[
https://issues.apache.org/jira/browse/HIVE-8263?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14153446#comment-14153446
]
Harish Butani commented on HIVE-8263:
-------------------------------------
Failure in 'groupby_bigdata' is not related to this patch.
> CBO : TPC-DS Q64 is item is joined last with store_sales while it should be
> first as it is the most selective
> -------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-8263
> URL: https://issues.apache.org/jira/browse/HIVE-8263
> Project: Hive
> Issue Type: Bug
> Components: CBO
> Affects Versions: 0.14.0
> Reporter: Mostafa Mokhtar
> Assignee: Harish Butani
> Fix For: 0.14.0
>
> Attachments: HIVE-8263.1.patch, Q64_cbo_on_explain_log.txt.zip
>
>
> Plan for TPC-DS Q64 shows that item is joined last with store_sales while
> store_sales x item is the most selective join in the plan.
> Interestingly predicate push down is applied on item but item comes so late
> in the join which most likely means that calculation of the join selectivity
> gave too high of a number of it was never considered.
> This is a subset of the logical plan showing that item was joined very last
> {code}
> HiveProjectRel(_o__col0=[$0], _o__col1=[$2], _o__col2=[$3], _o__col3=[$4],
> _o__col4=[$5], _o__col5=[$6], _o__col6=[$7], _o__col7=[$8], _o__col8=[$9],
> _o__col9=[$10], _o__col10=[$11], _o__col11=[$12], _o__col12=[$13],
> _o__col13=[$14], _o__col14=[$15], _o__col15=[$16], _o__col16=[$22],
> _o__col17=[$23], _o__col18=[$24], _o__col19=[$20], _o__col20=[$21]): rowcount
> = 1.0, cumulative cost = {1.1593403796322412E9 rows, 0.0 cpu, 0.0 io}, id =
> 990
> HiveFilterRel(condition=[<=($21, $13)]): rowcount = 1.0, cumulative cost
> = {1.1593403796322412E9 rows, 0.0 cpu, 0.0 io}, id = 988
> HiveProjectRel(_o__col0=[$0], _o__col1=[$1], _o__col2=[$2],
> _o__col3=[$3], _o__col4=[$4], _o__col5=[$5], _o__col6=[$6], _o__col7=[$7],
> _o__col8=[$8], _o__col9=[$9], _o__col10=[$10], _o__col11=[$11],
> _o__col12=[$12], _o__col15=[$13], _o__col16=[$14], _o__col17=[$15],
> _o__col18=[$16], _o__col13=[$17], _o__col20=[$18], _o__col30=[$19],
> _o__col120=[$20], _o__col150=[$21], _o__col160=[$22], _o__col170=[$23],
> _o__col180=[$24]): rowcount = 1.0, cumulative cost = {1.1593403796322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3571
> HiveJoinRel(condition=[AND(AND(=($1, $17), =($2, $18)), =($3, $19))],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1593403796322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3566
> HiveProjectRel(_o__col0=[$0], _o__col1=[$1], _o__col2=[$2],
> _o__col3=[$3], _o__col4=[$4], _o__col5=[$5], _o__col6=[$6], _o__col7=[$7],
> _o__col8=[$8], _o__col9=[$9], _o__col10=[$10], _o__col11=[$11],
> _o__col12=[$12], _o__col15=[$15], _o__col16=[$16], _o__col17=[$17],
> _o__col18=[$18]): rowcount = 1.0, cumulative cost = {1.1593403776322412E9
> rows, 0.0 cpu, 0.0 io}, id = 890
> HiveFilterRel(condition=[=($12, 2000)]): rowcount = 1.0,
> cumulative cost = {1.1593403776322412E9 rows, 0.0 cpu, 0.0 io}, id = 888
> HiveAggregateRel(group=[{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
> 12, 13, 14}], agg#0=[count()], agg#1=[sum($15)], agg#2=[sum($16)],
> agg#3=[sum($17)]): rowcount = 1.0, cumulative cost = {1.1593403776322412E9
> rows, 0.0 cpu, 0.0 io}, id = 886
> HiveProjectRel($f0=[$53], $f1=[$50], $f2=[$27], $f3=[$28],
> $f4=[$39], $f5=[$40], $f6=[$41], $f7=[$42], $f8=[$44], $f9=[$45], $f10=[$46],
> $f11=[$47], $f12=[$21], $f13=[$23], $f14=[$25], $f15=[$9], $f16=[$10],
> $f17=[$11]): rowcount = 1.0, cumulative cost = {1.1593403776322412E9 rows,
> 0.0 cpu, 0.0 io}, id = 884
> HiveProjectRel(ss_sold_date_sk=[$17], ss_item_sk=[$18],
> ss_customer_sk=[$19], ss_cdemo_sk=[$20], ss_hdemo_sk=[$21], ss_addr_sk=[$22],
> ss_store_sk=[$23], ss_promo_sk=[$24], ss_ticket_number=[$25],
> ss_wholesale_cost=[$26], ss_list_price=[$27], ss_coupon_amt=[$28],
> sr_item_sk=[$29], sr_ticket_number=[$30], c_customer_sk=[$31],
> c_current_cdemo_sk=[$32], c_current_hdemo_sk=[$33], c_current_addr_sk=[$34],
> c_first_shipto_date_sk=[$35], c_first_sales_date_sk=[$36], d_date_sk=[$37],
> d_year=[$38], d_date_sk0=[$39], d_year0=[$40], d_date_sk1=[$41],
> d_year1=[$42], s_store_sk=[$43], s_store_name=[$44], s_zip=[$45],
> cd_demo_sk=[$46], cd_marital_status=[$47], cd_demo_sk0=[$48],
> cd_marital_status0=[$49], p_promo_sk=[$0], hd_demo_sk=[$15],
> hd_income_band_sk=[$16], hd_demo_sk0=[$13], hd_income_band_sk0=[$14],
> ca_address_sk=[$6], ca_street_number=[$7], ca_street_name=[$8], ca_city=[$9],
> ca_zip=[$10], ca_address_sk0=[$1], ca_street_number0=[$2],
> ca_street_name0=[$3], ca_city0=[$4], ca_zip0=[$5], ib_income_band_sk=[$12],
> ib_income_band_sk0=[$11], i_item_sk=[$51], i_current_price=[$52],
> i_color=[$53], i_product_name=[$54], _o__col0=[$50]): rowcount = 1.0,
> cumulative cost = {1.1593403776322412E9 rows, 0.0 cpu, 0.0 io}, id = 3564
> HiveJoinRel(condition=[=($24, $0)], joinType=[inner]):
> rowcount = 1.0, cumulative cost = {1.1593403776322412E9 rows, 0.0 cpu, 0.0
> io}, id = 3562
> HiveProjectRel(p_promo_sk=[$0]): rowcount = 450.0,
> cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 928
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.promotion]]): rowcount
> = 450.0, cumulative cost = {0}, id = 58
> HiveJoinRel(condition=[=($33, $0)], joinType=[inner]):
> rowcount = 1.0, cumulative cost = {1.1593399266322412E9 rows, 0.0 cpu, 0.0
> io}, id = 3560
> HiveProjectRel(ca_address_sk=[$0],
> ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]):
> rowcount = 800000.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 940
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.customer_address]]):
> rowcount = 800000.0, cumulative cost = {0}, id = 61
> HiveJoinRel(condition=[=($16, $0)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1585399256322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3558
> HiveProjectRel(ca_address_sk=[$0],
> ca_street_number=[$2], ca_street_name=[$3], ca_city=[$6], ca_zip=[$9]):
> rowcount = 800000.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 940
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.customer_address]]):
> rowcount = 800000.0, cumulative cost = {0}, id = 61
> HiveJoinRel(condition=[=($3, $0)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1577399246322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3556
> HiveProjectRel(ib_income_band_sk=[$0]): rowcount
> = 20.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 948
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.income_band]]):
> rowcount = 20.0, cumulative cost = {0}, id = 63
> HiveJoinRel(condition=[=($4, $0)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1577399036322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3554
> HiveProjectRel(ib_income_band_sk=[$0]):
> rowcount = 20.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 948
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.income_band]]):
> rowcount = 20.0, cumulative cost = {0}, id = 63
> HiveJoinRel(condition=[=($5, $38)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1577398826322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3552
> HiveJoinRel(condition=[=($20, $0)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1577398806322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3550
> HiveProjectRel(hd_demo_sk=[$0],
> hd_income_band_sk=[$1]): rowcount = 7200.0, cumulative cost = {0.0 rows, 0.0
> cpu, 0.0 io}, id = 932
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.household_demographics]]):
> rowcount = 7200.0, cumulative cost = {0}, id = 53
> HiveJoinRel(condition=[=($6, $0)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1577326796322412E9
> rows, 0.0 cpu, 0.0 io}, id = 3548
> HiveProjectRel(hd_demo_sk=[$0],
> hd_income_band_sk=[$1]): rowcount = 7200.0, cumulative cost = {0.0 rows, 0.0
> cpu, 0.0 io}, id = 932
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.household_demographics]]):
> rowcount = 7200.0, cumulative cost = {0}, id = 53
> HiveJoinRel(condition=[=($1, $33)],
> joinType=[inner]): rowcount = 1.0, cumulative cost = {1.1577254786322412E9
> rows, 0.0 cpu, 0.0 io}, id = 2795
> HiveFilterRel(condition=[<>($30,
> $32)]): rowcount = 1.0, cumulative cost = {1.1577254766322412E9 rows, 0.0
> cpu, 0.0 io}, id = 832
> HiveProjectRel(ss_sold_date_sk=[$0],
> ss_item_sk=[$1], ss_customer_sk=[$2], ss_cdemo_sk=[$3], ss_hdemo_sk=[$4],
> ss_addr_sk=[$5], ss_store_sk=[$6], ss_promo_sk=[$7], ss_ticket_number=[$8],
> ss_wholesale_cost=[$9], ss_list_price=[$10], ss_coupon_amt=[$11],
> sr_item_sk=[$31], sr_ticket_number=[$32], c_customer_sk=[$21],
> c_current_cdemo_sk=[$22], c_current_hdemo_sk=[$23], c_current_addr_sk=[$24],
> c_first_shipto_date_sk=[$25], c_first_sales_date_sk=[$26], d_date_sk=[$14],
> d_year=[$15], d_date_sk0=[$27], d_year0=[$28], d_date_sk1=[$29],
> d_year1=[$30], s_store_sk=[$16], s_store_name=[$17], s_zip=[$18],
> cd_demo_sk=[$12], cd_marital_status=[$13], cd_demo_sk0=[$19],
> cd_marital_status0=[$20]): rowcount = 3.9579965360452816, cumulative cost =
> {1.1577254766322412E9 rows, 0.0 cpu, 0.0 io}, id = 1998
> HiveJoinRel(condition=[AND(=($1,
> $31), =($8, $32))], joinType=[inner]): rowcount = 3.9579965360452816,
> cumulative cost = {1.1577254766322412E9 rows, 0.0 cpu, 0.0 io}, id = 1996
> HiveJoinRel(condition=[=($2,
> $21)], joinType=[inner]): rowcount = 1.0, cumulative cost =
> {1.1021474706322412E9 rows, 0.0 cpu, 0.0 io}, id = 1994
> HiveJoinRel(condition=[=($6,
> $16)], joinType=[inner]): rowcount = 1.0, cumulative cost =
> {1.1021474686322412E9 rows, 0.0 cpu, 0.0 io}, id = 1987
> HiveJoinRel(condition=[=($0,
> $14)], joinType=[inner]): rowcount = 299.6322411714753, cumulative cost =
> {1.102146957E9 rows, 0.0 cpu, 0.0 io}, id = 1985
>
> HiveJoinRel(condition=[=($3, $12)], joinType=[inner]): rowcount =
> 5.50076554E8, cumulative cost = {5.51997354E8 rows, 0.0 cpu, 0.0 io}, id =
> 1569
>
> HiveProjectRel(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3],
> ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7],
> ss_promo_sk=[$8], ss_ticket_number=[$9], ss_wholesale_cost=[$11],
> ss_list_price=[$12], ss_coupon_amt=[$19]): rowcount = 5.50076554E8,
> cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 892
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.store_sales]]):
> rowcount = 5.50076554E8, cumulative cost = {0}, id = 55
>
> HiveProjectRel(cd_demo_sk=[$0], cd_marital_status=[$2]): rowcount =
> 1920800.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 918
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.customer_demographics]]):
> rowcount = 1920800.0, cumulative cost = {0}, id = 56
>
> HiveProjectRel(d_date_sk=[$0], d_year=[$6]): rowcount = 73049.0, cumulative
> cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 902
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.date_dim]]): rowcount
> = 73049.0, cumulative cost = {0}, id = 65
>
> HiveProjectRel(s_store_sk=[$0], s_store_name=[$5], s_zip=[$25]): rowcount =
> 212.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 914
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.store]]): rowcount =
> 212.0, cumulative cost = {0}, id = 54
> HiveJoinRel(condition=[=($6,
> $10)], joinType=[inner]): rowcount = 1.0, cumulative cost = {5266899.0 rows,
> 0.0 cpu, 0.0 io}, id = 1992
> HiveJoinRel(condition=[=($7,
> $8)], joinType=[inner]): rowcount = 1.0, cumulative cost = {5193849.0 rows,
> 0.0 cpu, 0.0 io}, id = 1990
>
> HiveJoinRel(condition=[=($3, $0)], joinType=[inner]): rowcount = 1600000.0,
> cumulative cost = {3520800.0 rows, 0.0 cpu, 0.0 io}, id = 1578
>
> HiveProjectRel(cd_demo_sk=[$0], cd_marital_status=[$2]): rowcount =
> 1920800.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 918
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.customer_demographics]]):
> rowcount = 1920800.0, cumulative cost = {0}, id = 56
>
> HiveProjectRel(c_customer_sk=[$0], c_current_cdemo_sk=[$2],
> c_current_hdemo_sk=[$3], c_current_addr_sk=[$4], c_first_shipto_date_sk=[$5],
> c_first_sales_date_sk=[$6]): rowcount = 1600000.0, cumulative cost = {0.0
> rows, 0.0 cpu, 0.0 io}, id = 898
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.customer]]): rowcount
> = 1600000.0, cumulative cost = {0}, id = 59
>
> HiveProjectRel(d_date_sk=[$0], d_year=[$6]): rowcount = 73049.0, cumulative
> cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 902
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.date_dim]]): rowcount
> = 73049.0, cumulative cost = {0}, id = 65
>
> HiveProjectRel(d_date_sk=[$0], d_year=[$6]): rowcount = 73049.0, cumulative
> cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 902
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.date_dim]]): rowcount
> = 73049.0, cumulative cost = {0}, id = 65
> HiveProjectRel(sr_item_sk=[$2],
> sr_ticket_number=[$9]): rowcount = 5.5578005E7, cumulative cost = {0.0 rows,
> 0.0 cpu, 0.0 io}, id = 894
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.store_returns]]):
> rowcount = 5.5578005E7, cumulative cost = {0}, id = 62
> HiveProjectRel(_o__col0=[$0]): rowcount
> = 1.0, cumulative cost = {3.15348608E8 rows, 0.0 cpu, 0.0 io}, id = 880
> HiveFilterRel(condition=[>($1,
> *(CAST(2):DOUBLE NOT NULL, $2))]): rowcount = 1.0, cumulative cost =
> {3.15348608E8 rows, 0.0 cpu, 0.0 io}, id = 878
> HiveAggregateRel(group=[{0}],
> agg#0=[sum($1)], agg#1=[sum($2)]): rowcount = 38846.0, cumulative cost =
> {3.15348608E8 rows, 0.0 cpu, 0.0 io}, id = 876
> HiveProjectRel($f0=[$0],
> $f1=[$2], $f2=[+(+($5, $6), $7)]): rowcount = 6.692553251460564E8, cumulative
> cost = {3.15348608E8 rows, 0.0 cpu, 0.0 io}, id = 874
> HiveProjectRel(cs_item_sk=[$0],
> cs_order_number=[$1], cs_ext_list_price=[$2], cr_item_sk=[$3],
> cr_order_number=[$4], cr_refunded_cash=[$5], cr_reversed_charge=[$6],
> cr_store_credit=[$7]): rowcount = 6.692553251460564E8, cumulative cost =
> {3.15348608E8 rows, 0.0 cpu, 0.0 io}, id = 1132
>
> HiveJoinRel(condition=[AND(=($0, $3), =($1, $4))], joinType=[inner]):
> rowcount = 6.692553251460564E8, cumulative cost = {3.15348608E8 rows, 0.0
> cpu, 0.0 io}, id = 1127
>
> HiveProjectRel(cs_item_sk=[$15], cs_order_number=[$17],
> cs_ext_list_price=[$25]): rowcount = 2.86549727E8, cumulative cost = {0.0
> rows, 0.0 cpu, 0.0 io}, id = 962
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.catalog_sales]]):
> rowcount = 2.86549727E8, cumulative cost = {0}, id = 45
>
> HiveProjectRel(cr_item_sk=[$2], cr_order_number=[$16],
> cr_refunded_cash=[$23], cr_reversed_charge=[$24], cr_store_credit=[$25]):
> rowcount = 2.8798881E7, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id =
> 964
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.catalog_returns]]):
> rowcount = 2.8798881E7, cumulative cost = {0}, id = 46
> HiveFilterRel(condition=[AND(in($2, 'maroon',
> 'burnished', 'dim', 'steel', 'navajo', 'chocolate'), between(false, $1, 35,
> +(35, 10)), between(false, $1, +(35, 1), +(35, 15)))]): rowcount = 1.0,
> cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 864
> HiveProjectRel(i_item_sk=[$0],
> i_current_price=[$5], i_color=[$17], i_product_name=[$21]): rowcount =
> 48000.0, cumulative cost = {0.0 rows, 0.0 cpu, 0.0 io}, id = 862
>
> HiveTableScanRel(table=[[tpcds_bin_partitioned_orc_200.item]]): rowcount =
> 48000.0, cumulative cost = {0}, id = 68
> {code}
> Physical plan
> {code}
> STAGE PLANS:
> Stage: Stage-1
> Tez
> Edges:
> Map 10 <- Map 40 (BROADCAST_EDGE)
> Map 16 <- Map 2 (BROADCAST_EDGE), Map 23 (BROADCAST_EDGE), Map 6
> (BROADCAST_EDGE)
> Map 19 <- Map 42 (BROADCAST_EDGE)
> Map 33 <- Map 35 (BROADCAST_EDGE)
> Map 35 <- Map 1 (BROADCAST_EDGE), Map 16 (BROADCAST_EDGE), Map 3
> (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE)
> Map 36 <- Map 18 (BROADCAST_EDGE), Map 25 (BROADCAST_EDGE), Map 41
> (BROADCAST_EDGE)
> Map 38 <- Map 15 (BROADCAST_EDGE), Map 31 (BROADCAST_EDGE), Map 36
> (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE)
> Map 4 <- Map 38 (BROADCAST_EDGE)
> Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 22 (BROADCAST_EDGE), Map 24
> (BROADCAST_EDGE), Map 26 (BROADCAST_EDGE), Map 27 (BROADCAST_EDGE), Map 30
> (BROADCAST_EDGE), Map 32 (BROADCAST_EDGE), Map 39 (BROADCAST_EDGE), Map 4
> (BROADCAST_EDGE), Map 7 (BROADCAST_EDGE)
> Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
> Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE)
> Reducer 14 <- Reducer 13 (SIMPLE_EDGE)
> Reducer 20 <- Map 17 (BROADCAST_EDGE), Map 19 (SIMPLE_EDGE), Map 28
> (BROADCAST_EDGE), Map 29 (BROADCAST_EDGE), Map 33 (BROADCAST_EDGE), Map 34
> (BROADCAST_EDGE), Map 37 (BROADCAST_EDGE), Map 43 (BROADCAST_EDGE), Map 44
> (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE)
> Reducer 21 <- Reducer 20 (SIMPLE_EDGE)
> DagName: mmokhtar_20140925174747_6fa8c67a-6d24-43cc-8fbb-3be14937b8b1:1
> Vertices:
> Map 1
> Map Operator Tree:
> TableScan
> alias: d1
> filterExpr: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 73049 Data size: 81741831 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: d_date_sk (type: int), d_year (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 10
> Map Operator Tree:
> TableScan
> alias: catalog_sales
> filterExpr: (cs_item_sk is not null and cs_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 286549727 Data size: 38890158232
> Basic stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (cs_item_sk is not null and cs_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 71637432 Data size: 9722539591
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cs_item_sk (type: int), cs_order_number
> (type: int), cs_ext_list_price (type: float)
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 71637432 Data size: 9722539591
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col0} {_col2}
> 1 {_col2} {_col3} {_col4}
> keys:
> 0 _col0 (type: int), _col1 (type: int)
> 1 _col0 (type: int), _col1 (type: int)
> outputColumnNames: _col0, _col2, _col5, _col6, _col7
> input vertices:
> 1 Map 40
> Statistics: Num rows: 78801176 Data size: 10694794240
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col0 (type: int), _col2 (type:
> float), ((_col5 + _col6) + _col7) (type: float)
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 78801176 Data size:
> 10694794240 Basic stats: COMPLETE Column stats: NONE
> Group By Operator
> aggregations: sum(_col1), sum(_col2)
> keys: _col0 (type: int)
> mode: hash
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 78801176 Data size:
> 10694794240 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 78801176 Data size:
> 10694794240 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: double), _col2
> (type: double)
> Execution mode: vectorized
> Map 15
> Map Operator Tree:
> TableScan
> alias: customer
> filterExpr: (((((c_current_cdemo_sk is not null and
> c_first_sales_date_sk is not null) and c_first_shipto_date_sk is not null)
> and c_customer_sk is not null) and c_current_hdemo_sk is not null) and
> c_current_addr_sk is not null) (type: boolean)
> Statistics: Num rows: 1600000 Data size: 1376033128 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (((((c_current_cdemo_sk is not null and
> c_first_sales_date_sk is not null) and c_first_shipto_date_sk is not null)
> and c_customer_sk is not null) and c_current_hdemo_sk is not null) and
> c_current_addr_sk is not null) (type: boolean)
> Statistics: Num rows: 25000 Data size: 21500517 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: c_customer_sk (type: int),
> c_current_cdemo_sk (type: int), c_current_hdemo_sk (type: int),
> c_current_addr_sk (type: int), c_first_shipto_date_sk (type: int),
> c_first_sales_date_sk (type: int)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5
> Statistics: Num rows: 25000 Data size: 21500517 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int)
> sort order: +
> Map-reduce partition columns: _col1 (type: int)
> Statistics: Num rows: 25000 Data size: 21500517 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col0 (type: int), _col2 (type:
> int), _col3 (type: int), _col4 (type: int), _col5 (type: int)
> Execution mode: vectorized
> Map 16
> Map Operator Tree:
> TableScan
> alias: cd1
> filterExpr: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 1920800 Data size: 718379200 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cd_demo_sk (type: int), cd_marital_status
> (type: string)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col0} {_col1} {_col2} {_col4} {_col5} {_col6}
> {_col7} {_col8} {_col9} {_col10} {_col11}
> 1 {_col1}
> keys:
> 0 _col3 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col0, _col1, _col2, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col13
> input vertices:
> 0 Map 6
> Statistics: Num rows: 1181805 Data size: 51579732
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col6} {_col7}
> {_col8} {_col9} {_col10} {_col11} {_col13}
> 1
> keys:
> 0 _col0 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col13
> input vertices:
> 1 Map 23
> Statistics: Num rows: 1299985 Data size: 56737708
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col7}
> {_col8} {_col9} {_col10} {_col11} {_col13}
> 1 {_col1} {_col2}
> keys:
> 0 _col6 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col7, _col8, _col9, _col10, _col11, _col13, _col17, _col18
> input vertices:
> 1 Map 2
> Statistics: Num rows: 1429983 Data size: 62411480
> Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col2 (type: int)
> sort order: +
> Map-reduce partition columns: _col2 (type: int)
> Statistics: Num rows: 1429983 Data size:
> 62411480 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int), _col4
> (type: int), _col5 (type: int), _col7 (type: int), _col8 (type: int), _col9
> (type: float), _col10 (type: float), _col11 (type: float), _col13 (type:
> string), _col17 (type: string), _col18 (type: string)
> Execution mode: vectorized
> Map 17
> Map Operator Tree:
> TableScan
> alias: ib1
> filterExpr: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 20 Data size: 240 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: ib_income_band_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 18
> Map Operator Tree:
> TableScan
> alias: store_sales
> filterExpr: ((((((((ss_cdemo_sk is not null and
> ss_sold_date_sk is not null) and ss_store_sk is not null) and ss_customer_sk
> is not null) and ss_item_sk is not null) and ss_ticket_number is not null)
> and ss_hdemo_sk is not null) and ss_addr_sk is not null) and ss_promo_sk is
> not null) (type: boolean)
> Statistics: Num rows: 550076554 Data size: 24008004411
> Basic stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ((((((((ss_cdemo_sk is not null and
> ss_sold_date_sk is not null) and ss_store_sk is not null) and ss_customer_sk
> is not null) and ss_item_sk is not null) and ss_ticket_number is not null)
> and ss_hdemo_sk is not null) and ss_addr_sk is not null) and ss_promo_sk is
> not null) (type: boolean)
> Statistics: Num rows: 1074369 Data size: 46890665 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: ss_sold_date_sk (type: int), ss_item_sk
> (type: int), ss_customer_sk (type: int), ss_cdemo_sk (type: int), ss_hdemo_sk
> (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_promo_sk
> (type: int), ss_ticket_number (type: int), ss_wholesale_cost (type: float),
> ss_list_price (type: float), ss_coupon_amt (type: float)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5, _col6, _col7, _col8, _col9, _col10, _col11
> Statistics: Num rows: 1074369 Data size: 46890665 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col3 (type: int)
> sort order: +
> Map-reduce partition columns: _col3 (type: int)
> Statistics: Num rows: 1074369 Data size: 46890665
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col0 (type: int), _col1 (type:
> int), _col2 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type:
> int), _col7 (type: int), _col8 (type: int), _col9 (type: float), _col10
> (type: float), _col11 (type: float)
> Execution mode: vectorized
> Map 19
> Map Operator Tree:
> TableScan
> alias: catalog_sales
> filterExpr: (cs_item_sk is not null and cs_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 286549727 Data size: 38890158232
> Basic stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (cs_item_sk is not null and cs_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 71637432 Data size: 9722539591
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cs_item_sk (type: int), cs_order_number
> (type: int), cs_ext_list_price (type: float)
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 71637432 Data size: 9722539591
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col0} {_col2}
> 1 {_col2} {_col3} {_col4}
> keys:
> 0 _col0 (type: int), _col1 (type: int)
> 1 _col0 (type: int), _col1 (type: int)
> outputColumnNames: _col0, _col2, _col5, _col6, _col7
> input vertices:
> 1 Map 42
> Statistics: Num rows: 78801176 Data size: 10694794240
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col0 (type: int), _col2 (type:
> float), ((_col5 + _col6) + _col7) (type: float)
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 78801176 Data size:
> 10694794240 Basic stats: COMPLETE Column stats: NONE
> Group By Operator
> aggregations: sum(_col1), sum(_col2)
> keys: _col0 (type: int)
> mode: hash
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 78801176 Data size:
> 10694794240 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 78801176 Data size:
> 10694794240 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: double), _col2
> (type: double)
> Execution mode: vectorized
> Map 2
> Map Operator Tree:
> TableScan
> alias: store
> filterExpr: ((s_store_sk is not null and s_store_name is
> not null) and s_zip is not null) (type: boolean)
> Statistics: Num rows: 212 Data size: 405680 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: ((s_store_sk is not null and s_store_name is
> not null) and s_zip is not null) (type: boolean)
> Statistics: Num rows: 27 Data size: 51666 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: s_store_sk (type: int), s_store_name
> (type: string), s_zip (type: string)
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 27 Data size: 51666 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 27 Data size: 51666 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: string), _col2 (type:
> string)
> Execution mode: vectorized
> Map 22
> Map Operator Tree:
> TableScan
> alias: ib1
> filterExpr: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 20 Data size: 240 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: ib_income_band_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 23
> Map Operator Tree:
> TableScan
> alias: d1
> filterExpr: (d_date_sk is not null and (d_year = 2000))
> (type: boolean)
> Statistics: Num rows: 73049 Data size: 81741831 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (d_date_sk is not null and (d_year = 2000))
> (type: boolean)
> Statistics: Num rows: 18262 Data size: 20435178 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: d_date_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 18262 Data size: 20435178 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 18262 Data size: 20435178 Basic
> stats: COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 24
> Map Operator Tree:
> TableScan
> alias: hd1
> filterExpr: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 7200 Data size: 799 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: hd_demo_sk (type: int), hd_income_band_sk
> (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 1800 Data size: 199 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 25
> Map Operator Tree:
> TableScan
> alias: d1
> filterExpr: (d_date_sk is not null and (d_year = 2001))
> (type: boolean)
> Statistics: Num rows: 73049 Data size: 81741831 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (d_date_sk is not null and (d_year = 2001))
> (type: boolean)
> Statistics: Num rows: 18262 Data size: 20435178 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: d_date_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 18262 Data size: 20435178 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 18262 Data size: 20435178 Basic
> stats: COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 26
> Map Operator Tree:
> TableScan
> alias: promotion
> filterExpr: p_promo_sk is not null (type: boolean)
> Statistics: Num rows: 450 Data size: 530848 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: p_promo_sk is not null (type: boolean)
> Statistics: Num rows: 225 Data size: 265424 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: p_promo_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 225 Data size: 265424 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 225 Data size: 265424 Basic
> stats: COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 27
> Map Operator Tree:
> TableScan
> alias: hd1
> filterExpr: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 7200 Data size: 799 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: hd_demo_sk (type: int), hd_income_band_sk
> (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 1800 Data size: 199 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 28
> Map Operator Tree:
> TableScan
> alias: ad1
> filterExpr: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 800000 Data size: 811903688 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: ca_address_sk (type: int),
> ca_street_number (type: string), ca_street_name (type: string), ca_city
> (type: string), ca_zip (type: string)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 400000 Data size: 405951844
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: string), _col2 (type:
> string), _col3 (type: string), _col4 (type: string)
> Execution mode: vectorized
> Map 29
> Map Operator Tree:
> TableScan
> alias: item
> filterExpr: ((((i_color) IN ('maroon', 'burnished', 'dim',
> 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45) and
> i_current_price BETWEEN 36 AND 50) and i_item_sk is not null) (type: boolean)
> Statistics: Num rows: 48000 Data size: 68732712 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ((((i_color) IN ('maroon', 'burnished', 'dim',
> 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45) and
> i_current_price BETWEEN 36 AND 50) and i_item_sk is not null) (type: boolean)
> Statistics: Num rows: 3000 Data size: 4295794 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: i_item_sk (type: int), i_product_name
> (type: string)
> outputColumnNames: _col0, _col3
> Statistics: Num rows: 3000 Data size: 4295794 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 3000 Data size: 4295794 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col3 (type: string)
> Execution mode: vectorized
> Map 3
> Map Operator Tree:
> TableScan
> alias: customer
> filterExpr: (((((c_current_cdemo_sk is not null and
> c_first_sales_date_sk is not null) and c_first_shipto_date_sk is not null)
> and c_customer_sk is not null) and c_current_hdemo_sk is not null) and
> c_current_addr_sk is not null) (type: boolean)
> Statistics: Num rows: 1600000 Data size: 1376033128 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (((((c_current_cdemo_sk is not null and
> c_first_sales_date_sk is not null) and c_first_shipto_date_sk is not null)
> and c_customer_sk is not null) and c_current_hdemo_sk is not null) and
> c_current_addr_sk is not null) (type: boolean)
> Statistics: Num rows: 25000 Data size: 21500517 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: c_customer_sk (type: int),
> c_current_cdemo_sk (type: int), c_current_hdemo_sk (type: int),
> c_current_addr_sk (type: int), c_first_shipto_date_sk (type: int),
> c_first_sales_date_sk (type: int)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5
> Statistics: Num rows: 25000 Data size: 21500517 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int)
> sort order: +
> Map-reduce partition columns: _col1 (type: int)
> Statistics: Num rows: 25000 Data size: 21500517 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col0 (type: int), _col2 (type:
> int), _col3 (type: int), _col4 (type: int), _col5 (type: int)
> Execution mode: vectorized
> Map 30
> Map Operator Tree:
> TableScan
> alias: ib1
> filterExpr: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 20 Data size: 240 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: ib_income_band_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 31
> Map Operator Tree:
> TableScan
> alias: d1
> filterExpr: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 73049 Data size: 81741831 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: d_date_sk (type: int), d_year (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 32
> Map Operator Tree:
> TableScan
> alias: ad1
> filterExpr: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 800000 Data size: 811903688 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: ca_address_sk (type: int),
> ca_street_number (type: string), ca_street_name (type: string), ca_city
> (type: string), ca_zip (type: string)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 400000 Data size: 405951844
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: string), _col2 (type:
> string), _col3 (type: string), _col4 (type: string)
> Execution mode: vectorized
> Map 33
> Map Operator Tree:
> TableScan
> alias: store_returns
> filterExpr: (sr_item_sk is not null and sr_ticket_number is
> not null) (type: boolean)
> Statistics: Num rows: 55578005 Data size: 4377627636 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (sr_item_sk is not null and sr_ticket_number
> is not null) (type: boolean)
> Statistics: Num rows: 13894502 Data size: 1094406968
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: sr_item_sk (type: int), sr_ticket_number
> (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 13894502 Data size: 1094406968
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col4} {_col5} {_col7} {_col9} {_col10}
> {_col11} {_col13} {_col17} {_col18} {_col20} {_col23} {_col24} {_col28}
> {_col30}
> 1
> keys:
> 0 _col1 (type: int), _col8 (type: int)
> 1 _col0 (type: int), _col1 (type: int)
> outputColumnNames: _col1, _col4, _col5, _col7, _col9,
> _col10, _col11, _col13, _col17, _col18, _col20, _col23, _col24, _col28, _col30
> input vertices:
> 0 Map 35
> Statistics: Num rows: 15283953 Data size: 1203847680
> Basic stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (_col13 <> _col20) (type: boolean)
> Statistics: Num rows: 15283953 Data size:
> 1203847680 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col10 (type:
> float), _col11 (type: float), _col23 (type: int), _col24 (type: int), 2000
> (type: int), _col28 (type: int), _col30 (type: int), _col17 (type: string),
> _col18 (type: string), _col4 (type: int), _col5 (type: int), _col7 (type:
> int), _col9 (type: float)
> outputColumnNames: _col1, _col10, _col11, _col16,
> _col17, _col21, _col23, _col25, _col27, _col28, _col4, _col5, _col7, _col9
> Statistics: Num rows: 15283953 Data size:
> 1203847680 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int)
> sort order: +
> Map-reduce partition columns: _col1 (type: int)
> Statistics: Num rows: 15283953 Data size:
> 1203847680 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col4 (type: int), _col5
> (type: int), _col7 (type: int), _col9 (type: float), _col10 (type: float),
> _col11 (type: float), _col16 (type: int), _col17 (type: int), _col21 (type:
> int), _col23 (type: int), _col25 (type: int), _col27 (type: string), _col28
> (type: string)
> Execution mode: vectorized
> Map 34
> Map Operator Tree:
> TableScan
> alias: promotion
> filterExpr: p_promo_sk is not null (type: boolean)
> Statistics: Num rows: 450 Data size: 530848 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: p_promo_sk is not null (type: boolean)
> Statistics: Num rows: 225 Data size: 265424 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: p_promo_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 225 Data size: 265424 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 225 Data size: 265424 Basic
> stats: COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 35
> Map Operator Tree:
> TableScan
> alias: cd1
> filterExpr: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 1920800 Data size: 718379200 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cd_demo_sk (type: int), cd_marital_status
> (type: string)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1}
> 1 {_col0} {_col2} {_col3} {_col4} {_col5}
> keys:
> 0 _col0 (type: int)
> 1 _col1 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5, _col6,
> _col7
> input vertices:
> 1 Map 3
> Statistics: Num rows: 1056440 Data size: 395108576
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col6}
> 1 {_col1}
> keys:
> 0 _col7 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col6, _col9
> input vertices:
> 1 Map 8
> Statistics: Num rows: 1162084 Data size: 434619456
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col9}
> 1 {_col1}
> keys:
> 0 _col6 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col9, _col11
> input vertices:
> 1 Map 1
> Statistics: Num rows: 1278292 Data size:
> 478081408 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: string), _col11
> (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: int), _col9
> (type: int)
> outputColumnNames: _col1, _col11, _col2, _col4,
> _col5, _col9
> Statistics: Num rows: 1278292 Data size:
> 478081408 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col4} {_col5} {_col7} {_col8}
> {_col9} {_col10} {_col11} {_col13} {_col17} {_col18}
> 1 {_col1} {_col4} {_col5} {_col9} {_col11}
> keys:
> 0 _col2 (type: int)
> 1 _col2 (type: int)
> outputColumnNames: _col1, _col4, _col5,
> _col7, _col8, _col9, _col10, _col11, _col13, _col17, _col18, _col20, _col23,
> _col24, _col28, _col30
> input vertices:
> 0 Map 16
> Statistics: Num rows: 1572981 Data size:
> 68652632 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int), _col8
> (type: int)
> sort order: ++
> Map-reduce partition columns: _col1 (type:
> int), _col8 (type: int)
> Statistics: Num rows: 1572981 Data size:
> 68652632 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col4 (type: int), _col5
> (type: int), _col7 (type: int), _col9 (type: float), _col10 (type: float),
> _col11 (type: float), _col13 (type: string), _col17 (type: string), _col18
> (type: string), _col20 (type: string), _col23 (type: int), _col24 (type:
> int), _col28 (type: int), _col30 (type: int)
> Execution mode: vectorized
> Map 36
> Map Operator Tree:
> TableScan
> alias: cd1
> filterExpr: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 1920800 Data size: 718379200 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cd_demo_sk (type: int), cd_marital_status
> (type: string)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col0} {_col1} {_col2} {_col4} {_col5} {_col6}
> {_col7} {_col8} {_col9} {_col10} {_col11}
> 1 {_col1}
> keys:
> 0 _col3 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col0, _col1, _col2, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col13
> input vertices:
> 0 Map 18
> Statistics: Num rows: 1181805 Data size: 51579732
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col6} {_col7}
> {_col8} {_col9} {_col10} {_col11} {_col13}
> 1
> keys:
> 0 _col0 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col13
> input vertices:
> 1 Map 25
> Statistics: Num rows: 1299985 Data size: 56737708
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col7}
> {_col8} {_col9} {_col10} {_col11} {_col13}
> 1 {_col1} {_col2}
> keys:
> 0 _col6 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col7, _col8, _col9, _col10, _col11, _col13, _col17, _col18
> input vertices:
> 1 Map 41
> Statistics: Num rows: 1429983 Data size: 62411480
> Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col2 (type: int)
> sort order: +
> Map-reduce partition columns: _col2 (type: int)
> Statistics: Num rows: 1429983 Data size:
> 62411480 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int), _col4
> (type: int), _col5 (type: int), _col7 (type: int), _col8 (type: int), _col9
> (type: float), _col10 (type: float), _col11 (type: float), _col13 (type:
> string), _col17 (type: string), _col18 (type: string)
> Execution mode: vectorized
> Map 37
> Map Operator Tree:
> TableScan
> alias: ib1
> filterExpr: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 20 Data size: 240 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: ib_income_band_sk is not null (type: boolean)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: ib_income_band_sk (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 10 Data size: 120 Basic stats:
> COMPLETE Column stats: NONE
> Execution mode: vectorized
> Map 38
> Map Operator Tree:
> TableScan
> alias: cd1
> filterExpr: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 1920800 Data size: 718379200 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: cd_demo_sk is not null (type: boolean)
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cd_demo_sk (type: int), cd_marital_status
> (type: string)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 960400 Data size: 359189600 Basic
> stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1}
> 1 {_col0} {_col2} {_col3} {_col4} {_col5}
> keys:
> 0 _col0 (type: int)
> 1 _col1 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5, _col6,
> _col7
> input vertices:
> 1 Map 15
> Statistics: Num rows: 1056440 Data size: 395108576
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col6}
> 1 {_col1}
> keys:
> 0 _col7 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col6, _col9
> input vertices:
> 1 Map 31
> Statistics: Num rows: 1162084 Data size: 434619456
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col4} {_col5} {_col9}
> 1 {_col1}
> keys:
> 0 _col6 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col2, _col4, _col5,
> _col9, _col11
> input vertices:
> 1 Map 5
> Statistics: Num rows: 1278292 Data size:
> 478081408 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: string), _col11
> (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: int), _col9
> (type: int)
> outputColumnNames: _col1, _col11, _col2, _col4,
> _col5, _col9
> Statistics: Num rows: 1278292 Data size:
> 478081408 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col4} {_col5} {_col7} {_col8}
> {_col9} {_col10} {_col11} {_col13} {_col17} {_col18}
> 1 {_col1} {_col4} {_col5} {_col9} {_col11}
> keys:
> 0 _col2 (type: int)
> 1 _col2 (type: int)
> outputColumnNames: _col1, _col4, _col5,
> _col7, _col8, _col9, _col10, _col11, _col13, _col17, _col18, _col20, _col23,
> _col24, _col28, _col30
> input vertices:
> 0 Map 36
> Statistics: Num rows: 1572981 Data size:
> 68652632 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int), _col8
> (type: int)
> sort order: ++
> Map-reduce partition columns: _col1 (type:
> int), _col8 (type: int)
> Statistics: Num rows: 1572981 Data size:
> 68652632 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col4 (type: int), _col5
> (type: int), _col7 (type: int), _col9 (type: float), _col10 (type: float),
> _col11 (type: float), _col13 (type: string), _col17 (type: string), _col18
> (type: string), _col20 (type: string), _col23 (type: int), _col24 (type:
> int), _col28 (type: int), _col30 (type: int)
> Execution mode: vectorized
> Map 39
> Map Operator Tree:
> TableScan
> alias: item
> filterExpr: ((((i_color) IN ('maroon', 'burnished', 'dim',
> 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45) and
> i_current_price BETWEEN 36 AND 50) and i_item_sk is not null) (type: boolean)
> Statistics: Num rows: 48000 Data size: 68732712 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ((((i_color) IN ('maroon', 'burnished', 'dim',
> 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45) and
> i_current_price BETWEEN 36 AND 50) and i_item_sk is not null) (type: boolean)
> Statistics: Num rows: 3000 Data size: 4295794 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: i_item_sk (type: int), i_product_name
> (type: string)
> outputColumnNames: _col0, _col3
> Statistics: Num rows: 3000 Data size: 4295794 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 3000 Data size: 4295794 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col3 (type: string)
> Execution mode: vectorized
> Map 4
> Map Operator Tree:
> TableScan
> alias: store_returns
> filterExpr: (sr_item_sk is not null and sr_ticket_number is
> not null) (type: boolean)
> Statistics: Num rows: 55578005 Data size: 4377627636 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (sr_item_sk is not null and sr_ticket_number
> is not null) (type: boolean)
> Statistics: Num rows: 13894502 Data size: 1094406968
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: sr_item_sk (type: int), sr_ticket_number
> (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 13894502 Data size: 1094406968
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col4} {_col5} {_col7} {_col9} {_col10}
> {_col11} {_col13} {_col17} {_col18} {_col20} {_col23} {_col24} {_col28}
> {_col30}
> 1
> keys:
> 0 _col1 (type: int), _col8 (type: int)
> 1 _col0 (type: int), _col1 (type: int)
> outputColumnNames: _col1, _col4, _col5, _col7, _col9,
> _col10, _col11, _col13, _col17, _col18, _col20, _col23, _col24, _col28, _col30
> input vertices:
> 0 Map 38
> Statistics: Num rows: 15283953 Data size: 1203847680
> Basic stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (_col13 <> _col20) (type: boolean)
> Statistics: Num rows: 15283953 Data size:
> 1203847680 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col10 (type:
> float), _col11 (type: float), _col23 (type: int), _col24 (type: int), 2001
> (type: int), _col28 (type: int), _col30 (type: int), _col17 (type: string),
> _col18 (type: string), _col4 (type: int), _col5 (type: int), _col7 (type:
> int), _col9 (type: float)
> outputColumnNames: _col1, _col10, _col11, _col16,
> _col17, _col21, _col23, _col25, _col27, _col28, _col4, _col5, _col7, _col9
> Statistics: Num rows: 15283953 Data size:
> 1203847680 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int)
> sort order: +
> Map-reduce partition columns: _col1 (type: int)
> Statistics: Num rows: 15283953 Data size:
> 1203847680 Basic stats: COMPLETE Column stats: NONE
> value expressions: _col4 (type: int), _col5
> (type: int), _col7 (type: int), _col9 (type: float), _col10 (type: float),
> _col11 (type: float), _col16 (type: int), _col17 (type: int), _col21 (type:
> int), _col23 (type: int), _col25 (type: int), _col27 (type: string), _col28
> (type: string)
> Execution mode: vectorized
> Map 40
> Map Operator Tree:
> TableScan
> alias: catalog_returns
> filterExpr: (cr_item_sk is not null and cr_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 28798881 Data size: 3057234680 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (cr_item_sk is not null and cr_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 7199721 Data size: 764308749 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cr_item_sk (type: int), cr_order_number
> (type: int), cr_refunded_cash (type: float), cr_reversed_charge (type:
> float), cr_store_credit (type: float)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4
> Statistics: Num rows: 7199721 Data size: 764308749
> Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int), _col1 (type: int)
> sort order: ++
> Map-reduce partition columns: _col0 (type: int),
> _col1 (type: int)
> Statistics: Num rows: 7199721 Data size: 764308749
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col2 (type: float), _col3 (type:
> float), _col4 (type: float)
> Execution mode: vectorized
> Map 41
> Map Operator Tree:
> TableScan
> alias: store
> filterExpr: ((s_store_sk is not null and s_store_name is
> not null) and s_zip is not null) (type: boolean)
> Statistics: Num rows: 212 Data size: 405680 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: ((s_store_sk is not null and s_store_name is
> not null) and s_zip is not null) (type: boolean)
> Statistics: Num rows: 27 Data size: 51666 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: s_store_sk (type: int), s_store_name
> (type: string), s_zip (type: string)
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 27 Data size: 51666 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 27 Data size: 51666 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: string), _col2 (type:
> string)
> Execution mode: vectorized
> Map 42
> Map Operator Tree:
> TableScan
> alias: catalog_returns
> filterExpr: (cr_item_sk is not null and cr_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 28798881 Data size: 3057234680 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (cr_item_sk is not null and cr_order_number is
> not null) (type: boolean)
> Statistics: Num rows: 7199721 Data size: 764308749 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: cr_item_sk (type: int), cr_order_number
> (type: int), cr_refunded_cash (type: float), cr_reversed_charge (type:
> float), cr_store_credit (type: float)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4
> Statistics: Num rows: 7199721 Data size: 764308749
> Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int), _col1 (type: int)
> sort order: ++
> Map-reduce partition columns: _col0 (type: int),
> _col1 (type: int)
> Statistics: Num rows: 7199721 Data size: 764308749
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col2 (type: float), _col3 (type:
> float), _col4 (type: float)
> Execution mode: vectorized
> Map 43
> Map Operator Tree:
> TableScan
> alias: ad1
> filterExpr: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 800000 Data size: 811903688 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: ca_address_sk (type: int),
> ca_street_number (type: string), ca_street_name (type: string), ca_city
> (type: string), ca_zip (type: string)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 400000 Data size: 405951844
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: string), _col2 (type:
> string), _col3 (type: string), _col4 (type: string)
> Execution mode: vectorized
> Map 44
> Map Operator Tree:
> TableScan
> alias: hd1
> filterExpr: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 7200 Data size: 799 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: hd_demo_sk (type: int), hd_income_band_sk
> (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 1800 Data size: 199 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 5
> Map Operator Tree:
> TableScan
> alias: d1
> filterExpr: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 73049 Data size: 81741831 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: d_date_sk (type: int), d_year (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 6
> Map Operator Tree:
> TableScan
> alias: store_sales
> filterExpr: ((((((((ss_cdemo_sk is not null and
> ss_sold_date_sk is not null) and ss_store_sk is not null) and ss_customer_sk
> is not null) and ss_item_sk is not null) and ss_ticket_number is not null)
> and ss_hdemo_sk is not null) and ss_addr_sk is not null) and ss_promo_sk is
> not null) (type: boolean)
> Statistics: Num rows: 550076554 Data size: 24008004411
> Basic stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ((((((((ss_cdemo_sk is not null and
> ss_sold_date_sk is not null) and ss_store_sk is not null) and ss_customer_sk
> is not null) and ss_item_sk is not null) and ss_ticket_number is not null)
> and ss_hdemo_sk is not null) and ss_addr_sk is not null) and ss_promo_sk is
> not null) (type: boolean)
> Statistics: Num rows: 1074369 Data size: 46890665 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: ss_sold_date_sk (type: int), ss_item_sk
> (type: int), ss_customer_sk (type: int), ss_cdemo_sk (type: int), ss_hdemo_sk
> (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_promo_sk
> (type: int), ss_ticket_number (type: int), ss_wholesale_cost (type: float),
> ss_list_price (type: float), ss_coupon_amt (type: float)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5, _col6, _col7, _col8, _col9, _col10, _col11
> Statistics: Num rows: 1074369 Data size: 46890665 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col3 (type: int)
> sort order: +
> Map-reduce partition columns: _col3 (type: int)
> Statistics: Num rows: 1074369 Data size: 46890665
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col0 (type: int), _col1 (type:
> int), _col2 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type:
> int), _col7 (type: int), _col8 (type: int), _col9 (type: float), _col10
> (type: float), _col11 (type: float)
> Execution mode: vectorized
> Map 7
> Map Operator Tree:
> TableScan
> alias: ad1
> filterExpr: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 800000 Data size: 811903688 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: ca_address_sk is not null (type: boolean)
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: ca_address_sk (type: int),
> ca_street_number (type: string), ca_street_name (type: string), ca_city
> (type: string), ca_zip (type: string)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4
> Statistics: Num rows: 400000 Data size: 405951844 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 400000 Data size: 405951844
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: string), _col2 (type:
> string), _col3 (type: string), _col4 (type: string)
> Execution mode: vectorized
> Map 8
> Map Operator Tree:
> TableScan
> alias: d1
> filterExpr: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 73049 Data size: 81741831 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: d_date_sk is not null (type: boolean)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: d_date_sk (type: int), d_year (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 36525 Data size: 40871475 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Map 9
> Map Operator Tree:
> TableScan
> alias: hd1
> filterExpr: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 7200 Data size: 799 Basic stats:
> COMPLETE Column stats: NONE
> Filter Operator
> predicate: (hd_demo_sk is not null and hd_income_band_sk
> is not null) (type: boolean)
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Select Operator
> expressions: hd_demo_sk (type: int), hd_income_band_sk
> (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 1800 Data size: 199 Basic stats:
> COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int)
> sort order: +
> Map-reduce partition columns: _col0 (type: int)
> Statistics: Num rows: 1800 Data size: 199 Basic
> stats: COMPLETE Column stats: NONE
> value expressions: _col1 (type: int)
> Execution mode: vectorized
> Reducer 11
> Reduce Operator Tree:
> Group By Operator
> aggregations: sum(VALUE._col0), sum(VALUE._col1)
> keys: KEY._col0 (type: int)
> mode: mergepartial
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 39400588 Data size: 5347397120 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (_col1 > (UDFToDouble(2) * _col2)) (type:
> boolean)
> Statistics: Num rows: 13133529 Data size: 1782465661 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col0 (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 13133529 Data size: 1782465661
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col4} {_col5} {_col7} {_col9} {_col10}
> {_col11} {_col16} {_col17} {_col21} {_col23} {_col25} {_col27} {_col28}
> 1
> keys:
> 0 _col1 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col4, _col5, _col7, _col9,
> _col10, _col11, _col16, _col17, _col21, _col23, _col25, _col27, _col28
> input vertices:
> 0 Map 4
> Statistics: Num rows: 16812348 Data size: 1324232448
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col10 (type: float),
> _col11 (type: float), _col16 (type: int), _col17 (type: int), _col21 (type:
> int), _col23 (type: int), _col25 (type: int), _col27 (type: string), _col28
> (type: string), _col4 (type: int), _col5 (type: int), _col7 (type: int),
> _col9 (type: float)
> outputColumnNames: _col1, _col10, _col11, _col16,
> _col17, _col21, _col23, _col25, _col27, _col28, _col4, _col5, _col7, _col9
> Statistics: Num rows: 16812348 Data size: 1324232448
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1}
> 1 {_col1} {_col5} {_col7} {_col9} {_col10}
> {_col11} {_col16} {_col17} {_col21} {_col23} {_col25} {_col27} {_col28}
> keys:
> 0 _col0 (type: int)
> 1 _col4 (type: int)
> outputColumnNames: _col1, _col3, _col7, _col9,
> _col11, _col12, _col13, _col18, _col19, _col23, _col25, _col27, _col29, _col30
> input vertices:
> 0 Map 24
> Statistics: Num rows: 18493584 Data size:
> 1456655744 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col11 (type:
> float), _col12 (type: float), _col13 (type: float), _col18 (type: int),
> _col19 (type: int), _col23 (type: int), _col25 (type: int), _col27 (type:
> int), _col29 (type: string), _col3 (type: int), _col30 (type: string), _col7
> (type: int), _col9 (type: int)
> outputColumnNames: _col1, _col11, _col12, _col13,
> _col18, _col19, _col23, _col25, _col27, _col29, _col3, _col30, _col7, _col9
> Statistics: Num rows: 18493584 Data size:
> 1456655744 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1}
> 1 {_col1} {_col3} {_col7} {_col9} {_col11}
> {_col12} {_col13} {_col19} {_col23} {_col25} {_col27} {_col29} {_col30}
> keys:
> 0 _col0 (type: int)
> 1 _col18 (type: int)
> outputColumnNames: _col1, _col3, _col5, _col9,
> _col11, _col13, _col14, _col15, _col21, _col25, _col27, _col29, _col31, _col32
> input vertices:
> 0 Map 27
> Statistics: Num rows: 20342942 Data size:
> 1602321408 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col3} {_col9} {_col11} {_col13}
> {_col14} {_col15} {_col21} {_col25} {_col27} {_col29} {_col31} {_col32}
> 1 {_col0} {_col3}
> keys:
> 0 _col5 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col3, _col9,
> _col11, _col13, _col14, _col15, _col21, _col25, _col27, _col29, _col31,
> _col32, _col38, _col41
> input vertices:
> 1 Map 39
> Statistics: Num rows: 22377236 Data size:
> 1762553600 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col11
> (type: int), _col13 (type: float), _col14 (type: float), _col15 (type:
> float), _col21 (type: int), _col25 (type: int), _col27 (type: int), _col29
> (type: int), _col3 (type: int), _col31 (type: string), _col32 (type: string),
> _col38 (type: int), _col41 (type: string), _col9 (type: int)
> outputColumnNames: _col1, _col11, _col13,
> _col14, _col15, _col21, _col25, _col27, _col29, _col3, _col31, _col32,
> _col38, _col41, _col9
> Statistics: Num rows: 22377236 Data size:
> 1762553600 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0
> 1 {_col1} {_col9} {_col11} {_col13}
> {_col14} {_col15} {_col21} {_col25} {_col27} {_col29} {_col31} {_col32}
> {_col38} {_col41}
> keys:
> 0 _col0 (type: int)
> 1 _col3 (type: int)
> outputColumnNames: _col2, _col10, _col12,
> _col14, _col15, _col16, _col22, _col26, _col28, _col30, _col32, _col33,
> _col39, _col42
> input vertices:
> 0 Map 22
> Statistics: Num rows: 24614960 Data size:
> 1938808960 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col10 (type: int), _col12
> (type: int), _col14 (type: float), _col15 (type: float), _col16 (type:
> float), _col2 (type: int), _col22 (type: int), _col26 (type: int), _col28
> (type: int), _col30 (type: int), _col32 (type: string), _col33 (type:
> string), _col39 (type: int), _col42 (type: string)
> outputColumnNames: _col10, _col12,
> _col14, _col15, _col16, _col2, _col22, _col26, _col28, _col30, _col32,
> _col33, _col39, _col42
> Statistics: Num rows: 24614960 Data
> size: 1938808960 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0
> 1 {_col10} {_col12} {_col14}
> {_col15} {_col16} {_col22} {_col26} {_col28} {_col30} {_col32} {_col33}
> {_col39} {_col42}
> keys:
> 0 _col0 (type: int)
> 1 _col2 (type: int)
> outputColumnNames: _col11, _col13,
> _col15, _col16, _col17, _col23, _col27, _col29, _col31, _col33, _col34,
> _col40, _col43
> input vertices:
> 0 Map 30
> Statistics: Num rows: 27076456 Data
> size: 2132689920 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col11 (type: int),
> _col13 (type: int), _col15 (type: float), _col16 (type: float), _col17 (type:
> float), _col23 (type: int), _col27 (type: int), _col29 (type: int), _col31
> (type: int), _col33 (type: string), _col34 (type: string), _col40 (type:
> int), _col43 (type: string)
> outputColumnNames: _col11, _col13,
> _col15, _col16, _col17, _col23, _col27, _col29, _col31, _col33, _col34,
> _col40, _col43
> Statistics: Num rows: 27076456 Data
> size: 2132689920 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col3}
> {_col4}
> 1 {_col13} {_col15} {_col16}
> {_col17} {_col23} {_col27} {_col29} {_col31} {_col33} {_col34} {_col40}
> {_col43}
> keys:
> 0 _col0 (type: int)
> 1 _col11 (type: int)
> outputColumnNames: _col1, _col2,
> _col3, _col4, _col18, _col20, _col21, _col22, _col28, _col32, _col34, _col36,
> _col38, _col39, _col45, _col48
> input vertices:
> 0 Map 32
> Statistics: Num rows: 29784102
> Data size: 2345958912 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type:
> string), _col18 (type: int), _col2 (type: string), _col20 (type: float),
> _col21 (type: float), _col22 (type: float), _col28 (type: int), _col3 (type:
> string), _col32 (type: int), _col34 (type: int), _col36 (type: int), _col38
> (type: string), _col39 (type: string), _col4 (type: string), _col45 (type:
> int), _col48 (type: string)
> outputColumnNames: _col1,
> _col18, _col2, _col20, _col21, _col22, _col28, _col3, _col32, _col34, _col36,
> _col38, _col39, _col4, _col45, _col48
> Statistics: Num rows: 29784102
> Data size: 2345958912 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col3}
> {_col4}
> 1 {_col1} {_col2} {_col3}
> {_col4} {_col18} {_col20} {_col21} {_col22} {_col32} {_col34} {_col36}
> {_col38} {_col39} {_col45} {_col48}
> keys:
> 0 _col0 (type: int)
> 1 _col28 (type: int)
> outputColumnNames: _col1,
> _col2, _col3, _col4, _col6, _col7, _col8, _col9, _col23, _col25, _col26,
> _col27, _col37, _col39, _col41, _col43, _col44, _col50, _col53
> input vertices:
> 0 Map 7
> Statistics: Num rows:
> 32762512 Data size: 2580554752 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type:
> string), _col2 (type: string), _col23 (type: int), _col25 (type: float),
> _col26 (type: float), _col27 (type: float), _col3 (type: string), _col37
> (type: int), _col39 (type: int), _col4 (type: string), _col41 (type: int),
> _col43 (type: string), _col44 (type: string), _col50 (type: int), _col53
> (type: string), _col6 (type: string), _col7 (type: string), _col8 (type:
> string), _col9 (type: string)
> outputColumnNames: _col1,
> _col2, _col23, _col25, _col26, _col27, _col3, _col37, _col39, _col4, _col41,
> _col43, _col44, _col50, _col53, _col6, _col7, _col8, _col9
> Statistics: Num rows:
> 32762512 Data size: 2580554752 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0
> 1 {_col1} {_col2}
> {_col3} {_col4} {_col6} {_col7} {_col8} {_col9} {_col25} {_col26} {_col27}
> {_col37} {_col39} {_col41} {_col43} {_col44} {_col50} {_col53}
> keys:
> 0 _col0 (type: int)
> 1 _col23 (type: int)
> outputColumnNames: _col2,
> _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col26, _col27, _col28,
> _col38, _col40, _col42, _col44, _col45, _col51, _col54
> input vertices:
> 0 Map 26
> Statistics: Num rows:
> 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col54
> (type: string), _col51 (type: int), _col44 (type: string), _col45 (type:
> string), _col7 (type: string), _col8 (type: string), _col9 (type: string),
> _col10 (type: string), _col2 (type: string), _col3 (type: string), _col4
> (type: string), _col5 (type: string), _col38 (type: int), _col40 (type: int),
> _col42 (type: int), _col26 (type: float), _col27 (type: float), _col28 (type:
> float)
> outputColumnNames:
> _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10,
> _col11, _col12, _col13, _col14, _col15, _col16, _col17
> Statistics: Num rows:
> 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> Group By Operator
> aggregations:
> count(), sum(_col15), sum(_col16), sum(_col17)
> keys: _col0 (type:
> string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4
> (type: string), _col5 (type: string), _col6 (type: string), _col7 (type:
> string), _col8 (type: string), _col9 (type: string), _col10 (type: string),
> _col11 (type: string), _col12 (type: int), _col13 (type: int), _col14 (type:
> int)
> mode: hash
> outputColumnNames:
> _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10,
> _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18
> Statistics: Num rows:
> 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions:
> _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type:
> string), _col4 (type: string), _col5 (type: string), _col6 (type: string),
> _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10
> (type: string), _col11 (type: string), _col12 (type: int), _col13 (type:
> int), _col14 (type: int)
> sort order:
> +++++++++++++++
> Map-reduce
> partition columns: _col0 (type: string), _col1 (type: int), _col2 (type:
> string), _col3 (type: string), _col4 (type: string), _col5 (type: string),
> _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9
> (type: string), _col10 (type: string), _col11 (type: string), _col12 (type:
> int), _col13 (type: int), _col14 (type: int)
> Statistics: Num
> rows: 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> value expressions:
> _col15 (type: bigint), _col16 (type: double), _col17 (type: double), _col18
> (type: double)
> Reducer 12
> Reduce Operator Tree:
> Group By Operator
> aggregations: count(VALUE._col0), sum(VALUE._col1),
> sum(VALUE._col2), sum(VALUE._col3)
> keys: KEY._col0 (type: string), KEY._col1 (type: int),
> KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string),
> KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string),
> KEY._col8 (type: string), KEY._col9 (type: string), KEY._col10 (type:
> string), KEY._col11 (type: string), KEY._col12 (type: int), KEY._col13 (type:
> int), KEY._col14 (type: int)
> mode: mergepartial
> outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15,
> _col16, _col17, _col18
> Statistics: Num rows: 18019382 Data size: 1419305088 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col2 (type: string), _col3
> (type: string), _col12 (type: int), _col15 (type: bigint), _col16 (type:
> double), _col17 (type: double), _col18 (type: double)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5, _col6, _col7
> Statistics: Num rows: 18019382 Data size: 1419305088 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: int), _col1 (type: string),
> _col2 (type: string)
> sort order: +++
> Map-reduce partition columns: _col0 (type: int), _col1
> (type: string), _col2 (type: string)
> Statistics: Num rows: 18019382 Data size: 1419305088
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col3 (type: int), _col4 (type:
> bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double)
> Execution mode: vectorized
> Reducer 13
> Reduce Operator Tree:
> Merge Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {VALUE._col0} {KEY.reducesinkkey1} {KEY.reducesinkkey2}
> {VALUE._col1} {VALUE._col2} {VALUE._col3} {VALUE._col4} {VALUE._col5}
> {VALUE._col6} {VALUE._col7} {VALUE._col8} {VALUE._col9} {VALUE._col10}
> {VALUE._col11} {VALUE._col12} {VALUE._col13}
> 1 {VALUE._col0} {VALUE._col1} {VALUE._col2} {VALUE._col3}
> {VALUE._col4}
> outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6,
> _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16,
> _col20, _col21, _col22, _col23, _col24
> Statistics: Num rows: 19821320 Data size: 1561235584 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (_col21 <= _col13) (type: boolean)
> Statistics: Num rows: 6607106 Data size: 520411808 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col0 (type: string), _col2 (type: string),
> _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6
> (type: string), _col7 (type: string), _col8 (type: string), _col9 (type:
> string), _col10 (type: string), _col11 (type: string), _col12 (type: int),
> _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16
> (type: double), _col22 (type: double), _col23 (type: double), _col24 (type:
> double), _col20 (type: int), _col21 (type: bigint)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14,
> _col15, _col16, _col17, _col18, _col19, _col20
> Statistics: Num rows: 6607106 Data size: 520411808 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col0 (type: string), _col1 (type:
> string), _col20 (type: bigint)
> sort order: +++
> Statistics: Num rows: 6607106 Data size: 520411808
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col2 (type: string), _col3 (type:
> string), _col4 (type: string), _col5 (type: string), _col6 (type: string),
> _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10
> (type: string), _col11 (type: int), _col12 (type: bigint), _col13 (type:
> double), _col14 (type: double), _col15 (type: double), _col16 (type: double),
> _col17 (type: double), _col18 (type: double), _col19 (type: int)
> Reducer 14
> Reduce Operator Tree:
> Select Operator
> expressions: KEY.reducesinkkey0 (type: string),
> KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), VALUE._col1
> (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string),
> VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type:
> string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9
> (type: int), VALUE._col10 (type: bigint), VALUE._col11 (type: double),
> VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type:
> double), VALUE._col15 (type: double), VALUE._col16 (type: double),
> VALUE._col17 (type: int), KEY.reducesinkkey2 (type: bigint)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15,
> _col16, _col17, _col18, _col19, _col20
> Statistics: Num rows: 6607106 Data size: 520411808 Basic
> stats: COMPLETE Column stats: NONE
> File Output Operator
> compressed: false
> Statistics: Num rows: 6607106 Data size: 520411808 Basic
> stats: COMPLETE Column stats: NONE
> 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
> Execution mode: vectorized
> Reducer 20
> Reduce Operator Tree:
> Group By Operator
> aggregations: sum(VALUE._col0), sum(VALUE._col1)
> keys: KEY._col0 (type: int)
> mode: mergepartial
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 39400588 Data size: 5347397120 Basic
> stats: COMPLETE Column stats: NONE
> Filter Operator
> predicate: (_col1 > (UDFToDouble(2) * _col2)) (type:
> boolean)
> Statistics: Num rows: 13133529 Data size: 1782465661 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col0 (type: int)
> outputColumnNames: _col0
> Statistics: Num rows: 13133529 Data size: 1782465661
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col4} {_col5} {_col7} {_col9} {_col10}
> {_col11} {_col16} {_col17} {_col21} {_col23} {_col25} {_col27} {_col28}
> 1
> keys:
> 0 _col1 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col4, _col5, _col7, _col9,
> _col10, _col11, _col16, _col17, _col21, _col23, _col25, _col27, _col28
> input vertices:
> 0 Map 33
> Statistics: Num rows: 16812348 Data size: 1324232448
> Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col10 (type: float),
> _col11 (type: float), _col16 (type: int), _col17 (type: int), _col21 (type:
> int), _col23 (type: int), _col25 (type: int), _col27 (type: string), _col28
> (type: string), _col4 (type: int), _col5 (type: int), _col7 (type: int),
> _col9 (type: float)
> outputColumnNames: _col1, _col10, _col11, _col16,
> _col17, _col21, _col23, _col25, _col27, _col28, _col4, _col5, _col7, _col9
> Statistics: Num rows: 16812348 Data size: 1324232448
> Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1}
> 1 {_col1} {_col5} {_col7} {_col9} {_col10}
> {_col11} {_col16} {_col17} {_col21} {_col23} {_col25} {_col27} {_col28}
> keys:
> 0 _col0 (type: int)
> 1 _col4 (type: int)
> outputColumnNames: _col1, _col3, _col7, _col9,
> _col11, _col12, _col13, _col18, _col19, _col23, _col25, _col27, _col29, _col30
> input vertices:
> 0 Map 9
> Statistics: Num rows: 18493584 Data size:
> 1456655744 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col11 (type:
> float), _col12 (type: float), _col13 (type: float), _col18 (type: int),
> _col19 (type: int), _col23 (type: int), _col25 (type: int), _col27 (type:
> int), _col29 (type: string), _col3 (type: int), _col30 (type: string), _col7
> (type: int), _col9 (type: int)
> outputColumnNames: _col1, _col11, _col12, _col13,
> _col18, _col19, _col23, _col25, _col27, _col29, _col3, _col30, _col7, _col9
> Statistics: Num rows: 18493584 Data size:
> 1456655744 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1}
> 1 {_col1} {_col3} {_col7} {_col9} {_col11}
> {_col12} {_col13} {_col19} {_col23} {_col25} {_col27} {_col29} {_col30}
> keys:
> 0 _col0 (type: int)
> 1 _col18 (type: int)
> outputColumnNames: _col1, _col3, _col5, _col9,
> _col11, _col13, _col14, _col15, _col21, _col25, _col27, _col29, _col31, _col32
> input vertices:
> 0 Map 44
> Statistics: Num rows: 20342942 Data size:
> 1602321408 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col3} {_col9} {_col11} {_col13}
> {_col14} {_col15} {_col21} {_col25} {_col27} {_col29} {_col31} {_col32}
> 1 {_col0} {_col3}
> keys:
> 0 _col5 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col1, _col3, _col9,
> _col11, _col13, _col14, _col15, _col21, _col25, _col27, _col29, _col31,
> _col32, _col38, _col41
> input vertices:
> 1 Map 29
> Statistics: Num rows: 22377236 Data size:
> 1762553600 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type: int), _col11
> (type: int), _col13 (type: float), _col14 (type: float), _col15 (type:
> float), _col21 (type: int), _col25 (type: int), _col27 (type: int), _col29
> (type: int), _col3 (type: int), _col31 (type: string), _col32 (type: string),
> _col38 (type: int), _col41 (type: string), _col9 (type: int)
> outputColumnNames: _col1, _col11, _col13,
> _col14, _col15, _col21, _col25, _col27, _col29, _col3, _col31, _col32,
> _col38, _col41, _col9
> Statistics: Num rows: 22377236 Data size:
> 1762553600 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0
> 1 {_col1} {_col9} {_col11} {_col13}
> {_col14} {_col15} {_col21} {_col25} {_col27} {_col29} {_col31} {_col32}
> {_col38} {_col41}
> keys:
> 0 _col0 (type: int)
> 1 _col3 (type: int)
> outputColumnNames: _col2, _col10, _col12,
> _col14, _col15, _col16, _col22, _col26, _col28, _col30, _col32, _col33,
> _col39, _col42
> input vertices:
> 0 Map 37
> Statistics: Num rows: 24614960 Data size:
> 1938808960 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col10 (type: int), _col12
> (type: int), _col14 (type: float), _col15 (type: float), _col16 (type:
> float), _col2 (type: int), _col22 (type: int), _col26 (type: int), _col28
> (type: int), _col30 (type: int), _col32 (type: string), _col33 (type:
> string), _col39 (type: int), _col42 (type: string)
> outputColumnNames: _col10, _col12,
> _col14, _col15, _col16, _col2, _col22, _col26, _col28, _col30, _col32,
> _col33, _col39, _col42
> Statistics: Num rows: 24614960 Data
> size: 1938808960 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0
> 1 {_col10} {_col12} {_col14}
> {_col15} {_col16} {_col22} {_col26} {_col28} {_col30} {_col32} {_col33}
> {_col39} {_col42}
> keys:
> 0 _col0 (type: int)
> 1 _col2 (type: int)
> outputColumnNames: _col11, _col13,
> _col15, _col16, _col17, _col23, _col27, _col29, _col31, _col33, _col34,
> _col40, _col43
> input vertices:
> 0 Map 17
> Statistics: Num rows: 27076456 Data
> size: 2132689920 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col11 (type: int),
> _col13 (type: int), _col15 (type: float), _col16 (type: float), _col17 (type:
> float), _col23 (type: int), _col27 (type: int), _col29 (type: int), _col31
> (type: int), _col33 (type: string), _col34 (type: string), _col40 (type:
> int), _col43 (type: string)
> outputColumnNames: _col11, _col13,
> _col15, _col16, _col17, _col23, _col27, _col29, _col31, _col33, _col34,
> _col40, _col43
> Statistics: Num rows: 27076456 Data
> size: 2132689920 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col3}
> {_col4}
> 1 {_col13} {_col15} {_col16}
> {_col17} {_col23} {_col27} {_col29} {_col31} {_col33} {_col34} {_col40}
> {_col43}
> keys:
> 0 _col0 (type: int)
> 1 _col11 (type: int)
> outputColumnNames: _col1, _col2,
> _col3, _col4, _col18, _col20, _col21, _col22, _col28, _col32, _col34, _col36,
> _col38, _col39, _col45, _col48
> input vertices:
> 0 Map 43
> Statistics: Num rows: 29784102
> Data size: 2345958912 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type:
> string), _col18 (type: int), _col2 (type: string), _col20 (type: float),
> _col21 (type: float), _col22 (type: float), _col28 (type: int), _col3 (type:
> string), _col32 (type: int), _col34 (type: int), _col36 (type: int), _col38
> (type: string), _col39 (type: string), _col4 (type: string), _col45 (type:
> int), _col48 (type: string)
> outputColumnNames: _col1,
> _col18, _col2, _col20, _col21, _col22, _col28, _col3, _col32, _col34, _col36,
> _col38, _col39, _col4, _col45, _col48
> Statistics: Num rows: 29784102
> Data size: 2345958912 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0 {_col1} {_col2} {_col3}
> {_col4}
> 1 {_col1} {_col2} {_col3}
> {_col4} {_col18} {_col20} {_col21} {_col22} {_col32} {_col34} {_col36}
> {_col38} {_col39} {_col45} {_col48}
> keys:
> 0 _col0 (type: int)
> 1 _col28 (type: int)
> outputColumnNames: _col1,
> _col2, _col3, _col4, _col6, _col7, _col8, _col9, _col23, _col25, _col26,
> _col27, _col37, _col39, _col41, _col43, _col44, _col50, _col53
> input vertices:
> 0 Map 28
> Statistics: Num rows:
> 32762512 Data size: 2580554752 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col1 (type:
> string), _col2 (type: string), _col23 (type: int), _col25 (type: float),
> _col26 (type: float), _col27 (type: float), _col3 (type: string), _col37
> (type: int), _col39 (type: int), _col4 (type: string), _col41 (type: int),
> _col43 (type: string), _col44 (type: string), _col50 (type: int), _col53
> (type: string), _col6 (type: string), _col7 (type: string), _col8 (type:
> string), _col9 (type: string)
> outputColumnNames: _col1,
> _col2, _col23, _col25, _col26, _col27, _col3, _col37, _col39, _col4, _col41,
> _col43, _col44, _col50, _col53, _col6, _col7, _col8, _col9
> Statistics: Num rows:
> 32762512 Data size: 2580554752 Basic stats: COMPLETE Column stats: NONE
> Map Join Operator
> condition map:
> Inner Join 0 to 1
> condition expressions:
> 0
> 1 {_col1} {_col2}
> {_col3} {_col4} {_col6} {_col7} {_col8} {_col9} {_col25} {_col26} {_col27}
> {_col37} {_col39} {_col41} {_col43} {_col44} {_col50} {_col53}
> keys:
> 0 _col0 (type: int)
> 1 _col23 (type: int)
> outputColumnNames: _col2,
> _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col26, _col27, _col28,
> _col38, _col40, _col42, _col44, _col45, _col51, _col54
> input vertices:
> 0 Map 34
> Statistics: Num rows:
> 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col54
> (type: string), _col51 (type: int), _col44 (type: string), _col45 (type:
> string), _col7 (type: string), _col8 (type: string), _col9 (type: string),
> _col10 (type: string), _col2 (type: string), _col3 (type: string), _col4
> (type: string), _col5 (type: string), _col38 (type: int), _col40 (type: int),
> _col42 (type: int), _col26 (type: float), _col27 (type: float), _col28 (type:
> float)
> outputColumnNames:
> _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10,
> _col11, _col12, _col13, _col14, _col15, _col16, _col17
> Statistics: Num rows:
> 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> Group By Operator
> aggregations:
> count(), sum(_col15), sum(_col16), sum(_col17)
> keys: _col0 (type:
> string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4
> (type: string), _col5 (type: string), _col6 (type: string), _col7 (type:
> string), _col8 (type: string), _col9 (type: string), _col10 (type: string),
> _col11 (type: string), _col12 (type: int), _col13 (type: int), _col14 (type:
> int)
> mode: hash
> outputColumnNames:
> _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10,
> _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18
> Statistics: Num rows:
> 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions:
> _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type:
> string), _col4 (type: string), _col5 (type: string), _col6 (type: string),
> _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10
> (type: string), _col11 (type: string), _col12 (type: int), _col13 (type:
> int), _col14 (type: int)
> sort order:
> +++++++++++++++
> Map-reduce
> partition columns: _col0 (type: string), _col1 (type: int), _col2 (type:
> string), _col3 (type: string), _col4 (type: string), _col5 (type: string),
> _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9
> (type: string), _col10 (type: string), _col11 (type: string), _col12 (type:
> int), _col13 (type: int), _col14 (type: int)
> Statistics: Num
> rows: 36038764 Data size: 2838610176 Basic stats: COMPLETE Column stats: NONE
> value expressions:
> _col15 (type: bigint), _col16 (type: double), _col17 (type: double), _col18
> (type: double)
> Reducer 21
> Reduce Operator Tree:
> Group By Operator
> aggregations: count(VALUE._col0), sum(VALUE._col1),
> sum(VALUE._col2), sum(VALUE._col3)
> keys: KEY._col0 (type: string), KEY._col1 (type: int),
> KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string),
> KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string),
> KEY._col8 (type: string), KEY._col9 (type: string), KEY._col10 (type:
> string), KEY._col11 (type: string), KEY._col12 (type: int), KEY._col13 (type:
> int), KEY._col14 (type: int)
> mode: mergepartial
> outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5,
> _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15,
> _col16, _col17, _col18
> Statistics: Num rows: 18019382 Data size: 1419305088 Basic
> stats: COMPLETE Column stats: NONE
> Select Operator
> expressions: _col0 (type: string), _col1 (type: int), _col2
> (type: string), _col3 (type: string), _col4 (type: string), _col5 (type:
> string), _col6 (type: string), _col7 (type: string), _col8 (type: string),
> _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12
> (type: int), _col15 (type: bigint), _col16 (type: double), _col17 (type:
> double), _col18 (type: double)
> outputColumnNames: _col0, _col1, _col2, _col3, _col4,
> _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14,
> _col15, _col16
> Statistics: Num rows: 18019382 Data size: 1419305088 Basic
> stats: COMPLETE Column stats: NONE
> Reduce Output Operator
> key expressions: _col1 (type: int), _col2 (type: string),
> _col3 (type: string)
> sort order: +++
> Map-reduce partition columns: _col1 (type: int), _col2
> (type: string), _col3 (type: string)
> Statistics: Num rows: 18019382 Data size: 1419305088
> Basic stats: COMPLETE Column stats: NONE
> value expressions: _col0 (type: string), _col4 (type:
> string), _col5 (type: string), _col6 (type: string), _col7 (type: string),
> _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11
> (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type:
> double), _col15 (type: double), _col16 (type: double)
> Execution mode: vectorized
> Stage: Stage-0
> Fetch Operator
> limit: -1
> Processor Tree:
> ListSink
> {code}
> Query
> {code}
> select cs1.product_name ,cs1.store_name ,cs1.store_zip ,cs1.b_street_number
> ,cs1.b_streen_name ,cs1.b_city
> ,cs1.b_zip ,cs1.c_street_number ,cs1.c_street_name ,cs1.c_city
> ,cs1.c_zip ,cs1.syear ,cs1.cnt
> ,cs1.s1 ,cs1.s2 ,cs1.s3
> ,cs2.s1 ,cs2.s2 ,cs2.s3 ,cs2.syear ,cs2.cnt
> from
> (select i_product_name as product_name ,i_item_sk as item_sk ,s_store_name as
> store_name
> ,s_zip as store_zip ,ad1.ca_street_number as b_street_number
> ,ad1.ca_street_name as b_streen_name
> ,ad1.ca_city as b_city ,ad1.ca_zip as b_zip ,ad2.ca_street_number as
> c_street_number
> ,ad2.ca_street_name as c_street_name ,ad2.ca_city as c_city ,ad2.ca_zip
> as c_zip
> ,d1.d_year as syear ,d2.d_year as fsyear ,d3.d_year as s2year ,count(*)
> as cnt
> ,sum(ss_wholesale_cost) as s1 ,sum(ss_list_price) as s2
> ,sum(ss_coupon_amt) as s3
> FROM store_sales
> JOIN store_returns ON store_sales.ss_item_sk =
> store_returns.sr_item_sk and store_sales.ss_ticket_number =
> store_returns.sr_ticket_number
> JOIN customer ON store_sales.ss_customer_sk = customer.c_customer_sk
> JOIN date_dim d1 ON store_sales.ss_sold_date_sk = d1.d_date_sk
> JOIN date_dim d2 ON customer.c_first_sales_date_sk = d2.d_date_sk
> JOIN date_dim d3 ON customer.c_first_shipto_date_sk = d3.d_date_sk
> JOIN store ON store_sales.ss_store_sk = store.s_store_sk
> JOIN customer_demographics cd1 ON store_sales.ss_cdemo_sk=
> cd1.cd_demo_sk
> JOIN customer_demographics cd2 ON customer.c_current_cdemo_sk =
> cd2.cd_demo_sk
> JOIN promotion ON store_sales.ss_promo_sk = promotion.p_promo_sk
> JOIN household_demographics hd1 ON store_sales.ss_hdemo_sk =
> hd1.hd_demo_sk
> JOIN household_demographics hd2 ON customer.c_current_hdemo_sk =
> hd2.hd_demo_sk
> JOIN customer_address ad1 ON store_sales.ss_addr_sk =
> ad1.ca_address_sk
> JOIN customer_address ad2 ON customer.c_current_addr_sk =
> ad2.ca_address_sk
> JOIN income_band ib1 ON hd1.hd_income_band_sk = ib1.ib_income_band_sk
> JOIN income_band ib2 ON hd2.hd_income_band_sk = ib2.ib_income_band_sk
> JOIN item ON store_sales.ss_item_sk = item.i_item_sk
> JOIN
> (select cs_item_sk
> ,sum(cs_ext_list_price) as
> sale,sum(cr_refunded_cash+cr_reversed_charge+cr_store_credit) as refund
> from catalog_sales JOIN catalog_returns
> ON catalog_sales.cs_item_sk = catalog_returns.cr_item_sk
> and catalog_sales.cs_order_number = catalog_returns.cr_order_number
> group by cs_item_sk
> having
> sum(cs_ext_list_price)>2*sum(cr_refunded_cash+cr_reversed_charge+cr_store_credit))
> cs_ui
> ON store_sales.ss_item_sk = cs_ui.cs_item_sk
> WHERE
> cd1.cd_marital_status <> cd2.cd_marital_status and
> i_color in ('maroon','burnished','dim','steel','navajo','chocolate')
> and
> i_current_price between 35 and 35 + 10 and
> i_current_price between 35 + 1 and 35 + 15
> group by i_product_name ,i_item_sk ,s_store_name ,s_zip ,ad1.ca_street_number
> ,ad1.ca_street_name ,ad1.ca_city ,ad1.ca_zip ,ad2.ca_street_number
> ,ad2.ca_street_name ,ad2.ca_city ,ad2.ca_zip ,d1.d_year ,d2.d_year
> ,d3.d_year
> ) cs1
> JOIN
> (select i_product_name as product_name ,i_item_sk as item_sk ,s_store_name as
> store_name
> ,s_zip as store_zip ,ad1.ca_street_number as b_street_number
> ,ad1.ca_street_name as b_streen_name
> ,ad1.ca_city as b_city ,ad1.ca_zip as b_zip ,ad2.ca_street_number as
> c_street_number
> ,ad2.ca_street_name as c_street_name ,ad2.ca_city as c_city ,ad2.ca_zip
> as c_zip
> ,d1.d_year as syear ,d2.d_year as fsyear ,d3.d_year as s2year ,count(*)
> as cnt
> ,sum(ss_wholesale_cost) as s1 ,sum(ss_list_price) as s2
> ,sum(ss_coupon_amt) as s3
> FROM store_sales
> JOIN store_returns ON store_sales.ss_item_sk =
> store_returns.sr_item_sk and store_sales.ss_ticket_number =
> store_returns.sr_ticket_number
> JOIN customer ON store_sales.ss_customer_sk = customer.c_customer_sk
> JOIN date_dim d1 ON store_sales.ss_sold_date_sk = d1.d_date_sk
> JOIN date_dim d2 ON customer.c_first_sales_date_sk = d2.d_date_sk
> JOIN date_dim d3 ON customer.c_first_shipto_date_sk = d3.d_date_sk
> JOIN store ON store_sales.ss_store_sk = store.s_store_sk
> JOIN customer_demographics cd1 ON store_sales.ss_cdemo_sk=
> cd1.cd_demo_sk
> JOIN customer_demographics cd2 ON customer.c_current_cdemo_sk =
> cd2.cd_demo_sk
> JOIN promotion ON store_sales.ss_promo_sk = promotion.p_promo_sk
> JOIN household_demographics hd1 ON store_sales.ss_hdemo_sk =
> hd1.hd_demo_sk
> JOIN household_demographics hd2 ON customer.c_current_hdemo_sk =
> hd2.hd_demo_sk
> JOIN customer_address ad1 ON store_sales.ss_addr_sk =
> ad1.ca_address_sk
> JOIN customer_address ad2 ON customer.c_current_addr_sk =
> ad2.ca_address_sk
> JOIN income_band ib1 ON hd1.hd_income_band_sk = ib1.ib_income_band_sk
> JOIN income_band ib2 ON hd2.hd_income_band_sk = ib2.ib_income_band_sk
> JOIN item ON store_sales.ss_item_sk = item.i_item_sk
> JOIN
> (select cs_item_sk
> ,sum(cs_ext_list_price) as
> sale,sum(cr_refunded_cash+cr_reversed_charge+cr_store_credit) as refund
> from catalog_sales JOIN catalog_returns
> ON catalog_sales.cs_item_sk = catalog_returns.cr_item_sk
> and catalog_sales.cs_order_number = catalog_returns.cr_order_number
> group by cs_item_sk
> having
> sum(cs_ext_list_price)>2*sum(cr_refunded_cash+cr_reversed_charge+cr_store_credit))
> cs_ui
> ON store_sales.ss_item_sk = cs_ui.cs_item_sk
> WHERE
> cd1.cd_marital_status <> cd2.cd_marital_status and
> i_color in ('maroon','burnished','dim','steel','navajo','chocolate')
> and
> i_current_price between 35 and 35 + 10 and
> i_current_price between 35 + 1 and 35 + 15
> group by i_product_name ,i_item_sk ,s_store_name ,s_zip ,ad1.ca_street_number
> ,ad1.ca_street_name ,ad1.ca_city ,ad1.ca_zip ,ad2.ca_street_number
> ,ad2.ca_street_name ,ad2.ca_city ,ad2.ca_zip ,d1.d_year ,d2.d_year
> ,d3.d_year
> ) cs2
> ON cs1.item_sk=cs2.item_sk
> where
> cs1.syear = 2000 and
> cs2.syear = 2000 + 1 and
> cs2.cnt <= cs1.cnt and
> cs1.store_name = cs2.store_name and
> cs1.store_zip = cs2.store_zip
> order by cs1.product_name ,cs1.store_name ,cs2.cnt
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
