Example machine learning pipeline with MLflow and Hydra

Anomaly Detection Pipeline with Isolation Forest model and Kedro framework

This project is focused on the Deployment phase of machine learning. The Docker and FastAPI are used to deploy a dockerized server of trained machine learning pipeline.

Attendance prediction tool for NBA games using machine learning. Full pipeline implemented in Python from data ingestion to prediction. Attained mean absolute error of around 800 people (about 5% capacity) on test set.

This repository shows the implementation of machine learning algorithms, data pipelines and data visualization with scikit-learn and python.

This repo showcases a project that transforms ML model training into a simplified, production-ready Kedro Dockerized Pipeline. It emphasizes best MLOps practices, enabling easy training, evaluation, and deployment of models, including XGBoost, LightGBM and Random Forest, with built-in visualization and logging features for effective monitoring.

A machine learning pipeline taking you from raw data to fully trained machine learning model - from data to model (d2m).

Develop a machine learning model that can predict whether people have diabetes when their characteristics are specified

The code snippet cleans and analyzes a hotel bookings dataset, handling missing values, dropping unnecessary columns, and creating new features. It visualizes the data using various plots and performs feature encoding and selection. It then trains machine learning models to predict hotel booking cancellations.

Explore a collection of Jupyter notebooks that guide you through various stages of the machine learning pipeline. From data analysis and feature engineering to model training and deployment, these notebooks provide practical insights for both beginners and experienced data enthusiasts. Let's dive into the world of data-driven decision-making! 📊🚀"

An advanced MLOps project featuring an end-to-end machine learning pipeline with a Random Forest Classifier. This repository automates data preprocessing, model training, hyperparameter tuning, and deployment using CI/CD, containerization, and cloud deployment. It includes real-time model monitoring, data versioning with DVC (Data Version Control)

A Python desktop application using CustomTkinter for data analysis and machine learning.

Pipeline for augmenting sparse data for genetic optimisation

Analyze disaster data from Figure Eight to build a model for an API that classifies disaster messages.

This repository contains a Machine Learning (ML) pipeline which predicts the response to messages in disaster situations. An ETL pipeline is also developed and everything is deployed with a web app based in Flask.

This repository has been created for Udacity Data Scientist Nanodegree Program - Data Engineering Part - Disaster Response Pipeline Project.

Developed a ETL pipeline, a ML training pipeline and a Flask web app that can classify disaster-related messages input by a user.

This repository lists one of my projects and findings as part of my Machine Learning DevOps Engineer Nanodegree.

DataCamp inetrmediate course on how and when to perform data preprocessing in any machine learning project to get the data ready for modeling

White and Red Wine classification using logistic regression