SELECT unnest(ARRAY['intercept','tax','bath','size']) as attribute,
unnest(coef) as coefficient,
unnest(std_err) as standard_error,
unnest(t_stats) as t_stat,
unnest(p_values) as pvalue
FROM houses_linregr;
SELECT houses.*,
madlib.linregr_predict( ARRAY[1,tax,bath,size],
m.coef
) as predict,
price -
madlib.linregr_predict( ARRAY[1,tax,bath,size],
m.coef
) as residual
FROM houses, houses_linregr m;
DROP TABLE IF EXISTS dt_golf;
CREATE TABLE dt_golf (
id integer NOT NULL,
"OUTLOOK" text,
temperature double precision,
humidity double precision,
windy text,
class text
) ;
INSERT INTO importance_table
SELECT regexp_split_to_table(val_names.cat_features, '.') AS categ_features,
unnest(val.cat_var_importance) AS cat_importance
FROM train_output_group AS val, train_output_summary AS val_names;
カテゴリ値の変数名と重要度がリストになっているかどうかを確認してください。
SELECT * FROM importance_table;
OUTLOOKとwindyがリストになっているはずです。
次に、連続値の変数をリストに加えます。
INSERT INTO importance_table
SELECT regexp_split_to_table(val_names.con_features, '.') AS con_features,
unnest(val.con_var_importance) AS con_importance
FROM train_output_group AS val, train_output_summary AS val_names;