The focus of this project is to predict drug use based on region according to economic, mental health, education, and incarceration data.
This analysis is divided into two parts in our repository.
- The directory titled "nc" contains the work conducted in the first part of the project. We studied the above features at the county-level in North Carolina. The three datasets we compiled, along with the Jupyter Notebook (and its converted python and html files) in which we conducted our analysis, can be found here. Additionally, a directory titled "excel_docs_with_variable_info" contains some of the orignial files we downloaded before cleansing.
- The directory titled "national" contains the work conducted in the second part of the project. We studied the above features at the state-level in the United States. The four datasets we utilized for our research, along with a Jupyter Notebook (and its converted python and html files) in which we conducted our analysis, are found within this directory. Additionally, some datasets at the state-level that were found but not used are in the directory "old_data".
NOTE Given the need for various imports (as well as significant runtime) to obtain results from the notebooks, we encourage you to access the following links if you would like to review our analysis.
- North Carolina county-level analysis: https://nbviewer.jupyter.org/github/calebsanfo/CS216-Final/blob/master/nc/nc_analysis.ipynb
- US state-level analysis: https://nbviewer.jupyter.org/github/calebsanfo/CS216-Final/blob/master/national/state_analysis.ipynb
Finally, the directory titled "results" contains three pdf files that document our progress, analysis, and findings.