COVID-19 Cases Prediction
0 任务简介
根据前面三天的数据预测后面一天的新冠概率
1 代码分析
Def and Class
import
# Numerical Operations
import math
import numpy as np
# Reading/Writing Data
import pandas as pd
import os
import csv
# For Progress Bar 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)。
from tqdm import tqdm
# Pytorch
import torch
# 模型
import torch.nn as nn
# 数据
from torch.utils.data import Dataset, DataLoader, random_split
# For plotting learning curve可视化的
from torch.utils.tensorboard import SummaryWriter
- numpy
- csv
- torch.nn
- torch.utils.tensorboard
seed
def same_seed(seed):
# A bool that, if True, causes cuDNN to only use deterministic convolution algorithms.
# cudnn: 是经GPU加速的深度神经网络基元库。cuDNN可大幅优化标准例程（例如用于前向传播和反向传播的卷积层、池化层、归一化层和激活层）的实施。
torch.backends.cudnn.deterministic = True
# A bool that, if True, causes cuDNN to benchmark multiple convolution algorithms and select the fastest.
torch.backends.cudnn.benchmark = False
# 用于生成指定的随机数
np.random.seed(seed)
# Sets the seed for generating random numbers. cpu生成随机数
torch.manual_seed(seed)
if torch.cuda.is_available():
# Sets the seed for generating random numbers for the current GPU. Gpu生成随机数
# It’s safe to call this function if CUDA is not available; in that case, it is silently ignored.cuda不可用就不会被调用
torch.cuda.manual_seed_all(seed)
主要作用：可重现一样的结果
set.seed()作用是设定生成随机数的种子，目的是为了让结果具有重复性，重现结果。
在神经网络中，参数默认是进行随机初始化的。如果不设置的话每次训练时的初始化都是随机的，导致结果不确定。如果设置初始化，则每次初始化都是固定的。
train_valid_split
将数据集划分为训练集和验证集（交叉验证）
def train_valid_split(data_set, valid_ratio, seed):
'''Split provided training data into training set and validation set'''
#验证集大小=验证比率（？）（自己设置的）*数据集长度
valid_set_size = int(valid_ratio * len(data_set))
#训练集=
train_set_size = len(data_set) - valid_set_size
# Randomly split a dataset into non-overlapping new datasets of given lengths.
# Optionally fix the generator for reproducible results
# 随机划分
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)
predict
模型训练出来后调用这个模块预测结果
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(): # with用法？
pred = model(x)
preds.append(pred.detach().cpu()) #我在想这里可不可以用pred.index
preds = torch.cat(preds, dim=0).numpy()
return preds
- detach()
作用：阻断反向传播的。
返回值：Tensor，且经过detach()方法后，变量仍然在GPU上。
output = output.detach().cpu() # 移至cpu 返回值是cpu上的Tensor
要注意，Tensor变量使用后会生成计算图，为计算反向传播做准备，但是会占用资源
此时output仍然在显存中，而内存操作可能会找不到该变量，也就是说，show(output)是没办法进行操作的。那么cpu()出现了。
output = output.detach().cpu() # 移至cpu 返回值是cpu上的Tensor
后续，则可以对该Tensor数据进行一系列操作，其中包括numpy()，该方法主要用于将cpu上的tensor转为numpy数据。
output = output.detach().cpu().numpy() # 返回值为numpy.array()
COVID19Dataset
生成数据集
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)
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)
My_Model
class Model(torch.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, 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
return x
- squeeze添加链接描述
select_feat
选择特征。。数据集中几十个元素中，选出一些影响较为大的。
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
# 感觉没啥用？
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
- 正则化
- 随机森林
添加链接描述
trainer
def trainer(train_loader, valid_loader, model, config, device):
criterion = nn.MSELoss(reduction='mean') # Define your loss function, do not modify this.损失函数MSE
# 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，lr指学习率，momentum=冲量？
optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9)
writer = SummaryWriter() # Writer of tensoboard.作图
if not os.path.isdir('./models'):
os.mkdir('./models') # Create directory of saving models.存训练模型
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
main
# 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('./Hw1/covid.train_new.csv').values, pd.read_csv('./Hw1/covid.test_un.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)
#start
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)
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')
2 总结
- tensorboard不会用
- 特征选择没做
- 测试模型，只有models怎么测，以及误差比较
%reload_ext tensorboard
%tensorboard --logdir=./runs/
扫一扫
585
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
