Venkat Raman
1 min readAug 22, 2021

Thanks for your reply. So my understanding from your reply is that pycaret ships 13 algorithms and one should just accept it as it is without questioning the rationale behind it (as in how they came up with this initial list of Algo's).

Also pycaret is just amalgamation of Sklearn + other libraries. And because other libraries can be bad (in terms of misspecification) Pycaret also gets the license to be as wrong as them.

Also you missed answering my point "Also you are selecting an algorithm solely based on AUC and other accuracy metric. As far as I can see, it is too close to call !! You are deciding based on 3rd decimal point ! Also I don't think it is the right way to select an algorithm from an cohort of algorithms merely based on their accuracy metrics."

Would love to know your justification on selecting algorithm based on AUC and that too based on 3rd decimal point !!

Sign up to discover human stories that deepen your understanding of the world.

Free

Distraction-free reading. No ads.

Organize your knowledge with lists and highlights.

Tell your story. Find your audience.

Membership

Read member-only stories

Support writers you read most

Earn money for your writing

Listen to audio narrations

Read offline with the Medium app

Venkat Raman
Venkat Raman

Written by Venkat Raman

Co-Founder of Aryma Labs. Data scientist/Statistician with business acumen. Hoping to amass knowledge and share it throughout my life. Rafa Nadal Fan.

Responses (1)

Write a response

To be clear, i am not the author of the article so i did not miss anaything. I have the same opinion as you, but i can understand the way, why the evaluation was done this way. In real life datasets there are also another things to be considered…

--