Model Testing App 🚀

This Streamlit-based web application allows users to test pre-trained machine learning models on plant transpiration data. It enables users to input their experimental data and visualize model predictions.

✅ Load and test models on user-provided data
✅ Select plant type and experiment details
✅ Retrieve and visualize transpiration data
✅ Generate model evaluation metrics and plots

1. Enter Details: Provide the Control ID, Experiment ID, and Plant ID.
2. Select Dates: Choose a date range for analysis.
3. Pick Plant Type: Tomato or Cereal.
4. Check Irrigation Status: Mark whether the plant was well irrigated.
5. Retrieve Data: Click "Test Model" to load data.
6. Evaluate Model: If the data looks correct, click "This is my data! Let's test the Model" to run the models and visualize results.

git clone https://github.com/yourusername/ModelTestingApp.git
cd ModelTestingApp

Ensure you have Python installed. Create a virtual environment and install dependencies:

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt

Start the Streamlit application with:

streamlit run app/TestModelApp.py

You can deploy this app using Streamlit Cloud:

1. Push the repository to GitHub.
2. Go to Streamlit Community Cloud.
3. Connect your repository.
4. Deploy the app.

/ModelTestingApp
│── app/                     # Contains main app-related scripts
│   ├─ TestModelApp.py       # Main Streamlit app file
│   └─ app_functions.py      # Contains utility functions (e.g., data retrieval & model testing)
│─ models/                   # Stores trained models (not included in the public repo)
│─ data/                     # Example dataset for users to test
│─ requirements.txt          # List of dependencies for setting up the environment
│─ README.md                 # Documentation explaining the app, setup, and usage
│─ .gitignore                # Excludes unnecessary files from version control
│─ LICENSE                   # Open-source license (optional)

Contributions are welcome! Feel free to fork the repo, make improvements, and submit a pull request.

This project is licensed under the MIT License.

For any issues or suggestions, feel free to reach out!