# 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

3. 定义函数

def same_seed(seed): '''Fixes random number generator seeds for reproducibility.'''torch.backends.cudnn.deterministic = Truetorch.backends.cudnn.benchmark = Falsenp.random.seed(seed)torch.manual_seed(seed)if torch.cuda.is_available():torch.cuda.manual_seed_all(seed)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_sizetrain_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)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 predsdef 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.Adam(model.parameters(), lr=config['learning_rate']) 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, 0for 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 += 1loss_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_losstorch.save(model.state_dict(), config['save_path']) # Save your best modelprint('Saving model with loss {:.3f}...'.format(best_loss))early_stop_count = 0else: early_stop_count += 1if early_stop_count >= config['early_stop']:print('\nModel is not improving, so we halt the training session.')return

4. 定义类（Dataset以及DNN）

class COVID19Dataset(Dataset):'''x: Features.y: Targets, if none, do prediction.'''def __init__(self, x, y=None):if y is None:self.y = yelse: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)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, 64),nn.LeakyReLU(0.1),nn.Linear(64, 32),nn.LeakyReLU(0.1),nn.Linear(32, 16),nn.LeakyReLU(0.1),nn.Linear(16, 8),nn.LeakyReLU(0.1),nn.Linear(8, 1),)def forward(self, x):x = self.layers(x)#x = nn.functional.dropout(x,p=0.01,training=self.training)x = x.squeeze(1) # (B, 1) -> (B)return xfrom google.colab import drive
drive.mount('/content/drive')

5. 特征选择

由于在测试集中需预测第五天的tested_postive，因此我选用了前四天的tested_positive作为feat_idx以增强数据之间的相关性。值得注意的是，在处理csv文件时需去除第一列（id对问题的解决无实际性意义）。

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_dataif select_all:feat_idx = list(range(raw_x_train.shape[1]))else:feat_idx = [53, 69, 85, 101] # 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

训练集covid.train.csv大致情况如下：

6. 定义超参数

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'n_epochs': 3000,     # Number of epochs.            'batch_size': 256, 'learning_rate': 1e-4,              '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.
}

7. 定义DataLoader

从文件中读取数据并设置培训、验证和测试集。

# Set seed for reproducibility
same_seed(config['seed'])# 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)
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'])# 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)# Pytorch data loader loads pytorch dataset into batches.
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)

8. 训练与预测

# Start Training !!!
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)# Start Predicting !!!
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')

五. 可视化分析

在深度学习框架中，有很多可视化的工具，其中，Tensorboard是一个工具，可以让您可视化训练进度。运行该配件时，需利用以下指令：

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

训练过程Loss在Train和Valid的下降过程如下：

此外，可以在board上滑动鼠标进行数值的更进一步分析：

六. 优缺点分析与改进建议

优点：

1. 本文从相关性出发针对性地选取了前四天的tested_positive，同时利用优化后的全连接层完成了回归预测。

2. 对优化器进行了改进，利用Adam使Loss下降更加平稳，同时稍提高learning rate以增加Loss的收敛速度

缺点：

1. 由于能力受限，无法对整个数据集中的所有指标进行相关性分析

2. learning rate不能随着学习过程的变化进行动态更替，导致训练后期并不能收敛到一个较低的值，而是进行反复地上下波动

3. 未考虑是否存在过拟合情况

改进建议：

1. 查阅文献，可采用余弦退火的技巧对learning rate进行动态更新

2. 可利用sklearn中的特征选择方法对Feature Selection进行更改，同时可对各个指标进行归一化

3. 在DNN模型定义中加入L2正则化，Dropout等方法防止模型过拟合