目标
- 使用DNN解决一个回归问题
- 理解DNN的基本训练技巧，比如超参数调优、特征选取、睁着
- 熟悉Pytorch
任务描述
- COVID-19 病例预测
- 基于调查数据预测测试阳性概率。
数据
Survey: symptoms, COVID-19 testing, social distancing, mental health, demographics,
economic effects, …
- States (37, encoded to one-hot vectors)
- COVID-like illness (4)
- cli、ili …
- Behavior Indicators (8)
○ wearing_mask、travel_outside_state … - Mental Health Indicators (3)
○ anxious、depressed … - Tested Positive Cases (1)
○ tested_positive (this is what we want to predict)
Trian.csv中的部分数据：
评价标准
M S E = 1 / N ∗ s u m i = 0 N ( y i − y h a t i ) 2 MSE=1/N*sum_{i=0}^N{(y_i -yhat_i)^2} MSE=1/N∗sumi=0N(yi−yhati)2
Kaggle -Submission
kaggle 地址： kaggle地址
作业 simple baseline：
1) Download data
数据集可从kaggle 上下载：covid-19数据集
2) Import packages
# 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
关于tensorboard 与pytorch 的简单应用：tensorboard
tensorboard： 可视化工具
3）Some Utility Function
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)
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)
def predict(test_loader, model, device):
model.eval() # Set your model to evaluation mode. 告诉网络，这个阶段是用来测试的，于是模型的参数在该阶段不进行更新
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
4）Dataset
class COVID19Dataset(Dataset):
'''
x: Features.
y: Targets, if none, do prediction.
'''
def __init__(self, x, y=None): ## 构造函数
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)
Neural Network Model
class My_Model(nn.Module):
def __init__(self, input_dim): ## 构造函数
super(My_Model, self).__init__() # 继承
# 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
Feature Selection (划分训练集、测试集、验证集的x、y)
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
Training Loop
设置损失函数、优化函数
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).
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
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
config contains hyper-parameters for training and the path to save your model.
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 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)
train_data size: (2160, 118)
valid_data size: (539, 118)
test_data size: (1078, 117)
number of features: 117
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)
运行结束后，在路径下多了 model 文件夹和 runs 文件夹
Plot learning curves with tensorboard
tensorboard is a tool that allows you to visualize your training progress.
If this block does not display your learning curve, please wait for few minutes, and re-run this block. It might take some time to load your logging information.
%reload_ext tensorboard
%tensorboard --logdir=./runs/
Testing
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')
在本次作业中，并没有基于前5天数据预测第五天的结果，而是基于当天的特征数据进行预测的。
细节知识点
pytorch中model eval和torch no grad()的区别
-
在PyTorch中进行validation时，会使用model.eval()切换到测试模式，在该模式下，主要用于通知dropout层和batchnorm层在train和val模式间切换
-
在train模式下，dropout网络层会按照设定的参数p设置保留激活单元的概率（保留概率=p); batchnorm层会继续计算数据的mean和var等参数并更新。
-
在val模式下，dropout层会让所有的激活单元都通过，而batchnorm层会停止计算和更新mean和var，直接使用在训练阶段已经学出的mean和var值。该模式不会影响各层的gradient计算行为，即gradient计算和存储与training模式一样，只是不进行反传（backprobagation）
-
而with torch.no_grad()则主要是用于停止autograd模块的工作，以起到加速和节省显存的作用，具体行为就是停止gradient计算，从而节省了GPU算力和显存，但是并不会影响dropout和batchnorm层的行为。
-
一般情况下，我们训练过程如下：
1、拿到数据后进行训练，在训练过程中，使用model.train(）：告诉我们的网络，这个阶段是用来训练的，可以更新参数。
2、训练完成后进行预测，在预测过程中，使用model.eval() ： 告诉我们的网络，这个阶段是用来测试的，于是模型的参数在该阶段不进行更新。 -
为什么在eval()阶段会使用with torch.no_grad()？
在eval阶段了，即使不更新，但是在模型中所使用的dropout或者batch norm也就失效了，直接都会进行预测，而使用no_grad则设置让梯度Autograd设置为False(因为在训练中我们默认是True)，这样保证了反向过程为纯粹的测试，而不变参数。
tqdm
Tqdm 是一个快速，可扩展的Python进度条，可以在 Python 长循环中添加一个进度提示信息，用户只需要封装任意的迭代器 tqdm(iterator)。
用法：tqdm(iterator)
使用方法一: 传入可迭代对象
import time
from tqdm import *
for i in tqdm(range(1000)):
time.sleep(.01) #进度条每0.1s前进一次，总时间为1000*0.1=100s
100%|██████████████████████████████████████████████████████████████████████████████| 1000/1000 [00:10<00:00, 93.97it/s]
使用方法二: trange
trange(i) 是 tqdm(range(i)) 的简单写法
from tqdm import trange
for i in trange(100):
#do something
pass
100%|█████████████████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 99344.01it/s]
使用方法三: 可以为进度条设置描述
在 for 循环外部初始化 tqdm，可以打印其他信息：
import time
from tqdm import tqdm
pbar = tqdm(["a", "b", "c", "d"])
for char in pbar:
# 设置描述
pbar.set_description("Processing %s" % char)
time.sleep(1)
Processing d: 100%|██████████████████████████████████████████████████████████████████
3359
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
