You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@madlib.apache.org by ri...@apache.org on 2017/12/05 08:19:35 UTC
madlib git commit: K-NN: Fix overloaded functions for defaults
Repository: madlib
Updated Branches:
refs/heads/master c73cf8507 -> f28c5a07e
K-NN: Fix overloaded functions for defaults
Some of the overloaded functions (meant for default arguments) were
incorrectly defined. This commit fixes that and adds test for those
function calls in the install-check.
Project: http://git-wip-us.apache.org/repos/asf/madlib/repo
Commit: http://git-wip-us.apache.org/repos/asf/madlib/commit/f28c5a07
Tree: http://git-wip-us.apache.org/repos/asf/madlib/tree/f28c5a07
Diff: http://git-wip-us.apache.org/repos/asf/madlib/diff/f28c5a07
Branch: refs/heads/master
Commit: f28c5a07e4bf6178330df936d0338de1e0d20a49
Parents: c73cf85
Author: Rahul Iyer <ri...@apache.org>
Authored: Tue Dec 5 00:17:21 2017 -0800
Committer: Rahul Iyer <ri...@apache.org>
Committed: Tue Dec 5 00:17:21 2017 -0800
----------------------------------------------------------------------
src/ports/postgres/modules/knn/knn.py_in | 8 +++++---
src/ports/postgres/modules/knn/knn.sql_in | 15 +++++++++------
src/ports/postgres/modules/knn/test/knn.sql_in | 13 ++-----------
3 files changed, 16 insertions(+), 20 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/madlib/blob/f28c5a07/src/ports/postgres/modules/knn/knn.py_in
----------------------------------------------------------------------
diff --git a/src/ports/postgres/modules/knn/knn.py_in b/src/ports/postgres/modules/knn/knn.py_in
index caa89e0..7729d2f 100644
--- a/src/ports/postgres/modules/knn/knn.py_in
+++ b/src/ports/postgres/modules/knn/knn.py_in
@@ -38,7 +38,8 @@ from utilities.control import MinWarning
def knn_validate_src(schema_madlib, point_source, point_column_name, point_id,
label_column_name, test_source, test_column_name,
- test_id, output_table, k, output_neighbors, fn_dist, **kwargs):
+ test_id, output_table, k, output_neighbors, fn_dist,
+ **kwargs):
input_tbl_valid(point_source, 'kNN')
input_tbl_valid(test_source, 'kNN')
output_tbl_valid(output_table, 'kNN')
@@ -108,8 +109,9 @@ def knn_validate_src(schema_madlib, point_source, point_column_name, point_id,
# ------------------------------------------------------------------------------
-def knn(schema_madlib, point_source, point_column_name, point_id, label_column_name,
- test_source, test_column_name, test_id, output_table, k, output_neighbors, fn_dist):
+def knn(schema_madlib, point_source, point_column_name, point_id,
+ label_column_name, test_source, test_column_name, test_id, output_table,
+ k, output_neighbors, fn_dist):
"""
KNN function to find the K Nearest neighbours
Args:
http://git-wip-us.apache.org/repos/asf/madlib/blob/f28c5a07/src/ports/postgres/modules/knn/knn.sql_in
----------------------------------------------------------------------
diff --git a/src/ports/postgres/modules/knn/knn.sql_in b/src/ports/postgres/modules/knn/knn.sql_in
index cdc9704..d45f0f4 100644
--- a/src/ports/postgres/modules/knn/knn.sql_in
+++ b/src/ports/postgres/modules/knn/knn.sql_in
@@ -456,7 +456,7 @@ CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.knn(
test_id VARCHAR,
output_table VARCHAR,
k INTEGER,
- output_neighbors Boolean,
+ output_neighbors BOOLEAN,
fn_dist TEXT
) RETURNS VARCHAR AS $$
PythonFunctionBodyOnly(`knn', `knn')
@@ -473,7 +473,6 @@ CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.knn(
k,
output_neighbors,
fn_dist
-
)
$$ LANGUAGE plpythonu VOLATILE
m4_ifdef(`__HAS_FUNCTION_PROPERTIES__', `MODIFIES SQL DATA', `');
@@ -488,12 +487,14 @@ CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.knn(
test_column_name VARCHAR,
test_id VARCHAR,
output_table VARCHAR,
- output_neighbors Boolean
+ k INTEGER,
+ output_neighbors BOOLEAN
) RETURNS VARCHAR AS $$
DECLARE
returnstring VARCHAR;
BEGIN
- returnstring = MADLIB_SCHEMA.knn($1,$2,$3,$4,$5,$6,$7,$8,1,$9, 'MADLIB_SCHEMA.squared_dist_norm2');
+ returnstring = MADLIB_SCHEMA.knn($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,
+ 'MADLIB_SCHEMA.squared_dist_norm2');
RETURN returnstring;
END;
$$ LANGUAGE plpgsql VOLATILE
@@ -513,7 +514,8 @@ CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.knn(
DECLARE
returnstring VARCHAR;
BEGIN
- returnstring = MADLIB_SCHEMA.knn($1,$2,$3,$4,$5,$6,$7,$8,$9,TRUE,'MADLIB_SCHEMA.squared_dist_norm2');
+ returnstring = MADLIB_SCHEMA.knn($1,$2,$3,$4,$5,$6,$7,$8,$9,TRUE,
+ 'MADLIB_SCHEMA.squared_dist_norm2');
RETURN returnstring;
END;
$$ LANGUAGE plpgsql VOLATILE
@@ -532,7 +534,8 @@ CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.knn(
DECLARE
returnstring VARCHAR;
BEGIN
- returnstring = MADLIB_SCHEMA.knn($1,$2,$3,$4,$5,$6,$7,$8,1,TRUE,'MADLIB_SCHEMA.squared_dist_norm2');
+ returnstring = MADLIB_SCHEMA.knn($1,$2,$3,$4,$5,$6,$7,$8,1,TRUE,
+ 'MADLIB_SCHEMA.squared_dist_norm2');
RETURN returnstring;
END;
$$ LANGUAGE plpgsql VOLATILE
http://git-wip-us.apache.org/repos/asf/madlib/blob/f28c5a07/src/ports/postgres/modules/knn/test/knn.sql_in
----------------------------------------------------------------------
diff --git a/src/ports/postgres/modules/knn/test/knn.sql_in b/src/ports/postgres/modules/knn/test/knn.sql_in
index 8bd1644..8c62dad 100644
--- a/src/ports/postgres/modules/knn/test/knn.sql_in
+++ b/src/ports/postgres/modules/knn/test/knn.sql_in
@@ -76,29 +76,20 @@ select knn('knn_train_data','data','id','label','knn_test_data','data','id','mad
select assert(array_agg(prediction order by id)='{1,1,0,1,0,0}', 'Wrong output in classification with k=3') from madlib_knn_result_classification;
drop table if exists madlib_knn_result_classification;
-select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,True,'MADLIB_SCHEMA.squared_dist_norm2');
+select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3);
select assert(array_agg(x)= '{1,2,3}','Wrong output in classification with k=3') from (select unnest(k_nearest_neighbours) as x from madlib_knn_result_classification where id = 1 order by x asc) y;
drop table if exists madlib_knn_result_regression;
select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,'MADLIB_SCHEMA.squared_dist_norm2');
select assert(array_agg(prediction order by id)='{1,1,0.5,1,0.25,0.25}', 'Wrong output in regression') from madlib_knn_result_regression;
drop table if exists madlib_knn_result_regression;
-select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',3,True,'MADLIB_SCHEMA.squared_dist_norm2');
+select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',3,True);
select assert(array_agg(x)= '{1,2,3}' , 'Wrong output in regression with k=3') from (select unnest(k_nearest_neighbours) as x from madlib_knn_result_regression where id = 1 order by x asc) y;
drop table if exists madlib_knn_result_classification;
select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,NULL);
select assert(array_agg(prediction order by id)='{1,1,0,1,0,0}', 'Wrong output in classification with k=3') from madlib_knn_result_classification;
-
-drop table if exists madlib_knn_result_regression;
-select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',3,True, NULL );
-select assert(array_agg(x)= '{1,2,3}' , 'Wrong output in regression with k=3') from (select unnest(k_nearest_neighbours) as x from madlib_knn_result_regression where id = 1 order by x asc) y;
-
-drop table if exists madlib_knn_result_regression;
-select knn('knn_train_data_reg','data','id','label','knn_test_data','data','id','madlib_knn_result_regression',4,False,NULL);
-select assert(array_agg(prediction order by id)='{1,1,0.5,1,0.25,0.25}', 'Wrong output in regression') from madlib_knn_result_regression;
-
drop table if exists madlib_knn_result_classification;
select knn('knn_train_data','data','id','label','knn_test_data','data','id','madlib_knn_result_classification',3,False,'MADLIB_SCHEMA.dist_norm1');
select assert(array_agg(prediction order by id)='{1,1,0,1,0,0}', 'Wrong output in classification with k=3') from madlib_knn_result_classification;