Download Data

If the Google drive links are dead, you can download data from kaggle, and upload data manually to the workspace.

tr_path = 'covid.train.csv'  # path to training data
tt_path = 'covid.test.csv'   # path to testing data

!gdown --id '19CCyCgJrUxtvgZF53vnctJiOJ23T5mqF' --output covid.train.csv
!gdown --id '1CE240jLm2npU-tdz81-oVKEF3T2yfT1O' --output covid.test.csv

Import Some Packages


# 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

# 固定隨機數種子
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)

固定隨機數種子

為什麽使用相同的網絡結構，跑出來的效果完全不同，儘管用的學習率，叠代次數，batch size 都是一樣？如果你用了cuda，別忘了cuda的隨機數種子。

區別在於：使用cpu時不需要設置GPU的額外參數，使用gpu時需要設置

在cpu中，我們只需要保證：

所有參數的初始化相同學習率、叠代次數、batch size相同那麽，參數的更新都是由梯度計算得到的，快慢、次數都相同，所以最後得到的模型的參數也相同，輸出結果就相同。

而當使用gpu訓練模型時，可能引入額外的隨機源，使得結果不能準確再現（gpu提供了多核並行計算的基礎結構）

torch.backends.cudnn.deterministic是啥？顧名思義，將這個 flag 置為True的話，每次返回的卷積算法將是確定的，即默認算法。如果配合上設置 Torch 的隨機種子為固定值的話，應該可以保證每次運行網絡的時候相同輸入的輸出是固定的

https://pytorch.org/docs/stable/notes/randomness.html

Some Utilities

You do not need to modify this part.

def get_device():
    ''' Get device (if GPU is available, use GPU) '''
    return 'cuda' if torch.cuda.is_available() else 'cpu'

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()

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()

Preprocess

We have three kinds of datasets:

train: for training
dev: for validation
test: for testing (w/o target value)

Dataset

The COVID19Dataset below does:

read .csv files
extract features
split covid.train.csv into train/dev sets
normalize features

Finishing TODO below might make you pass medium baseline.

Dataset

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:
            #先將全部data讀取
            data = list(csv.reader(fp))
            #np.array(data[1:]) 先捨棄掉第一列不是數據的部分,並轉化成np.array
            #[:, 1:].astype(float) 捨棄第一行, 因為此行是sample index, 並將型態轉成float
            data = np.array(data[1:])[:, 1:].astype(float)

        if not target_only:
            #共有40+18+18+18=94個features
            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
            #將sample index = 10的倍數設定為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)

DataLoader

A DataLoader loads data from a given Dataset into batches.


def prep_dataloader(path, mode, batch_size, n_jobs=0, target_only=False):
    ''' Generates a dataset, then is put into a dataloader. '''
    dataset = COVID19Dataset(path, mode=mode, target_only=target_only)  # Construct dataset
    dataloader = DataLoader(
        dataset, batch_size,
        shuffle=(mode == 'train'), drop_last=False,
        num_workers=n_jobs, pin_memory=True)                            # Construct dataloader
    return dataloader

Deep Neural Network

NeuralNet is an nn.Module designed for regression. The DNN consists of 2 fully-connected layers with ReLU activation. This module also included a function cal_loss for calculating loss.

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?
        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')

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

    def cal_loss(self, pred, target):
        ''' Calculate loss '''
        # TODO: you may implement L1/L2 regularization here
        return self.criterion(pred, target)

squeeze() 能夠去除維度、unsqueeze() 則能增加維度，正如 squeeze（擠出）和 unsqueeze（鬆開）的含意。

首先來看能夠去除維度的 squeeze()。

import torch

data = torch.tensor([
    [[0, 1, 2],
     [3, 4, 5],
     [6, 7, 8],]
])

print('Shape:', data.shape)

# squeeze()
squeeze_data = data.squeeze(0)
print('squeeze data:', squeeze_data)
print('squeeze(0) shape:', squeeze_data.shape)
#squeeze(0) shape: torch.Size([3, 3])


import torch

data = torch.tensor([
    [[0, 1, 2],
     [3, 4, 5],
     [6, 7, 8],]
])

print('Shape:', data.shape)

# unsqueeze()
unsqueeze_data = data.unsqueeze(0)
print('unsqueeze data:', unsqueeze_data)
print('unsqueeze(0) shape:', unsqueeze_data.shape)

Shape: torch.Size([1, 3, 3])
unsqueeze data: tensor([[[
[0, 1, 2],
[3, 4, 5],
[6, 7, 8]]]])
unsqueeze(0) shape: torch.Size([1, 1, 3, 3])

https://clay-atlas.com/blog/2020/09/02/pytorch-cn-squeeze-unsqueeze-usage/

Setup Hyper-parameters

config contains hyper-parameters for training and the path to save your model.

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
}

pytorch.detach() https://pytorch.org/docs/stable/generated/torch.Tensor.detach.html

Train/Dev/Test

Training

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 model已經存在在GPU所以不用移動
            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))
            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

Validation

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

Testing

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

Load data and model

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)

model = NeuralNet(tr_set.dataset.dim).to(device)  # Construct model and move to device

Start Training!

model_loss, model_loss_record = train(tr_set, dv_set, model, config, device)

plot_learning_curve(model_loss_record, title='deep model')

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

Testing

The predictions of your model on testing set will be stored at pred.csv.

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

Pin-Jiun / Machine-Learing-NTU

4.1-Homework 1: COVID-19 Cases Prediction (Regression) #27

Download Data

Import Some Packages

固定隨機數種子

Some Utilities

Preprocess

Dataset

Dataset

DataLoader

Deep Neural Network

Setup Hyper-parameters

Train/Dev/Test

Training

Validation

Testing

Load data and model

Start Training!

Testing