Skip to content

change distinct count since 30 days

change distinct count since 30 days checks

Description
Column-level check that ensures that the distinct count in a monitored column has changed by a fixed rate since the last readout from last month.


profile change distinct count since 30 days

Check description
Verifies that the distinct count in a monitored column has changed by a fixed rate since the last readout from last month.

Check name Check type Time scale Quality dimension Sensor definition Quality rule
profile_change_distinct_count_since_30_days profiling Consistency distinct_count change_percent_30_days

Enable check (Shell)
To enable this check provide connection name and check name in check enable command

dqo> check enable -c=connection_name -ch=profile_change_distinct_count_since_30_days
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=profile_change_distinct_count_since_30_days
It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below
dqo> check run -c=connection_name -ch=profile_change_distinct_count_since_30_days
It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below
dqo> check run -c=connection_name -t=schema_name.table_name -ch=profile_change_distinct_count_since_30_days
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=schema_name.table_name -col=column_name -ch=profile_change_distinct_count_since_30_days
Check structure (YAML)
      profiling_checks:
        uniqueness:
          profile_change_distinct_count_since_30_days:
            warning:
              max_percent: 5.0
              exact_day: false
            error:
              max_percent: 5.0
              exact_day: false
            fatal:
              max_percent: 5.0
              exact_day: false
Sample configuration (YAML)
The sample schema_name.table_name.dqotable.yaml file with the check configured is shown below.

# yaml-language-server: $schema=https://cloud.dqops.com/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:
        uniqueness:
          profile_change_distinct_count_since_30_days:
            warning:
              max_percent: 5.0
              exact_day: false
            error:
              max_percent: 5.0
              exact_day: false
            fatal:
              max_percent: 5.0
              exact_day: false
      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

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) 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

Expand the Configure with data grouping section to see additional examples for configuring this data quality checks to use data grouping (GROUP BY).

Configuration with data grouping

Sample configuration with data grouping enabled (YAML)
The sample below shows how to configure the data grouping and how it affects the generated SQL query.

# yaml-language-server: $schema=https://cloud.dqops.com/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:
        uniqueness:
          profile_change_distinct_count_since_30_days:
            warning:
              max_percent: 5.0
              exact_day: false
            error:
              max_percent: 5.0
              exact_day: false
            fatal:
              max_percent: 5.0
              exact_day: false
      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

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) 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 change distinct count since 30 days

Check description
Verifies that the distinct count in a monitored column has changed by a fixed rate since the last readout from last month.

Check name Check type Time scale Quality dimension Sensor definition Quality rule
daily_change_distinct_count_since_30_days monitoring daily Consistency distinct_count change_percent_30_days

Enable check (Shell)
To enable this check provide connection name and check name in check enable command

dqo> check enable -c=connection_name -ch=daily_change_distinct_count_since_30_days
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=daily_change_distinct_count_since_30_days
It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below
dqo> check run -c=connection_name -ch=daily_change_distinct_count_since_30_days
It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below
dqo> check run -c=connection_name -t=schema_name.table_name -ch=daily_change_distinct_count_since_30_days
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=schema_name.table_name -col=column_name -ch=daily_change_distinct_count_since_30_days
Check structure (YAML)
      monitoring_checks:
        daily:
          uniqueness:
            daily_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
Sample configuration (YAML)
The sample schema_name.table_name.dqotable.yaml file with the check configured is shown below.

# yaml-language-server: $schema=https://cloud.dqops.com/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:
      monitoring_checks:
        daily:
          uniqueness:
            daily_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) 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

Expand the Configure with data grouping section to see additional examples for configuring this data quality checks to use data grouping (GROUP BY).

Configuration with data grouping

Sample configuration with data grouping enabled (YAML)
The sample below shows how to configure the data grouping and how it affects the generated SQL query.

# yaml-language-server: $schema=https://cloud.dqops.com/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:
      monitoring_checks:
        daily:
          uniqueness:
            daily_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) 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 change distinct count since 30 days

Check description
Verifies that the distinct count in a monitored column has changed by a fixed rate since the last readout from last month.

Check name Check type Time scale Quality dimension Sensor definition Quality rule
monthly_change_distinct_count_since_30_days monitoring monthly Consistency distinct_count change_percent_30_days

Enable check (Shell)
To enable this check provide connection name and check name in check enable command

dqo> check enable -c=connection_name -ch=monthly_change_distinct_count_since_30_days
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=monthly_change_distinct_count_since_30_days
It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below
dqo> check run -c=connection_name -ch=monthly_change_distinct_count_since_30_days
It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below
dqo> check run -c=connection_name -t=schema_name.table_name -ch=monthly_change_distinct_count_since_30_days
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=schema_name.table_name -col=column_name -ch=monthly_change_distinct_count_since_30_days
Check structure (YAML)
      monitoring_checks:
        monthly:
          uniqueness:
            monthly_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
Sample configuration (YAML)
The sample schema_name.table_name.dqotable.yaml file with the check configured is shown below.

# yaml-language-server: $schema=https://cloud.dqops.com/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:
      monitoring_checks:
        monthly:
          uniqueness:
            monthly_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) 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

Expand the Configure with data grouping section to see additional examples for configuring this data quality checks to use data grouping (GROUP BY).

Configuration with data grouping

Sample configuration with data grouping enabled (YAML)
The sample below shows how to configure the data grouping and how it affects the generated SQL query.

# yaml-language-server: $schema=https://cloud.dqops.com/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:
      monitoring_checks:
        monthly:
          uniqueness:
            monthly_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) 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 change distinct count since 30 days

Check description
Verifies that the distinct count in a monitored column has changed by a fixed rate since the last readout from last month.

Check name Check type Time scale Quality dimension Sensor definition Quality rule
daily_partition_change_distinct_count_since_30_days partitioned daily Consistency distinct_count change_percent_30_days

Enable check (Shell)
To enable this check provide connection name and check name in check enable command

dqo> check enable -c=connection_name -ch=daily_partition_change_distinct_count_since_30_days
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=daily_partition_change_distinct_count_since_30_days
It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below
dqo> check run -c=connection_name -ch=daily_partition_change_distinct_count_since_30_days
It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below
dqo> check run -c=connection_name -t=schema_name.table_name -ch=daily_partition_change_distinct_count_since_30_days
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=schema_name.table_name -col=column_name -ch=daily_partition_change_distinct_count_since_30_days
Check structure (YAML)
      partitioned_checks:
        daily:
          uniqueness:
            daily_partition_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
Sample configuration (YAML)
The sample schema_name.table_name.dqotable.yaml file with the check configured is shown below.

# yaml-language-server: $schema=https://cloud.dqops.com/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
    partition_by_column: date_column
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      partitioned_checks:
        daily:
          uniqueness:
            daily_partition_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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
    date_column:
      labels:
      - "date or datetime column used as a daily or monthly partitioning key, dates\
        \ (and times) are truncated to a day or a month by the sensor's query for\
        \ partitioned checks"

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    CAST(analyzed_table.`date_column` AS DATE) AS time_period,
    TIMESTAMP(CAST(analyzed_table.`date_column` 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    DATE_FORMAT(analyzed_table.`date_column`, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.`date_column`, '%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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT
        original_table.*,
    TRUNC(CAST(original_table."date_column" AS DATE)) AS time_period,
    CAST(TRUNC(CAST(original_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    CAST(analyzed_table."date_column" AS date) AS time_period,
    CAST((CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    CAST(analyzed_table."date_column" AS date) AS time_period,
    CAST((CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    CAST(analyzed_table."date_column" AS date) AS time_period,
    TO_TIMESTAMP(CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) AS actual_value,
    CAST(analyzed_table.[date_column] AS date) AS time_period,
    CAST((CAST(analyzed_table.[date_column] 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.[date_column] AS date), CAST(analyzed_table.[date_column] AS date)
ORDER BY CAST(analyzed_table.[date_column] AS date)

Expand the Configure with data grouping section to see additional examples for configuring this data quality checks to use data grouping (GROUP BY).

Configuration with data grouping

Sample configuration with data grouping enabled (YAML)
The sample below shows how to configure the data grouping and how it affects the generated SQL query.

# yaml-language-server: $schema=https://cloud.dqops.com/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
    partition_by_column: date_column
  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:
          uniqueness:
            daily_partition_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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
    date_column:
      labels:
      - "date or datetime column used as a daily or monthly partitioning key, dates\
        \ (and times) are truncated to a day or a month by the sensor's query for\
        \ partitioned checks"
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    CAST(analyzed_table.`date_column` AS DATE) AS time_period,
    TIMESTAMP(CAST(analyzed_table.`date_column` 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_FORMAT(analyzed_table.`date_column`, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.`date_column`, '%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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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."date_column" AS DATE)) AS time_period,
    CAST(TRUNC(CAST(original_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."date_column" AS date) AS time_period,
    CAST((CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."date_column" AS date) AS time_period,
    CAST((CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."date_column" AS date) AS time_period,
    TO_TIMESTAMP(CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) AS actual_value,
    analyzed_table.[country] AS grouping_level_1,
    analyzed_table.[state] AS grouping_level_2,
    CAST(analyzed_table.[date_column] AS date) AS time_period,
    CAST((CAST(analyzed_table.[date_column] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state], CAST(analyzed_table.[date_column] AS date), CAST(analyzed_table.[date_column] AS date)
ORDER BY level_1, level_2CAST(analyzed_table.[date_column] AS date)

monthly partition change distinct count since 30 days

Check description
Verifies that the distinct count in a monitored column has changed by a fixed rate since the last readout from last month.

Check name Check type Time scale Quality dimension Sensor definition Quality rule
monthly_partition_change_distinct_count_since_30_days partitioned monthly Consistency distinct_count change_percent_30_days

Enable check (Shell)
To enable this check provide connection name and check name in check enable command

dqo> check enable -c=connection_name -ch=monthly_partition_change_distinct_count_since_30_days
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=monthly_partition_change_distinct_count_since_30_days
It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below
dqo> check run -c=connection_name -ch=monthly_partition_change_distinct_count_since_30_days
It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below
dqo> check run -c=connection_name -t=schema_name.table_name -ch=monthly_partition_change_distinct_count_since_30_days
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=schema_name.table_name -col=column_name -ch=monthly_partition_change_distinct_count_since_30_days
Check structure (YAML)
      partitioned_checks:
        monthly:
          uniqueness:
            monthly_partition_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
Sample configuration (YAML)
The sample schema_name.table_name.dqotable.yaml file with the check configured is shown below.

# yaml-language-server: $schema=https://cloud.dqops.com/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
    partition_by_column: date_column
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      partitioned_checks:
        monthly:
          uniqueness:
            monthly_partition_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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
    date_column:
      labels:
      - "date or datetime column used as a daily or monthly partitioning key, dates\
        \ (and times) are truncated to a day or a month by the sensor's query for\
        \ partitioned checks"

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    DATE_TRUNC(CAST(analyzed_table.`date_column` AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`date_column` 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    DATE_FORMAT(analyzed_table.`date_column`, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.`date_column`, '%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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT
        original_table.*,
    TRUNC(CAST(original_table."date_column" AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(original_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) AS actual_value,
    DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1) AS time_period,
    CAST((DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1), DATEADD(month, DATEDIFF(month, 0, analyzed_table.[date_column]), 0)
ORDER BY DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1)

Expand the Configure with data grouping section to see additional examples for configuring this data quality checks to use data grouping (GROUP BY).

Configuration with data grouping

Sample configuration with data grouping enabled (YAML)
The sample below shows how to configure the data grouping and how it affects the generated SQL query.

# yaml-language-server: $schema=https://cloud.dqops.com/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
    partition_by_column: date_column
  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:
        monthly:
          uniqueness:
            monthly_partition_change_distinct_count_since_30_days:
              warning:
                max_percent: 5.0
                exact_day: false
              error:
                max_percent: 5.0
                exact_day: false
              fatal:
                max_percent: 5.0
                exact_day: false
      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
    date_column:
      labels:
      - "date or datetime column used as a daily or monthly partitioning key, dates\
        \ (and times) are truncated to a day or a month by the sensor's query for\
        \ partitioned checks"
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key

Please expand the database engine name section to see the SQL query rendered by a Jinja2 template for the distinct_count sensor.

BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_TRUNC(CAST(analyzed_table.`date_column` AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`date_column` 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table.`target_column`)
    ) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_FORMAT(analyzed_table.`date_column`, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.`date_column`, '%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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) 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."date_column" AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(original_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT(
        DISTINCT({{ lib.render_target_column('analyzed_table') }})
    ) 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
    COUNT(
        DISTINCT(analyzed_table."target_column")
    ) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."date_column" 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 -%}
SELECT
    COUNT_BIG(
        DISTINCT({{ lib.render_target_column('analyzed_table')}})
    ) 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
    COUNT_BIG(
        DISTINCT(analyzed_table.[target_column])
    ) AS actual_value,
    analyzed_table.[country] AS grouping_level_1,
    analyzed_table.[state] AS grouping_level_2,
    DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1) AS time_period,
    CAST((DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1)) 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], DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1), DATEADD(month, DATEDIFF(month, 0, analyzed_table.[date_column]), 0)
ORDER BY level_1, level_2DATEFROMPARTS(YEAR(CAST(analyzed_table.[date_column] AS date)), MONTH(CAST(analyzed_table.[date_column] AS date)), 1)