回归实战2

import torch import matplotlib.pyplot as plt #画图 import matplotlib import numpy as np #矩阵相关 import csv #csv文件 import pandas #csv文件 from torch.utils.data import Dataset, DataLoader import torch.nn as nn from torch import optim import time class CovidDataset(Dataset): def __init__(self, file_path, mode): #mode用来选择是训练集验证集还是测试集 with open(file_path, r) as f: ori_data list(csv.reader(f)) #读文件 csv_data np.array(ori_data)[1:, 1:].astype(float) #不要第一行和第一列并转化为数字 #逢五取1不推荐 if mode train: indices [i for i in range(len(csv_data)) if i % 5 ! 0] #取下标 elif mode val: indices [i for i in range(len(csv_data)) if i % 5 0] elif mode test: indices [i for i in range(len(csv_data))] X torch.tensor(csv_data[indices, :93]) #剩下的数据取x转化为张量 if mode ! test: self.Y torch.tensor(csv_data[indices, -1]) #取y self.X (X - X.mean(dim0, keepdimTrue)) / X.std(dim0, keepdimTrue) #对每一列标准化数据的量纲不一样需要标准化x-均值/标准差 self.mode mode def __getitem__(self, item): #给一个下标返回数值 if self.mode test: #依旧测试集没有y return self.X[item].float() #将x的值转化为32位 else: return self.X[item].float(), self.Y[item].float() def __len__(self): return len(self.X) class myModel(nn.Module): def __init__(self, inDim): #输入维度 super(myModel, self).__init__() self.fc1 nn.Linear(inDim, 128) #全连接 self.relu1 nn.ReLU() #激活函数 self.fc2 nn.Linear(128, 1) def forward(self, x): #数据x通过模型 x self.fc1(x) x self.relu1(x) x self.fc2(x) if len(x.size()) 1: x x.squeeze(1) #如果x维度大于1 就去掉第二个维度与y的维度保持一致 return x def train_val(model, train_loader, val_loader, lr, optimizer, device, epochs, save_path): model model.to(device) #防止意外 plt_train_loss [] #总训练loss plt_val_loss [] min_val_loss 999999999999999999.9 for epoch in range(epochs): #发枪指令 冲锋的号角 模型训练的开始 model.train() start_time time.time() train_loss 0.0 #浮点形式 for x, y in train_loader: x, y x.to(device), y.to(device) y_pred model(x) bat_loss loss(y_pred, y, model) bat_loss.backward() optimizer.step() optimizer.zero_grad() train_loss bat_loss.cpu().item() plt_train_loss.append(train_loss/train_loader.__len__()) model.eval() val_loss 0.0 with torch.no_grad(): for val_x, val_y in val_loader: val_x, val_y val_x.to(device), val_y.to(device) val_pred_y model(val_x) val_bat_loss loss(val_pred_y, val_y, model) val_loss val_bat_loss.cpu().item() plt_val_loss.append(val_loss / val_loader.__len__()) #保存 if val_loss min_val_loss: min_val_loss val_loss torch.save(model, save_path) print([%03d/%03d] %2.2f sec(s) train_loss: %.6f val_loss:%.6f % \ (epoch, epochs, time.time()-start_time, plt_train_loss[-1], plt_val_loss[-1])) plt.plot(plt_train_loss) plt.plot(plt_val_loss) plt.title(loss) plt.legend([train, val]) plt.show() def evaluate(model_path, test_loader, rel_path, device): model torch.load(model_path).to(device) rel [] #记录预测结果 model.eval() with torch.no_grad(): for x in test_loader: x x.to(device) pred model(x) rel.append(pred.cpu().item()) with open(rel_path, w, newline) as f: csv_writer csv.writer(f) csv_writer.writerow([id, tested_positive]) for i, pred in enumerate(rel): #同时得到 第几个 和第几个的结果 enumrate csv_writer.writerow([str(i), str(pred)]) print(结果保存到了rel_path) train_file rD:\共享文件夹\李哥考研\课程\人工智能课程\beike代码\covid\covid.train.csv test_file rD:\共享文件夹\李哥考研\课程\人工智能课程\beike代码\covid\covid.test.csv # for x, y in train_set: # pred_y model(x) # print(pred_y) batch_size 16 train_set CovidDataset(train_file, train) val_set CovidDataset(train_file, val) test_set CovidDataset(test_file, test) train_loader DataLoader(train_set, batch_sizebatch_size, shuffleTrue) #取batch_size的数据打乱随机选 val_loader DataLoader(val_set, batch_sizebatch_size, shuffleTrue) test_loader DataLoader(test_set, batch_size1, shuffleFalse) def mseLoss(pred, target, model): loss nn.MSELoss(reductionmean) #平方差损失 Calculate loss regularization_loss 0 # 正则项 for param in model.parameters(): # TODO: you may implement L1/L2 regularization here # 使用L2正则项 # regularization_loss torch.sum(abs(param)) regularization_loss torch.sum(param ** 2) # 计算所有参数平方 return loss(pred, target) 0.00075 * regularization_loss # 返回损失。 loss mseLoss #损失函数 epochs 20 #运行轮次 lr 0.001 #学习率 device cuda if torch.cuda.is_available() else cpu #选择设备 print(device) data_dim 93 model myModel(data_dim).to(device) #数据放在设备上 save_path model_save/best_model.pth rel_path pred.csv optimizer optim.SGD(paramsmodel.parameters(), lrlr, momentum0.9) #优化器梯度下降momentum动量 train_val(model, train_loader, val_loader, lr, optimizer, device, epochs, save_path) #提交 evaluate(save_path, test_loader, rel_path, device)