There are 2 repositories under ml-pipelines topic.
An open-source ML pipeline development platform
An AutoML pipeline selection system to quickly select a promising pipeline for a new dataset.
Free Open-source ML observability course for data scientists and ML engineers. Learn how to monitor and debug your ML models in production.
Best practices for engineering ML pipelines.
Components that I have created for Kubeflow Pipelines. Try them in https://cloud-pipelines.net/pipeline-editor/
This Project is a part of Data Science Nanodegree Program by Udacity in collaboration with Figure Eight. The initial dataset contains pre-labelled tweet and messages from real-life disasters. The aim of this project is to build a Natural Language Processing tool that categorize messages.
This a repo that was created to learn more about Airflow and develop awesome data engineering projects. ππ
Fraud detection ML pipeline and serving POC using Dask and hopeit.engine. Project created with nbdev: https://www.fast.ai/2019/12/02/nbdev/
ML pipeline to categorize emergency messages based on the needs communicated by the sender.
Big data application of Machine Learning concepts for sentiment classification of US Airlines tweets. The focus is on the usage of pyspark libraries (ml-lib) on big data to solve a problem using Machine Learning algorithms and not about the choice of algorithm used in the ML model creation. It also involves data pre-processing using NLP techniques, cross-validation and parameter-grid builder.
This repository contains my code solution to DeepLearning.AIs Practical Data Science On AWS Cloud Specialization.
Develop algorithms to classify genetic mutations based on clinical evidence (text).
In this project, I developed a completed Vertex and Kubeflow pipelines SDK to build and deploy an AutoML / BigQuery ML regression model for online predictions. Using this ML Pipeline, I was able to develop, deploy, and manage the production ML lifecycle efficiently and reliably.
Proving Skills in Pipelines, Pickle Files and ML Modelling
Collaborative team machine learning project classifying reviews scraped from the IMDB website as either positive or negative using sentiment classification. Tools used: BeautifulSoup and Splinter to scrape reviews, Pyspark, SQLAlchemy and Heroku.
This shows the machine learning pipeline for Classification and Clustering using Pycaret 3.0 on jupyter notebook
A deployed machine learning model that has the capability to automatically classify the incoming disaster messages into related 36 categories. Project developed as a part of Udacity's Data Science Nanodegree program.
Website built in JavaScript & React as a "blog" to document an ML pipeline I built for Apartment Price Scraping project
Course 2 project of the Udacity ML DevOps Nanodegree Program