[
https://issues.apache.org/jira/browse/HIVEMALL-78?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Makoto Yui updated HIVEMALL-78:
-------------------------------
Description:
Support Area Under ROC of Binary Classification Metrics.
{code:sql}
-- option 1
select
auroc(label, prob) as auroc
from
data;
-- option 2
WITH roc as (
select
roc(label, prob) as tpr, tpr
from
data
)
select
auc(fpr, tpr) as auroc -- auc is UDAF, input is sorted by fp asc
from (
select
fpr, tpr
from
roc
DISTRIBUTE BY
floor(fpr / 0.2) -- 5 bins
SORT BY
fpr ASC
) t
{code}
Reference)
http://www.citeulike.org/user/myui/article/12615084
https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala
https://spark.apache.org/docs/latest/mllib-evaluation-metrics.html
was:
http://www.citeulike.org/user/myui/article/12615084
https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala
{code:sql}
-- option 1
select
auroc(label, prob) as auroc
from
data;
-- option 2
WITH roc as (
select
roc(label, prob) as tpr, tpr
from
data
)
select
auc(fpr, tpr) as auroc -- auc is UDAF, input is sorted by fp asc
from (
select
fpr, tpr
from
roc
DISTRIBUTE BY
floor(fpr / 0.2) -- 5 bins
SORT BY
fpr ASC
) t
{code}
> AUC UDAF for BinaryClassificationMetrics
> ----------------------------------------
>
> Key: HIVEMALL-78
> URL: https://issues.apache.org/jira/browse/HIVEMALL-78
> Project: Hivemall
> Issue Type: New Feature
> Reporter: Makoto Yui
> Assignee: Takuya Kitazawa
> Priority: Minor
>
> Support Area Under ROC of Binary Classification Metrics.
> {code:sql}
> -- option 1
> select
> auroc(label, prob) as auroc
> from
> data;
> -- option 2
> WITH roc as (
> select
> roc(label, prob) as tpr, tpr
> from
> data
> )
> select
> auc(fpr, tpr) as auroc -- auc is UDAF, input is sorted by fp asc
> from (
> select
> fpr, tpr
> from
> roc
> DISTRIBUTE BY
> floor(fpr / 0.2) -- 5 bins
> SORT BY
> fpr ASC
> ) t
> {code}
> Reference)
> http://www.citeulike.org/user/myui/article/12615084
> https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala
> https://spark.apache.org/docs/latest/mllib-evaluation-metrics.html
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)