[GitHub] spark pull request: [SPARK-6239] [MLLib] [FPGrowth] Possibility to...

[mengxr <gi...@git.apache.org>]

Github user mengxr commented on the pull request:

    https://github.com/apache/spark/pull/5246#issuecomment-90293963
  
    Agree with @srowen . Using a constant minCount is not scale invariant. The results may differ a lot from runs, e.g., daily transactions. If you want to use the absolute count, you can cache and count the data and figure out the minSupport value. There will be small overhead if the data is fully cached. If the additional "data.count()" in the implementation is expensive, we can merge it to the job of item counts. For each transaction, we generate a special key with value 1L. So we know the global count and item counts together.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org