alteryx/evalml

Data Health: Sparsity Refactor

Aperta

#1801 aperta il 9 feb 2021

 (2 commenti) (1 reazione) (1 assegnatario)Python (93 fork)auto 404
enhancementgood first issue

Metriche repository

Star
 (852 stelle)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

Currently, the sparsity score is calculated using a discrete count of values as a threshold. It might make more sense to refactor the SparsityDataCheck to use a relative threshold instead of a fixed count threshold.

SparsityDataCheck.sparsity_score(col, relative_count_threshold=0.10):
    <implementation>

Here the new relative_count_threshold should be a percentage of the total length of the column.

Guida contributor