- Introduction
- Data Cleaning
- Exploratory Data Analysis
- Feature Engineering
- Modeling
- Conclusion
Welcome to the Healthcare Stroke Data Machine Learning Analysis project! This repository contains a Jupyter notebook that performs data analysis and builds machine learning models to predict stroke occurrences based on healthcare data.
The goal of this project is to apply machine learning techniques to a healthcare dataset to predict the likelihood of a stroke. This notebook covers the entire process from data cleaning and preprocessing to model building and evaluation.
Data Cleaning: Handling missing values, data transformation, and feature selection.
Exploratory Data Analysis (EDA): Visualizations and insights into the dataset's key features.
Feature Engineering: Scaling and transforming features to prepare for model training.
Model Building: Training and tuning various machine learning models, including:
- Random Forest
- Bagging Classifier
- AdaBoost
- Gradient Boosting
- Voting Classifier
- Logistic Regression
- K-Nearest Neighbors (KNN)
- Support Vector Machine (SVM)
- Decision Trees
Model Evaluation: Assessing the performance of models using metrics like accuracy, precision, recall, and F1-score
The models built in this project are evaluated using several metrics, and the best-performing model is identified based on its ability to predict strokes effectively.
The best performing model is Random Forest.
We found the correlation between samples here :
Install my-project with npm
npm install my-project
cd my-projectContributions are always welcome!
See contributing.md for ways to get started.
Please adhere to this project's code of conduct.