News for hackers. Stuff that matters.

A comment on Metaflow, Netflix's Python framework for data science, is now open source.

Re:Metaflow, Netflix's Python framework for data science, is... by purple-again on Tuesday December 03, 2019 @07:58PM (#21698618)
We are on Azure using Spark via Databricks. We had to abandon sci kit learn because of this choice. Does your service require AWS and can it be used in conjunction with Spark? Thank you for your time and consideration.
[ Parent | on HN ]
Re:Metaflow, Netflix's Python framework for data science, is... by rxin on Wednesday December 04, 2019 @12:39AM (#21699894)
What's the reason you need to abandon scikit-learn? You can run scikit-learn on Databricks, and many of our customers do.

Disclaimer: Databricks cofounder.

[ Parent | on HN ]
Re:Metaflow, Netflix's Python framework for data science, is... by pela on Tuesday December 03, 2019 @08:10PM (#21698680)
We currently provide integrations with AWS (S3 and Batch) and it is easy to extend Metaflow to work with other cloud providers. https://docs.metaflow.org/internals-of-metaflow/technical-ov...
[ Parent | on HN ]
Re:Metaflow, Netflix's Python framework for data science, is... by missosoup on Tuesday December 03, 2019 @08:32PM (#21698822)
What about databricks made you abandon sklearn?
[ Parent | on HN ]
Re:Metaflow, Netflix's Python framework for data science, is... by manojlds on Wednesday December 04, 2019 @12:08AM (#21699755)
MLLib I would think - https://spark.apache.org/docs/latest/ml-guide.html
[ Parent | on HN ]