AnalyticDB for PostgreSQL では、分析クエリのパフォーマンス評価に使用可能な TPC-H サンプルデータセットを提供しています。
データセットの概要
| プロパティ | 値 |
|---|---|
| データベース名 | adb_sampledata_tpch |
| スキーマ名 | public |
| テーブル | PART、PARTSUPP、CUSTOMER、ORDERS、LINEITEM、NATION、REGION、SUPPLIER |
このデータセットは、TPC-H ベンチマーク仕様に従い、注文、明細行、部品、サプライヤー、顧客、国、地域を含む卸売業者ビジネスをモデル化しています。完全なスキーマ定義については、「TPC-H 公式ウェブサイト」をご参照ください。
クエリ例
以下のクエリは TPC-H ベンチマークから引用したものです。詳細については、「TPC-H 公式ウェブサイト」をご参照ください。
全 22 個のクエリは、adb_sampledata_tpch データベース内のテーブルを使用します。各クエリは、卸売業者データセットに関する特定のビジネス課題に対応しています。
Q1：価格集計レポート
指定された日付時点における請求済み、出荷済み、返品済みの明細行を、返品フラグおよび明細ステータスごとに集計してレポートします。
set laser.enable = on;
select
l_returnflag,
l_linestatus,
sum(l_quantity) as sum_qty,
sum(l_extendedprice) as sum_base_price,
sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
avg(l_quantity) as avg_qty,
avg(l_extendedprice) as avg_price,
avg(l_discount) as avg_disc,
count(*) as count_order
from
lineitem
where
l_shipdate <= date '1998-12-01' - interval '93 day'
group by
l_returnflag,
l_linestatus
order by
l_returnflag,
l_linestatus;Q2：最低コストサプライヤー
指定されたリージョン内で、特定の部品タイプについて最も低コストで供給可能なサプライヤーを検索します。
select
s_acctbal,
s_name,
n_name,
p_partkey,
p_mfgr,
s_address,
s_phone,
s_comment
from
part,
supplier,
partsupp,
nation,
region
where
p_partkey = ps_partkey
and s_suppkey = ps_suppkey
and p_size = 23
and p_type like '%STEEL'
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'EUROPE'
and ps_supplycost = (
select
min(ps_supplycost)
from
partsupp,
supplier,
nation,
region
where
p_partkey = ps_partkey
and s_suppkey = ps_suppkey
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'EUROPE'
)
order by
s_acctbal desc,
n_name,
s_name,
p_partkey
limit 100;Q3：出荷優先度
指定された日付までに未出荷であり、かつ収益が最も高い注文を上位から特定します。
select
l_orderkey,
sum(l_extendedprice * (1 - l_discount)) as revenue,
o_orderdate,
o_shippriority
from
customer,
orders,
lineitem
where
c_mktsegment = 'MACHINERY'
and c_custkey = o_custkey
and l_orderkey = o_orderkey
and o_orderdate < date '1995-03-24'
and l_shipdate > date '1995-03-24'
group by
l_orderkey,
o_orderdate,
o_shippriority
order by
revenue desc,
o_orderdate
limit 10;Q4：注文優先度の確認
注文の優先度別件数をカウントし、注文登録用の優先度システムが適切に機能しているかを評価します。
select
o_orderpriority,
count(*) as order_count
from
orders
where
o_orderdate >= date '1996-08-01'
and o_orderdate < date '1996-08-01' + interval '3' month
and exists (
select
*
from
lineitem
where
l_orderkey = o_orderkey
and l_commitdate < l_receiptdate
)
group by
o_orderpriority
order by
o_orderpriority;Q5：ローカルサプライヤーの売上高
指定されたリージョンおよび年度内における、ローカルサプライヤーからの注文に起因する売上高を測定します。
select
n_name,
sum(l_extendedprice * (1 - l_discount)) as revenue
from
customer,
orders,
lineitem,
supplier,
nation,
region
where
c_custkey = o_custkey
and l_orderkey = o_orderkey
and l_suppkey = s_suppkey
and c_nationkey = s_nationkey
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'MIDDLE EAST'
and o_orderdate >= date '1994-01-01'
and o_orderdate < date '1994-01-01' + interval '1' year
group by
n_name
order by
revenue desc;Q6：収益変動の予測
指定された年度において、特定の割引を撤廃した場合の収益への影響を推定します。
select
sum(l_extendedprice * l_discount) as revenue
from
lineitem
where
l_shipdate >= date '1994-01-01'
and l_shipdate < date '1994-01-01' + interval '1' year
and l_discount between 0.06 - 0.01 and 0.06 + 0.01
and l_quantity < 24;Q7: 大量出荷
2 年間の期間において、2 つの国間の出荷量を算出します。
select
supp_nation,
cust_nation,
l_year,
sum(volume) as revenue
from
(
select
n1.n_name as supp_nation,
n2.n_name as cust_nation,
extract(year from l_shipdate) as l_year,
l_extendedprice * (1 - l_discount) as volume
from
supplier,
lineitem,
orders,
customer,
nation n1,
nation n2
where
s_suppkey = l_suppkey
and o_orderkey = l_orderkey
and c_custkey = o_custkey
and s_nationkey = n1.n_nationkey
and c_nationkey = n2.n_nationkey
and (
(n1.n_name = 'JORDAN' and n2.n_name = 'INDONESIA')
or (n1.n_name = 'INDONESIA' and n2.n_name = 'JORDAN')
)
and l_shipdate between date '1995-01-01' and date '1996-12-31'
) as shipping
group by
supp_nation,
cust_nation,
l_year
order by
supp_nation,
cust_nation,
l_year;Q8：国内市場シェア
指定されたリージョンにおけるサプライヤーの所属国が、2 年間にわたり市場シェアをどのように変化させたかを判定します。
select
o_year,
sum(case
when nation = 'INDONESIA' then volume
else 0
end) / sum(volume) as mkt_share
from
(
select
extract(year from o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) as volume,
n2.n_name as nation
from
part,
supplier,
lineitem,
orders,
customer,
nation n1,
nation n2,
region
where
p_partkey = l_partkey
and s_suppkey = l_suppkey
and l_orderkey = o_orderkey
and o_custkey = c_custkey
and c_nationkey = n1.n_nationkey
and n1.n_regionkey = r_regionkey
and r_name = 'ASIA'
and s_nationkey = n2.n_nationkey
and o_orderdate between date '1995-01-01' and date '1996-12-31'
and p_type = 'STANDARD BRUSHED BRASS'
) as all_nations
group by
o_year
order by
o_year;Q9：製品タイプ別の利益測定
特定の製品名パターンを含む注文から生じる、各国および各年度の利益をレポートします。
select
nation,
o_year,
sum(amount) as sum_profit
from
(
select
n_name as nation,
extract(year from o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity as amount
from
part,
supplier,
lineitem,
partsupp,
orders,
nation
where
s_suppkey = l_suppkey
and ps_suppkey = l_suppkey
and ps_partkey = l_partkey
and p_partkey = l_partkey
and o_orderkey = l_orderkey
and s_nationkey = n_nationkey
and p_name like '%chartreuse%'
) as profit
group by
nation,
o_year
order by
nation,
o_year desc;Q10：返品アイテムの報告
指定された四半期にアイテムを返品した顧客を、損失収益額の大きい順に特定します。
select
c_custkey,
c_name,
sum(l_extendedprice * (1 - l_discount)) as revenue,
c_acctbal,
n_name,
c_address,
c_phone,
c_comment
from
customer,
orders,
lineitem,
nation
where
c_custkey = o_custkey
and l_orderkey = o_orderkey
and o_orderdate >= date '1994-08-01'
and o_orderdate < date '1994-08-01' + interval '3' month
and l_returnflag = 'R'
and c_nationkey = n_nationkey
group by
c_custkey,
c_name,
c_acctbal,
c_phone,
n_name,
c_address,
c_comment
order by
revenue desc
limit 20;Q11：重要在庫の特定
指定された国において、総在庫価値に占める割合が顕著な部品を検索します。
select
ps_partkey,
sum(ps_supplycost * ps_availqty) as value
from
partsupp,
supplier,
nation
where
ps_suppkey = s_suppkey
and s_nationkey = n_nationkey
and n_name = 'INDONESIA'
group by
ps_partkey having
sum(ps_supplycost * ps_availqty) > (
select
sum(ps_supplycost * ps_availqty) * 0.0001000000
from
partsupp,
supplier,
nation
where
ps_suppkey = s_suppkey
and s_nationkey = n_nationkey
and n_name = 'INDONESIA'
)
order by
value desc;Q12：出荷モードと注文優先度
緊急および高優先度の注文が、指定された出荷モードで所定の期日までに到着しているかを評価します。
select
l_shipmode,
sum(case
when o_orderpriority = '1-URGENT'
or o_orderpriority = '2-HIGH'
then 1
else 0
end) as high_line_count,
sum(case
when o_orderpriority <> '1-URGENT'
and o_orderpriority <> '2-HIGH'
then 1
else 0
end) as low_line_count
from
orders,
lineitem
where
o_orderkey = l_orderkey
and l_shipmode in ('REG AIR', 'TRUCK')
and l_commitdate < l_receiptdate
and l_shipdate < l_commitdate
and l_receiptdate >= date '1994-01-01'
and l_receiptdate < date '1994-01-01' + interval '1' year
group by
l_shipmode
order by
l_shipmode;Q13：顧客分布
特別な注文コメントを除き、顧客が発注した注文件数ごとにカウントします。
select
c_count,
count(*) as custdist
from
(
select
c_custkey,
count(o_orderkey)
from
customer left outer join orders on
c_custkey = o_custkey
and o_comment not like '%pending%requests%'
group by
c_custkey
) as c_orders (c_custkey, c_count)
group by
c_count
order by
custdist desc,
c_count desc;Q14：プロモーション効果
指定された月に出荷されたプロモーション対象部品による収益の割合を算出します。
select
100.00 * sum(case
when p_type like 'PROMO%'
then l_extendedprice * (1 - l_discount)
else 0
end) / sum(l_extendedprice * (1 - l_discount)) as promo_revenue
from
lineitem,
part
where
l_partkey = p_partkey
and l_shipdate >= date '1994-11-01'
and l_shipdate < date '1994-11-01' + interval '1' month;Q15：トップサプライヤー
指定された四半期において、最も高い収益をもたらしたサプライヤーを特定します。
select
s_suppkey,
s_name,
s_address,
s_phone,
total_revenue
from
supplier,
revenue0
where
s_suppkey = supplier_no
and total_revenue = (
select
max(total_revenue)
from
revenue0
)
order by
s_suppkey;Q16：部品／サプライヤー関係
顧客からの苦情を報告したサプライヤーを除外し、特定の部品サイズおよびタイプごとのサプライヤー数をカウントします。
select
p_brand,
p_type,
p_size,
count(distinct ps_suppkey) as supplier_cnt
from
partsupp,
part
where
p_partkey = ps_partkey
and p_brand <> 'Brand#44'
and p_type not like 'SMALL BURNISHED%'
and p_size in (36, 27, 34, 45, 11, 6, 25, 16)
and ps_suppkey not in (
select
s_suppkey
from
supplier
where
s_comment like '%Customer%Complaints%'
)
group by
p_brand,
p_type,
p_size
order by
supplier_cnt desc,
p_brand,
p_type,
p_size;Q17：小数量注文の収益
特定のブランドおよびコンテナについて、小数量注文による年間平均収益損失を推定します。
select
sum(l_extendedprice) / 7.0 as avg_yearly
from
lineitem,
part
where
p_partkey = l_partkey
and p_brand = 'Brand#42'
and p_container = 'JUMBO PACK'
and l_quantity < (
select
0.2 * avg(l_quantity)
from
lineitem
where
l_partkey = p_partkey
);Q18：大量注文顧客
明細行の数量合計が指定されたしきい値を超える注文を発注した顧客を検索します。
select
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice,
sum(l_quantity)
from
customer,
orders,
lineitem
where
o_orderkey in (
select
l_orderkey
from
lineitem
group by
l_orderkey having
sum(l_quantity) > 312
)
and c_custkey = o_custkey
and o_orderkey = l_orderkey
group by
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice
order by
o_totalprice desc,
o_orderdate
limit 100;Q19：割引適用収益
特定のブランド、コンテナ、数量条件を満たす航空便出荷アイテムから得られる収益を算出します。
select
sum(l_extendedprice* (1 - l_discount)) as revenue
from
lineitem,
part
where
(
p_partkey = l_partkey
and p_brand = 'Brand#43'
and p_container in ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG')
and l_quantity >= 5 and l_quantity <= 5 + 10
and p_size between 1 and 5
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
or
(
p_partkey = l_partkey
and p_brand = 'Brand#45'
and p_container in ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK')
and l_quantity >= 12 and l_quantity <= 12 + 10
and p_size between 1 and 10
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
or
(
p_partkey = l_partkey
and p_brand = 'Brand#11'
and p_container in ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG')
and l_quantity >= 24 and l_quantity <= 24 + 10
and p_size between 1 and 15
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
);Q20：潜在的な部品プロモーション
指定された国において、特定の部品について、総出荷数量に対する過剰在庫を持つサプライヤーを特定します。
select
s_name,
s_address
from
supplier,
nation
where
s_suppkey in (
select
ps_suppkey
from
partsupp
where
ps_partkey in (
select
p_partkey
from
part
where
p_name like 'magenta%'
)
and ps_availqty > (
select
0.5 * sum(l_quantity)
from
lineitem
where
l_partkey = ps_partkey
and l_suppkey = ps_suppkey
and l_shipdate >= date '1996-01-01'
and l_shipdate < date '1996-01-01' + interval '1' year
)
)
and s_nationkey = n_nationkey
and n_name = 'RUSSIA'
order by
s_name;Q21：注文の遅延を引き起こしたサプライヤー
指定された国において、出荷により注文の遅延を引き起こしたサプライヤーを検索します。
select
s_name,
count(*) as numwait
from
supplier,
lineitem l1,
orders,
nation
where
s_suppkey = l1.l_suppkey
and o_orderkey = l1.l_orderkey
and o_orderstatus = 'F'
and l1.l_receiptdate > l1.l_commitdate
and exists (
select
*
from
lineitem l2
where
l2.l_orderkey = l1.l_orderkey
and l2.l_suppkey <> l1.l_suppkey
)
and not exists (
select
*
from
lineitem l3
where
l3.l_orderkey = l1.l_orderkey
and l3.l_suppkey <> l1.l_suppkey
and l3.l_receiptdate > l3.l_commitdate
)
and s_nationkey = n_nationkey
and n_name = 'MOZAMBIQUE'
group by
s_name
order by
numwait desc,
s_name
limit 100;Q22：グローバル販売機会
注文履歴がないが、平均以上の口座残高を持つ顧客について、国別コードごとの口座残高および顧客数をレポートします。
select
cntrycode,
count(*) as numcust,
sum(c_acctbal) as totacctbal
from
(
select
substring(c_phone from 1 for 2) as cntrycode,
c_acctbal
from
customer
where
substring(c_phone from 1 for 2) in
('13', '31', '23', '29', '30', '18', '17')
and c_acctbal > (
select
avg(c_acctbal)
from
customer
where
c_acctbal > 0.00
and substring(c_phone from 1 for 2) in
('13', '31', '23', '29', '30', '18', '17')
)
and not exists (
select
*
from
orders
where
o_custkey = c_custkey
)
) as custsale
group by
cntrycode
order by
cntrycode;