Data Science Project:
Telehealth Effectiveness and Satisfaction
I did a group project as part of my data science class. The goal of the project is to do answer a data science question from beginning to finish. For this project, my group had to come up with an original question, find our own data, clean and wrangle the data, do exploratory data analysis, and document our findings in a report. We used Git for version control.
Our research question is: do post-pandemic American patients who have telehealth available to them prefer telehealth over traditional in-person methods of care?
Some EDAs we did for our project.
My Contributions
My Contributions
ORGANISATION
I organized weekly meetings for my group and directed the topic of each meeting. I also helped organize our group repository on GitHub.
DATA CLEANING
Most of our datasets that we found online were made to be read by people, not computers. As such, we needed to convert them from pdf files into csv files, clean the artifacts from formatting , clean and wrangle the data.
I parsed through 300 pages of tables to select useful data, converted them into csv files, edited them, and then cleaned the wrangles the data with python.
Cleaned data sheets in our repository.
EXPLORATORY DATA ANALYSIS
In order to answer our research question, we needed to perform exploratory data analysis on the datasets we cleaned and wrangled.
I performed EDA on some of our datasets, yielding three graphs.
Graphs I made through EDA.