sql aggregate expr column

sql aggregate expr column checks

Description
Column level check that calculates a given SQL aggregate expression on a column and compares it with a maximum accepted value.

---

profile sql aggregate expr column

Check description
Verifies that a custom aggregated SQL expression (MIN, MAX, etc.) is not outside the set range.

Check name	Check type	Time scale	Sensor definition	Quality rule
profile_sql_aggregate_expr_column	profiling		sql_aggregated_expression	between_floats

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_sql_aggregate_expr_column

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

dqo> check run -ch=profile_sql_aggregate_expr_column

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_sql_aggregate_expr_column

It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below

dqo> check run -c=connection_name -t=table_name -ch=profile_sql_aggregate_expr_column

It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below

dqo> check run -c=connection_name -t=table_name -col=column_name -ch=profile_sql_aggregate_expr_column

Check structure (Yaml)

      profiling_checks:
        sql:
          profile_sql_aggregate_expr_column:
            parameters:
              sql_expression: "MAX({column})"
            warning:
              from: 10.0
              to: 20.5
            error:
              from: 10.0
              to: 20.5
            fatal:
              from: 10.0
              to: 20.5

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      profiling_checks:
        sql:
          profile_sql_aggregate_expr_column:
            parameters:
              sql_expression: "MAX({column})"
            warning:
              from: 10.0
              to: 20.5
            error:
              from: 10.0
              to: 20.5
            fatal:
              from: 10.0
              to: 20.5
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      profiling_checks:
        sql:
          profile_sql_aggregate_expr_column:
            parameters:
              sql_expression: "MAX({column})"
            warning:
              from: 10.0
              to: 20.5
            error:
              from: 10.0
              to: 20.5
            fatal:
              from: 10.0
              to: 20.5
      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

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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 sql aggregate expr column

Check description
Verifies that a custom aggregated SQL expression (MIN, MAX, etc.) is not outside the set range. Stores the most recent captured value for each day when the data quality check was evaluated.

Check name	Check type	Time scale	Sensor definition	Quality rule
daily_sql_aggregate_expr_column	recurring	daily	sql_aggregated_expression	between_floats

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_sql_aggregate_expr_column

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

dqo> check run -ch=daily_sql_aggregate_expr_column

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_sql_aggregate_expr_column

It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below

dqo> check run -c=connection_name -t=table_name -ch=daily_sql_aggregate_expr_column

It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below

dqo> check run -c=connection_name -t=table_name -col=column_name -ch=daily_sql_aggregate_expr_column

Check structure (Yaml)

      recurring_checks:
        daily:
          sql:
            daily_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      recurring_checks:
        daily:
          sql:
            daily_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      recurring_checks:
        daily:
          sql:
            daily_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      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

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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 sql aggregate expr column

Check description
Verifies that a custom aggregated SQL expression (MIN, MAX, etc.) is not outside the set range. Stores the most recent row count for each month when the data quality check was evaluated.

Check name	Check type	Time scale	Sensor definition	Quality rule
monthly_sql_aggregate_expr_column	recurring	monthly	sql_aggregated_expression	between_floats

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_sql_aggregate_expr_column

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

dqo> check run -ch=monthly_sql_aggregate_expr_column

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_sql_aggregate_expr_column

It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below

dqo> check run -c=connection_name -t=table_name -ch=monthly_sql_aggregate_expr_column

It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below

dqo> check run -c=connection_name -t=table_name -col=column_name -ch=monthly_sql_aggregate_expr_column

Check structure (Yaml)

      recurring_checks:
        monthly:
          sql:
            monthly_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      recurring_checks:
        monthly:
          sql:
            monthly_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      recurring_checks:
        monthly:
          sql:
            monthly_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      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

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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 sql aggregate expr column

Check description
Verifies that a custom aggregated SQL expression (MIN, MAX, etc.) is not outside the set range. Creates a separate data quality check (and an alert) for each daily partition.

Check name	Check type	Time scale	Sensor definition	Quality rule
daily_partition_sql_aggregate_expr_column	partitioned	daily	sql_aggregated_expression	between_floats

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_sql_aggregate_expr_column

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

dqo> check run -ch=daily_partition_sql_aggregate_expr_column

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_sql_aggregate_expr_column

It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below

dqo> check run -c=connection_name -t=table_name -ch=daily_partition_sql_aggregate_expr_column

It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below

dqo> check run -c=connection_name -t=table_name -col=column_name -ch=daily_partition_sql_aggregate_expr_column

Check structure (Yaml)

      partitioned_checks:
        daily:
          sql:
            daily_partition_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      partitioned_checks:
        daily:
          sql:
            daily_partition_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.`target_column`)) AS actual_value,
    CAST(analyzed_table.`` AS DATE) AS time_period,
    TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.`target_column`)) AS actual_value,
    DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.[target_column])) AS actual_value,
    CAST(analyzed_table.[] AS date) AS time_period,
    CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY CAST(analyzed_table.[] AS date)

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      partitioned_checks:
        daily:
          sql:
            daily_partition_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      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

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.`target_column`)) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    CAST(analyzed_table.`` AS DATE) AS time_period,
    TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

MySQL

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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.``, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Snowflake

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."" AS date) AS time_period,
    TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

SQL Server

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.[target_column])) AS actual_value,
    analyzed_table.[country] AS grouping_level_1,
    analyzed_table.[state] AS grouping_level_2,
    CAST(analyzed_table.[] AS date) AS time_period,
    CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state], CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY level_1, level_2CAST(analyzed_table.[] AS date)

---

monthly partition sql aggregate expr column

Check description
Verifies that a custom aggregated SQL expression (MIN, MAX, etc.) is not outside the set range. Creates a separate data quality check (and an alert) for each monthly partition.

Check name	Check type	Time scale	Sensor definition	Quality rule
monthly_partition_sql_aggregate_expr_column	partitioned	monthly	sql_aggregated_expression	between_floats

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_sql_aggregate_expr_column

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

dqo> check run -ch=monthly_partition_sql_aggregate_expr_column

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_sql_aggregate_expr_column

It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below

dqo> check run -c=connection_name -t=table_name -ch=monthly_partition_sql_aggregate_expr_column

It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below

dqo> check run -c=connection_name -t=table_name -col=column_name -ch=monthly_partition_sql_aggregate_expr_column

Check structure (Yaml)

      partitioned_checks:
        monthly:
          sql:
            monthly_partition_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  columns:
    target_column:
      partitioned_checks:
        monthly:
          sql:
            monthly_partition_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.`target_column`)) AS actual_value,
    DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.`target_column`)) AS actual_value,
    DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table."target_column")) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(analyzed_table.[target_column])) AS actual_value,
    DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1) AS time_period,
    CAST((DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] 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.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1), DATEADD(month, DATEDIFF(month, 0, analyzed_table.[]), 0)
ORDER BY DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1)

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      partitioned_checks:
        monthly:
          sql:
            monthly_partition_sql_aggregate_expr_column:
              parameters:
                sql_expression: "MAX({column})"
              warning:
                from: 10.0
                to: 20.5
              error:
                from: 10.0
                to: 20.5
              fatal:
                from: 10.0
                to: 20.5
      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

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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.`` AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY 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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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.``, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY 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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY 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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY 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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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."" AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY 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
    ({{ parameters.sql_expression | replace('{column}', lib.render_target_column('analyzed_table')) |
        replace('{table}', lib.render_target_table()) | replace('{alias}', '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
    (MAX(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.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1) AS time_period,
    CAST((DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] 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.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1), DATEADD(month, DATEDIFF(month, 0, analyzed_table.[]), 0)
ORDER BY level_1, level_2DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1)

---