Feb 17th Mark's work

[ZIBOWANGKANGYU]

Hi everyone,

I wanted to give you a head-up on the work that I completed today before going to sleep.

(1) Gathering and cleaning data

• US daily COVID-19 features, using source recommended by Citadel from https://covidtracking.com/. Documentation of variables can be found here.
• US mobility data, coming from Community Mobility Reports. Its documentation can be found here.
• US state-level government response data, gathered from here. The dataset itself is a bit complicated. However, for the variables that I selected, basically higher numbers indicate more strict restrictions, and "flags" indicate whether a policy is targeted at a region or general to the whole state.
• US misinformation data. I used API to get Google Trend data. I only used the term "plandemic" since many terms in the Google doc have too small sample sizes. Maybe we need to think of new terms. Unlike other sources which are daily data, this data is weekly.
  All code to collect and manipulate data are directly under our root folder.

(2) Merging and aggregating data
I merged all datasets, except for the misinformation data into data/cleamed/US_daily_cleaned.csv. This merged dataset is at daily time intervals and the state level. I did not have the time to aggregate data to weekly intervals and merge the misinformation data.

(3) Writing a bit of report.
I briefly wrote down what I have done in the report.

Talk to you tomorrow!