Saving all output to "!!{outputDirectory}!!/groupby2_noskew.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/groupby2_noskew.q >>> set hive.map.aggr=false; No rows affected >>> set hive.groupby.skewindata=false; No rows affected >>> set mapred.reduce.tasks=31; No rows affected >>> >>> CREATE TABLE dest_g2(key STRING, c1 INT, c2 STRING) STORED AS TEXTFILE; No rows affected >>> >>> EXPLAIN FROM src INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1); 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_g2))) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))))) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-0 depends on stages: Stage-1' ' Stage-2 depends on stages: Stage-0' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: key, value' ' Reduce Output Operator' ' key expressions:' ' expr: substr(key, 1, 1)' ' type: string' ' expr: substr(value, 5)' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: substr(key, 1, 1)' ' type: string' ' tag: -1' ' Reduce Operator Tree:' ' Group By Operator' ' aggregations:' ' expr: count(DISTINCT KEY._col1:0._col0)' ' expr: sum(KEY._col1:0._col0)' ' bucketGroup: false' ' keys:' ' expr: KEY._col0' ' type: string' ' mode: complete' ' outputColumnNames: _col0, _col1, _col2' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: bigint' ' expr: concat(_col0, _col2)' ' type: string' ' outputColumnNames: _col0, _col1, _col2' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: UDFToInteger(_col1)' ' type: int' ' expr: _col2' ' type: string' ' outputColumnNames: _col0, _col1, _col2' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: groupby2_noskew.dest_g2' '' ' Stage: Stage-0' ' Move Operator' ' tables:' ' replace: true' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: groupby2_noskew.dest_g2' '' ' Stage: Stage-2' ' Stats-Aggr Operator' '' '' 85 rows selected >>> >>> FROM src INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1); '_col0','_col1','_col2' No rows selected >>> >>> SELECT dest_g2.* FROM dest_g2; 'key','c1','c2' '0','1','00.0' '1','71','116414.0' '2','69','225571.0' '3','62','332004.0' '4','74','452763.0' '5','6','5397.0' '6','5','6398.0' '7','6','7735.0' '8','8','8762.0' '9','7','91047.0' 10 rows selected >>> !record