pandas==1.2.4
numpy==1.20.1
matplotlib==3.3.4
sklearn
scikit-learn==0.24.1
streamlit==1.2.0
fastapi==0.70.0
uvicorn==0.15.0
aiohttp==3.8.1
python-multipart==0.0.5
seaborn==0.11.1
gunicorn==20.1.0
statsmodels==0.13.2

pip install streamlit

pip install fastapi
pip install uvicorn
pip install python-multipart

To run this app locally, clone the code from the local branch (very important). Then, set up the virtual environment in your system and run the following command:

pip install -r requirements.txt

After that, run the following below servers:

streamlit run web_app/frontend.py

For Isolation Forest:

uvicorn api.if:ifr --reload

For LOF:

uvicorn api.lof:lof --reload

For STL Decomposition:

uvicorn api.stl:stl_decomposition --reload

Now your app should be running on your localhost with the port 8501 depending upon your system (please check the streamlit terminal). You can access it most probably with the following link: http://localhost:8501/ or http://127.0.0.1:8501/

The deployed Streamlit Cloud Web App makes the API calls to these Heroku API endpoints to get the anomalies. If you want to check these endpoints individually, just click on the respective endpoint and try out the post method by uploading the test csv file.