机器学习homework1

!nvidia-smi #查看gpu型号，cpu和amd显卡不适用

#下载数据集
!wget -O covid_train.csv https://www.dropbox.com/s/lmy1riadzoy0ahw/covid.train.csv?dl=0
!wget -O covid_test.csv https://www.dropbox.com/s/zalbw42lu4nmhr2/covid.test.csv?dl=0


#导入相关的包
# Numerical Operations
import math
import numpy as np

# Reading/Writing Data
import pandas as pd
import os
import csv

# For Progress Bar
from tqdm import tqdm

# Pytorch
import torch 
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader, random_split

# For plotting learning curve
from torch.utils.tensorboard import SummaryWriter


#一些函数
def same_seed(seed): 
    '''Fixes random number generator seeds for reproducibility.'''
    torch.backends.cudnn.deterministic = True
    torch.backends.cudnn.benchmark = False
    np.random.seed(seed)
    torch.manual_seed(seed)  #每次产生随机数为一致的随机数
    if torch.cuda.is_available():
        torch.cuda.manual_seed_all(seed)

def train_valid_split(data_set, valid_ratio, seed):#将训练数据分成训练数据集和验证数据集
    '''Split provided training data into training set and validation set'''
    valid_set_size = int(valid_ratio * len(data_set)) 
    train_set_size = len(data_set) - valid_set_size
    train_set, valid_set = random_split(data_set, [train_set_size, valid_set_size], generator=torch.Generator().manual_seed(seed))#随机分割
    return np.array(train_set), np.array(valid_set)

def predict(test_loader, model, device):
    model.eval() # Set your model to evaluation mode.，设置成验证/测试模式
    preds = []
    for x in tqdm(test_loader):
        x = x.to(device)                        
        with torch.no_grad():                   
            pred = model(x)   #将输入转换成输出                  
            preds.append(pred.detach().cpu())   
    preds = torch.cat(preds, dim=0).numpy()  
    return preds


#创建数据集
class COVID19Dataset(Dataset):
    '''
    x: Features.
    y: Targets, if none, do prediction.
    '''
    def __init__(self, x, y=None):
        if y is None:
            self.y = y
        else:
            self.y = torch.FloatTensor(y)  #类型转换
        self.x = torch.FloatTensor(x)

    def __getitem__(self, idx):
        if self.y is None:
            return self.x[idx]
        else:
            return self.x[idx], self.y[idx]

    def __len__(self):
        return len(self.x)


#定义模型
class My_Model(nn.Module):
    def __init__(self, input_dim):
        super(My_Model, self).__init__()
        # TODO: modify model's structure, be aware of dimensions.#创建神经网络
        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) # (B, 1) -> (B)
        return x


#选择合适的特征来进行回归，即为多少个x对应一个y
def select_feat(train_data, valid_data, test_data, select_all=True):
    '''Selects useful features to perform regression'''
    y_train, y_valid = train_data[:,-1], valid_data[:,-1] #表示选取所有行的最后一列。
    raw_x_train, raw_x_valid, raw_x_test = train_data[:,:-1], valid_data[:,:-1], test_data  #取除最后一列之外的所有列

    if select_all:
        feat_idx = list(range(raw_x_train.shape[1]))    #获得有多少列
    else:
        feat_idx = [1,2,3,4,5,6,7,8,10,20,25,26,30,35,36,38] # TODO: Select suitable feature columns.   #自己选择某几列

    return raw_x_train[:,feat_idx], raw_x_valid[:,feat_idx], raw_x_test[:,feat_idx], y_train, y_valid


#进行训练
def trainer(train_loader, valid_loader, model, config, device):

    criterion = nn.MSELoss(reduction='mean') # Define your loss function, do not modify this.

    # Define your optimization algorithm.
    # TODO: Please check https://pytorch.org/docs/stable/optim.html to get more available algorithms.
    # TODO: L2 regularization (optimizer(weight decay...) or implement by your self).
    optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.7, weight_decay=0.01)
    writer = SummaryWriter() # Writer of tensoboard.

    if not os.path.isdir('./models'):
        os.mkdir('./models') # Create directory of saving models.

    n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0

    for epoch in range(n_epochs):   #n_epochs次循环次数，可以提前终止，第几轮训练
        model.train() # Set your model to train mode.  设置成训练模式
        loss_record = []

        # tqdm is a package to visualize your training progress.
        train_pbar = tqdm(train_loader, position=0, leave=True)

        for x, y in train_pbar:                
            optimizer.zero_grad()               # Set gradient to zero.
            x, y = x.to(device), y.to(device)   # Move your data to device.
            pred = model(x)
            loss = criterion(pred, y)
            loss.backward()                     # Compute gradient(backpropagation).
            optimizer.step()                    # Update parameters.
            step += 1                      #第几次训练
            loss_record.append(loss.detach().item())

            # Display current epoch number and loss on tqdm progress bar.
            train_pbar.set_description(f'Epoch [{epoch+1}/{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)

        model.eval() # Set your model to evaluation mode.
        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.item())

        mean_valid_loss = sum(loss_record)/len(loss_record)
        print(f'Epoch [{epoch+1}/{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']) # Save your best model，保存模型官方推荐
            print('Saving model with loss {:.3f}...'.format(best_loss))
            early_stop_count = 0
        else:
            early_stop_count += 1

        if early_stop_count >= config['early_stop']:
            print('\nModel is not improving, so we halt the training session.')
            return


#配置一些参数
device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
    'seed': 5201314,      # Your seed number, you can pick your lucky number. :)
    'select_all': False,   # Whether to use all features.
    'valid_ratio': 0.2,   # validation_size = train_size * valid_ratio，验证集的比率
    'n_epochs': 5000,     # Number of epochs.   迭代次数
    'batch_size': 256,
    'learning_rate': 1e-5,
    'early_stop': 600,    # If model has not improved for this many consecutive epochs, stop training.    #提前终止的循环次数
    'save_path': './models/model.ckpt'  # Your model will be saved here.  #模型保存的路径
}

#准备一些数据
same_seed(config['seed'])
train_data, test_data = pd.read_csv('./covid_train.csv').values, pd.read_csv('./covid_test.csv').values
train_data, valid_data = train_valid_split(train_data, config['valid_ratio'], config['seed'])

# Print out the data size.
print(f"""train_data size: {train_data.shape}
valid_data size: {valid_data.shape}
test_data size: {test_data.shape}""")

# Select features
x_train, x_valid, x_test, y_train, y_valid = select_feat(train_data, valid_data, test_data, config['select_all'])  #实际用于训练的数据

# Print out the number of features.
print(f'number of features: {x_train.shape[1]}')

train_dataset, valid_dataset, test_dataset = COVID19Dataset(x_train, y_train), \
                                            COVID19Dataset(x_valid, y_valid), \
                                            COVID19Dataset(x_test)        #将其转换成torch格式


# Pytorch data loader loads pytorch dataset into batches.训练，验证，测试集
train_loader = DataLoader(train_dataset, batch_size=config['batch_size'], shuffle=True, pin_memory=True)
valid_loader = DataLoader(valid_dataset, batch_size=config['batch_size'], shuffle=True, pin_memory=True)
test_loader = DataLoader(test_dataset, batch_size=config['batch_size'], shuffle=False, pin_memory=True)


#开始训练
model = My_Model(input_dim=x_train.shape[1]).to(device) # put your model and data on the same computation device.有多少列
trainer(train_loader, valid_loader, model, config, device)


#之后可以使用命令进行查看绘制的曲线
%reload_ext tensorboard
%tensorboard --logdir=./runs/


# def save_pred(preds, file):
#     ''' Save predictions to specified 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])

# model = My_Model(input_dim=x_train.shape[1]).to(device)
# model.load_state_dict(torch.load(config['save_path']))#利用保存的模型进行预测
# preds = predict(test_loader, model, device)
# save_pred(preds, 'pred.csv')