👩🏻⚕️Covid-19 estimation and forecast using statistical model; 新型冠状病毒肺炎统计模型预测 (Jan 2020)
简体中文 | English
估计和预测 2019-nCoV 新型冠状病毒在武汉的爆发情况
MSE, basic SEIR model, sentiment analysis 了解 SEIR 模型原理
根据丁香园实时数据预测全国未来两个月的肺炎趋势
Author: Shih Heng Lo(模型灵感的提供以及指导者); Yiran Jing.
Baseline: Ridge regression, improved by Dynamic SEIR model
2020年1月23日,交通枢纽的武汉市被封城。900万人民被困在武汉市区。在此之前,有500万人因春节离开武汉。估计机场的国际人流量为1900万。
考虑到新型武汉肺炎的快速传播性和武汉居住人口在封城前后变化巨大,我选择了不同的模型来估计封城前后武汉的感染人数,主要参考和借鉴今日发表的相关论文,数据参考官方数据。
Method: Considering Wuhan is the major air and train transportation hub of China, we use the number of cases exported from Wuhan internationally as the sample, assuming the infected people follow a Possion distribution, then calculate the 95% confidence interval by profile likelihood method. Sensitivity analysis followed by.
Reference: report2 (Jan 21)
Method: Deterministic SEIR (susceptible-exposed-infectious- recovered) model and Sensitivity analysis
根据2月2号官方媒体爆料,患者发现并不及时而且隔离措施也没有做的很好。基于这个现实,武汉肺炎患者的实际峰值很可能超过10万甚至15万。 更新:2月5号之后,武汉新建的三所医院开始收纳病患(共计有6000床位),所以现在的传染风险应该有明显下降,毕竟更多的病人可以被医院收容(治疗/强制隔离)
Method: Dynamic SEIR (susceptible-exposed-infectious- recovered) model, Gradient Descent Model comparison based on the test score (MAPE) of last 5 days, baseline is ridge Ridge regression Reference: Dynamic SIR model
红色的线为现存感染人数的走势预测 注释:
The mean absolute percentage error (MAPE) is a measure of prediction accuracy of a forecasting method in statistics. The MAPE of confirmed cases using data between 2020- 2-14 to 2020-02-22 is 0.0066. The figure below visualizes the real observation and the SEIR model predictions for the next 9 days. Overall, SEIR model predicts well for the peaking time and the general trend.
Optimization algorithm Gradient Descent
## Update data from DXY
$ cd ../data_processing && python DXY_AreaData_query.py # save data out to data folder.
CoronaTracker Analytics Dashboard
目前关于肺炎的学习和任务,以及接下来的方向在这里更新:Project
如果你对肺炎相关的数据分析和可视化感兴趣,请联系我!