Only Ridge regression in DSS, not the equivalent of R lm() function

titouan3412
titouan3412 Registered Posts: 8 ✭✭✭✭

Hi,
I used a multiple linear regression with R 's lm() function to understand the importance of each regressor thanks to their coefficient / weight. And I want to reproduce it on DSS.

When I create a prediction model with Expert mode and "Choose Algorithms", in "Basic target" I indicate "Regression" for "target prediction type": in "Modeling > Algorithms" only a Ridge regression is proposed , not the equivalent of lm() function in R.

In addition, I don't want a train/test set but full dataset for train (it's for undestanding not to predict).
So is it possible to have 100% dataset for train and use the equivalent of lm() function of R in DSS?
Thanks to you.
Théo

Answers

  • tgb417
    tgb417 Dataiku DSS Core Designer, Dataiku DSS & SQL, Dataiku DSS ML Practitioner, Dataiku DSS Core Concepts, Neuron 2020, Neuron, Registered, Dataiku Frontrunner Awards 2021 Finalist, Neuron 2021, Neuron 2022, Frontrunner 2022 Finalist, Frontrunner 2022 Winner, Dataiku Frontrunner Awards 2021 Participant, Frontrunner 2022 Participant, Neuron 2023 Posts: 1,601 Neuron

    Théo (@titouan3412
    )

    Just a thought. You can add ML Models to Dataiku. One of the easiest ways is to use some of the other models provided by SciKit-Learn in a Custom Model.

    Adding Models from Scikit-Learn.jpg

Setup Info
    Tags
      Help me…