Skip to content

arpitkumar2004/DA96_webapp

Repository files navigation

Predicting risk factors by Determining Social Determinants of Health variables using a probabilistic model.

Files in the zip:

D:\GC_2024\FINAL\STREAMLIT-FINAL
│   hello.py
│   HUD 2020 Crosswalk.csv
│   imputed_merged.csv
│   out.pkl
│   output_streamlit.csv
│   readme.md
│   requirements.txt
│   Updated columns - Gemini.csv
│   Variable mapped with Risk Factors.xlsx
│
├───.streamlit
│       config.toml
│
├───pages
│   │   1_questionnare.py
│   │   3_score_card.py
│   │   fetch_resources.py
│   │
│   └───__pycache__
│           fetch_resources.cpython-310.pyc
│           fetch_resources.cpython-311.pyc
│
└───resources
        adult_day_care.csv
        assisted_living.csv
        florida_hospitals.csv
        florida_long_term_care.csv
        florida_providers.csv
        Food_Services.csv
        Geriatic_Care_Managers.csv
        Home_Care.csv
        Home_Health_rating.csv
        Hospitals.csv
        independent_living.csv
        long_term_care_ratings.csv
        memory_care.csv
        Suppliers.csv
        Transportation.csv
        uszips.csv

Steps to run the program:

  1. open a terminal / command prompt in the working directory
  2. make sure all required dependencies are installed. we used python==3.10.13 and required pip modules are listed in requirements.txt. Installation can be done using the following command:
pip install -r requirements.txt
  1. To run the webapp, use the following command:
streamlit run hello.py
  1. Follow the instructions and fill the questionnare. Upon submitting, the last runs input gets saved locally and a scorecard is shown containing risk levels for the 5 broad topics and each section can be expanded to see the sublevels upon which each Social determinant is based.
  2. Upon encountering high enough risk, certain information is provided for the user to follow up according to their predicted needs.

About

Predicting risk factors by Determining Social Determinants of Health variables using a probabilistic model.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages