PREHOOK: query: create table tab_date ( origin_city_name string, dest_city_name string, fl_date date, arr_delay float, fl_num int ) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@tab_date POSTHOOK: query: create table tab_date ( origin_city_name string, dest_city_name string, fl_date date, arr_delay float, fl_num int ) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tab_date PREHOOK: query: -- insert some data load data local inpath '../../data/files/flights_join.txt' overwrite into table tab_date PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@tab_date POSTHOOK: query: -- insert some data load data local inpath '../../data/files/flights_join.txt' overwrite into table tab_date POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@tab_date PREHOOK: query: select count(*) from tab_date PREHOOK: type: QUERY PREHOOK: Input: default@tab_date #### A masked pattern was here #### POSTHOOK: query: select count(*) from tab_date POSTHOOK: type: QUERY POSTHOOK: Input: default@tab_date #### A masked pattern was here #### 20 PREHOOK: query: -- compute statistical summary of data select compute_stats(fl_date, 16) from tab_date PREHOOK: type: QUERY PREHOOK: Input: default@tab_date #### A masked pattern was here #### POSTHOOK: query: -- compute statistical summary of data select compute_stats(fl_date, 16) from tab_date POSTHOOK: type: QUERY POSTHOOK: Input: default@tab_date #### A masked pattern was here #### {"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":18} PREHOOK: query: explain analyze table tab_date compute statistics for columns fl_date PREHOOK: type: QUERY POSTHOOK: query: explain analyze table tab_date compute statistics for columns fl_date POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: tab_date Select Operator expressions: fl_date (type: date) outputColumnNames: fl_date Group By Operator aggregations: compute_stats(fl_date, 16) mode: hash outputColumnNames: _col0 Reduce Output Operator sort order: value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 File Output Operator compressed: false 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 Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: fl_date Column Types: date Table: default.tab_date PREHOOK: query: analyze table tab_date compute statistics for columns fl_date PREHOOK: type: QUERY PREHOOK: Input: default@tab_date #### A masked pattern was here #### POSTHOOK: query: analyze table tab_date compute statistics for columns fl_date POSTHOOK: type: QUERY POSTHOOK: Input: default@tab_date #### A masked pattern was here #### PREHOOK: query: describe formatted tab_date fl_date PREHOOK: type: DESCTABLE PREHOOK: Input: default@tab_date POSTHOOK: query: describe formatted tab_date fl_date POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@tab_date # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment fl_date date 2000-11-20 2010-10-29 0 18 from deserializer PREHOOK: query: -- Update stats manually. Try both yyyy-mm-dd and integer value for high/low value alter table tab_date update statistics for column fl_date set ('numDVs'='19', 'highValue'='2015-01-01', 'lowValue'='0') PREHOOK: type: ALTERTABLE_UPDATETABLESTATS POSTHOOK: query: -- Update stats manually. Try both yyyy-mm-dd and integer value for high/low value alter table tab_date update statistics for column fl_date set ('numDVs'='19', 'highValue'='2015-01-01', 'lowValue'='0') POSTHOOK: type: ALTERTABLE_UPDATETABLESTATS PREHOOK: query: describe formatted tab_date fl_date PREHOOK: type: DESCTABLE PREHOOK: Input: default@tab_date POSTHOOK: query: describe formatted tab_date fl_date POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@tab_date # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment fl_date date 1970-01-01 2015-01-01 0 19 from deserializer