How saranya-aluru/cropwise works
CropWise is a Streamlit crop-recommendation dashboard. Users enter seven soil and environmental readings, which the app uses to produce a crop recommendation and show probabilities and an input summary. The app also provides model-explanation and performance pages. The source excerpt describes training a logistic-regression model from the CSV and using a demo fallback if it is missing; this differs from the README’s description of the current implementation as rule-based. The app is a single-file implementation, so its distinct responsibilities share one source path. Edges reflect the shown excerpt or documented workflow; unsampled page internals are not inferred.
Main entry points: app.py Streamlit App · Crop_recommendation.csv Crop Dataset
Components 9
Dashboard
- Streamlit App
cropwise/app.py - Field Inputs
cropwise/app.py
Data and Prediction
- Crop Dataset
cropwise/Crop_recommendation.csv - Model Training
cropwise/app.py - Crop Prediction
cropwise/app.py
Results and Evaluation
- Recommendation View
cropwise/app.py - Model Explanation
cropwise/app.py - Performance Dashboard
cropwise/app.py
Other components
- User
Connections 10
- User → Streamlit App: uses
README.md - Streamlit App → Field Inputs: presents
README.md - Field Inputs → Crop Prediction: provides readings
README.md - Streamlit App → Model Training: trains on startup
cropwise/app.py - Model Training → Crop Dataset: reads
cropwise/app.py - Crop Prediction → Recommendation View: displays result
README.md - Recommendation View → User: shows recommendation
README.md - Streamlit App → Model Explanation: provides page
README.md - Streamlit App → Performance Dashboard: provides page
README.md - Model Training → Crop Prediction: supplies model
cropwise/app.py