adding function to predict the importance of different features to a dataset.

2016-03-31 11:25:30 -04:00
parent d140b4249e
commit e73862a6e1
2 changed files with 39 additions and 21 deletions
@@ -13,6 +13,18 @@ AS $$
  return segmentation.create_segment(segment_name,table_name,column_name,geoid_column,census_table,'random_forest')
 $$ LANGUAGE plpythonu;

+CREATE OR REPLACE FUNCTION
+  cdb_correlated_variables(
+    query text,
+    geoid_column text DEFAULT 'geoid',
+    census_table text DEFAULT 'ml_learning_block_groups_clipped'
+  )
+RETURNS TABLE(feature text, importance NUMERIC, std NUMERIC)
+AS $$
+  from crankshaft.segmentation import correlated_variables
+  return correlated_variables(query,geoid_column,census_table)
+$$ LANGUAGE plpythonu;
+
 CREATE OR REPLACE FUNCTION
  cdb_predict_segment (
      segment_name TEXT,