How yess1ne/breast_cancer_themed_ml_project works
This is a Flask breast-cancer risk application with two prediction modes: numeric-feature assessment and image-based assessment. The visible app routes accept inputs and render forms or results; image uploads are saved and results are retrieved through a redirect. Separate training scripts produce the models and feature artifacts. The README documents setup, not the user workflow, and omitted app sections limit confirmation of model invocation and some result handling.
Main entry points: app.py Flask routes · MLP_model_training.py Numeric model training · image_based_RFC_model_training.py Image model training · index.html Home page
Components 18
Web application
- Flask routes
app.py - Home page
templates/index.html - Numeric form
templates/MB_form.html - Numeric result
templates/MB_result.html - Image result
templates/result.html - Image uploads
static/uploads
Model training
- Numeric model training
MLP_model_training.py - Image model training
image_based_RFC_model_training.py
Model artifacts
- Numeric dataset
wdbc_mean10_encoded.csv - MLP model
models/mlp_mean10.pkl - Numeric scaler
models/scaler_mean10.pkl - Feature order
models/mean10_feature_order.json - Image features
features.csv - Random forest model
risk_model.pkl - Image scaler
scaler.pkl - Evaluation results
risk_results.csv
Other components
- User
- Gemini API
Connections 15
- User → Flask routes: submits requests
app.py - Flask routes → Home page: renders
app.py - Flask routes → Numeric form: renders
app.py - Flask routes → Numeric result: renders
app.py - Flask routes → Image uploads: saves uploads
app.py - Flask routes → Image result: renders
app.py - Flask routes → Gemini API: requests explanations
app.py - Numeric model training → Numeric dataset: reads
MLP_model_training.py - Numeric model training → MLP model: writes
MLP_model_training.py - Numeric model training → Numeric scaler: writes
MLP_model_training.py - Numeric model training → Feature order: writes
MLP_model_training.py - Image model training → Image features: writes
image_based_RFC_model_training.py - Image model training → Random forest model: writes
image_based_RFC_model_training.py - Image model training → Image scaler: writes
image_based_RFC_model_training.py - Image model training → Evaluation results: writes
image_based_RFC_model_training.py