Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

RF: Use NULL::integer[] when no continuous features #249

Closed
wants to merge 1 commit into from
Closed

RF: Use NULL::integer[] when no continuous features #249

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
15 changes: 9 additions & 6 deletions src/ports/postgres/modules/recursive_partitioning/random_forest.py_in
View file
Open in desktop
Expand Up @@ -946,6 +946,11 @@ def _calculate_oob_prediction(

oob_var_dist_view = unique_string()
if importance:
if con_features:
initialized_float_array = ("{0}.array_of_float({1})::integer[]".
format(schema_madlib, len(con_features)))
else:
initialized_float_array = "NULL::integer[]"
sql_create_oob_var_dist_view = """
CREATE VIEW {oob_var_dist_view} AS
SELECT
Expand All @@ -966,12 +971,10 @@ def _calculate_oob_prediction(
{con_features_str}::double precision[],
con_splits
), -- bin_indices, -1 for NaN
1 -- -1 shift to 0 for nulls
1 -- -1 shifted to 0 for null values
),
{schema_madlib}.array_fill(
{schema_madlib}.array_of_float({n_con})::integer[],
({num_bins}+1)::integer
)
{schema_madlib}.array_fill({initialized_float_array},
({num_bins} + 1)::integer)
-- level of any continuous feature == num_bins
) AS con_index_distributions
FROM
Expand All @@ -986,7 +989,7 @@ def _calculate_oob_prediction(
{con_splits_table}
USING (gid)
GROUP BY gid
""".format(n_con=len(con_features), **locals())
""".format(**locals())
else:
sql_create_oob_var_dist_view = """
CREATE VIEW {oob_var_dist_view} AS
Expand Down
3 changes: 2 additions & 1 deletion src/ports/postgres/modules/recursive_partitioning/test/random_forest.sql_in
View file
Open in desktop
Expand Up @@ -265,6 +265,7 @@ from generate_series(1, 5) sid;

-------------------------------------------------------------------------
-- Test case for the case where a group has a filtered feature
-- Also testing var_importance=TRUE with no continuous features (MADLIB-1219)

DROP TABLE IF EXISTS rf_gr_test CASCADE;
CREATE TABLE rf_gr_test (
Expand All @@ -289,7 +290,7 @@ SELECT forest_train(
'train_output', -- output model table
'id', -- id column
'cl', -- response
'f1, f2, f3', -- features
'f1, f2', -- features
NULL, -- exclude columns
'gr', -- grouping
2, -- num of trees
Expand Down