string match date regex percent
string match date regex percent checks
Description
Column check that calculates percentage of values that match the date regex in a column.
profile string match date regex percent
Check description
Verifies that the percentage of strings matching the date format regex in a column does not fall below the minimum accepted percentage.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| profile_string_match_date_regex_percent | profiling | string_match_date_regex_percent | min_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=profile_string_match_date_regex_percent
profiling_checks:
strings:
profile_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
profiling_checks:
strings:
profile_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
profiling_checks:
strings:
profile_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state]
ORDER BY level_1, level_2
,
daily string match date regex percent
Check description
Verifies that the percentage of strings matching the date format regex in a column does not fall below the minimum accepted percentage. Stores the most recent captured value for each day when the data quality check was evaluated.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| daily_string_match_date_regex_percent | recurring | daily | string_match_date_regex_percent | min_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=daily_string_match_date_regex_percent
recurring_checks:
daily:
strings:
daily_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
recurring_checks:
daily:
strings:
daily_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(CURRENT_TIMESTAMP() AS DATE) AS time_period,
TIMESTAMP(CAST(CURRENT_TIMESTAMP() AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
CAST(SYSDATETIMEOFFSET() AS date) AS time_period,
CAST((CAST(SYSDATETIMEOFFSET() AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
recurring_checks:
daily:
strings:
daily_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
CAST(CURRENT_TIMESTAMP() AS DATE) AS time_period,
TIMESTAMP(CAST(CURRENT_TIMESTAMP() AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
CAST(SYSDATETIMEOFFSET() AS date) AS time_period,
CAST((CAST(SYSDATETIMEOFFSET() AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state]
ORDER BY level_1, level_2
,
monthly string match date regex percent
Check description
Verifies that the percentage of strings matching the date format regex in a column does not exceed the maximum accepted percentage. Stores the most recent row count for each month when the data quality check was evaluated.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| monthly_string_match_date_regex_percent | recurring | monthly | string_match_date_regex_percent | min_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=monthly_string_match_date_regex_percent
recurring_checks:
monthly:
strings:
monthly_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
recurring_checks:
monthly:
strings:
monthly_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
recurring_checks:
monthly:
strings:
monthly_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state]
ORDER BY level_1, level_2
,
daily partition string match date regex percent
Check description
Verifies that the percentage of strings matching the date format regex in a column does not fall below the minimum accepted percentage. Creates a separate data quality check (and an alert) for each daily partition.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| daily_partition_string_match_date_regex_percent | partitioned | daily | string_match_date_regex_percent | min_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=daily_partition_string_match_date_regex_percent
partitioned_checks:
daily:
strings:
daily_partition_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
partitioned_checks:
daily:
strings:
daily_partition_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(analyzed_table.`` AS DATE) AS time_period,
TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
CAST(analyzed_table."" AS date) AS time_period,
TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
CAST(analyzed_table.[] AS date) AS time_period,
CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY CAST(analyzed_table.[] AS date)
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
partitioned_checks:
daily:
strings:
daily_partition_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
CAST(analyzed_table.`` AS DATE) AS time_period,
TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(analyzed_table."" AS date) AS time_period,
TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
120
{%- elif date_formats == 'MM/DD/YYYY' -%}
101
{%- elif date_formats == 'DD/MM/YYYY' -%}
103
{%- elif date_formats == 'YYYY/MM/DD'-%}
111
{%- elif date_formats == 'Month D, YYYY'-%}
107
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, {{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT_BIG(analyzed_table.[target_column]) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_CONVERT(DATETIME, analyzed_table.[target_column], 120) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT_BIG(*)
END AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
CAST(analyzed_table.[] AS date) AS time_period,
CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state], CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY level_1, level_2CAST(analyzed_table.[] AS date)
monthly partition string match date regex percent
Check description
Verifies that the percentage of strings matching the date format regex in a column does not fall below the minimum accepted percentage. Creates a separate data quality check (and an alert) for each monthly partition.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| monthly_partition_string_match_date_regex_percent | partitioned | monthly | string_match_date_regex_percent | min_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below
dqo> check run -c=connection_name -t=table_name -ch=monthly_partition_string_match_date_regex_percent
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=monthly_partition_string_match_date_regex_percent
partitioned_checks:
monthly:
strings:
monthly_partition_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
partitioned_checks:
monthly:
strings:
monthly_partition_string_match_date_regex_percent:
parameters:
date_formats: YYYY-MM-DD
warning:
min_percent: 100.0
error:
min_percent: 99.0
fatal:
min_percent: 95.0
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE({{render_date_formats(parameters.date_formats)}}, {{ lib.render_target_column('analyzed_table') }}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN SAFE.PARSE_DATE('%Y-%m-%d', analyzed_table.`target_column`) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%Y-%m-%d'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%m/%d/%Y'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%d/%m/%Y'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%Y/%m/%d'
{%- elif date_formats == 'Month D, YYYY'-%}
'%b %d, %Y'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE({{ lib.render_target_column('analyzed_table') }}, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table.`target_column`) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN STR_TO_DATE(analyzed_table.`target_column`, '%Y-%m-%d') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'%YYYY-%MM-%DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'%MM/%DD/%YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'%DD/%MM/%YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'%YYYY/%MM/%DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'%Month %DD,%YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE({{ lib.render_target_column('analyzed_table') }}::VARCHAR, {{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TO_DATE(analyzed_table."target_column"::VARCHAR, '%YYYY-%MM-%DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
{% macro render_date_formats(date_formats) %}
{%- if date_formats == 'YYYY-MM-DD'-%}
'YYYY-MM-DD'
{%- elif date_formats == 'MM/DD/YYYY' -%}
'MM/DD/YYYY'
{%- elif date_formats == 'DD/MM/YYYY' -%}
'DD/MM/YYYY'
{%- elif date_formats == 'YYYY/MM/DD'-%}
'YYYY/MM/DD'
{%- elif date_formats == 'Month D, YYYY'-%}
'Month DD,YYYY'
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT({{ lib.render_target_column('analyzed_table') }}) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE ({{ lib.render_target_column('analyzed_table') }},{{render_date_formats(parameters.date_formats)}}) IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(analyzed_table."target_column") = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN TRY_TO_DATE (analyzed_table."target_column",'YYYY-MM-DD') IS NOT NULL
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc