[gpadmin@pod4-be ~]$ -bash: ddemo: command not found
-bash: -bash:: command not found
[gpadmin@pod4-be ~]$ \c training1
-bash: c: command not found
[gpadmin@pod4-be ~]$ psql training1
psql (8.2.15)
Type "help" for help.
training1=# psql
training1-# \c training1
You are now connected to database "training1" as user "gpadmin".
training1-# SET search_path TO ddemo, public;
ERROR: syntax error at or near "psql"
LINE 1: psql
^
training1=# \dt
List of relations
Schema |
Name
| Type | Owner | Storage
--------+--------------+-------+---------+--------public | weekly_sales | table | gpadmin | heap
(1 row)
training1=# \dn
List of schemas
Name
| Owner
--------------------+--------ddemo
| gpadmin
gp_toolkit
| gpadmin
information_schema | gpadmin
madlib
| gpadmin
myschema
| gpadmin
pg_aoseg
| gpadmin
pg_bitmapindex
| gpadmin
pg_catalog
| gpadmin
pg_toast
| gpadmin
public
| gpadmin
(10 rows)
training1=# SET search_path TO ddemo, public;
SET
training1=#
training1=# \dt
List of relations
Schema |
Name
| Type | Owner | Storage
--------+---------------------------+-------+---------+------------ddemo | campaign_dim
| table | gpadmin | heap
ddemo | campaign_dim_stage
| table | gpadmin | heap
ddemo | categories_dim
| table | gpadmin | append only
ddemo | city_state_zip
| table | gpadmin | append only
ddemo | customer_addresses_dim
| table | gpadmin | append only
ddemo | customer_demographics
| table | gpadmin | heap
ddemo | customers_dim
| table | gpadmin | append only
ddemo | date_dim
| table | gpadmin | heap
ddemo | day_weights
| table | gpadmin | heap
ddemo | distribution
| table | gpadmin | heap
ddemo | email_addresses_dim
| table | gpadmin | append only
ddemo | female_first_names_xt_err | table | gpadmin | heap
ddemo | kid_friendly_dvds
| table | gpadmin | append only
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
ddemo |
(29 rows)
kid_friendly_dvds_xt_err
list_c
male_first_names_xt_err
order_lineitems
order_lineitems_stage
orders
payment_methods
products_dim
products_xt_err
raw_zip_city_state_xt_err
state_sales_taxes_xt_err
streets
streets_xt_err
surnames_xt_err
websites_xt_err
weekly_sales
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
table
table
table
table
table
table
table
table
table
table
table
table
table
table
table
table
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
gpadmin
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
heap
heap
heap
append
heap
append
append
append
heap
heap
heap
append
heap
heap
heap
heap
only
only
only
only
only
training1=# \d+ customers_dim
Append-Only Table "ddemo.customer
s_dim"
Column
Type
|
Modifiers
| Storage | Description
-------------+------------------------+--------------------------------------------------------------------+----------+------------customer_id | integer
| not null default nextval('customers_dim_
customer_id_seq'::regclass) | plain
|
first_name | character varying(100) | not null
| extended |
last_name | character varying(200) | not null
| extended |
gender
| character(1)
|
| extended |
Compression Type: quicklz
Compression Level: 1
Block Size: 32768
Checksum: f
Has OIDs: no
Options: appendonly=true, compresstype=quicklz
Distributed by: (customer_id)
training1=# SELECT gender,count(*) FROM customers_dim GROUP BY gender;
gender | count
--------+-------M
| 500959
F
| 499041
(2 rows)
training1=#
training1=#
training1-#
training1-#
training1-#
training1-#
training1-#
training1-#
training1-#
SELECT
c.gender
, AVG(o.item_price) AS avg_price
FROM
ddemo.order_lineitems AS o
JOIN
ddemo.customers_dim AS c
ON o.customer_id = c.customer_id
training1-# GROUP BY c.gender
training1-# ;
gender |
avg_price
--------+--------------------M
| 33.8456101189216746
F
| 33.7982853835904994
(2 rows)
training1-# \q
[gpadmin@pod4-be ~]$
[gpadmin@pod4-be ~]$ cd LAB01
[gpadmin@pod4-be LAB01]$
[gpadmin@pod4-be LAB01]$ psql -d training1 -f lab1p1step6.sql
gender |
avg_price
--------+--------------------M
| 33.8456101189216746
F
| 33.7982853835904994
(2 rows)
[gpadmin@pod4-be LAB01]$ psql -d training1 -f lab1p1step7.sql
sum
|
product_category_name
-------------+---------------------------------27638821.85 | Kitchen
27027249.97 | Home Improvement
17284431.77 | DVD
13628527.17 | Sports
10841356.88 | Automotive Parts and Accessories
9974722.57 | Toy
(6 rows)
[gpadmin@pod4-be LAB01]$
[gpadmin@pod4-be LAB01]$
[gpadmin@pod4-be LAB01]$ psql
psql (8.2.15)
Type "help" for help.
template1=# \c training2
You are now connected to database "training2" as user "gpadmin".
training2=# \dt
List of relations
Schema | Name | Type | Owner | Storage
--------+---------+-------+---------+--------public | fips
| table | gpadmin | heap
public | housing | table | gpadmin | heap
public | persons | table | gpadmin | heap
public | zeta
| table | gpadmin | heap
(4 rows)
training2=#
training2=# \dn
List of schemas
Name
| Owner
--------------------+--------gp_toolkit
| gpadmin
information_schema | gpadmin
madlib
| gpadmin
myschema
| gpadmin
pg_aoseg
| gpadmin
pg_bitmapindex
| gpadmin
pg_catalog
| gpadmin
pg_toast
| gpadmin
public
| gpadmin
(9 rows)
training2=#
training2=# SELECT
training2-# SUM(c) AS total_records
training2-# , SUM(CASE WHEN c>1 THEN c-1 ELSE 0 END) AS total_dupes
training2-# , COUNT(*) AS total_uniques
training2-# FROM (
training2(# SELECT
training2(# COUNT(*) AS c
training2(# FROM
training2(# housing
training2(# GROUP BY
training2(# serialno
training2(# , state
training2(# ) AS dupes
training2-# ;
total_records | total_dupes | total_uniques
---------------+-------------+--------------12515394 |
6257697 |
6257697
(1 row)
training2=# \dt
List of relations
Schema | Name | Type | Owner | Storage
--------+---------+-------+---------+--------public | fips
| table | gpadmin | heap
public | housing | table | gpadmin | heap
public | persons | table | gpadmin | heap
public | zeta
| table | gpadmin | heap
(4 rows)
training2=# DROP TABLE IF EXISTS housing_nodupes;
NOTICE: table "housing_nodupes" does not exist, skipping
DROP TABLE
training2=#
training2-#
training2-#
training2-#
training2-#
training2-#
training2-#
CREATE TABLE housing_nodupes AS
SELECT DISTINCT ON
(serialno, state) *
FROM
housing
DISTRIBUTED BY (serialno, state)
;
SELECT 6257697
training2=#
training2=#
training2=# SELECT
training2-# SUM(c) AS total_records
training2-# , SUM(CASE WHEN c>1 THEN c-1 ELSE 0 END) AS total_dupes
training2-# , COUNT(*) AS total_uniques
training2-# FROM (
training2(# SELECT
training2(# COUNT(*) AS c
training2(# FROM
training2(# housing_nodupes
training2(# GROUP BY
training2(# serialno
training2(# , state
training2(# ) AS dupes
training2-# ;
total_records | total_dupes | total_uniques
---------------+-------------+--------------6257697 |
0 |
6257697
(1 row)
training2=# SELECT
training2-# corr(hinc, rooms)
training2-# FROM
training2-# housing_nodupes
training2-# WHERE
training2-# state = 25
training2-# ;
corr
------------------0.374485423827578
(1 row)
training2=#
training2=# SELECT * FROM fips WHERE code = 25;
code | name
------+-----25 | MA
(1 row)
training2=#
training2=#
training2=# SELECT
training2-# regr_r2(hinc, rooms)
training2-# FROM
training2-# housing_nodupes
training2-# WHERE
training2-# state = 25
training2-# ;
regr_r2
------------------0.140239332659321
(1 row)
training2=#
training2-#
training2-#
training2-#
training2-#
training2-#
training2-#
training2-#
training2-#
training2-#
training2=#
SELECT
serialno
, hinc
, rooms
FROM
housing_nodupes
WHERE
hinc > 0
AND state = 25
;
\a
\o lab1_01.txt
SELECT
serialno
, hinc
, rooms
FROM
housing_nodupes
WHERE
hinc > 0
AND state = 25
;
the output is file lab_01.txt
serialno | hinc | rooms
----------+---------+------45 | 68100 |
2
103 | 359000 |
5
159 | 14700 |
4
697 | 101500 |
9
749 | 38600 |
3
962 | 86480 |
8
1051 | 81300 |
6
1514 | 90000 |
3
1537 | 28000 |
8
1791 | 271800 |
8
1942 | 18200 |
9
2028 | 122300 |
7
2197 | 42400 |
5
2293 | 90000 |
5
2295 | 29000 |
5
2402 |
5300 |
3
2583 | 31000 |
6
2697 | 322000 |
9
