利用神经网络预测新冠确诊率

本文的数据以及程序均来源于李宏毅老师2021机器学习课程：https://www.bilibili.com/video/BV1Wv411h7kN?p=7

如果看不懂代码，可以先查看我另一篇文章《Pytorch教学及示例》。https://tianjuewudi.gitee.io/

首先看一下给出的数据，一个训练集covid.train.csv，一个测试集covid.test.csv。

首先数据的第一列是变换，后面的四十列是state one-hot encoding，意思是只有一个值为1，其余为0。用来代表美国一个州。再往后的18列是第一天的调查数据以及确诊率，一次类推再往后的36列是第二第三天的调查数据以及确诊率。训练和测试数据集的不同在于测试集少了最后一列第三天的结果，需要自己建立神经网络去得出结果。

首先导入包：

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

# For data preprocess
import numpy as np
import csv
import os

# For plotting
import matplotlib.pyplot as plt
from matplotlib.pyplot import figure

myseed = 42069  # set a random seed for reproducibility
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(myseed)
torch.manual_seed(myseed)
if torch.cuda.is_available():
    torch.cuda.manual_seed_all(myseed)

为什么使用相同的网络结构，跑出来的效果完全不同，用的学习率，迭代次数，batch size 都是一样？固定随机数种子是非常重要的。但是如果你使用的是PyTorch等框架，还要看一下框架的种子是否固定了。还有，如果你用了cuda，别忘了cuda的随机数种子。这里还需要用到torch.backends.cudnn.deterministic.

torch.backends.cudnn.deterministic这个 flag 置为True的话，每次返回的卷积算法将是确定的，即默认算法。如果配合上设置 Torch 的随机种子为固定值的话，应该可以保证每次运行网络的时候相同输入的输出是固定的，因此才有了最后的几行。

一些不用更改的函数：

#在有GPU的时候使用GPU
def get_device():
    ''' Get device (if GPU is available, use GPU) '''
    return 'cuda' if torch.cuda.is_available() else 'cpu'

#输入的是一个包含训练集Loss列表和开发集的Loss列表
def plot_learning_curve(loss_record, title=''):
    ''' Plot learning curve of your DNN (train & dev loss) '''
    total_steps = len(loss_record['train'])
    x_1 = range(total_steps)
    x_2 = x_1[::len(loss_record['train']) // len(loss_record['dev'])]
    figure(figsize=(6, 4))
    plt.plot(x_1, loss_record['train'], c='tab:red', label='train')
    plt.plot(x_2, loss_record['dev'], c='tab:cyan', label='dev')
    plt.ylim(0.0, 5.)
    plt.xlabel('Training steps')
    plt.ylabel('MSE loss')
    plt.title('Learning curve of {}'.format(title))
    plt.legend()
    plt.show()

#绘制一个表示预测值与真实值插件的散点图，其中斜率为1的直线代表无误差
def plot_pred(dv_set, model, device, lim=35., preds=None, targets=None):
    ''' Plot prediction of your DNN '''
    if preds is None or targets is None:
        model.eval()
        preds, targets = [], []
        for x, y in dv_set:
            x, y = x.to(device), y.to(device)
            with torch.no_grad():
                pred = model(x)
                preds.append(pred.detach().cpu())
                targets.append(y.detach().cpu())
        preds = torch.cat(preds, dim=0).numpy()
        targets = torch.cat(targets, dim=0).numpy()

    figure(figsize=(5, 5))
    plt.scatter(targets, preds, c='r', alpha=0.5)
    plt.plot([-0.2, lim], [-0.2, lim], c='b')
    plt.xlim(-0.2, lim)
    plt.ylim(-0.2, lim)
    plt.xlabel('ground truth value')
    plt.ylabel('predicted value')
    plt.title('Ground Truth v.s. Prediction')
    plt.show()

处理数据：

class COVID19Dataset(Dataset):
    ''' Dataset for loading and preprocessing the COVID19 dataset '''
    def __init__(self,
                 path,
                 mode='train',
                 target_only=False):
        self.mode = mode

        # Read data into numpy arrays
        with open(path, 'r') as fp:
            data = list(csv.reader(fp))
            data = np.array(data[1:])[:, 1:].astype(float)
        
        if not target_only:
            feats = list(range(93))
        else:
            # TODO: Using 40 states & 2 tested_positive features (indices = 57 & 75)
            pass

        if mode == 'test':
            # Testing data
            # data: 893 x 93 (40 states + day 1 (18) + day 2 (18) + day 3 (17))
            data = data[:, feats]
            self.data = torch.FloatTensor(data)
        else:
            # Training data (train/dev sets)
            # data: 2700 x 94 (40 states + day 1 (18) + day 2 (18) + day 3 (18))
            target = data[:, -1]
            data = data[:, feats]
            
            # Splitting training data into train & dev sets
            if mode == 'train':
                indices = [i for i in range(len(data)) if i % 10 != 0]
            elif mode == 'dev':
                indices = [i for i in range(len(data)) if i % 10 == 0]
            
            # Convert data into PyTorch tensors
            self.data = torch.FloatTensor(data[indices])
            self.target = torch.FloatTensor(target[indices])

        # Normalize features (you may remove this part to see what will happen)
        self.data[:, 40:] = \
            (self.data[:, 40:] - self.data[:, 40:].mean(dim=0, keepdim=True)) \
            / self.data[:, 40:].std(dim=0, keepdim=True)

        self.dim = self.data.shape[1]

        print('Finished reading the {} set of COVID19 Dataset ({} samples found, each dim = {})'
              .format(mode, len(self.data), self.dim))

    def __getitem__(self, index):
        # Returns one sample at a time
        if self.mode in ['train', 'dev']:
            # For training
            return self.data[index], self.target[index]
        else:
            # For testing (no target)
            return self.data[index]

    def __len__(self):
        # Returns the size of the dataset
        return len(self.data)

这个类继承于dataset类，因此需要重新三个函数。第一个函数是初始化函数init，用来处理数据，把数据集分成训练的数据和标签两部分。然后再getitem中指定索引来确定数据的顺序的样本的标签的对应关系。len函数中返回整个样本集的个数。

模型构建

class NeuralNet(nn.Module):
    ''' A simple fully-connected deep neural network '''
    def __init__(self, input_dim):
        super(NeuralNet, self).__init__()
        # Define your neural network here
        # TODO: How to modify this model to achieve better performance?
        #Sequential一个有序的容器，神经网络模块将按照在传入构造器的顺序依次被添加到计算图中执行
        #同时以神经网络模块为元素的有序字典也可以作为传入参数。
        self.net = nn.Sequential(
            nn.Linear(input_dim, 64),
            nn.ReLU(),
            nn.Linear(64, 1)
        )
        # Mean squared error loss
        self.criterion = nn.MSELoss(reduction='mean')

    #计算输出结果
    def forward(self, x):
        ''' Given input of size (batch_size x input_dim), compute output of the network '''
        return self.net(x).squeeze(1)

    #计算Loss
    def cal_loss(self, pred, target):
        ''' Calculate loss '''
        # TODO: you may implement L2 regularization here
        return self.criterion(pred, target)

训练

def train(tr_set, dv_set, model, config, device):
    ''' DNN training '''

    n_epochs = config['n_epochs']  # Maximum number of epochs

    # Setup optimizer
    optimizer = getattr(torch.optim, config['optimizer'])(
        model.parameters(), **config['optim_hparas'])

    min_mse = 1000.
    loss_record = {'train': [], 'dev': []}      # for recording training loss
    early_stop_cnt = 0
    epoch = 0
    while epoch < n_epochs:
        model.train()                           # set model to training mode
        for x, y in tr_set:                     # iterate through the dataloader
            optimizer.zero_grad()               # set gradient to zero
            x, y = x.to(device), y.to(device)   # move data to device (cpu/cuda)
            pred = model(x)                     # forward pass (compute output)
            mse_loss = model.cal_loss(pred, y)  # compute loss
            mse_loss.backward()                 # compute gradient (backpropagation)
            optimizer.step()                    # update model with optimizer
            loss_record['train'].append(mse_loss.detach().cpu().item())

        # After each epoch, test your model on the validation (development) set.
        dev_mse = dev(dv_set, model, device)
        if dev_mse < min_mse:
            # Save model if your model improved
            min_mse = dev_mse
            print('Saving model (epoch = {:4d}, loss = {:.4f})'
                .format(epoch + 1, min_mse))
            #注意保存模型
            torch.save(model.state_dict(), config['save_path'])  # Save model to specified path
            early_stop_cnt = 0
        else:
            early_stop_cnt += 1

        epoch += 1
        loss_record['dev'].append(dev_mse)
        if early_stop_cnt > config['early_stop']:
            # Stop training if your model stops improving for "config['early_stop']" epochs.
            break

    print('Finished training after {} epochs'.format(epoch))
    return min_mse, loss_record

验证集计算Loss

验证集从训练集中分离而出，这是事先验证用多少个epoch进行训练才不会过拟合，然后再把所有的数据扔进去训练。

def dev(dv_set, model, device):
    model.eval()                                # set model to evalutation mode
    total_loss = 0
    for x, y in dv_set:                         # iterate through the dataloader
        x, y = x.to(device), y.to(device)       # move data to device (cpu/cuda)
        with torch.no_grad():                   # disable gradient calculation
            pred = model(x)                     # forward pass (compute output)
            mse_loss = model.cal_loss(pred, y)  # compute loss
        total_loss += mse_loss.detach().cpu().item() * len(x)  # accumulate loss
    total_loss = total_loss / len(dv_set.dataset)              # compute averaged loss

    return total_loss

测试集预测

def test(tt_set, model, device):
    model.eval()                                # set model to evalutation mode
    preds = []
    for x in tt_set:                            # iterate through the dataloader
        x = x.to(device)                        # move data to device (cpu/cuda)
        with torch.no_grad():                   # disable gradient calculation
            pred = model(x)                     # forward pass (compute output)
            preds.append(pred.detach().cpu())   # collect prediction
    preds = torch.cat(preds, dim=0).numpy()     # concatenate all predictions and convert to a numpy array
    return preds

设置超参数

device = get_device()                 # get the current available device ('cpu' or 'cuda')
os.makedirs('models', exist_ok=True)  # The trained model will be saved to ./models/
target_only = False                   # TODO: Using 40 states & 2 tested_positive features

# TODO: How to tune these hyper-parameters to improve your model's performance?
config = {
    'n_epochs': 3000,                # maximum number of epochs
    'batch_size': 270,               # mini-batch size for dataloader
    'optimizer': 'SGD',              # optimization algorithm (optimizer in torch.optim)
    'optim_hparas': {                # hyper-parameters for the optimizer (depends on which optimizer you are using)
        'lr': 0.001,                 # learning rate of SGD
        'momentum': 0.9              # momentum for SGD
    },
    'early_stop': 200,               # early stopping epochs (the number epochs since your model's last improvement)
    'save_path': 'models/model.pth'  # your model will be saved here
}

正式训练前价值数据

tr_set = prep_dataloader(tr_path, 'train', config['batch_size'], target_only=target_only)
dv_set = prep_dataloader(tr_path, 'dev', config['batch_size'], target_only=target_only)
tt_set = prep_dataloader(tt_path, 'test', config['batch_size'], target_only=target_only)

正式训练

model = NeuralNet(tr_set.dataset.dim).to(device) 
model_loss, model_loss_record = train(tr_set, dv_set, model, config, device)

绘制两个数据集的Loss图

plot_learning_curve(model_loss_record, title='deep model')

根据预测值绘制散点图

del model
model = NeuralNet(tr_set.dataset.dim).to(device)
ckpt = torch.load(config['save_path'], map_location='cpu')  # Load your best model
model.load_state_dict(ckpt)
plot_pred(dv_set, model, device)  # Show prediction on the validation set

保存预测数据

def save_pred(preds, file):
    ''' Save predictions to specified file '''
    print('Saving results to {}'.format(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])

preds = test(tt_set, model, device)  # predict COVID-19 cases with your model
save_pred(preds, 'pred.csv')         # save prediction file to pred.csv