Data Science Deployed

Data Science Deployed

By @dsdeployedTechnology
Download on the App Store

Data Science Deployed episodes

  • Episode #9 - Linked Data with Donny Winston

    This week we talk about linked data, how to get started with it, and how it is currently being used.

    Donny's Linked Data GitHub Repo and Course - https://github.com/polyneme/intro-linkeddata-mongo-python

    YouTube PlayList - https://youtube.com/playlist?list=PL9QvE4W_ly6NzUSUIpsGJOtFM-aot5H2q

    ----------------------------------------

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

    ----------------------------------------

    Donny Winston

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston
    Website: https://polyneme.xyz/
    LinkedIn: https://www.linkedin.com/in/donnywinston/

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/
    Website: https://sparrow.dev/

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

    Website: https://www.dabbleofdevops.com
    Twitter: www.twitter.com/jillianerowe
    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    57 min
  • Episode #8 Computer Vision Annotation with Label Studio

    This week we talk about computer vision annotation platforms in general and Label studio in particular!

    Label studio: https://labelstud.io/

    Webinar Replay on Instnace Segmentation - https://youtu.be/ULeWxgVH4SY

    ----------------------------------------

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

    ----------------------------------------

    Donny Winston

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston
    Website: https://polyneme.xyz/
    LinkedIn: https://www.linkedin.com/in/donnywinston/

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/
    Website: https://sparrow.dev/

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

    Website: https://www.dabbleofdevops.com
    Twitter: www.twitter.com/jillianerowe
    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    43 min
  • Episode #7 - Python Package Management with Poetry

    This week we're talking about Python Package management with Poetry along with general data versioning and software stack management tips, tricks, and complaints.

     

    Ben started us off with an article he wrote introducing Poetry - https://sparrow.dev/python-poetry-machine-learning/

     

    ----------------------------------------

     

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

     

    ----------------------------------------

     

    Donny Winston

     

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston

    Website: https://polyneme.xyz/

    LinkedIn: https://www.linkedin.com/in/donnywinston/

     

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

     

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/

    Website: https://sparrow.dev/

     

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

     

    Website: https://www.dabbleofdevops.com

    Twitter: www.twitter.com/jillianerowe

    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    47 min
  • Data Versioning for Data Science

    Today we talk about Data Versioning. Why you should do it, what to do about humans in the loop, and how to minimize mistakes. 

     

    Tools mentioned:

     

    DVC - https://dvc.org/

    Quilt Data Versioning - https://quiltdata.com/

    Apache Airflow - https://airflow.apache.org/

    Apache Superset - https://superset.apache.org/

    OpenProject - https://www.openproject.org/

     

    ----------------------------------------

     

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

     

    ----------------------------------------

     

    Donny Winston

     

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston

    Website: https://polyneme.xyz/

    LinkedIn: https://www.linkedin.com/in/donnywinston/

     

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

     

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/

    Website: https://sparrow.dev/

     

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

     

    Website: https://www.dabbleofdevops.com

    Twitter: www.twitter.com/jillianerowe

    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    52 min
  • Episode#5 - Building Data Science Stacks like Pangeo

    This week we discuss Pangeo, how they structured their project from infrastructure to data science, and how that can inform other projects.


    Read more about Pangeo: https://medium.com/pangeo/pangeo-2-0-2bedf099582d

    And see the showcase: https://pangeo.io/pangeo-showcase.html#pangeo-showcase


    ----------------------------------------

     

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

     

    ----------------------------------------

     

    Donny Winston

     

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston

    Website: https://polyneme.xyz/

    LinkedIn: https://www.linkedin.com/in/donnywinston/

     

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

     

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/

    Website: https://sparrow.dev/

     

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

     

    Website: https://www.dabbleofdevops.com

    Twitter: www.twitter.com/jillianerowe

    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    44 min
  • Episode #4 with Greg Wilson - Building Better Data Science Communities

    We're talking with Greg this week about the peopling around data science. He brings up tons of excellent points. 

     

    You can find out more about Greg on Twitter: https://twitter.com/gvwilson 

     

    https://github.com/gvwilson/12-design

    https://merely-useful.tech/py-rse/

    https://www.amazon.com/Fearless-Change-Patterns-Introducing-paperback/dp/0134395255

    https://www.amazon.com/dp/B0051HSJBE/ref=dp-kindle-redirect?_encoding=UTF8&btkr=1

    https://www.amazon.com/Discussion-Book-Great-People-Talking/dp/1119049717

    https://producingoss.com/

    https://codebender.org/

     

    ----------------------------------------

     

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

     

    ----------------------------------------

     

    Donny Winston

     

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston

    Website: https://polyneme.xyz/

    LinkedIn: https://www.linkedin.com/in/donnywinston/

     

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

     

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/

    Website: https://sparrow.dev/

     

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

     

    Website: https://www.dabbleofdevops.com

    Twitter: www.twitter.com/jillianerowe

    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    1 hr 7 min
  • Data Science Deployed - Episode 3 - Ben Cook

    Co-Host Ben Cooks discusses his work around deploying Machine Learning models, and how you can make sure you are set up for success before you ever start writing code.


    https://sparrow.dev/source-code-layout-ai-pipelines/

    ----------------------------------------

     

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

     

    ----------------------------------------

     

    Donny Winston

     

    I help researchers do data-intensive science together.

    Twitter: https://twitter.com/donnywinston @donnywinston

    Website: https://polyneme.xyz/

    LinkedIn: https://www.linkedin.com/in/donnywinston/

     

    Ben Cook

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

     

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/

    Website: https://sparrow.dev/

     

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

     

    BioDeploy: https://github.com/dabble-of-devops-biodeploy

    Website: https://www.dabbleofdevops.com

    Twitter: www.twitter.com/jillianerowe

    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    48 min
  • Episode 2 - Meet the Hosts - Bioinformatics and BioDeploy with Jillian Rowe

    This week we talk to cohost Jillian Rowe, an independent consultant for Bioinformatics. She is currently developing BioDeploy, a science-first approach to deploy High-Performance Compute Infrastructure on AWS. 


    You can follow along with the development on her blog at https://www.dabbleofdevops.com/blog, or on GitHub at https://github.com/dabble-of-devops-biodeploy.

    ----------------------------------------

     

    Follow the podcast on Twitter: @dsdeployed

    https://twitter.com/dsdeployed

     

    ----------------------------------------

     

    Donny Winston

     

    I help researchers do data-intensive science together.

     

    Website: https://polyneme.xyz/

    LinkedIn: https://www.linkedin.com/in/donnywinston/

     

    Ben Cook

     

    I help data science teams deploy their algorithms because a machine learning model is only as good as the system that delivers it.

     

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn: https://www.linkedin.com/in/jbencook/

    Website: https://sparrow.dev/

     

    Jillian Rowe

    I help biotech startups deploy scalable high performance compute infrastructure on AWS.

    Website: https://www.dabbleofdevops.com

    Twitter: www.twitter.com/jillianerowe

    LinkedIn: https://www.linkedin.com/in/jillian-rowe-9410437a/

    49 min
  • Episode #1 - Meet the Hosts - Materials Project with Donny Winston

    Donny talks about the Materials Project.

     

    You can find out more here

    https://docs.materialsproject.org/methodology/elasticity-prediction/
    https://raw.githubusercontent.com/materialsproject/propjockey/master/docs/gateways2016-talk-slides.pdf
     

     

    Contact the Hosts for Consulting:

     

    Jillian

    https://www.dabbleofdevops.com

    Twitter: @jillianerowe https://twitter.com/jillianerowe

    LinkedIn

     

    Ben Cook

    Twitter: ​​@jbencook https://twitter.com/jbencook

    LinkedIn

     

    Donny Winston

     Website

     LinkedIn

     Website

    52 min

About Data Science Deployed

From the publisher's feed

The podcast for discussions on creating, managing and deploying data science projects in biotech, materials science and computer vision.