How manjulasrirama/irrigation-water-requirement-prediction-ml works
This is a Streamlit application for predicting irrigation requirement levels. A user enters soil, weather, crop, and irrigation details; the app combines those inputs into a row, sends it to a saved model, and displays the predicted level and, when supported, class probabilities. The CSV supplies both dropdown choices and numeric defaults. The repository also contains a small script that loads the model and prints a status message. The README is empty, and the notebook’s role cannot be established from the available source, so neither is represented as a training workflow.
Main entry points: app.py Streamlit app · irrigation_model.pkl Saved model · prediction.py Model load check · irrigation_prediction.csv Irrigation data
Components 7
User interface
- Streamlit app
app.py - Prediction inputs
app.py - Level and probabilities
app.py
Prediction
- Model load check
prediction.py
Model and data
- Saved model
models/irrigation_model.pkl - Irrigation data
dataset/irrigation_prediction.csv
Other components
- User
Connections 8
- User → Streamlit app: enters details
- Streamlit app → Irrigation data: reads defaults and options
- Streamlit app → Prediction inputs: collects details
- Streamlit app → Saved model: loads model
- Streamlit app → Saved model: predicts and scores
- Saved model → Streamlit app: returns predictions
- Streamlit app → Level and probabilities: displays results
- Model load check → Saved model: loads model