How priyankagarsole/diabetespredictions works
This is a small Flask diabetes-prediction web app. A user opens the home page, submits clinical measurements to the prediction route, and receives a rendered classification. The route scales the submitted values and passes them to a loaded logistic-regression model. The source excerpt supports the web and inference flow; the dataset and notebook are present in the tree, but their contents and relationship to the deployed model were not inspected.
Main entry points: application.py Flask app and routes · index.html Home template · pred.html Prediction template · stdscaler.pkl Feature scaler
Components 6
Web interface
- Flask app and routes
application.py - Home template
templates/index.html - Prediction template
templates/pred.html
Prediction inference
- Feature scaler
models/stdscaler.pkl - Logistic classifier
models/log_reg_model.pkl
Other components
- User
Connections 6
- User → Flask app and routes: requests page
application.py - Flask app and routes → Home template: renders home
application.py - User → Flask app and routes: submits measurements
application.py - Flask app and routes → Feature scaler: transforms inputs
application.py - Flask app and routes → Logistic classifier: predicts class
application.py - Flask app and routes → Prediction template: renders result
application.py