README.md

metadata

title: AgAi
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.0.1
app_file: app.py
pinned: false
license: mit
short_description: Web app to use the AgAi model that predicts crop yield

What is this?

• Our demo models run on this Hugging Face Space, a completely self-contained and remotely hosted app that we call "AgAiSpace".

What do I need to make it work?

• The great thing about Hugging Face Spaces is that it requires no setup to run. No libraries need to be installed, and the code just runs on upload (after the build process is complete).
• We automatically import weights from our model repo on Hugging Face, and any data input is delivered through the UI.
  • Link the model repo (just stores the trained weights) here: https://huggingface.co/AgAiPpl/AgAi
• If you want to see all of our code used to make our model, check out our master notebook "Final_Project_Combined_Notebook".

What if I want to run it locally?

• In that case, follow the simple rules down below to get the app running. You'll need to have Python installed. The steps below will take care of installing any libraries you need (for reference, it will install huggingface_hub, gradio, scikit-learn, joblib, numpy, pandas, xgboost).
• The directions below are basically equivalent to clicking the snowman options button on the top right and following the directions for "Run Locally."

1. Clone the repo

2. Create and activate Python environment

python -m venv env source env/bin/activate

3. Install dependencies

pip install -r requirements.txt

5. Run the program

python app.py