anomaly differencing distinct count

anomaly differencing distinct count checks

Description
Column-level check that ensures that the distinct count in a monitored column is within a two-tailed percentile from measurements made during the last 90 days.

profile anomaly differencing distinct count

Check description
Verifies that the distinct count in a monitored column is within a two-tailed percentile from measurements made during the last 90 days.

Check name	Check type	Time scale	Quality dimension	Sensor definition	Quality rule
profile_anomaly_differencing_distinct_count	profiling		Consistency	distinct_count	anomaly_differencing_percentile_moving_average

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_anomaly_differencing_distinct_count

Run check (Shell)
To run this check provide check name in check run command

dqo> check run -ch=profile_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

Check structure (YAML)

      profiling_checks:
        uniqueness:
          profile_anomaly_differencing_distinct_count:
            warning:
              anomaly_percent: 0.1
            error:
              anomaly_percent: 0.1
            fatal:
              anomaly_percent: 0.1

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_anomaly_differencing_distinct_count:
            warning:
              anomaly_percent: 0.1
            error:
              anomaly_percent: 0.1
            fatal:
              anomaly_percent: 0.1
      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

Sensor template for BigQueryRendered SQL for 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

Sensor template for MySQLRendered SQL for 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

Sensor template for OracleRendered SQL for 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

Sensor template for PostgreSQLRendered SQL for 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

Sensor template for RedshiftRendered SQL for 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

Sensor template for SnowflakeRendered SQL for 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

Sensor template for SQL ServerRendered SQL for 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_anomaly_differencing_distinct_count:
            warning:
              anomaly_percent: 0.1
            error:
              anomaly_percent: 0.1
            fatal:
              anomaly_percent: 0.1
      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

Sensor template for BigQueryRendered SQL for 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

Sensor template for MySQLRendered SQL for 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

Sensor template for OracleRendered SQL for 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

Sensor template for PostgreSQLRendered SQL for 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

Sensor template for RedshiftRendered SQL for 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

Sensor template for SnowflakeRendered SQL for 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

Sensor template for SQL ServerRendered SQL for 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 anomaly differencing distinct count

Check description
Verifies that the distinct count in a monitored column is within a two-tailed percentile from measurements made during the last 90 days.

Check name	Check type	Time scale	Quality dimension	Sensor definition	Quality rule
daily_anomaly_differencing_distinct_count	monitoring	daily	Consistency	distinct_count	anomaly_differencing_percentile_moving_average

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_anomaly_differencing_distinct_count

Run check (Shell)
To run this check provide check name in check run command

dqo> check run -ch=daily_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

Check structure (YAML)

      monitoring_checks:
        daily:
          uniqueness:
            daily_anomaly_differencing_distinct_count:
              warning:
                anomaly_percent: 0.1
              error:
                anomaly_percent: 0.1
              fatal:
                anomaly_percent: 0.1

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_anomaly_differencing_distinct_count:
              warning:
                anomaly_percent: 0.1
              error:
                anomaly_percent: 0.1
              fatal:
                anomaly_percent: 0.1
      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

Sensor template for BigQueryRendered SQL for 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

Sensor template for MySQLRendered SQL for 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

Sensor template for OracleRendered SQL for 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

Sensor template for PostgreSQLRendered SQL for 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

Sensor template for RedshiftRendered SQL for 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

Sensor template for SnowflakeRendered SQL for 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

Sensor template for SQL ServerRendered SQL for 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_anomaly_differencing_distinct_count:
              warning:
                anomaly_percent: 0.1
              error:
                anomaly_percent: 0.1
              fatal:
                anomaly_percent: 0.1
      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

Sensor template for BigQueryRendered SQL for 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

Sensor template for MySQLRendered SQL for 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

Sensor template for OracleRendered SQL for 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

Sensor template for PostgreSQLRendered SQL for 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

Sensor template for RedshiftRendered SQL for 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

Sensor template for SnowflakeRendered SQL for 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

Sensor template for SQL ServerRendered SQL for 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 anomaly differencing distinct count

Check description
Verifies that the distinct count in a monitored column is within a two-tailed percentile from measurements made during the last 90 days.

Check name	Check type	Time scale	Quality dimension	Sensor definition	Quality rule
monthly_anomaly_differencing_distinct_count	monitoring	monthly	Consistency	distinct_count	anomaly_differencing_percentile_moving_average

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_anomaly_differencing_distinct_count

Run check (Shell)
To run this check provide check name in check run command

dqo> check run -ch=monthly_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

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_anomaly_differencing_distinct_count

Check structure (YAML)

      monitoring_checks:
        monthly:
          uniqueness:
            monthly_anomaly_differencing_distinct_count:
              warning:
                anomaly_percent: 0.1
              error:
                anomaly_percent: 0.1
              fatal:
                anomaly_percent: 0.1

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_anomaly_differencing_distinct_count:
              warning:
                anomaly_percent: 0.1
              error:
                anomaly_percent: 0.1
              fatal:
                anomaly_percent: 0.1
      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

Sensor template for BigQueryRendered SQL for 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

Sensor template for MySQLRendered SQL for 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

Sensor template for OracleRendered SQL for 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

Sensor template for PostgreSQLRendered SQL for 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

Sensor template for RedshiftRendered SQL for 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

Sensor template for SnowflakeRendered SQL for 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

Sensor template for SQL ServerRendered SQL for 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_anomaly_differencing_distinct_count:
              warning:
                anomaly_percent: 0.1
              error:
                anomaly_percent: 0.1
              fatal:
                anomaly_percent: 0.1
      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

Sensor template for BigQueryRendered SQL for 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

Sensor template for MySQLRendered SQL for 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

Sensor template for OracleRendered SQL for 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

Sensor template for PostgreSQLRendered SQL for 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

Sensor template for RedshiftRendered SQL for 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

Sensor template for SnowflakeRendered SQL for 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

Sensor template for SQL ServerRendered SQL for 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
        ,