How koteeswarar/heart-disease-prediction works
This repository is a notebook-based heart-disease classification project. Its documented workflow loads the Cleveland dataset, cleans and encodes it, splits the data, trains a decision tree, and presents model evaluation and visualizations; pruning is also documented. The tree reflects README-described relationships only: no notebook source excerpts were available to verify implementation details or finer control flow.
Main entry points: HeartDiseasePrediction.ipynb Decision tree
Components 12
Data preparation
- Data loading
HeartDiseasePrediction.ipynb - Data cleaning
HeartDiseasePrediction.ipynb - Exploratory analysis
HeartDiseasePrediction.ipynb - Feature encoding
HeartDiseasePrediction.ipynb - Target conversion
HeartDiseasePrediction.ipynb
Modeling
- Train-test split
HeartDiseasePrediction.ipynb - Decision tree
HeartDiseasePrediction.ipynb - Cost-complexity pruning
HeartDiseasePrediction.ipynb
Evaluation
- Confusion matrix
HeartDiseasePrediction.ipynb - Tree visualization
HeartDiseasePrediction.ipynb
Other components
- Analyst
- UCI dataset
Connections 11
- Analyst → Data loading: runs analysis
README.md - UCI dataset → Data loading: provides data
README.md - Data loading → Data cleaning: cleans data
README.md - Data cleaning → Exploratory analysis: explores data
README.md - Data cleaning → Feature encoding: encodes features
README.md - Feature encoding → Target conversion: converts target
README.md - Target conversion → Train-test split: splits data
README.md - Train-test split → Decision tree: trains classifier
README.md - Decision tree → Cost-complexity pruning: prunes model
README.md - Decision tree → Confusion matrix: evaluates with
README.md - Decision tree → Tree visualization: plots tree
README.md