读取训练集和测试集的数据文件

train_df = pd.read_excel(train_data_path) test_df = pd.read_excel(test_data_path)

将数据进行归一化处理

train_df_values = train_df.values test_df_values = test_df.values

train_data = train_df_values[:, 1 :-1] train_data = (train_data - np.min(train_data)) / (np.max(train_data) - np.min(train_data)) # 最值归一化 train_data = np.expand_dims(train_data, axis=1) # 增加维度，变成[batch_size,1,features] train_label = train_df_values[:, -1] train_label = train_label.astype(np.uint8) train_data, train_label = torch.FloatTensor(train_data), torch.LongTensor(train_label)

test_data = test_df_values[:, 1 :-1] test_data = (test_data - np.min(test_data)) / (np.max(test_data) - np.min(test_data)) # 最值归一化 test_data = np.expand_dims(test_data, axis=1) # 增加维度，变成[batch_size,1,features] test_label = test_df_values[:, -1] test_label = test_label.astype(np.uint8) test_data, test_label = torch.FloatTensor(test_data), torch.LongTensor(test_label)

对读取的数据进行最值归一化处理，并将数据增加维度，以便后续进行模型训练和测试。最后将数据转换成PyTorch的张量数据。