MLOps with R: The Whole Game of End-to-End Data Science & Model Deployment

แชร์
ฝัง
  • เผยแพร่เมื่อ 1 ธ.ค. 2024

ความคิดเห็น • 18

  • @djangoworldwide7925
    @djangoworldwide7925 ปีที่แล้ว +3

    As a junior data analyst i felt hurt when you "assumed you already did data collection" 😂 it's basically the most daunting part of the job. Deploying models is fun! Building dockers that dont work is not!

  • @ghettoghost2657
    @ghettoghost2657 3 หลายเดือนก่อน

    This is a great page

  • @flonga2302
    @flonga2302 ปีที่แล้ว +1

    Thank you for the great r content James

  • @kyleGrealis
    @kyleGrealis 6 หลายเดือนก่อน

    Thanks, James, this was an excellent tutorial.

  • @00moumou00
    @00moumou00 5 หลายเดือนก่อน

    Thank you very much. This is fantastic.

  • @TURALOWEN
    @TURALOWEN ปีที่แล้ว +1

    Suggestions: (1) work on a dataset that one can monitor with real data (2) deploy the model API to AWS and/or posit connect (3) showcase drifts when they happen, and show the ways to handle them. I would learn a lot from these items. Thanks for the video!

    • @james-h-wade
      @james-h-wade  ปีที่แล้ว

      Thank you for the suggestions. Those are great ideas for future videos.

    • @hanselpalencia2822
      @hanselpalencia2822 ปีที่แล้ว

      @@james-h-wade Seconding the posit connect point, would be really get to get a view into how it's done there. I've had issues deploying as there are hardly any good walkthroughs!

  • @staticalmo
    @staticalmo ปีที่แล้ว

    which quarto function did you use to create the chunk with numbers on the right that shows the explanation?

  • @ntran04299
    @ntran04299 ปีที่แล้ว

    Hello James, I have a question.
    I see that you did EDA first, then split the data into train and test sets. Shouldn't I do EDA after the split to avoid data leakage?

  • @ARandomDataGuy
    @ARandomDataGuy ปีที่แล้ว +1

    Great series! A bit confusing was the part of model deployment-why HuggingFace, what is HuggingFace, other options, etc.

    • @james-h-wade
      @james-h-wade  ปีที่แล้ว +1

      Thanks for sharing that. I'm thinking that should be a topic for a future video. There are many to choose from, and it's hard to understand the differences. My advice is to use the one that works. Posit Connect is the easiest to use in my experience, but it's a pro product.

    • @staticalmo
      @staticalmo ปีที่แล้ว

      @@james-h-wadeyes easy, but with a price, even for amateurs. I don't know yet something easier than HF, even though the docker part might scare

  • @aephidayatuloh
    @aephidayatuloh 5 หลายเดือนก่อน

    Great video, now I ca deploy my model as API
    Can you make a video like this for plumber API deployment to vercel app project? It would be helfpul since if I using huggingface the space must a public and poeple can access to my R code files.

  • @dreznik
    @dreznik ปีที่แล้ว +1

    auc is an unreliable metric if classes are imbalanced; prediction probabilities need to be adjusted to "undo" the stratified sampling. you should keep a hold out set (randomly sampled) to verify the performance

  • @tarasst6887
    @tarasst6887 ปีที่แล้ว

    🎉🎉🎉

  • @dreznik
    @dreznik ปีที่แล้ว

    the mlops workflow should become a tool that hides the code and only exposes options