# Healthcare Related Project
This project was built during my Data Science internship. It focuses on analyzing heart disease data using Python libraries like Pandas, Seaborn, NumPy, and Machine Learning.
## 🧠 Tools Used
- Python
- Jupyter Notebook
- Pandas, NumPy, Seaborn
- Machine Learning (e.g., Logistic Regression)
## 📊 Dataset
The dataset used is heart\_disease.csv.
## 📈 Goal
To build a predictive model for detecting heart disease.
## 📂 Files
- Untitled.ipynb - Main Jupyter Notebook
- heart\_disease.csv - Dataset
- .gitignore - Git ignore settings
*Developed by Abhiram V*
This project was developed as part of my 1-month internship at Zephyr Technologies Pvt. Ltd from 19 May to 19 June 2025.
It focuses on predicting the presence of heart disease using various machine learning techniques and exploratory data analysis.
- Python (Pandas, NumPy, Scikit-learn, Seaborn, Matplotlib)
- Jupyter Notebook
- Machine Learning Algorithms:
- Logistic Regression
- Random Forest
- K-Nearest Neighbors
- CSV Dataset (
heart_disease.csv)
- ✅ Cleaned and preprocessed healthcare dataset
- 📈 Visualized key features affecting heart disease
- 🧠 Trained and tested multiple ML models
- 📉 Compared model accuracy
- 💾 Exported results and graphs
| File | Description |
|---|---|
heart_disease_prediction.ipynb |
Main notebook containing data analysis, model training, and results |
heart_disease.csv |
Dataset used for training and testing |
output_chart.png |
Sample accuracy chart of model |
README.md |
Project documentation |
.gitignore |
To avoid pushing unnecessary system/cache files |
Click here to view output screenshots
| Model | Accuracy |
|---|---|
| Logistic Regression | 85% |
| Random Forest | 88% |
| KNN | 81% |
Abhiram V
Data Science Intern @ Zephyr Technologies
May 2025 – June 2025
Feel free to explore the code, run it on your own data, or suggest improvements!