DOI: https://doi.org/10.24433/CO.2791944.v1
Y. Takefuji, "The Best and Sustainable COVID-19 Policy in the World," in IEEE Transactions on Computational Social Systems, doi: 10.1109/TCSS.2022.3227926.
Takefuji, Y. Toyokura, J. Time-series COVID-19 policy outcome analysis of the 50 U.S. states. Clinical Immunology Communications. https://doi.org/10.1016/j.clicom.2023.08.002 (2023).
This is a practice or exercise for students.
-
Build a program for scoring U.S. states' policies toward the COVID-19 pandemic. Scoring is based on the number of deaths per population (millions).
-
Then, use machine learning for understanding the relationship between its scores and other indicators. Specify feature-importances in descending order.
Indicators such as the number of deaths, immunization rates, population, poverty rates, and others must be used in machine learning.
- Examine whether the result will play a key role for policymakers in their decision-making against the pandemic.
https://data.cdc.gov/api/views/9bhg-hcku/rows.csv
usscore is to score state COVID-19 policies in the US. Scoring is calculated by dividing the number of deaths due to COVID-19 by the population in millions. The goal of usscore is for states with poor scores to learn good strategies from states with excellent scores.
$ pip install usscore
$ pip install usscore --force-reinstall --no-cache-dir --no-binary :all:
$ usscore
The result of sorted scores is shown as follows as of March 10 2022.
Comparison with other countries on scores generated by scorecovid: https://pypi.org/project/scorecovid
https://github.com/nytimes/covid-19-data/raw/master/live/us-states.csv
https://covid.ourworldindata.org/data/vaccinations/us_state_vaccinations.csv
https://data.ers.usda.gov/reports.aspx?ID=17827