covid19病例预测

李宏毅机器学习2022

用神经网络做回归预测新冠病例数
参考链接

# 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
device = "cuda" if torch.cuda.is_available() else "cpu"

数据集

covid.train.csv 没有y
random_split划分训练集和验证集
对标注数据做x,y
convid19dataset(重写DataSet)封装
DataLoader迭代


import pandas as pd
train=pd.read_csv("covid.train.csv").values
train.shape
test_data=pd.read_csv("covid.test.csv").values
test_data.shapedef train_valid_split(data,valid_ratio):valid_len=int(valid_ratio*len(data))print(valid_len)train_len=len(data)-valid_lentrain_data,valid_data= random_split(data,[train_len,valid_len], generator=torch.Generator().manual_seed(0))print((train_data))return np.array(train_data),np.array(valid_data)
def select_feat(train_data,valid_data,test_data,select_all=True):y_train,y_valid = train_data[:,-1],valid_data[:,-1]raw_train_data,raw_valid_data,raw_test_data=train_data[:,:-1],valid_data[:,:-1],test_data[:,:]if select_all==True:fea_idx=list(range(raw_train_data.shape[1]))else:fea_idx=[0,1,2,3,4]return raw_train_data[:,fea_idx],raw_valid_data[:,fea_idx],raw_test_data[:,fea_idx],y_train,y_valid
train_data,valid_data=train_valid_split(train,0.2)
## 最后train_data.shape 没有值是因为传入的dataset 是dataframe --> subset--> narray
raw_train_data,raw_valid_data,raw_test_data,y_train,y_valid=select_feat(train_data,valid_data,test_data)
# class self
class covid19dataset(Dataset):def __init__(self,x,y=None):if y is not None:self.x=torch.FloatTensor(x)self.y=torch.FloatTensor(y)else:self.x=torch.FloatTensor(x)def __getitem__(self,idx):if self.y is not None:return self.x[idx],self.y[idx]else :return self.x[idx]def __len__(self):return len(self.x)
train_data=covid19dataset(raw_train_data,y_train)# train_datar 遍历unpack
valid_data=covid19dataset(raw_valid_data,y_valid)
test_data=covid19dataset(raw_test_data)
train_loader=DataLoader(train_data,batch_size=256,shuffle=True)
valid_loader=DataLoader(valid_data,batch_size=256,shuffle=True)
test_loader=DataLoader(test_data,batch_size=256,shuffle=False)

 ## 定义模型class MyModel(nn.Module):def __init__(self,input_dim):super(MyModel,self).__init__()self.layers=nn.Sequential(nn.Linear(input_dim,16),nn.ReLU(),nn.Linear(16,8),nn.ReLU(),nn.Linear(8,1),nn.ReLU())def forward(self,x):y = self.layers(x)return y.squeeze(1)

训练模型

模型
决策：均方损失函数 dim=1
算法：adam 梯度优化、在valid上做选择

GPU:
model.to(device)
X,Yto(device)

输入到模型的变量：FloatTensor()
与模型相关的变量取值要detach()
取值item()


len(raw_train_data)
raw_train_data.shape[1]
model=MyModel(raw_train_data.shape[1])
model.to(device)
def trainer(train_loader,valid_loader,model,epochs=3000):criteron=torch.nn.MSELoss(reduction='mean')optim=torch.optim.SGD(model.parameters(),lr=1e-5)step=0# 训练过程可视化器writer = SummaryWriter()  # Writer of tensoboard.if os.path.isdir('.\\model'):passelse:os.mkdir(".\\model")for epoch in range(epochs):  model.train()loss_record=[]train_pbar=tqdm(train_loader,position=0)for x,y in train_pbar:x=x.to(device)y=y.to(device)optim.zero_grad()preds=model(x)# y dim = 1loss=criteron(preds,y)loss_record.append(loss.detach().item())loss.backward()optim.step()step+=1train_pbar.set_description(f'Epoch [{epoch+1}/{epochs}]')train_pbar.set_postfix({'loss': loss.detach().item()})mean_train_loss=sum(loss_record)/len(loss_record)writer.add_scalar('losstrain',mean_train_loss,step)model.eval()loss_record=[]for x,y in valid_loader:x=x.to(device)y=y.to(device)with torch.no_grad():preds=model(x)loss=criteron(preds,y)loss_record.append(loss.item())mean_valid_loss=sum(loss_record)/len(loss_record)writer.add_scalar('lossvalid',mean_valid_loss,epoch) print(f'Epoch [{epoch + 1}/{epochs}]: Train loss: {mean_train_loss:.4f}, Valid loss: {mean_valid_loss:.4f}')best_loss = math.infif mean_valid_loss<best_loss:best_loss=mean_valid_losstorch.save(model.state_dict(),'./models/model.ckpt')print(f"new model{best_loss}")early_stop_count = 0else:early_stop_count += 1if early_stop_count >= 20:print('\nModel is not improving, so we halt the training session.')return
trainer(train_loader,valid_loader,model)

可视化

get_ipython().run_line_magic('reload_ext', 'tensorboard')
get_ipython().run_line_magic('tensorboard', '--logdir=./runs/')

预测

def predict(x,model)model.eval()y_record=[]for x in test_loader:x.to(device)with torch.no_grad():y=model(x)y_record.append(y)return y_record=torch.cat(y_record,dim=0)

covid19病例预测相关推荐

独家 | 可预测COVID-19病例峰值的新算法
作者:Esther Shein 翻译:王晓颖校对:吴金笛本文长度为3900字,建议阅读10分钟本文介绍了新的COVID-19病例峰值预测算法. 标签:COVID-19 预警系统的模型使用的数据是 ...
【深度学习】在PyTorch中使用 LSTM 进行新冠病例预测
时间序列数据,顾名思义是一种随时间变化的数据.例如,24 小时时间段内的温度,一个月内各种产品的价格,特定公司一年内的股票价格.长短期记忆网络(LSTM)等高级深度学习模型能够捕捉时间序列数据中的模式 ...
肯尼亚第三方支付_肯尼亚的COVID-19病例正在Swift增加，我们不知道为什么。
肯尼亚第三方支付 COVID-19 cases in Kenya are accelerating rapidly. New cases have increased 300% month-over- ...
【中国图形图像学报】面向COVID-19疫情预测的图卷积神经网络时空数据学习——CCF B、CSCD
[中国图形图像学报]面向COVID-19疫情预测的图卷积神经网络时空数据学习摘要当前的疾病传播研究主要集中于时序数据和传染病模型,缺乏运用空间信息提升预测精度的探索和解释.在处理时空数据时需要分 ...
【机器学习入门】(9) 逻辑回归算法：原理、精确率、召回率、实例应用(癌症病例预测)附python完整代码和数据集
各位同学好,今天我和大家分享一下python机器学习中的逻辑回归算法.内容主要有: (1) 算法原理:(2) 精确率和召回率:(3) 实例应用--癌症病例预测. 文末有数据集和python完整代码 1 ...
Covid-19病例监测公用数据集
原文: Covid-19 Case Surveillance Public Use Dataset Discover Demographic Trends of COVID-19 cases in t ...
修正 SEIR传染病动力学模型应用于冠状病毒病( COVID-19) 疫情预测和评估
修正 SEIR传染病动力学模型应用于冠状病毒病( COVID-19) 疫情预测和评估传统的 SEIR 模型在传统的 SEIR 模型中,研究对象被分成 S.E.I.R 等 4 种类型. (1)S ...
使用基于GAN的过采样技术提高非平衡COVID-19死亡率预测的模型准确性
作者|THILAKADIBOINA 编译|Flin 来源|analyticsvidhya 介绍本文介绍了生成性对抗网络(Generative attersarial Networks,GAN)的使用 ...
基于SEIR模型对美国COVID-19疫情传播的预测和分析
原文链接:易安的小窝 https://jingblog.tech/2022/09/22/mei-guo-xin-guan-yi-qing-yu-ce/ 1.思路基于每日发布的COVID-19确诊感染 ...

covid19病例预测

李宏毅机器学习2022

数据集

训练模型

可视化

预测

covid19病例预测相关推荐

最新文章

热门文章