This page shows the usage of General Binary Classifier using a9a dataset.

Training

create table model
as
select 
 feature,
 avg(weight) as weight
from (
  select 
     train_classifier(
       add_bias(features), label, 
       "-loss logistic -iter 30"
     ) as (feature,weight)
  from 
     a9a_train
 ) t 
group by feature;

Prediction

create table predict 
as
WITH exploded as (
select 
  rowid,
  label,
  extract_feature(feature) as feature,
  extract_weight(feature) as value
from 
  a9a_test LATERAL VIEW explode(add_bias(features)) t AS feature
)
select
  t.rowid, 
  sigmoid(sum(m.weight * t.value)) as prob,
  (case when sigmoid(sum(m.weight * t.value)) >= 0.5 then 1.0 else 0.0 end) as label
from 
  exploded t LEFT OUTER JOIN
  model m ON (t.feature = m.feature)
group by
  t.rowid;

Evaluation

create or replace view submit as
select 
  t.label as actual, 
  p.label as predicted, 
  p.prob as probability
from 
  a9a_test t 
  JOIN predict p on (t.rowid = p.rowid);

select 
  sum(if(actual == predicted, 1, 0)) / count(1) as accuracy
from
  submit;

0.8462625145875561

The following table shows accuracy for changing optimizer by -loss logistic -opt XXXXXX -reg l1 -iter 30 option: