MLOps Pipeline with Python, AWS, Docker – YouTube Viewer Sentiment

Post Content

This comprehensive course teaches you to build an end-to-end MLOps pipeline that analyzes YouTube sentiment in real-time through a Chrome extension. You’ll master modern ML tools like MLflow, DVC, Docker, and AWS while developing a complete solution from data collection to deployment. You’ll gain hands-on experience with real-world ML engineering and MLOps practices.

Code: https://github.com/entbappy/End-to-end-Youtube-Sentiment

Bappy’s YouTube Channel: https://www.youtube.com/@dswithbappy
Bappy’s LinkedIn profile: https://www.linkedin.com/in/boktiarahmed73/
Bappy’s Udemy: https://www.udemy.com/user/boktiar-ahmed-bappy/

Support for this channel comes from our friends at Scrimba – the coding platform that’s reinvented interactive learning: https://scrimba.com/freecodecamp

Contents
(0:00:00) Introduction & Project Planning
(0:19:52) Data Collection
(0:21:28) Data Preprocessing & EDA
(0:41:43) Setup MLFlow Server on AWS
(0:57:34) Building Baseline Model
(1:06:25) Improving Baseline Model – BOW, TFIDF
(1:14:56) Improving Baseline Model – Max features
(1:20:55) Improving Baseline Model – Handling Imbalanced Data
(1:26:54) Improving Baseline Model – Hyperparameter tuning with Multiple Improving Baseline Model
(1:32:13) Stacking Models
(1:34:14) Building an ML Pipeline using DVC
(1:38:22) Data Ingestion Component
(1:46:01) Data Preprocessing Component
(1:48:11) Model Building Component
(1:52:28) Model Evaluation Component with MLFlow
(1:59:58) Model Register Component with MLFlow
(2:02:42) Flask API Implementation
(2:14:20) Implementation of Chrome Plugin
(2:24:27) Adding Docker
(2:25:46) CICD Deployment on AWS

Thanks to our Champion and Sponsor supporters:
Drake Milly
Ulises Moralez
Goddard Tan
David MG
Matthew Springman
Claudio
Oscar R.
jedi-or-sith
Nattira Maneerat
Justin Hual