pip install -r requirements.txt
- Get the model in Google Drive and put it under your working folder (Under folder "rfModelAndPipeline") https://drive.google.com/drive/folders/1FPLl3oOSxoQyjyiF6Qd4jkWyaoFWch2N?usp=sharing
- Test out the test.ipynb first
- Then in terminal
streamlit run app.py
- Python 3.8
- Spark 3.5.1
- Hadoop 3.3.4
- openjdk version 1.8.0_412-412
- winutils.exe and hadoop.dll to solve hadoop dependency issue in Windows from https://github.com/cdarlint/winutils