Used machine learning models to predict spam mails, loan, diabetes etc... also done web scraping, sentiment analysis, EDA. Have fun.
-
Updated
Jun 17, 2024 - Jupyter Notebook
Used machine learning models to predict spam mails, loan, diabetes etc... also done web scraping, sentiment analysis, EDA. Have fun.
End-to-end diabetes risk predictor: XGBoost (0.824 AUC, 73% recall) + SHAP explainability + FastAPI + Streamlit. Handles class imbalance with tuned threshold for clinical screening. 253K CDC BRFSS samples.
Identified the optimal order of preprocessing for Pima Diabetes Dataset, how feature selection and upsampling affects the evaluation metrics
used diabetes dataset from kaggle and performed prediction using Logistic Regression, Random Forest, XGBoost
Add a description, image, and links to the diabtetes-prediction topic page so that developers can more easily learn about it.
To associate your repository with the diabtetes-prediction topic, visit your repo's landing page and select "manage topics."