w2v_path = os.path.join(path_prefix, 'w2v_all.model')
sen_len = 30
fix_embedding = True
batch_size = 128
epoch = 5
lr = 0.001
model_dir = path_prefix
print("loading data ...")
train_x, y = load_training_data(train_with_label)
train_x_no_label = load_training_data(train_no_label)
preprocess = Preprocess(train_x, sen_len, w2v_path=w2v_path)
embedding = preprocess.make_embedding(load=True)
train_x = preprocess.sentence_word2idx()
y = preprocess.labels_to_tensor(y)
model = LSTM_Net(embedding, embedding_dim=250, hidden_dim=250, num_layers=1, dropout=0.5, fix_embedding=fix_embedding)
model = model.to(device)
X_train, X_val, y_train, y_val = train_x[:190000], train_x[190000:], y[:190000], y[190000:]
train_dataset = TwitterDataset(X=X_train, y=y_train)
val_dataset = TwitterDataset(X=X_val, y=y_val)
train_loader = torch.utils.data.DataLoader(dataset = train_dataset,
batch_size = batch_size,
shuffle = True,
num_workers = 8)
val_loader = torch.utils.data.DataLoader(dataset = val_dataset,
batch_size = batch_size,
shuffle = False,
num_workers = 8)
training(batch_size, epoch, lr, model_dir, train_loader, val_loader, model, device)
训练结果如下：
- 进行预测并保存结果
print("loading testing data ...")
test_x = load_testing_data(testing_data)
preprocess = Preprocess(test_x, sen_len, w2v_path=w2v_path)
embedding = preprocess.make_embedding(load=True)
test_x = preprocess.sentence_word2idx()
test_dataset = TwitterDataset(X=test_x, y=None)
test_loader = torch.utils.data.DataLoader(dataset = test_dataset,
batch_size = batch_size,
shuffle = False,
num_workers = 8)
print('\nload model ...')
model = torch.load(os.path.join(model_dir, 'ckpt.model'))
outputs = testing(batch_size, test_loader, model, device)
tmp = pd.DataFrame({"id":[str(i) for i in range(len(test_x))],"label":outputs})
print("save csv ...")
tmp.to_csv(os.path.join(path_prefix, 'predict.csv'), index=False)
print("Finish Predicting")
Original: https://blog.csdn.net/hello_JeremyWang/article/details/121071281
Author: hello_JeremyWang
Title: Pytorch实战__LSTM做文本分类
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/707809/
转载文章受原作者版权保护。转载请注明原作者出处！