上周学习了训练word2vec模型,这周进行相关实战
1. 导入所需库和设备配置
import torch
import torch.nn as nn
import torchvision
from torchvision import transforms, datasets
import os, PIL, pathlib, warnings
warnings.filterwarnings("ignore") # 忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
import pandas as pd
2. 加载数据
train_data = pd.read_csv('./train.csv', sep='\t', header=None)
print(train_data)
3. 数据预处理
def coustom_data_iter(texts, labels):
for x, y in zip(texts, labels):
yield x, y
x = train_data[0].values[:]
y = train_data[1].values[:]
from gensim.models.word2vec import Word2Vec
import numpy as np
w2v = Word2Vec(vector_size=100, min_count=3)
w2v.build_vocab(x)
w2v.train(x, total_examples=w2v.corpus_count, epochs=20)
- 定义自定义数据迭代器
coustom_data_iter
。 - 提取文本和标签数据。
- 使用
Word2Vec
训练词向量模型,设置词向量维度为100,最小词频为3。
def average_vec(text):
vec = np.zeros(100).reshape((1, 100))
for word in text:
try:
vec += w2v.wv[word].reshape((1, 100))
except KeyError:
continue
return vec
x_vec = np.concatenate([average_vec(z) for z in x])
w2v.save('w2v_model.pkl')
train_iter = coustom_data_iter(x_vec, y)
print(len(x), len(x_vec))
label_name = list(set(train_data[1].values[:]))
print(label_name)
text_pipeline = lambda x: average_vec(x)
label_pipeline = lambda x: label_name.index(x)
print(text_pipeline("你在干嘛"))
print(label_pipeline("Travel-Query"))
- 定义函数
average_vec
,将文本转换为词向量的平均值。 - 将所有文本转换为词向量并保存
Word2Vec
模型。 - 打印文本和向量的数量,以及所有标签的名称。
- 定义文本和标签的预处理函数
text_pipeline
和label_pipeline
。
4. 数据加载器
from torch.utils.data import DataLoader
def collate_batch(batch):
label_list, text_list = [], []
for (_text, _label) in batch:
label_list.append(label_pipeline(_label))
processed_text = torch.tensor(text_pipeline(_text), dtype=torch.float32)
text_list.append(processed_text)
label_list = torch.tensor(label_list, dtype=torch.int64)
text_list = torch.cat(text_list)
return text_list.to(device), label_list.to(device)
dataloader = DataLoader(train_iter, batch_size=8, shuffle=False, collate_fn=collate_batch)
- 定义函数
collate_batch
,将批次中的文本和标签转换为张量。 - 创建数据加载器
dataloader
。
5. 定义模型
class TextClassificationModel(nn.Module):
def __init__(self, num_class):
super(TextClassificationModel, self).__init__()
self.fc = nn.Linear(100, num_class)
def forward(self, text):
return self.fc(text)
num_class = len(label_name)
model = TextClassificationModel(num_class).to(device)
- 定义文本分类模型
TextClassificationModel
,包含一个全连接层。 - 初始化模型,设置输出类别数。
6. 训练和评估函数
import time
def train(dataloader):
model.train()
total_acc, train_loss, total_count = 0, 0, 0
log_interval = 50
start_time = time.time()
for idx, (text, label) in enumerate(dataloader):
predicted_label = model(text)
optimizer.zero_grad()
loss = criterion(predicted_label, label)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), 0.1)
optimizer.step()
total_acc += (predicted_label.argmax(1) == label).sum().item()
train_loss += loss.item()
total_count += label.size(0)
if idx % log_interval == 0 and idx > 0:
elapsed = time.time() - start_time
print('| epoch {:1d} | {:4d}/{:4d} batches | train_acc {:4.3f} train_loss {:4.5f}'.format(
epoch, idx, len(dataloader), total_acc / total_count, train_loss / total_count))
total_acc, train_loss, total_count = 0, 0, 0
start_time = time.time()
def evaluate(dataloader):
model.eval()
total_acc, train_loss, total_count = 0, 0, 0
with torch.no_grad():
for idx, (text, label) in enumerate(dataloader):
predicted_label = model(text)
loss = criterion(predicted_label, label)
total_acc += (predicted_label.argmax(1) == label).sum().item()
train_loss += loss.item()
total_count += label.size(0)
return total_acc / total_count, train_loss / total_count
- 定义训练函数
train
和评估函数evaluate
。
7. 训练模型
from torch.utils.data.dataset import random_split
from torchtext.data.functional import to_map_style_dataset
EPOCHS = 10
LR = 5
BATCH_SIZE = 64
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=LR)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.1)
total_accu = None
train_iter = coustom_data_iter(train_data[0].values[:], train_data[1].values[:])
train_dataset = to_map_style_dataset(train_iter)
split_train_, split_valid_ = random_split(train_dataset, [int(len(train_dataset) * 0.8), int(len(train_dataset) * 0.2)])
train_dataloader = DataLoader(split_train_, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
valid_dataloader = DataLoader(split_valid_, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
for epoch in range(1, EPOCHS + 1):
epoch_start_time = time.time()
train(train_dataloader)
val_acc, val_loss = evaluate(valid_dataloader)
lr = optimizer.state_dict()['param_groups'][0]['lr']
if total_accu is not None and total_accu > val_acc:
scheduler.step()
else:
total_accu = val_acc
print('-' * 69)
print('| epoch {:1d} | time: {:4.2f}s | valid_acc {:4.3f} valid_loss {:4.3f} | lr {:4.6f}'.format(
epoch, time.time() - epoch_start_time, val_acc, val_loss, lr))
print('-' * 69)
test_acc, test_loss = evaluate(valid_dataloader)
print('模型准确率为:{:5.4f}'.format(test_acc))
- 定义超参数并初始化损失函数、优化器和学习率调度器。
- 创建数据集并进行训练集和验证集的划分。
- 训练模型并在每个epoch后进行验证。
8. 预测函数
def predict(text, text_pipeline):
with torch.no_grad():
text = torch.tensor(text_pipeline(text), dtype=torch.float32)
print(text.shape)
output = model(text)
return output.argmax(1).item()
ex_text_str = "还有双鸭山到淮阴的汽车票吗13号的"
model = model.to("cpu")
print("该文本的类别是:%s" % label_name[predict(ex_text_str, text_pipeline)])
- 定义预测函数
predict
,将文本转换为张量并使用模型进行预测。 - 使用示例文本进行预测并输出结果。