How robust-enigma/cardiovascular-disease-prediction works
This repository is a Streamlit application for exploring uploaded cardiovascular-disease data and comparing classifiers for heart-disease prediction. Its workflow includes target normalization and train/test splitting, optional SMOTEENN balancing, individual or multi-model training, and metric/confusion-matrix visualizations; it also offers exploratory plots. The sampled code shows these responsibilities in one file. The excerpts do not establish how the bundled CSV is used or expose all UI routing, so those connections are omitted.
Main entry points: project.py Data preparation
Components 10
Data exploration
- Uploaded dataset
- Exploratory plots
project.py
Modeling
- Data preparation
project.py - SMOTEENN balancing
project.py - Selected classifier
project.py - Six-model comparison
project.py
Evaluation and results
- Classification metrics
project.py - Confusion matrix plot
project.py - Streamlit results
project.py
Other components
- App user
Connections 11
- App user → Uploaded dataset: uploads
- Uploaded dataset → Exploratory plots: reads
project.py - Uploaded dataset → Data preparation: reads
project.py - Data preparation → Selected classifier: splits data
project.py - Data preparation → Six-model comparison: supplies split
project.py - SMOTEENN balancing → Six-model comparison: resamples data
project.py - Selected classifier → Classification metrics: evaluates predictions
project.py - Six-model comparison → Confusion matrix plot: plots predictions
project.py - Classification metrics → Streamlit results: displays scores
project.py - Confusion matrix plot → Streamlit results: renders plot
project.py - Exploratory plots → Streamlit results: renders plots
project.py