李宏毅2023机器学习作业1--homework1

一、前期准备

下载训练数据和测试数据

# dropbox link
!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

导入包

# Numerical Operations
import math
import numpy as np        # numpy操作数据，增加删除查找修改

# Reading/Writing Data
import pandas as pd       # pandas读取csv文件
import os                 # 进行文件夹操作
import csv

# For Progress Bar
from tqdm import tqdm     # 可视化

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

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

定义一些功能函数

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)
    if torch.cuda.is_available():
        torch.cuda.manual_seed_all(seed)

# 划分训练数据集和验证数据集
def train_valid_split(data_set, valid_ratio, seed):
    '''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))
    return np.array(train_set), np.array(valid_set)

配置项

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
    'n_epochs': 5000,     # Number of epochs.
    'batch_size': 256,
    'learning_rate': 1e-5,
    'early_stop': 600,    # If model has not improved for this many consecutive epochs, stop training.
    'save_path': './models/model.ckpt'  # Your model will be saved here.
}

二、创建数据

创建Dataset

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)
        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)

特征选择

删除了belife和mental 的特征，belife和mental都是心理上精神上的特征，感觉可能和阳性率的偏差较大，就删去了这两类的特征

def select_feat(train_data, valid_data, test_data, select_all=True):
    '''Selects useful features to perform regression'''
    # [:,-1]第一个维度选择所有，选取所有行，第二个维度选择-1，-1是倒数第一个元素，也就是标签label
    y_train, y_valid = train_data[:,-1], valid_data[:,-1]   # 选择标签元素
    # [:,:-1]第一个维度选择所有，所有行，第二个维度从开始元素到倒数第一个元素（不包含倒数第一个元素）
    raw_x_train, raw_x_valid, raw_x_test = train_data[:,:-1], valid_data[:,:-1], test_data

    if select_all:
        feat_idx = list(range(raw_x_train.shape[1]))
    else:
        # feat_idx = list(range(35, raw_x_train.shape[1])) # TODO: Select suitable feature columns.
        """删除了belife和mental 的特征
        [0, 38, 39, 46, 51, 56, 57, 64, 69, 74, 75, 82, 87]是belife和mental所在列
        """
        del_col = [0, 38, 39, 46, 51, 56, 57, 64, 69, 74, 75, 82, 87]  
        raw_x_train = np.delete(raw_x_train, del_col, axis=1) # numpy数组增删查改方法
        raw_x_valid = np.delete(raw_x_valid, del_col, axis=1)
        raw_x_test = np.delete(raw_x_test, del_col, axis=1)

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

创建 Dataloader

读取文件，设置训练，验证和测试数据集

# Set seed for reproducibility
same_seed(config['seed'])

# train_data size: 3009 x 89 (35 states + 18 features x 3 days)  
# train_data共3009条数据，每条数据89个维度
# test_data size: 997 x 88 (without last day's positive rate)
# test_data共997条数据，每条数据88个维度，没有最后一天的最后一列数据positive rate

# pands读取csv数据
train_data, test_data = pd.read_csv('./covid_train.csv').values, pd.read_csv('./covid_test.csv').values     

# train_valid_split切分训练集和验证集
train_data, valid_data = train_valid_split(train_data, config['valid_ratio'], config['seed'])

# Print out the data size.打印数据尺寸
print(f"""train_data size: {train_data.shape}
valid_data size: {valid_data.shape}
test_data size: {test_data.shape}""")

# Select features 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 out the number of features. 打印特征数
print(f'number of features: {x_train.shape[1]}')

# 生成dataset
train_dataset, valid_dataset, test_dataset = COVID19Dataset(x_train, y_train), \
                                            COVID19Dataset(x_valid, y_valid), \
                                            COVID19Dataset(x_test)

# Pytorch data loader loads pytorch dataset into batches.
# pytorch的dataloder加载dataset
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)

三、创建神经网络模型

class My_Model(nn.Module):         
    def __init__(self, input_dim):
        super(My_Model, self).__init__()
        # TODO: modify model's structure, be aware of dimensions.
        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

四、模型训练和模型测试

模型训练

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=0.9)
    writer = SummaryWriter() # Writer of tensoboard.

    # 如果没有models文件夹，创建名称为models的文件夹，保存模型
    if not os.path.isdir('./models'):    
        os.mkdir('./models') # Create directory of saving models.

    # math.inf为无限大
    n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0

    for epoch in range(n_epochs):
        model.train() # Set your model to train mode.
        loss_record = []    # 记录损失

        # 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)                     # 数据传入模型model，生成预测值pred
            loss = criterion(pred, y)           # 预测值pred和真实值y计算损失loss  
            loss.backward()                     # Compute gradient(backpropagation).
            optimizer.step()                    # Update parameters.
            step += 1
            loss_record.append(loss.detach().item())   # 当前步骤的loss加到loss_record[]

            # 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)      # 计算训练集上平均损失
        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)      # 计算验证集上平均损失     
        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)

        # 保存验证集上平均损失最小的模型
        if mean_valid_loss < best_loss:         
            best_loss = mean_valid_loss
            torch.save(model.state_dict(), config['save_path']) # Save your best model
            print('Saving model with loss {:.3f}...'.format(best_loss))
            early_stop_count = 0
        else:
            early_stop_count += 1
        
        # 设置早停early_stop_count
        # 如果early_stop_count次数，验证集上的平均损失没有变化，模型性能没有提升，停止训练
        if early_stop_count >= config['early_stop']:   
            print('\nModel is not improving, so we halt the training session.')
            return

模型测试

# 测试数据集的预测
def predict(test_loader, model, device):
    model.eval() # Set your model to evaluation mode.
    preds = []
    for x in tqdm(test_loader):
        x = x.to(device)
        with torch.no_grad():   # 关闭梯度
            pred = model(x)
            preds.append(pred.detach().cpu())
    preds = torch.cat(preds, dim=0).numpy()
    return preds

五、训练模型

model = My_Model(input_dim=x_train.shape[1]).to(device) # put your model and data on the same computation device.

trainer(train_loader, valid_loader, model, config, device)

六、测试模型，生成预测值

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']))    # 加载模型
preds = predict(test_loader, model, device)               # 生成预测结果preds
save_pred(preds, 'pred.csv')                              # 保存preds到pred.csv   

tensorboard可视化训练和验证损失图像

%reload_ext tensorboard
%tensorboard --logdir=./runs/

参考：

李宏毅_机器学习_作业1（详解）_COVID-19 Cases Prediction (Regression)-物联沃-IOTWORD物联网

【深度学习】2023李宏毅homework1作业一代码详解_李宏毅作业1-CSDN博客

np.delete详解-CSDN博客