使用自己的数据利用pytorch搭建全连接神经网络进行分类预测

  • 1、导入库
  • 2、自定义函数
  • 3、定义主函数main()
  • 4、执行
  • 5、完整代码部分

这段代码实现了一个神经网络模型在数据集上的训练和测试。具体流程如下：

1、导入库

引入必要的库，包括PyTorch、Pandas等。

2、自定义函数

（1）定义数据预处理函数zscore()，用于将数据进行标准化处理。
（2）定义MyDataset类，继承自pytorch的Dataset类，用于加载数据集并封装为可迭代对象。
（3）定义神经网络模型Net类，继承自nn.Module类，包含若干个全连接层和Dropout层，以及ReLU激活函数。
（4）定义训练模型函数train_model()，用于对模型进行训练，并返回每次训练的损失值和精度。
（5）定义测试模型函数test_model()，用于对模型进行测试，并返回每次测试的损失值和精度。

3、定义主函数main()

（1）定义超参数，包括输入数据的维度、输出类别数、学习率、训练代数、批次大小、dropout比例等。
（2）加载数据集，提取特征和标签，将数据集分割为训练集和测试集，并进行标准化处理。
（3）创建tensor数据集，创建训练集和测试集的DataLoader对象，用于批量读取数据。
（4）初始化模型、损失函数和优化器。
（5）对模型进行训练，并输出每次训练和测试的损失值和精度。

4、执行

主函数被调用以执行整个程序。

5、完整代码部分

import torchimport torch.nn as nnimport torch.optim as optimimport torchvision.transforms as transformsfrom torch.utils.data import DataLoader, Datasetimport pandas as pdfrom sklearn import preprocessingfrom sklearn.model_selection import train_test_splitdef zscore(train, test):standardScaler = preprocessing.StandardScaler()standardScaler.fit(train)train_data = standardScaler.transform(train)test_data = standardScaler.transform(test)return train_data, test_dataclass MyDataset(Dataset):def __init__(self, data, labels):self.data = dataself.labels = labelsdef __len__(self):return len(self.data)def __getitem__(self, index):sample = torch.tensor(self.data[index], dtype=torch.float32)label = torch.tensor(self.labels[index], dtype=torch.long)return sample, label# 定义神经网络模型class Net(nn.Module):def __init__(self, input_size, output_size, dropout_prob):super(Net, self).__init__()self.fc1 = nn.Linear(input_size, 128)self.fc2 = nn.Linear(128, 512)self.fc3 = nn.Linear(512, 256)self.fc4 = nn.Linear(256, 128)self.fc5 = nn.Linear(128, output_size)self.dropout = nn.Dropout(dropout_prob)self.relu = nn.ReLU()def forward(self, x):x = self.dropout(self.relu(self.fc1(x)))x = self.dropout(self.relu(self.fc2(x)))x = self.dropout(self.relu(self.fc3(x)))x = self.dropout(self.relu(self.fc4(x)))x = self.fc5(x)return x# 训练模型def train_model(model, train_loader, criterion, optimizer):model.train()running_loss = 0.0correct = 0total = 0for i, data in enumerate(train_loader, 0):inputs, labels = dataoptimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, labels)loss.backward()optimizer.step()running_loss += loss.item()_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()train_loss = running_loss / len(train_loader)train_acc = 100 * correct / totalreturn train_loss, train_acc# 测试模型def test_model(model, test_loader, criterion):model.eval()running_loss = 0.0correct = 0total = 0with torch.no_grad():for data in test_loader:inputs, labels = dataoutputs = model(inputs)loss = criterion(outputs, labels)running_loss += loss.item()_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()test_loss = running_loss / len(test_loader)test_acc = 100 * correct / totalreturn test_loss, test_acc# 主函数def main():# 定义超参数input_size = 9 # 输入数据的维度，可参考feature_select的个数output_size = 4 # 类别数learning_rate = 0.005 # 学习率num_epochs = 300 # 训练代数batch_size = 128 # 每次训练的批次大小dropout_prob = 0.2 # dropout的比例data_path = 'dataset.csv' #数据的路径feature_select = ['timestamp', 'day_of_week', 'is_weekend', 'is_holiday', 'temperature','is_start_of_semester', 'is_during_semester', 'month', 'hour']# 定义数据预处理操作,图像专用# transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(0, 1)])# load datadata = pd.read_csv(data_path, engine='python')# 提取特征和标签x_data, y_data = data[feature_select], data["label"]test_size = 0.25# 测试集大小为20%， 80%/20%分x_train, x_test, y_train, y_test = train_test_split(x_data.values, y_data.values, test_size=test_size, random_state=0)# 标准化x_train, x_test = zscore(x_train, x_test)# 加载数据集train_dataset = MyDataset(x_train, y_train)test_dataset = MyDataset(x_test, y_test)train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)# 初始化模型、损失函数和优化器model = Net(input_size, output_size, dropout_prob)criterion = nn.CrossEntropyLoss()optimizer = optim.Adam(model.parameters(), lr=learning_rate)# 训练模型for epoch in range(num_epochs):train_loss, train_acc = train_model(model, train_loader, criterion, optimizer)test_loss, test_acc = test_model(model, test_loader, criterion)print('Epoch [{}/{}], Train Loss: {:.4f}, Train Acc: {:.2f}%, Test Loss: {:.4f}, Test Acc: {:.2f}%'.format(epoch + 1, num_epochs, train_loss, train_acc, test_loss, test_acc))if __name__ == '__main__':main()