hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject [04/39] hive git commit: HIVE-12181 : Change hive.stats.fetch.column.stats value to true for MiniTezCliDriver (Ashutosh Chauhan via Jesus Camacho Rodriguez)
Date Wed, 10 Aug 2016 16:32:43 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/17ddc9a1/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out
index 5a6ebc1..bd69359 100644
--- a/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out
@@ -150,22 +150,22 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2601650 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((762 = cbigint) or ((UDFToFloat(csmallint) < cfloat) and (UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint))) or (cstring1 = 'a') or ((CAST( cbigint AS decimal(22,3)) <= -1.389) and (cstring2 <> 'a') and (79.553 <> CAST( cint AS decimal(13,3))) and (cboolean2 <> cboolean1))) (type: boolean)
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 5466 Data size: 1157380 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint)
                       outputColumnNames: cint, cdouble, csmallint, cfloat, ctinyint
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 5466 Data size: 1157380 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
-                        Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col0 (type: struct<count:bigint,sum:double,input:int>), _col1 (type: double), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,input:float>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: tinyint), _col8 (type: bigint)
             Execution mode: vectorized
         Reducer 2 
@@ -174,14 +174,14 @@ STAGE PLANS:
                 aggregations: avg(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_samp(VALUE._col3), var_samp(VALUE._col4), avg(VALUE._col5), stddev_samp(VALUE._col6), min(VALUE._col7), count(VALUE._col8)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
-                Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: double), (_col0 + -3728.0) (type: double), (- (_col0 + -3728.0)) (type: double), (- (- (_col0 + -3728.0))) (type: double), ((- (- (_col0 + -3728.0))) * (_col0 + -3728.0)) (type: double), _col1 (type: double), (- _col0) (type: double), _col2 (type: double), (((- (- (_col0 + -3728.0))) * (_col0 + -3728.0)) * (- (- (_col0 + -3728.0)))) (type: double), _col3 (type: double), (- _col2) (type: double), (_col2 - (- (- (_col0 + -3728.0)))) (type: double), ((_col2 - (- (- (_col0 + -3728.0)))) * _col2) (type: double), _col4 (type: double), _col5 (type: double), (10.175 - _col4) (type: double), (- (10.175 - _col4)) (type: double), ((- _col2) / -563.0) (type: double), _col6 (type: double), (- ((- _col2) / -563.0)) (type: double), (_col0 / _col1) (type: double), _col7 (type: tinyint), _col8 (type: bigint), (UDFToDouble(_col7) / ((- _col2) / -563.0)) (type: double), (- (_col0 / _col1)) (type: double)
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
-                  Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 492 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -362,22 +362,22 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2036734 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or ((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or ((UDFToFloat(ctinyint) > cfloat) and cstring1 regexp '.*ss.*') or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean)
-                    Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 6826 Data size: 1131534 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint)
                       outputColumnNames: cint, cbigint, csmallint, cdouble, ctinyint
-                      Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6826 Data size: 1131534 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
-                        Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,input:tinyint>), _col5 (type: int), _col6 (type: double), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>)
             Execution mode: vectorized
         Reducer 2 
@@ -386,14 +386,14 @@ STAGE PLANS:
                 aggregations: max(VALUE._col0), var_pop(VALUE._col1), stddev_pop(VALUE._col2), max(VALUE._col3), avg(VALUE._col4), min(VALUE._col5), min(VALUE._col6), stddev_samp(VALUE._col7), var_samp(VALUE._col8)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
-                Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: int), (UDFToDouble(_col0) / -3728.0) (type: double), (_col0 * -3728) (type: int), _col1 (type: double), (- (_col0 * -3728)) (type: int), _col2 (type: double), (-563 % (_col0 * -3728)) (type: int), (_col1 / _col2) (type: double), (- _col2) (type: double), _col3 (type: double), _col4 (type: double), (_col2 - 10.175) (type: double), _col5 (type: int), (UDFToDouble((_col0 * -3728)) % (_col2 - 10.175)) (type: double), (- _col3) (type: double), _col6 (type: double), (_col3 % -26.28) (type: double), _col7 (type: double), (- (UDFToDouble(_col0) / -3728.0)) (type: double), ((- (_col0 * -3728)) % (-563 % (_col0 * -3728))) (type: int), ((UDFToDouble(_col0) / -3728.0) - _col4) (type: double), (- (_col0 * -3728)) (type: int), _col8 (type: double)
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22
-                  Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -566,22 +566,22 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((ctimestamp1 = ctimestamp2) or (762 = cfloat) or (cstring1 = 'ss') or ((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and ctimestamp2 is not null and (cstring2 > 'a'))) (type: boolean)
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double)
                       outputColumnNames: cbigint, ctinyint, csmallint, cint, cdouble
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                        Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col0 (type: struct<count:bigint,sum:double,variance:double>), _col1 (type: bigint), _col2 (type: tinyint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: int), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: bigint), _col7 (type: struct<count:bigint,sum:double,input:tinyint>)
             Execution mode: vectorized
         Reducer 2 
@@ -590,14 +590,14 @@ STAGE PLANS:
                 aggregations: var_pop(VALUE._col0), count(VALUE._col1), max(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), stddev_samp(VALUE._col5), count(VALUE._col6), avg(VALUE._col7)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: double), (- _col0) (type: double), (_col0 - (- _col0)) (type: double), _col1 (type: bigint), (CAST( _col1 AS decimal(19,0)) % 79.553) (type: decimal(5,3)), _col2 (type: tinyint), (UDFToDouble(_col1) - (- _col0)) (type: double), (- (- _col0)) (type: double), (-1.0 % (- _col0)) (type: double), _col1 (type: bigint), (- _col1) (type: bigint), _col3 (type: double), (- (- (- _col0))) (type: double), (762 * (- _col1)) (type: bigint), _col4 (type: int), (UDFToLong(_col2) + (762 * (- _col1))) (type: bigint), ((- _col0) + UDFToDouble(_col4)) (type: double), _col5 (type: double), ((- _col1) % _col1) (type: bigint), _col6 (type: bigint), _col7 (type: double), (-3728 % (UDFToLong(_col2) + (762 * (- _col1)))) (type: bigint)
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
-                  Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -749,22 +749,22 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2139070 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((ctimestamp2 <= ctimestamp1) and (UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1)) or ((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17)) (type: boolean)
-                    Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2835 Data size: 493648 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float)
                       outputColumnNames: ctinyint, cbigint, cint, cfloat
-                      Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2835 Data size: 493648 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col0 (type: struct<count:bigint,sum:double,input:tinyint>), _col1 (type: bigint), _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: float)
             Execution mode: vectorized
         Reducer 2 
@@ -773,14 +773,14 @@ STAGE PLANS:
                 aggregations: avg(VALUE._col0), max(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_pop(VALUE._col4), max(VALUE._col5)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: double), (_col0 + 6981.0) (type: double), ((_col0 + 6981.0) + _col0) (type: double), _col1 (type: bigint), (((_col0 + 6981.0) + _col0) / _col0) (type: double), (- (_col0 + 6981.0)) (type: double), _col2 (type: double), (_col0 % (- (_col0 + 6981.0))) (type: double), _col3 (type: double), _col4 (type: double), (- _col1) (type: bigint), (UDFToDouble((- _col1)) / _col2) (type: double), _col5 (type: float), (_col4 * -26.28) (type: double)
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
-                  Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -940,18 +940,18 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 3056470 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((cstring1 regexp 'a.*' and (cstring2 like '%ss%')) or ((1 <> cboolean2) and (CAST( csmallint AS decimal(8,3)) < 79.553) and (-257 <> UDFToInteger(ctinyint))) or ((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))) (type: boolean)
-                    Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 9898 Data size: 2462086 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - CAST( cint AS decimal(10,0))) (type: decimal(14,3)), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - CAST( cint AS decimal(10,0))) - -26.28) (type: decimal(15,3)), (- cfloat) (type: float), (cdouble * -89010.0) (type: double), (UDFToDouble(ctinyint) / 988888.0) (type: double), (- ctinyint) (type: tinyint), (79.553 / CAST( ctinyint AS decimal(3,0))) (type: decimal(20,18))
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22
-                      Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 9898 Data size: 5632662 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: decimal(14,3)), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: decimal(15,3)), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: decimal(20,18))
                         sort order: +++++++++++++++++++++++
-                        Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 9898 Data size: 5632662 Basic stats: COMPLETE Column stats: COMPLETE
                         TopN Hash Memory Usage: 0.1
             Execution mode: vectorized
         Reducer 2 
@@ -960,13 +960,13 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: boolean), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: float), KEY.reducesinkkey7 (type: timestamp), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: bigint), KEY.reducesinkkey10 (type: bigint), KEY.reducesinkkey11 (type: int), KEY.reducesinkkey12 (type: decimal(14,3)), KEY.reducesinkkey13 (type: smallint), KEY.reducesinkkey14 (type: smallint), KEY.reducesinkkey15 (type: smallint), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: decimal(15,3)), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: tinyint), KEY.reducesinkkey22 (type: decimal(20,18))
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22
-                Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 9898 Data size: 5632662 Basic stats: COMPLETE Column stats: COMPLETE
                 Limit
                   Number of rows: 50
-                  Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 50 Data size: 28540 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 50 Data size: 28540 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1200,18 +1200,18 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2601650 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((197 > UDFToInteger(ctinyint)) and (UDFToLong(cint) = cbigint)) or (cbigint = 359) or (cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))) (type: boolean)
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 8195 Data size: 1735170 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (CAST( cbigint AS decimal(19,0)) % 79.553) (type: decimal(5,3)), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % cfloat) (type: float), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359.0 - cdouble) (type: double), (- csmallint) (type: smallint)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 8195 Data size: 3349694 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean), _col10 (type: double), _col11 (type: decimal(5,3)), _col12 (type: double), _col13 (type: float), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double), _col24 (type: smallint)
                         sort order: +++++++++++++++++++++++++
-                        Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 8195 Data size: 3349694 Basic stats: COMPLETE Column stats: COMPLETE
                         TopN Hash Memory Usage: 0.1
             Execution mode: vectorized
         Reducer 2 
@@ -1220,13 +1220,13 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: boolean), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: timestamp), KEY.reducesinkkey7 (type: smallint), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: decimal(5,3)), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey13 (type: float), KEY.reducesinkkey14 (type: float), KEY.reducesinkkey15 (type: float), KEY.reducesinkkey16 (type: float), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: bigint), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: smallint), KEY.reducesinkkey22 (type: bigint), KEY.reducesinkkey23 (type: double), KEY.reducesinkkey21 (type: smallint)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
-                Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 8195 Data size: 3349694 Basic stats: COMPLETE Column stats: COMPLETE
                 Limit
                   Number of rows: 25
-                  Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 25 Data size: 10520 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 25 Data size: 10520 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1409,18 +1409,18 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2601650 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((CAST( csmallint AS decimal(7,2)) > -26.28) and (cstring2 like 'ss')) or ((cdouble <= UDFToDouble(cbigint)) and (cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble)) or (UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= CAST( csmallint AS decimal(7,2))))) (type: boolean)
-                    Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10922 Data size: 2312410 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / CAST( ctinyint AS decimal(3,0))) (type: decimal(19,18)), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
-                      Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 10922 Data size: 3594034 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: decimal(19,18)), _col19 (type: double), _col20 (type: smallint), _col21 (type: int)
                         sort order: +++++++++++++++++++++++
-                        Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 10922 Data size: 3594034 Basic stats: COMPLETE Column stats: COMPLETE
                         TopN Hash Memory Usage: 0.1
                         value expressions: _col2 (type: boolean)
             Execution mode: vectorized
@@ -1430,13 +1430,13 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey7 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: bigint), KEY.reducesinkkey13 (type: float), KEY.reducesinkkey14 (type: bigint), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: bigint), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: decimal(19,18)), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: smallint), KEY.reducesinkkey22 (type: int)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
-                Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 10922 Data size: 3594034 Basic stats: COMPLETE Column stats: COMPLETE
                 Limit
                   Number of rows: 75
-                  Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 75 Data size: 24810 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 75 Data size: 24810 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1676,18 +1676,18 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2528254 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((-1.389 >= CAST( cint AS decimal(13,3))) and (csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint))) or ((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > CAST( cbigint AS decimal(22,3))))) (type: boolean)
-                    Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 3868 Data size: 795962 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (- cdouble) (type: double), (cdouble * (- cdouble)) (type: double)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
-                      Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 3868 Data size: 748844 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col14 (type: double), _col15 (type: double)
                         sort order: +++++++++++++++
-                        Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3868 Data size: 748844 Basic stats: COMPLETE Column stats: COMPLETE
                         TopN Hash Memory Usage: 0.1
                         value expressions: _col0 (type: timestamp)
             Execution mode: vectorized
@@ -1697,13 +1697,13 @@ STAGE PLANS:
               Select Operator
                 expressions: VALUE._col0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: float), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey14 (type: double)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
-                Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3868 Data size: 748844 Basic stats: COMPLETE Column stats: COMPLETE
                 Limit
                   Number of rows: 45
-                  Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 45 Data size: 8880 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 45 Data size: 8880 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1885,25 +1885,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean)
-                    Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2503 Data size: 52344 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint)
                       outputColumnNames: csmallint, cbigint, ctinyint
-                      Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2503 Data size: 52344 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count()
                         keys: csmallint (type: smallint)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4
-                        Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1128 Data size: 201900 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           key expressions: _col0 (type: smallint)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: smallint)
-                          Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 1128 Data size: 201900 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: bigint)
             Execution mode: vectorized
         Reducer 2 
@@ -1913,15 +1913,15 @@ STAGE PLANS:
                 keys: KEY._col0 (type: smallint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4
-                Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1128 Data size: 39468 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / CAST( _col0 AS decimal(5,0))) (type: decimal(19,18)), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint)
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
-                  Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1128 Data size: 197388 Basic stats: COMPLETE Column stats: COMPLETE
                   Reduce Output Operator
                     key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(19,18)), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint)
                     sort order: +++++++++++
-                    Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1128 Data size: 197388 Basic stats: COMPLETE Column stats: COMPLETE
                     TopN Hash Memory Usage: 0.1
         Reducer 3 
             Execution mode: vectorized
@@ -1929,13 +1929,13 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: decimal(19,18)), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: int), KEY.reducesinkkey9 (type: bigint), KEY.reducesinkkey10 (type: bigint)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
-                Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1128 Data size: 197388 Basic stats: COMPLETE Column stats: COMPLETE
                 Limit
                   Number of rows: 20
-                  Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 20 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 20 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2093,25 +2093,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 293580 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (cfloat < -5638.15)) or (2563.58 = CAST( ctinyint AS decimal(6,2))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > CAST( cbigint AS decimal(21,2)))))) (type: boolean)
-                    Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2503 Data size: 59820 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cdouble (type: double), cfloat (type: float)
                       outputColumnNames: cdouble, cfloat
-                      Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2503 Data size: 59820 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble)
                         keys: cdouble (type: double)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
-                        Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 870 Data size: 234888 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           key expressions: _col0 (type: double)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: double)
-                          Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 870 Data size: 234888 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: double)
             Execution mode: vectorized
         Reducer 2 
@@ -2121,15 +2121,15 @@ STAGE PLANS:
                 keys: KEY._col0 (type: double)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
-                Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 870 Data size: 46968 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double)
                   outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
-                  Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 870 Data size: 109608 Basic stats: COMPLETE Column stats: COMPLETE
                   Reduce Output Operator
                     key expressions: _col0 (type: double)
                     sort order: +
-                    Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 870 Data size: 109608 Basic stats: COMPLETE Column stats: COMPLETE
                     value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double)
         Reducer 3 
             Execution mode: vectorized
@@ -2137,10 +2137,10 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
-                Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 870 Data size: 109608 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 870 Data size: 109608 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2348,25 +2348,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean)
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double)
                       outputColumnNames: ctimestamp1, cstring1, cint, csmallint, ctinyint, cfloat, cdouble
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint)
                         keys: ctimestamp1 (type: timestamp), cstring1 (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
-                        Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 6144 Data size: 5199016 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           key expressions: _col0 (type: timestamp), _col1 (type: string)
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string)
-                          Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 6144 Data size: 5199016 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,input:smallint>), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,input:int>), _col9 (type: struct<count:bigint,sum:double,variance:double>), _col10 (type: struct<count:bigint,sum:double,input:float>), _col11 (type: double), _col12 (type: struct<count:bigint,sum:double,variance:double>), _col13 (type: struct<count:bigint,sum:double,variance:double>), _col14 (type: bigint)
             Execution mode: vectorized
         Reducer 2 
@@ -2376,15 +2376,15 @@ STAGE PLANS:
                 keys: KEY._col0 (type: timestamp), KEY._col1 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
-                Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3072 Data size: 645716 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (-
  _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / CAST( (- _col5) AS decimal(3,0))) (type: decimal(20,18)), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double)
                   outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38
-                  Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3072 Data size: 1542740 Basic stats: COMPLETE Column stats: COMPLETE
                   Reduce Output Operator
                     key expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double), _col11 (type: tinyint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double), _col26 (type: double), _col27 (type: tinyint), _col28 (type: double), _col29 (type: double), _col30 (type: double), _col31 (type: double), _col32 (type: decimal(20,18)), _col33 (type: double), _col34 (type: bigint), _col35 (type: double), _col36 (type: bigint), _col37 (type: bigint), _col38 (type: double)
                     sort order: +++++++++++++++++++++++++++++++++++++++
-                    Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 3072 Data size: 1542740 Basic stats: COMPLETE Column stats: COMPLETE
                     TopN Hash Memory Usage: 0.1
         Reducer 3 
             Execution mode: vectorized
@@ -2392,13 +2392,13 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: bigint), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: tinyint), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey13 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: double), KEY.reducesinkkey22 (type: double), KEY.reducesinkkey23 (type: double), KEY.reducesinkkey24 (type: double), KEY.reducesinkkey25 (type: double), KEY.reducesinkkey26 (type: double), KE
 Y.reducesinkkey27 (type: tinyint), KEY.reducesinkkey28 (type: double), KEY.reducesinkkey29 (type: double), KEY.reducesinkkey30 (type: double), KEY.reducesinkkey31 (type: double), KEY.reducesinkkey32 (type: decimal(20,18)), KEY.reducesinkkey33 (type: double), KEY.reducesinkkey34 (type: bigint), KEY.reducesinkkey35 (type: double), KEY.reducesinkkey36 (type: bigint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey38 (type: double)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38
-                Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3072 Data size: 1542740 Basic stats: COMPLETE Column stats: COMPLETE
                 Limit
                   Number of rows: 50
-                  Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 50 Data size: 25172 Basic stats: COMPLETE Column stats: COMPLETE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 50 Data size: 25172 Basic stats: COMPLETE Column stats: COMPLETE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2681,25 +2681,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 2601650 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((((cdouble < UDFToDouble(csmallint)) and (cboolean2 = cboolean1) and (CAST( cbigint AS decimal(22,3)) <= -863.257)) or ((cint >= -257) and cstring1 is not null and (cboolean1 >= 1)) or cstring2 regexp 'b' or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null)) and cboolean1 is not null) (type: boolean)
-                    Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 7845 Data size: 1661020 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint)
                       outputColumnNames: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint
-                      Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 7845 Data size: 1661020 Basic stats: COMPLETE Column stats: COMPLETE
                       Group By Operator
                         aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint)
                         keys: cboolean1 (type: boolean)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
-                        Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE
                         Reduce Output Operator
                           key expressions: _col0 (type: boolean)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: boolean)
-                          Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 3 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE
                           value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:double>), _col5 (type: bigint), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: bigint), _col8 (type: struct<count:bigint,sum:double,variance:double>), _col9 (type: struct<count:bigint,sum:double,variance:double>), _col10 (type: struct<count:bigint,sum:double,input:int>)
             Execution mode: vectorized
         Reducer 2 
@@ -2709,15 +2709,15 @@ STAGE PLANS:
                 keys: KEY._col0 (type: boolean)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
-                Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
                 Select Operator
                   expressions: _col0 (type: boolean), _col1 (type: float), (UDFToDouble((CAST( _col2 AS decimal(19,0)) - 10.175)) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + (- _col1))) (type: float), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * CAST( _col5 AS decimal(19,0))) (type: decimal(24,3)), (- _col1) (type: float), (CAST( _col7 AS decimal(19,0)) - (-1.389 * CAST( _col5 AS decimal(19,0)))) (type: decimal(25,3)), _col9 (type: double), (- (CAST( _col7 AS decimal(19,0)) - (-1.389 * CAST( _col5 AS decimal(19,0))))) (type: decimal(25,3)), _col10 (type: double), (- _col10) (type: double), (_col10 * UDFToDouble(_col7)) (type: double), (-26.28 / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (CAST( _col2 AS decimal(19,0)) - 10.175) (type: decimal(23,3)), _col3 (type: double), (_col3 % UDFToDouble(_col1)) (type: double), (10.175 + (- _col1)) (type: floa
 t), _col4 (type: double)
                   outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col3, _col4, _col5, _col6, _col7, _col8, _col9
-                  Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
                   Reduce Output Operator
                     key expressions: _col0 (type: boolean)
                     sort order: +
-                    Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
                     value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(23,3)), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: float), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,3)), _col21 (type: double), _col22 (type: decimal(25,3)), _col23 (type: double), _col24 (type: double), _col25 (type: double)
         Reducer 3 
             Execution mode: vectorized
@@ -2725,10 +2725,10 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: decimal(23,3)), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: float), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col12 (type: float), VALUE._col15 (type: bigint), VALUE._col16 (type: double), VALUE._col17 (type: decimal(24,3)), VALUE._col18 (type: decimal(25,3)), VALUE._col19 (type: double), VALUE._col20 (type: decimal(25,3)), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (type: double)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25
-                Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/17ddc9a1/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorized_case.q.out b/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
index 28b7f9b..8068d81 100644
--- a/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
@@ -47,17 +47,17 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean)
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 6 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string)
                       outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE
                       File Output Operator
                         compressed: false
-                        Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE
                         table:
                             input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                             output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -161,17 +161,17 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean)
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 6 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN (null) ELSE ('c') END (type: string)
                       outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE
                       File Output Operator
                         compressed: false
-                        Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE
                         table:
                             input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                             output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/17ddc9a1/ql/src/test/results/clientpositive/tez/vectorized_casts.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorized_casts.q.out b/ql/src/test/results/clientpositive/tez/vectorized_casts.q.out
index 231cdba..1fbec69 100644
--- a/ql/src/test/results/clientpositive/tez/vectorized_casts.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorized_casts.q.out
@@ -169,17 +169,17 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 1684250 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: ((cbigint % 250) = 0) (type: boolean)
-                    Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 6144 Data size: 842180 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: UDFToBoolean(ctinyint) (type: boolean), UDFToBoolean(csmallint) (type: boolean), UDFToBoolean(cint) (type: boolean), UDFToBoolean(cbigint) (type: boolean), UDFToBoolean(cfloat) (type: boolean), UDFToBoolean(cdouble) (type: boolean), cboolean1 (type: boolean), UDFToBoolean((cbigint * 0)) (type: boolean), UDFToBoolean(ctimestamp1) (type: boolean), UDFToBoolean(cstring1) (type: boolean), UDFToInteger(ctinyint) (type: int), UDFToInteger(csmallint) (type: int), cint (type: int), UDFToInteger(cbigint) (type: int), UDFToInteger(cfloat) (type: int), UDFToInteger(cdouble) (type: int), UDFToInteger(cboolean1) (type: int), UDFToInteger(ctimestamp1) (type: int), UDFToInteger(cstring1) (type: int), UDFToInteger(substr(cstring1, 1, 1)) (type: int), UDFToByte(cfloat) (type: tinyint), UDFToShort(cfloat) (type: smallint), UDFToLong(cfloat) (type: bigint), UDFToDouble(ctinyint) (type: double), UDFToDouble(csmallint) (type: double), UDFToDouble(cint) (type: double), 
 UDFToDouble(cbigint) (type: double), UDFToDouble(cfloat) (type: double), cdouble (type: double), UDFToDouble(cboolean1) (type: double), UDFToDouble(ctimestamp1) (type: double), UDFToDouble(cstring1) (type: double), UDFToDouble(substr(cstring1, 1, 1)) (type: double), UDFToFloat(cint) (type: float), UDFToFloat(cdouble) (type: float), CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp), UDFToString(ctinyint) (type: string), UDFToString(csmallint) (type: string), UDFToString(cint) (type: string), UDFToString(cbigint) (type: 
 string), UDFToString(cfloat) (type: string), UDFToString(cdouble) (type: string), UDFToString(cboolean1) (type: string), UDFToString((cbigint * 0)) (type: string), UDFToString(ctimestamp1) (type: string), cstring1 (type: string), UDFToString(CAST( cstring1 AS CHAR(10)) (type: string), UDFToString(CAST( cstring1 AS varchar(10))) (type: string), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), UDFToString(sin(cfloat)) (type: string), (UDFToDouble(UDFToFloat(cint)) + UDFToDouble(cboolean1)) (type: double)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55, _col56, _col57, _col58, _col59, _col60, _col61
-                      Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6144 Data size: 17929060 Basic stats: COMPLETE Column stats: COMPLETE
                       File Output Operator
                         compressed: false
-                        Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 6144 Data size: 17929060 Basic stats: COMPLETE Column stats: COMPLETE
                         table:
                             input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                             output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/17ddc9a1/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out
index 9f5c65c..aa4e111 100644
--- a/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out
@@ -108,21 +108,21 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: alltypesorc
-                  Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
                   Select Operator
                     expressions: cint (type: int)
                     outputColumnNames: cint
-                    Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE
                     Group By Operator
                       keys: cint (type: int)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 5775 Data size: 17248 Basic stats: COMPLETE Column stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 5775 Data size: 17248 Basic stats: COMPLETE Column stats: COMPLETE
             Execution mode: vectorized
         Reducer 2 
             Execution mode: vectorized
@@ -131,15 +131,15 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 5775 Data size: 17248 Basic stats: COMPLETE Column stats: COMPLETE
                 Group By Operator
                   aggregations: sum(_col0), count(_col0), avg(_col0), std(_col0)
                   mode: hash
                   outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
                   Reduce Output Operator
                     sort order: 
-                    Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
                     value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: struct<count:bigint,sum:double,input:int>), _col3 (type: struct<count:bigint,sum:double,variance:double>)
         Reducer 3 
             Reduce Operator Tree:
@@ -147,10 +147,10 @@ STAGE PLANS:
                 aggregations: sum(VALUE._col0), count(VALUE._col1), avg(VALUE._col2), std(VALUE._col3)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat


Mime
View raw message