收获（源于学长代码讲解）

打断点

之前也知道程序要打断点，就比如刷力扣的题目。不过对于深度学习就没有想起来打断点的习惯。一个特别大的好处是打断点之后，就可以清晰地知道各个变量的数据类型，和具体的情况，而不用一个个去打印出来查看。

抽象类和非抽象类

抽象类的作用是定义各种接口，但是不具体定义各种功能，不可以使用super方法。 非抽象类可以使用super方法继承。

类（变量） 对象（变量）

这种会把参数传到哪里？ 类内会自带

Import packages

问：tqdm类有啥用？

问：tensorboard、Dateset、Dateloader如何导入？

# 导入需要的包
# Numerical Operations
import math
import numpy as np

# Reading/Writing Data
import pandas as pd     # 用于读取文件
import os   # 对文件和文件夹进行操作
import csv

# For Progress Bar
from tqdm import tqdm   # 答：tqdm库用于生成训练时的进度条展示（需要pip）

# Pytorch
import torch
import torch.nn as nn   # torch.nn是pytorch中自带的一个函数库，里面包含了神经网络中使用的一些常用函数
# 答：导入方式如下。
from torch.utils.data import Dataset, DataLoader, random_split
'''
Dataset:提供一种方式去获取数据及label，数据集在什么位置
DataLoader:为之后的网络提供不同的数据形式
random_split:无重复的随机划分数据集
'''

# For plotting learning curve
# 可视化工具 tensorboard
from torch.utils.tensorboard import SummaryWriter

Some Utility Functions

same_seed函数作用？

def same_seed(seed):
    '''Fixes random number generator seeds for reproducibility.'''
    '''固定random seed 还原实验结果'''
    '''答：可以使得训练集和验证集的划分是无覆盖的，也就是总数据 = 训练集 + 测试集 并且训练集和测试集没有交集'''
    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)

# 定义一些功能
# 该方法在接下来DataLoader部分有调用，用于划分训练集和验证集
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))   # 验证集的长度
    train_set_size = len(data_set) - valid_set_size     # 训练集的长度 = 总长度 - 验证集长度
    # random_split无重复的随机划分数据集,第二个参数中传入的是需要划分成的两个数据集size
    train_set, valid_set = random_split(data_set, [train_set_size, valid_set_size], generator=torch.Generator().manual_seed(seed))
    # 返回numpy数组形式
    return np.array(train_set), np.array(valid_set)

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

Dateset

# 数据集构造
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)
    # 获取某一个具体数据
    def __getitem__(self, idx):
        if self.y is None:
            return self.x[idx]
        else:
            return self.x[idx], self.y[idx]
    # 数据集长度
    def __len__(self):
        return len(self.x)

Neural Network Model

问：如何实现各网络层的打包？

# 设计模型
class My_Model(nn.Module):
    def __init__(self, input_dim):
        super(My_Model, self).__init__()  # 继承nn.Module类
        # TODO: modify model's structure, be aware of dimensions.
        # 答：使用nn.Swquential来进行层结构构建。
        self.layers = nn.Sequential(
            nn.Linear(input_dim, 16),
            nn.ReLU(),
            nn.Linear(16, 8),
            nn.ReLU(),
            nn.Linear(8, 1)
        )
    # 定义正向传播的过程
    def forward(self, x):
        x = self.layers(x)
        x = x.squeeze(1)  # (B, 1) -> (B)
        return x

Feature Selection

为什么要进行特征选择？

# 特征选择
def select_feat(train_data, valid_data, test_data, select_all=True):
    '''Selects useful features to perform regression'''
    # [:,-1]冒号表示第一个维度选择全部，即全部行，-1：表示倒数第一个元素，即label
    y_train, y_valid = train_data[:, -1], valid_data[:, -1]
    #   #[:,:-1]第一个冒号表示第一个维度选择全部，即全部行，
    #   :-1表示在第二个维度上从开始至最后一个元素（不包含最后一个元素）即选择了除最后一列的所有特征
    raw_x_train, raw_x_valid, raw_x_test = train_data[:, :-1], valid_data[:, :-1], test_data
    # 答：有一些特征对于训练效果没有用，甚至起反作用，要进行特征筛选。
    # 选择所有特征
    if select_all:
        feat_idx = list(range(raw_x_train.shape[1]))
    # 选择部分特征
    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

Training Loop

# 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).
    # 优化算法 随机梯度下降算法 SGD
    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):
        # 开启训练模式batchNorm层，dropout层等用于优化训练而添加的网络层开启
        model.train()  # Set your model to train mode.
        loss_record = []

        # tqdm is a package to visualize your training progress.
        # tqdm用在dataloader上其实是对每个batch和batch总数做的进度条
        train_pbar = tqdm(train_loader, position=0, leave=True)

        for x, y in train_pbar:
            optimizer.zero_grad()  # Set gradient to zero.
            # x.to(device)将所有最开始读取数据时的tensor变量copy一份到device所指定的GPU上去，
            # 之后的运算都在GPU上进行。
            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)
            # 不再进行梯度计算
            # 把模型用在验证集上 并计算损失
            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)

        # 保存训练的最好结果对应的模型参数
        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

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

Configurations

# 参数配置
# 用GPU跑
device = 'cuda' if torch.cuda.is_available() else 'cpu'

# 字典设置参数
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

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

# 准备验证集和训练集数据
# train_data size: 2699 x 118 (id + 37 states + 16 features x 5 days)
# test_data size: 1078 x 117 (without last day's positive rate)
# 读取文件中的数据
train_data, test_data = pd.read_csv('./covid.train.csv').values, pd.read_csv('./covid.test.csv').values
# 无覆盖的随机划分数据集
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'])

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

# #生成dataset实例
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.
# 划分成多个batches 提高训练效率
# pin_memory默认false，打开后更快
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)

Start training!

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

Testing

# 用训练好的模型进行预测并保存数据
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')