I'm creating a suggestion model through MBA.

I observed that in my particular model, that if the min_support was placed as 0, the model would take an insanely long time to run, before crashing.

Place the min_support as 0.6, and no values were generated.

Through trial and error, I came to see that a min_support value of 0.02 hit the sweet spot, giving me 50 to 100 rows to work with.

Is there a way that I can mathematically calculate the optimal min_support value.

I'm not looking for a simple for loop that iterates, recalculating each time and checks the number of rows.

hf =apriori(df,min_support=0.02,use_colnames=True).sort_values(by['support'],ascending=False)`

In this case hf has 51 rows.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.