extra-trees

using Drebin dataset to distinguish between malwares and not malwares

Rice Crop Yield Estimation Using Satellite Data - EY Open Science Data Challenge 2023

This repository contains the source code to reproduce the paper "Feature-based No-Reference Video Quality Assessment using Extra Trees".

End-to-End Used Car Price Prediction using Ensemble Learning | Extra Trees, Random Forest, Gradient Boosting | Python • Scikit-learn

Project 2 Group C - Predicting FinTech Bootcamp Graduate Salaries

Prediction of forest cover type in Python.

Machine learning pipeline for predicting employee attrition using ensemble models and feature engineering.

Sampling Assignment: Download dataset, balance classes, apply ML models with different sampling techniques to evaluate performance.

Predicting Appliance Energy use in Residential Buildings.

Precision-preserving optimized inference for one-dimensional reactive contaminant transport, with validated ADR1D-ML-Compact and ADR1D-NN-Fast models and reproducible Python workflows.

Data Science Project (Autonomous Driving Dataset Analysis)

An AI-driven hotel classification system using Extra Trees with SHAP-based explainability. Includes Streamlit frontend and FastAPI backend for deployment.

End-to-end Data Science project on Amazon Sales. Features data cleaning, EDA, outlier detection, and predictive modeling using Python, Pandas, and Scikit-learn.

Mitsui Kaggle — ExtraTrees with single-lag & group-lag features

Credit Card Fraud Detection with Python. Implemented various classification algorithms in scikit-learn and Built a Neural Network in Tensorflow

Fast gradient-boosted decision trees for Apple Silicon. A lightweight, sklearn-style Python API powered by MPS and Metal.

A website visualising various classification algorithms

Classical machine learning techniques to the problem of protein function prediction based solely on amino acid sequences. The task is formulated as a supervised multi-class classification problem, using functional annotations derived from the UniProt and Gene Ontology databases.

Machine learning project predicting electricity consumption based on ASHRAE dataset.

A dashboard where a pretrained ML model predicts whether a user is diabetic, or estimates their diabetes risk score, while gpt-5-mini uses its shap values and prediction to generate a report, which is then formatted into a downloadable PDF.