madlib-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ri...@apache.org
Subject [madlib] branch master updated: Encode categorical: Add BIGINT as valid categorical type
Date Tue, 29 Jan 2019 19:03:07 GMT
This is an automated email from the ASF dual-hosted git repository.

riyer pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/madlib.git


The following commit(s) were added to refs/heads/master by this push:
     new 7c3c1a3  Encode categorical: Add BIGINT as valid categorical type
7c3c1a3 is described below

commit 7c3c1a35ab921f2401df4684ab6d48a14fa51b2d
Author: Rahul Iyer <riyer@apache.org>
AuthorDate: Fri Jan 18 14:52:28 2019 -0800

    Encode categorical: Add BIGINT as valid categorical type
    
    JIRA: MADLIB-1295
---
 src/ports/postgres/modules/utilities/encode_categorical.py_in       | 2 +-
 src/ports/postgres/modules/utilities/test/encode_categorical.sql_in | 5 ++++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/src/ports/postgres/modules/utilities/encode_categorical.py_in b/src/ports/postgres/modules/utilities/encode_categorical.py_in
index cd08012..8695a73 100644
--- a/src/ports/postgres/modules/utilities/encode_categorical.py_in
+++ b/src/ports/postgres/modules/utilities/encode_categorical.py_in
@@ -396,7 +396,7 @@ class CategoricalEncoder(object):
         self._all_cols_types = get_cols_and_types(self.source_table)
 
         # any column belonging to the following types are considered categorical
-        int_types = ['integer', 'smallint']
+        int_types = ['integer', 'smallint', 'bigint']
         text_types = ['text', 'varchar', 'character varying', 'char', 'character']
         boolean_types = ['boolean']
         self._cat_types = set(int_types + text_types + boolean_types)
diff --git a/src/ports/postgres/modules/utilities/test/encode_categorical.sql_in b/src/ports/postgres/modules/utilities/test/encode_categorical.sql_in
index 7dc6169..f7addc8 100644
--- a/src/ports/postgres/modules/utilities/test/encode_categorical.sql_in
+++ b/src/ports/postgres/modules/utilities/test/encode_categorical.sql_in
@@ -109,7 +109,7 @@ CREATE TABLE abalone_special_char (
     "len$$'%*()gth" double precision,
     diameter double precision,
     height double precision,
-    "ClaЖss" integer
+    "ClaЖss" bigint
 );
 COPY abalone_special_char ("se$$''x", "len$$'%*()gth", diameter, height, "ClaЖss") FROM
stdin WITH DELIMITER '|' NULL as '@';
 F"F|0.475|0.37|0.125|2
@@ -121,6 +121,9 @@ M,M|0.47|0.355|0.100|1
 'F'F'|0.55|0.44|0.15|0
 \.
 
+select encode_categorical_variables('abalone_special_char', 'abalone_special_char_out0',
'*');
+select * from abalone_special_char_out0;
+
 select encode_categorical_variables('abalone_special_char', 'abalone_special_char_out1',
'"se$$''''x", "len$$''%*()gth"');
 select * from abalone_special_char_out1;
 


Mime
View raw message