spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Dibyendu Chakrabarti <>
Subject Is there any known limitation of the MLlib algorithms?
Date Sat, 11 Sep 2021 20:48:26 GMT
Dear Users,

This question is about the MLlib algorithms in general. Consider a hypothetical situation
where you have a dataset with n records and assume n could be very large. Will all the MLlib
algorithms work for such a dataset even when a very minimal cluster is set up (even with degraded
performance)? Is there any relationship between n, choice of algorithm and hardware set up?
If the general question is difficult, can something be said about the popular classification
and clustering algorithms?

Thanks and regards,

To unsubscribe e-mail:

View raw message