https://github.com/noahgift/databricks-zero-to-mlops
https://github.com/noahgift/databricks-zero-to-mlops
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/noahgift/databricks-zero-to-mlops
- Owner: noahgift
- License: cc0-1.0
- Created: 2022-02-14T17:28:50.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-05-14T21:13:25.000Z (over 3 years ago)
- Last Synced: 2025-04-08T14:40:35.320Z (6 months ago)
- Language: Python
- Size: 157 KB
- Stars: 27
- Watchers: 2
- Forks: 17
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# databricks-zero-to-mlops
A four week course on MLOps with Spark and Databricks. By the end of this course, you will be able to develop ML models using standardized workflows for data processing and model management and maintenance using open-source tools. This is accomplished by using PySpark and MLflow to build scalable and reproducible solutions using MLOps methodologies.
## Syllabus
* [syllabus](docs/syllabus.md)
## Demos and Deliverables
This course includes a weekly demo video assignment. You will report on the progress of your ongoing project with a 30-90 second video, including screen-casting of your progress. The reason for this weekly demo is to increase metacognition as well teach other students what you now, thus increasing the learning experience for everyone.
## Artifacts
## Datasets
* [Azure Open Datasets](https://docs.microsoft.com/en-us/azure/open-datasets/dataset-catalog#AzureDatabricks)
* [Example Open Dataset (TartanAir)](https://docs.microsoft.com/en-us/azure/open-datasets/dataset-tartanair-simulation)
* [Example Open Dataset NyTaxi](https://github.com/MicrosoftDocs/azure-docs/blob/main/articles/machine-learning/tutorial-auto-train-models.md?context=azure%2fopen-datasets%2fcontext%2fopen-datasets-context)
* [Fake News Classification](https://www.kaggle.com/ruchi798/source-based-news-classification)
* [Social Power NBA](https://github.com/noahgift/socialpowernba/blob/master/data/nba_2017_players_with_salary_wiki_twitter.csv)
## Pre-work before start
* [Need Free Azure Account for Databricks](https://azure.microsoft.com/free/)
* [Follow Azure Databricks Quickstart](https://docs.microsoft.com/en-us/azure/databricks/scenarios/quickstart-create-databricks-workspace-portal?tabs=azure-portal)
## References
* [MLOps Platforms YouTube Video](https://www.youtube.com/watch?v=PUXhWZQW8BI)
* [MLOps Platforms O'Reilly Video](https://learning.oreilly.com/videos/mlops-platforms-from/032232022VIDEOPAIML/)
* [Azure Databricks](https://azure.microsoft.com/en-us/services/databricks/)
* [Cloud Computing for Data Duke Course](https://github.com/noahgift/cloud-data-analysis-at-scale)
* [Learning Spark 2nd Edition](https://pages.databricks.com/rs/094-YMS-629/images/LearningSpark2.0.pdf)