[UNMAINTAINED] Automated machine learning for analytics & production

(AAAI' 20) A Python Toolbox for Machine Learning Model Combination

Distributed Machine Learning Patterns from Manning Publications by Yuan Tang https://bit.ly/2RKv8Zo

Primitives for machine learning and data science.

Provenance and caching library for python functions, built for creating lightweight machine learning pipelines

Wind Power Forecasting using Machine Learning techniques.

Python library for Executable Machine Learning Knowledge Graphs

kubeflow example

create a robust, simple, effecient, and modern end to end ML Batch Serving Pipeline Using set of modern open-source/free Platforms/Tools

A code-first way to define Ploomber pipelines

Improved pipelines for data science projects.

Sentiment analysis on customer reviews using machine learning and python

Example string processing pipeline on Triton Inference Server

based on the befitting sensors fetched data, prediction is to be made whether the failure in a vehicle is due to APS or some other component. Emphasis is on reducing the consequential cost by reducing the false positives and false negatives and more importantly false negatives as it appears cost incurred due to them is 50 times higher.

🚀 Smart Product Pricing Challenge (Amazon ML Hackathon 2025) AI-powered multimodal solution for optimal product price prediction using text, image, and tabular data. Built with SBERT, ResNet50, and LightGBM + Ridge stacking, with GPU acceleration.

ML AutoTrainer Engine, developed using Streamlit, is an advanced app designed to automate the machine learning workflow. It provides a user-friendly platform for data processing, model training, and prediction, enabling a seamless, code-free interaction for machine learning tasks.

Building machine learning pipelines with procedural programming, custom-pipeline or third-party code using the titanic data set from Kaggle

An end-to-end toolkit for ingesting, normalizing, and processing diverse egocentric datasets for humanoid robotics research. It provides a flexible pipeline for converting multiple data formats into a unified canonical schema, enriching them with features like object detection, training toolsets and visualizations.

Machine Learning pipelines are deployed to accomplish the objective of credit risk analysis.

A modular and reproducible Random Forest pipeline (built on Kedro) for high-fidelity variable star classification, strategically utilizing synthetic data augmentation.