This project aims to understand and predict a car's fuel efficiency based on its characteristics. I have built a multiple linear regression model using stats models and scikit-learn.

Data pre-processing with modular components for: normalizer/standarizer, unbiaser, trimmer and feature selector.

End-to-End Machine Learning project I made as a machine learning intern @ Mentorness

Machine Learning in R

Synthetic data generation package to balance imblanaced datasets

Feature selection package of the mlr3 ecosystem.

Developer Version of the R package CAST: Caret Applications for Spatio-Temporal models

This project explores an IBM telecom dataset, conducting initial EDA and data preprocessing. It examines three genetic algorithm variations for feature selection: one-point, two-point, and uniform crossover. Logistic regression is used to predict customer churn, and performance is evaluated using error bar plots.

This project uses Exploratory Data Analysis (EDA) to uncover trends and insights from restaurant cuisine ratings, helping improve menus, enhance customer experiences, and guide targeted marketing strategies for business success.

Desbordante is a high-performance data profiler that is capable of discovering many different patterns in data using various algorithms. It also allows to run data cleaning scenarios using these algorithms. Desbordante has a console version and an easy-to-use web application.

Feature selection with Firefly Algorithm

Machine learning and data analysis package implemented in JavaScript and its online demo.

EvalML is an AutoML library written in python.

Principal Component Analysis (PCA) is a powerful dimensionality reduction technique commonly used in machine learning and data analysis. It transforms a dataset into a set of linearly uncorrelated variables called principal components.

Easy to use Python library of customized functions for cleaning and analyzing data.

The repository presents the notebooks and models used for my experimental thesis entitled: "Experimental Study of the Steel Market Through CNN-LSTM Deep Learning Models: Practical Applications for Cost Reduction in Industries"

The goal is to eliminate manual work in identifying faulty wafers. Opening and handling suspected wafers disrupts the entire process. False negatives result in wasted time, manpower, and costs.

Workflow to generate interactive html feature selection report for longitudinal and cross-sectional microbiome studies

mRMR (minimum-Redundancy-Maximum-Relevance) for automatic feature selection at scale.

Feature Selection using Metaheuristics Made Easy: Open Source MAFESE Library in Python