2022李宏毅机器学习hw1

目录

一、任务

 数据

结果

 二、基础代码

随机数种子定义，放入gpu

数据集切割

预测函数

数据格式定义

模型定义

特征选取

训练

测试保存

三、改进方法

3.1怎么样知道这个特征是好的，排除掉无用特征

3.2神经网络模型设计（加BN层，增加隐藏层）

3.3超参数设计（各层神经元的数量、batch_size的取值、参数更新时的学习率、权值衰减系数或学习的epoch）

3.4优化器改变

四、还可以改进的方向

---

Machine Learning HW1 COVID-19 Cases Prediction

一、任务

随机数种子定义，放入gpu

        Given survey results in the past 5 days in a specifific state in U.S., then predict the percentage of new tested positive cases in the 5th day.

 数据

结果

全过strong baselin，public score与bossline差0.01

 二、基础代码

随机数种子定义，放入gpu

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)

数据集切割

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)

预测函数

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():
            pred = model(x)
            preds.append(pred.detach().cpu())
    preds = torch.cat(preds, dim=0).numpy()
    return preds

数据格式定义

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)

模型定义

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

特征选取

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]
    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 = [0, 1, 2, 3, 4]  # TODO: Select suitable feature columns.

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

训练

def trainer(train_loader, valid_loader, model, config, device):
    global aa
    criterion = nn.MSELoss(reduction='mean')  # Define your loss function, do not modify this.
    optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9)
    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):
        model.train()  # Set your model to train mode.
        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
            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
            aa = best_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

        if early_stop_count >= config['early_stop']:
            print('\nModel is not improving, so we halt the training session.')
            return
device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
    'seed': 5201314,  # Your seed number, you can pick your lucky number. :)
    'select_all': True,  # Whether to use all features.
    'valid_ratio': 0.2,  # validation_size = train_size * valid_ratio
    'n_epochs': 3000,  # Number of epochs.
    'batch_size': 256,
    'learning_rate': 1e-5,
    'early_stop': 400,  # If model has not improved for this many consecutive epochs, stop training.
    'save_path': './models/model.ckpt'  # Your model will be saved here.
}

"""# Dataloader
Read data from files and set up training, validation, and testing sets. You do not need to modify this part.
"""

# Set seed for reproducibility
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(f"""train_data size: {train_data.shape} 
valid_data size: {valid_data.shape} 
test_data size: {test_data.shape}""")
x_train, x_valid, x_test, y_train, y_valid = select_feat(train_data, valid_data, test_data, config['select_all'])
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)
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)
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)

测试保存

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']))
preds = predict(test_loader, model, device)
save_pred(preds, 'pred.csv')
print("Loss is {}".format(aa))

三、改进方法

3.1怎么样知道这个特征是好的，排除掉无用特征

def select_feat(train_data, valid_data, test_data, select_all=True):
    '''Selects useful features to perform regression'''
    #选择label
    y_train, y_valid = train_data[:, -1], valid_data[:, -1]

    #获取除最后一列（label）之外的所有行和列。
    raw_x_train, raw_x_valid, raw_x_test = train_data[:, :-1], valid_data[:, :-1], test_data

    #做选择，shape表示维度的维数，shape[0]为第一维，即行数 shape[1]为第二维，即列数
    if select_all:
        feat_idx = list(range(raw_x_train.shape[1]))
    else:
        feat_idx = list(range(1,38))+[38,39,40,41,53,54,55,56,57,69,70,71,72,73,85,86,87,88,89,101,102,103,104,105]  # TODO: Select suitable feature columns.
    return raw_x_train[:, feat_idx], raw_x_valid[:, feat_idx], raw_x_test[:, feat_idx], y_train, y_valid
# device_name = torch.cuda.get_device_name(0)

3.2神经网络模型设计（加BN层，增加隐藏层）

class My_Model(nn.Module):
    def __init__(self, input_dim):
        #子类把父类的__init__()放到自己的__init__()当中，这样子类就有了父类的__init__()的那些东西。
        super(My_Model, self).__init__()
        # TODO: modify model's structure, be aware of dimensions.
        #nn.Sequential() 可以允许将整个容器视为单个模块（即相当于把多个模块封装成一个模块）
        # forward()方法接收输入之后，nn.Sequential()按照内部模块的顺序自动依次计算并输出结果。
        self.layers = nn.Sequential(
            # 线性运算wx+b，输入维度转化成16维度
            nn.Linear(input_dim, 64),
            # nn.BatchNorm1d(64),
            nn.LeakyReLU(0.1),
            nn.Linear(64, 1),
        )
    def forward(self, x):
        x = self.layers(x)
        x = x.squeeze(1)  # (B, 1) -> (B) 去掉维数为1的维度
        return x

    def cal_loss(self, pred, target):
        return torch.sqrt(self.criterion(pred, target))

3.3超参数设计（各层神经元的数量、batch_size的取值、参数更新时的学习率、权值衰减系数或学习的epoch）

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': 3000,  # Number of epochs.
    'batch_size': 512,
    'learning_rate': 1e-5,
    'early_stop': 400,  # If model has not improved for this many consecutive epochs, stop training.
    'save_path': './models/model.ckpt'  # Your model will be saved here.
}

3.4优化器改变

#优化算法SGD，带动量的随机梯度下降Momentum-SGD
    optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.95,weight_decay=0.001)#

四、还可以改进的方向

1.为什么会出现测试集准确率高的问题？

测试集的数据特征比较明显。

2.优化方法待改进

数据预处理，调参方法，训练效果可视化分析

3.训练时间过长

使用服务器