eg美国新冠预测参考【2022版李宏毅机器学习作业讲解】-HW1_哔哩哔哩_bilibili一、引入需要的库import math import numpy as np #矩阵处理 import pandas as pd #读取excel import os import csv from tqdm import tqdm #进度条 import torch import torch.nn as nn from torch.utils.data import DataLoader,Dataset,random_split from torch.utils.tensorboard import SummaryWriter二、相关函数与参数准备1.设置随机种子#设置随机种子,以实现结果可重复-》复现实验结果可当作模板使用 def same_seed(seed): torch.backends.cudnn.deterministic True torch.backends.cudnn.benchmark False np.random.seed(seed) torch.manual_seed(seed) if torch.cuda.is_available(): torch.cuda.manual_seed_all(seed)2.准备数据#划分数据集,划分出训练集和验证集 def train_valid_split(data_set,valid_radio,seed): valid_data_size int(len(data_set)*valid_radio) train_data_size len(data_set) - valid_data_size train_data,valid_data random_split(data_set,[train_data_size,valid_data_size],generatortorch.Generator().manual_seed(seed)) return np.array(train_data),np.array(valid_data)3.选择特征#选择特征 def select_feat(train_data,valid_data,test_data,select_all True): #选择label y_train train_data[:,-1] y_valid valid_data[:,-1] #选择feature raw_x_train train_data[:,:-1] #除了最后一列 raw_x_valid valid_data[:,:-1] raw_x_test test_data if select_all: feat_idx list(range(raw_x_train.shape[1])) else: feat_idx [0,1,2,3,4] return raw_x_train[:,feat_idx],raw_x_valid[:,feat_idx],raw_x_test[:,feat_idx],y_train,y_valid4.构造数据集#数据集 class COVID19Dataset(Dataset): def __init__(self,features,targetsNone): if targets is None: self.targets targets else: self.targets torch.FloatTensor(targets) self.features torch.FloatTensor(features) def __getitem__(self, idx): if self.targets is None: return self.features[idx] else: return self.features[idx],self.targets[idx] def __len__(self): return len(self.features)5.构造网络结构#神经网络 class My_Model(nn.Module): def __init__(self, input_dim): super(My_Model,self).__init__() self.layers nn.Sequential( nn.Linear(input_dim,16), nn.ReLU(), nn.Linear(16,8), nn.ReLU(), nn.Linear(8,1) ) def forward(self,x): x self.layers(x) x x.squeeze(1) return x6、参数设置#参数设置 device cuda if torch.cuda.is_available() else cpu config { seed:1122408, select_all:True, valid_radio:0.2, n_epochs:3000, batch_size:256, learning_rate:1e-5, early_stop:400, save_path:./models/model.ckpt }7.训练过程#训练过程 def trainer(train_loader,valid_loader,model,config,device): criterion nn.MSELoss(reductionmean) optimizer torch.optim.SGD(model.parameters(),lr config[learning_rate],momentum0.9) writer SummaryWriter() #可视化可注释 if not os.path.isdir(./models): os.mkdir(./models) n_epochs config[n_epochs] best_loss math.inf step 0 early_stop_count 0 for epoch in range(n_epochs): model.train() loss_record [] train_pbar tqdm(train_loader,position0,leaveTrue) #进度条可视化显示 #train loop for x,y in train_pbar: optimizer.zero_grad() x,y x.to(device),y.to(device) pred model(x) loss criterion(pred,y) loss.backward() optimizer.step() step 1 loss_record.append(loss.detach().item()) #显示训练过程 train_pbar.set_description(fEpoch[{epoch1}/{n_epochs}]) train_pbar.set_postfix({loss:loss.detach().item()}) mean_train_loss sum(loss_record) / len(loss_record) writer.add_scalar(Loss/train,mean_train_loss,step)#可视化图表 #valid loop model.eval() loss_record [] for x,y in valid_loader: x,y x.to(device),y.to(device) with torch.no_grad(): pred model(x) loss criterion(pred,y) loss_record.append(loss.detach().item()) mean_valid_loss sum(loss_record) / len(loss_record) print(fEpoch[{epoch1}/{n_epochs}]: Train loss:{mean_train_loss:.4f},Valid loss:{mean_valid_loss:.4f}) writer.add_scalar(Loss/valid,mean_valid_loss,step) if mean_valid_loss best_loss: best_loss mean_valid_loss torch.save(model.state_dict(),config[save_path]) print(Saving model with loss {:.3}..format(best_loss)) early_stop_count 0 else: early_stop_count 1 if early_stop_count config[early_stop]: print(\n Model is not improvinng, so we halt train session.) return三、开始训练前的准备工作准备工作 # 1.设置随机种子 same_seed(config[seed]) # 2.准备数据 # pandas库读取数据 train_data pd.read_csv(./covid.train_new.csv).values test_data pd.read_csv(./covid.test_un.csv).values # 划分数据集 train_data,valid_data train_valid_split(train_data,config[valid_radio],config[seed]) print(ftrain_data size:{train_data.shape},valid_data size:{valid_data.shape},test_data size:{test_data.shape}) # 3.选择特征 x_train,x_valid,x_test, y_train,y_valid select_feat(train_data,valid_data,test_data,config[select_all]) print(fthe number of feature: {x_train.shape[1]}) # 4.构造数据集 train_dataset COVID19Dataset(x_train,y_train) valid_dataset COVID19Dataset(x_valid,y_valid) test_dataset COVID19Dataset(x_test) # 5.封装加载数据集 train_loader DataLoader(train_dataset,batch_sizeconfig[batch_size],shuffleTrue,pin_memoryTrue) valid_loader DataLoader(valid_dataset,batch_sizeconfig[batch_size],shuffleTrue,pin_memoryTrue) test_loader DataLoader(test_dataset,batch_sizeconfig[batch_size],shuffleFalse,pin_memoryTrue)四、开始训练开始训练 model My_Model(input_dimx_train.shape[1]).to(device) trainer(train_loader,valid_loader,model,config,device) #根据测试集进行预测 def predict(test_loader,model,device): model.eval() preds [] for x in tqdm(test_loader): x x.to(device) with torch.no_grad(): pred model(x) preds.append(pred.detach().cpu()) preds torch.cat(preds,dim0).numpy() #转化成numpy数组 return preds def save_pred(preds,file): with open(file,w) as fp: writer csv.writer(fp) writer.writerow([id,tested_positive]) for i,p in enumerate(preds): writer.writerow([i,p]) #预测并保存结果 model My_Model(input_dimx_train.shape[1]).to(device) model.load_state_dict(torch.load(config[save_path])) preds predict(test_loader,model,device) save_pred(preds,pred.csv)