Skip to content

mantaslu/AML-2022Fall-MP1

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Viral data science from October 2021

Here are some Python Jupyter data science notebooks from October 2022 analyzing apenly available data.

They are some of (the better) solutions produced by students as the first mini-project (out of three) in P176M010 Advanced Machine Learning course at Kaunas University of Technology Faculty of Informatics given by Mantas Lukoševičius.

Students had to come up with their own unique questions and answer them using the data. A solution template notebook was provided.

The notebooks are provided for reference and instruction with no warranty of any kind. They are in the state that they were submitted originally. They are anonymized if the author so desired. Some additional data needed to run them might not be easily shareable. For that you may contact the authors directly.

The Mini-Projects:


Questions:

  1. Is there any correlation between new deaths per million in a country on 2020 each month with the reproduction rate difference from 2020 to 2021?
  2. How does stringency and new vaccinations in the country during pandemic affected new registered Covid cases per million in 2021?
  3. How well can we classify European continent response for education format based on country's total new Covid case (per million), new and total vaccinations (per million), stringency index and ICU patients (per million) from 2020 to 2021?

Data sources:


Questions:

  1. Do countries with a greater average of beds per thousand people have less death rate compared to other countries? Take into account covid and other diseases from num. of deaths by cause dataset.
  2. Can we predict different disease death rates from death rates by various risks (pollution, alcohol use, unsafe water sources, etc.) using supervised machine learning?
  3. Can we predict the number of hospital patients from new cases per million and new deaths in countries where the data exist?

Data sources:


Questions:

  1. During which hours and weekdays do most road traffic accidents occur in NYC that cause casualties (injuries/deaths)?
  2. Are there any meteorological indicators that correlate with the amount of road traffic accidents in NYC that cause casualties during certain points in time?
  3. Is it possible to accurately predict whether or not a road traffic accident in NYC will have casualties based on the date, time, geographic coordinates and meteorological data?

Data sources:


Acknowledgments

The course was aided by TAs: Lukas Stankevičius and Eglė Butkevičiūtė.

License

The authors agreed to their work being published under a Creative Commons Attribution 4.0 International license. Creative Commons licencija

So is this intro summary by Mantas Lukoševičius.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages