How sahbimlesh007/end-to-end-heart-disease-analytics-and-prediction works
This repository combines heart-disease data analysis and reporting with a Streamlit prediction app. The evidenced user workflow collects patient measurements, aligns and scales them, runs the saved classifier, and displays a risk prediction. The README also documents EDA, MySQL, and Power BI capabilities; their detailed wiring is not visible in the sampled source, so those links are left out.
Main entry points: app.py Prediction App · scaler.pkl Feature Scaler · LOG_heart.pkl Heart Classifier · columns.pkl Feature Columns
Components 15
Risk Prediction
- Prediction App
app.py - Input Preparation
app.py - Feature Scaler
scaler.pkl - Heart Classifier
LOG_heart.pkl - Feature Columns
columns.pkl - Risk Result
app.py
Data Analysis
- Heart Dataset
heart.csv - EDA Notebook
ML_Project_02 (EDA).ipynb
SQL Database
- MySQL Database
- Database Setup
MySQL Queries/create_database.sql - Table Design
MySQL Queries/create_table.sql - SQL Views
MySQL Queries/create_views.sql - SQL Indexes
MySQL Queries/create_index.sql
BI Reporting
- Power BI Report
Heart Disease BI Report.pbix
Other components
- User
Connections 13
- User → Prediction App: enters measurements
- Prediction App → Feature Columns: loads columns
- Prediction App → Feature Scaler: loads scaler
- Prediction App → Heart Classifier: loads classifier
- Prediction App → Input Preparation: builds input
- Input Preparation → Feature Columns: aligns features
- Input Preparation → Feature Scaler: scales input
- Input Preparation → Heart Classifier: predicts risk
- Prediction App → Risk Result: displays prediction
- Database Setup → MySQL Database: creates database
- Table Design → MySQL Database: defines table
- SQL Views → MySQL Database: creates views
- SQL Indexes → MySQL Database: adds indexes