[jira] [Updated] (HIVEMALL-274) Wrong target variable name in the step-by-step tutorial

["Makoto Yui (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/HIVEMALL-274?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Makoto Yui updated HIVEMALL-274:
--------------------------------
    Fix Version/s: 0.6.0

> Wrong target variable name in the step-by-step tutorial
> -------------------------------------------------------
>
>                 Key: HIVEMALL-274
>                 URL: https://issues.apache.org/jira/browse/HIVEMALL-274
>             Project: Hivemall
>          Issue Type: Bug
>            Reporter: Aki Ariga
>            Assignee: Makoto Yui
>            Priority: Minor
>             Fix For: 0.6.0
>
>
> In the step-by-step tutorial, the target column name of regression should be `num_purchases` instead of `label`.
> {code:java}
> create table if not exists regressor as
> select
>   train_regressor(
>     features, -- feature vector
>     num_purchases, -- target value
>     '-loss_function squared -optimizer AdaGrad -regularization l2' -- hyper-parameters
>   ) as (feature, weight)
> from
>   training
> ;
> {code}
> {code:java}
> with features_exploded as (
>   select
>     id,
>     extract_feature(fv) as feature,
>     extract_weight(fv) as value
>   from
>     training t1 
>     LATERAL VIEW explode(features) t2 as fv
> ),
> predictions as (
>   select
>     t1.id,
>     sum(p1.weight * t1.value) as predicted_num_purchases
>   from
>     features_exploded t1
>     LEFT OUTER JOIN regressor p1 ON (t1.feature = p1.feature)
>   group by
>     t1.id
> )
> select
>   rmse(t1.predicted_num_purchases, t2.num_purchases) as rmse,
>   mae(t1.predicted_num_purchases, t2.num_purchases) as mae
> from
>   predictions t1
> join
>   training t2 on (t1.id = t2.id)
> ;
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)