This project builds a Decision Tree model to predict diabetes outcomes based on patient health data.
- Analyze relationships between health features and diabetes outcome
- Build a classification model using Decision Tree
- Identify the most important features affecting predictions
- Exploratory Data Analysis (EDA)
- Decision Tree Classifier (scikit-learn)
- Feature Importance Analysis
- Python (pandas, numpy, scikit-learn)
- Data Visualization (matplotlib, seaborn)
- Diabetes dataset (Pima Indians Diabetes dataset)
- Glucose level is the most important factor influencing diabetes prediction
- BMI and Age also significantly impact the model
- Some features (e.g., SkinThickness, Insulin) have lower importance
- Decision Tree provides interpretable results for feature impact
pip install -r requirements.txt