Mercurial > gemma
annotate schema/reports.sql @ 5390:90fc90148ef8 extented-report
Added materialized views based data quality report
author | Sascha Wilde <wilde@intevation.de> |
---|---|
date | Fri, 02 Jul 2021 18:56:59 +0200 |
parents | |
children | 1dd63a2405bc |
rev | line source |
---|---|
5390
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
1 -- This is Free Software under GNU Affero General Public License v >= 3.0 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
2 -- without warranty, see README.md and license for details. |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
3 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
4 -- SPDX-License-Identifier: AGPL-3.0-or-later |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
5 -- License-Filename: LICENSES/AGPL-3.0.txt |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
6 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
7 -- Copyright (C) 2021 by via donau |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
8 -- – Österreichische Wasserstraßen-Gesellschaft mbH |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
9 -- Software engineering by Intevation GmbH |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
10 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
11 -- Author(s): |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
12 -- * Sascha Wilde <sascha.wilde@intevation.de> |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
13 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
14 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
15 -- Materialized Views with statistical data for data quality reports |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
16 CREATE MATERIALIZED VIEW waterway.dqr_gauge_stats AS |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
17 WITH d AS ( SELECT ym::date, d::date |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
18 FROM generate_series( '2019-10-01'::date, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
19 now() - interval '1 day', |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
20 '1 month'::interval ) ym, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
21 generate_series( ym, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
22 ( ym + interval '1 month' |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
23 - interval '1 day'), |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
24 '1 day'::interval ) d ), |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
25 g AS ( SELECT d.ym, d.d AS day, (location).country_code AS cc, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
26 objname, array_agg(distinct(location)) AS locations |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
27 FROM waterway.gauges,d |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
28 GROUP BY objname,d.d,(location).country_code,d.ym ), |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
29 measure AS ( |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
30 SELECT g.ym, g.cc, g.objname, g.day, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
31 CASE WHEN count(measure_date) = 0 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
32 THEN 1 ELSE 0 END AS missing |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
33 FROM g |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
34 LEFT OUTER JOIN waterway.gauge_measurements gm |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
35 ON ARRAY[location] <@ g.locations |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
36 AND g.day <= measure_date |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
37 AND measure_date < (g.day + interval '1 day') |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
38 GROUP BY g.objname,g.day,g.ym,g.cc ) |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
39 SELECT cc, ym AS month, objname, sum(missing) AS daynodata |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
40 FROM measure |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
41 GROUP BY cc, ym, objname; |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
42 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
43 CREATE MATERIALIZED VIEW waterway.dqr_bottleneck_stats AS |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
44 WITH d AS ( SELECT ym::date |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
45 FROM generate_series( '2019-10-01'::date, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
46 now() - interval '1 day', |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
47 '1 month'::interval ) ym), |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
48 bn AS ( SELECT DISTINCT objnam, responsible_country AS cc |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
49 FROM waterway.bottlenecks ), |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
50 bid AS (SELECT objnam, array_agg(distinct(bottleneck_id)) AS ids |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
51 FROM waterway.bottlenecks GROUP BY objnam) |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
52 SELECT bn.cc, d.ym AS month, bid.objnam, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
53 COALESCE(count(distinct(sr.date_info)),0) AS srcnt, |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
54 COALESCE(count(distinct(efa.measure_date)),0) AS fwacnt |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
55 FROM bn, bid |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
56 CROSS JOIN d |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
57 LEFT OUTER JOIN waterway.sounding_results sr |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
58 ON ARRAY[sr.bottleneck_id] <@ bid.ids |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
59 AND d.ym <= sr.date_info |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
60 AND sr.date_info < (d.ym + interval '1 month') |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
61 LEFT OUTER JOIN waterway.fairway_availability fa |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
62 ON ARRAY[fa.bottleneck_id] <@ bid.ids |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
63 LEFT OUTER JOIN waterway.effective_fairway_availability efa |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
64 ON fairway_availability_id = fa.id |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
65 AND d.ym <= efa.measure_date |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
66 AND efa.measure_date < (d.ym + interval '1 month') |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
67 AND efa.measure_type = 'Measured' |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
68 WHERE bid.objnam = bn.objnam |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
69 GROUP BY bn.cc, d.ym, bid.objnam; |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
70 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
71 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
72 -- Config update statement |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
73 |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
74 -- TODO |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
75 -- |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
76 -- INSERT INTO sys_admin.stats_updates |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
77 -- VALUES ('Data quality report', |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
78 -- 'REFRESH MATERIALIZED VIEW waterway.dqr_bottleneck_stats; |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
79 -- REFRESH MATERIALIZED VIEW waterway.dqr_gauge_stats;'); |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
80 -- |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
81 -- THIS DOES _NOT_ WORK! |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
82 -- To make this work we need a wrapper function with owner rights for |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
83 -- the refresh, as (from the PGSQL manual): "REFRESH MATERIALIZED VIEW |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
84 -- completely replaces the contents of a materialized view. To execute |
90fc90148ef8
Added materialized views based data quality report
Sascha Wilde <wilde@intevation.de>
parents:
diff
changeset
|
85 -- this command you must be the owner of the materialized view."" |