number value in set percent
number value in set percent checks
Description
Column level check that calculates the percentage of rows for which the tested numeric column contains a value from the set of expected values.
Columns with null values are also counted as a passing value (the sensor assumes that a 'null' is also an expected and accepted value).
The check raises a data quality issue when the percentage of rows with a not null column value that is not expected (not one of the values in the expected_values set)
is below an expected threshold, for example 99% of rows should have values from the defined domain.
This data quality check is useful for checking numeric columns that store numeric codes (such as status codes) that the only values found in the column are from a set of expected values.
profile number value in set percent
Check description
The check measures the percentage of rows whose value in a tested column is one of values from a list of expected values or the column value is null. Verifies that the percentage of rows having a valid column value does not exceed the minimum accepted percentage.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| profile_number_value_in_set_percent | profiling | number_value_in_set_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_number_value_in_set_percent
profiling_checks:
numeric:
profile_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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:
numeric:
profile_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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:
numeric:
profile_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.grouping_level_1,
analyzed_table.grouping_level_2
,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
original_table."country" AS grouping_level_1,
original_table."state" AS grouping_level_2,
TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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 number value in set percent
Check description
The check measures the percentage of rows whose value in a tested column is one of values from a list of expected values or the column value is null. Verifies that the percentage of rows having a valid column value does not exceed 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_number_value_in_set_percent | recurring | daily | number_value_in_set_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_number_value_in_set_percent
recurring_checks:
daily:
numeric:
daily_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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:
numeric:
daily_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS time_period,
CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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:
numeric:
daily_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.grouping_level_1,
analyzed_table.grouping_level_2
,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
original_table."country" AS grouping_level_1,
original_table."state" AS grouping_level_2,
TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS time_period,
CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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 number value in set percent
Check description
The check measures the percentage of rows whose value in a tested column is one of values from a list of expected values or the column value is null. Verifies that the percentage of rows having a valid column value does not exceed the minimum 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_number_value_in_set_percent | recurring | monthly | number_value_in_set_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_number_value_in_set_percent
recurring_checks:
monthly:
numeric:
monthly_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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:
numeric:
monthly_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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:
numeric:
monthly_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.grouping_level_1,
analyzed_table.grouping_level_2
,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
original_table."country" AS grouping_level_1,
original_table."state" AS grouping_level_2,
TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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 number value in set percent
Check description
The check measures the percentage of rows whose value in a tested column is one of values from a list of expected values or the column value is null. Verifies that the percentage of rows having a valid column value does not exceed 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_number_value_in_set_percent | partitioned | daily | number_value_in_set_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_number_value_in_set_percent
partitioned_checks:
daily:
numeric:
daily_partition_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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:
numeric:
daily_partition_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
TRUNC(CAST(original_table."" AS DATE)) AS time_period,
CAST(TRUNC(CAST(original_table."" AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT_BIG(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT_BIG(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table.[target_column] IN (2, 3
))
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:
numeric:
daily_partition_number_value_in_set_percent:
parameters:
expected_values:
- 2
- 3
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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 extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} 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(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table.`target_column` IN (2, 3)
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
Oracle
{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
{%- macro extract_in_list(values_list) -%}
{{ values_list|join(', ') -}}
{% endmacro %}
{%- macro actual_value() -%}
{%- if 'expected_values' not in parameters or parameters.expected_values|length == 0 -%}
{#- Two approaches could be taken here. What if COUNT(*) = 0 AND value set is empty? This solution is the most convenient. -#}
0.0
{%- else -%}
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} IN ({{ extract_in_list(parameters.expected_values) }})
THEN 1
ELSE 0
END
) / COUNT(*)
END
{%- endif -%}
{% endmacro -%}
SELECT
{{ actual_value() }} AS actual_value
{{- lib.render_data_grouping_projections_reference('analyzed_table') }}
{{- lib.render_time_dimension_projection_reference('analyzed_table') }}
FROM(
SELECT
original_table.*
{{- lib.render_data_grouping_projections('original_table') }}
{{- lib.render_time_dimension_projection('original_table') }}
FROM {{ lib.render_target_table() }} original_table
{{- lib.render_where_clause(table_alias_prefix='original_table') }}
) analyzed_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
CASE
WHEN COUNT(*) = 0 THEN 100.0
ELSE 100.0 * SUM(
CASE
WHEN analyzed_table."target_column" IN (2, 3)
THEN 1
ELSE 0
END
) / COUNT(*)
END AS actual_value,
analyzed_table.grouping_level_1,
analyzed_table.grouping_level_2
,
time_period,
time_period_utc
FROM(
SELECT
original_table.*,
original_table."country" AS grouping_level_1,
original_table."state" AS grouping_level_2,
TRUNC(CAST(original_table."" AS DATE)) AS time_period,
CAST(TRUNC(CAST(original_table."" AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "<target_schema>"."<target_table>" original_table
) 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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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 extract_in_list(values_list) -%}
{{values_list|join(', ')}}
{% endmacro %}
{%- macro render_else() -%}
{%- if parameters.expected_values|length == 0 -%}
0.0
{%- else -%}
100.0 * SUM(
CASE
WHEN ({{lib.render_target_column('analyzed_table')}} IN ({{extract_in_list(parameters.expected_values)}}))
THEN 1
ELSE 0
END
)/COUNT(*)
{%- endif -%}
{% endmacro -%}
SELECT
CASE
WHEN COUNT(*) = 0 THEN NULL
ELSE {{render_else()}}
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(*) = 0 THEN NULL
ELSE 100.0 * SUM(
CASE
WHEN (analyzed_table."target_column" IN (2, 3
))
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