classification-report

Understanding emotions from audio files using neural networks and multiple datasets.

Artificial intelligence (AI, ML, DL) performance metrics implemented in Python

Tool demonstrating building credit risk models

Sentiment analysis on customer reviews using machine learning and python

A machine learning web application and classification pipeline detecting real vs. fake news articles. Built with a Streamlit interface and an optimized Python NLP pipeline using TF-IDF vectorization and Logistic Regression. Achieves a 98.57% stratified test accuracy, 98.63% F1-score, and a 0.999 AUC-ROC.

A collection of statistical methods

Flexible utility functions for use with the sklearn library

This repository contains functions to produce summary reports for machine learning solutions.

A web application that predicts whether a patient has malaria and identifies the specific strain (P. falciparum, P. malariae, or P. vivax) based on symptoms, vitals, and medical history, before lab tests are conducted. It uses three independently trained machine learning models and displays results with confidence scores.

Created a model to enable face recognition on a dataset from AT&T laboratories Cambridge. The images were taken at a different time and with varying lights, with different facial expression (open/closed eyes, smiling/not smiling) and with/without glasses.