td_intern otto

pred_cv.sql

-- トレーニング
INSERT OVERWRITE TABLE model_cv
  SELECT train_randomforest_classifier(features, label, '-trees 500')
  FROM train_cv;

-- 予測
INSERT OVERWRITE TABLE pred_cv 
SELECT 
  t2.rowid as rowid,
  t2.predicted.label as label,
  t2.predicted.probability as probability, 
  t2.predicted.probabilities as probabilities
FROM(
  SELECT
    rowid as rowid, 
    rf_ensemble(predicted) as predicted
  FROM (
    SELECT
      t.rowid as rowid, t.label as actual, 
      -- hivemall v0.4.1-alpha.2 and before
      -- tree_predict(p.model, t.features, ${classification}) as predicted
      -- hivemall v0.4.1 and later
      tree_predict(p.model_id, p.model_type, p.pred_model, t.features, true) as predicted
    FROM model p 
    LEFT OUTER JOIN test_cv t
    ) t1
  group by
    rowid
) t2;