Skip to content

non negative percent

non negative percent checks

Description
Column level check that ensures that there are no more than a set percentage of negative values in a monitored column.


profile non negative percent

Check description
Verifies that the percentage of non-negative values in a column does not exceed the maximum accepted percentage.

Check name Check type Time scale Sensor definition Quality rule
profile_non_negative_percent profiling non_negative_percent max_percent

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_non_negative_percent
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=profile_non_negative_percent
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_non_negative_percent
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_non_negative_percent
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_non_negative_percent
Check structure (Yaml)
      profiling_checks:
        numeric:
          profile_non_negative_percent:
            warning:
              max_percent: 100.0
            error:
              max_percent: 99.0
            fatal:
              max_percent: 95.0
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:
        numeric:
          profile_non_negative_percent:
            warning:
              max_percent: 100.0
            error:
              max_percent: 99.0
            fatal:
              max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) AS actual_value,
    DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
    CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      profiling_checks:
        numeric:
          profile_non_negative_percent:
            warning:
              max_percent: 100.0
            error:
              max_percent: 99.0
            fatal:
              max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key
BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,

                analyzed_table.grouping_level_1,

                analyzed_table.grouping_level_2
,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    original_table."country" AS grouping_level_1,
    original_table."state" AS grouping_level_2,
    TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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 non negative percent

Check description
Verifies that the percentage of non-negative values in a column does not exceed the maximum accepted percentage. Stores the most recent captured value for each day when the data quality check was evaluated.

Check name Check type Time scale Sensor definition Quality rule
daily_non_negative_percent recurring daily non_negative_percent max_percent

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_non_negative_percent
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=daily_non_negative_percent
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_non_negative_percent
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_non_negative_percent
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_non_negative_percent
Check structure (Yaml)
      recurring_checks:
        daily:
          numeric:
            daily_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
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:
          numeric:
            daily_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(CURRENT_TIMESTAMP() AS DATE) AS time_period,
    TIMESTAMP(CAST(CURRENT_TIMESTAMP() AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS time_period,
    CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(LOCALTIMESTAMP AS date) AS time_period,
    CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(LOCALTIMESTAMP AS date) AS time_period,
    CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
    TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) AS actual_value,
    CAST(SYSDATETIMEOFFSET() AS date) AS time_period,
    CAST((CAST(SYSDATETIMEOFFSET() AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      recurring_checks:
        daily:
          numeric:
            daily_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key
BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    CAST(CURRENT_TIMESTAMP() AS DATE) AS time_period,
    TIMESTAMP(CAST(CURRENT_TIMESTAMP() AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,

                analyzed_table.grouping_level_1,

                analyzed_table.grouping_level_2
,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    original_table."country" AS grouping_level_1,
    original_table."state" AS grouping_level_2,
    TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS time_period,
    CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(LOCALTIMESTAMP AS date) AS time_period,
    CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(LOCALTIMESTAMP AS date) AS time_period,
    CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
    TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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 non negative percent

Check description
Verifies that the percentage of non-negative values in a column does not exceed the maximum accepted percentage. Stores the most recent row count for each month when the data quality check was evaluated.

Check name Check type Time scale Sensor definition Quality rule
monthly_non_negative_percent recurring monthly non_negative_percent max_percent

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_non_negative_percent
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=monthly_non_negative_percent
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_non_negative_percent
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_non_negative_percent
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_non_negative_percent
Check structure (Yaml)
      recurring_checks:
        monthly:
          numeric:
            monthly_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
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:
          numeric:
            monthly_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) AS actual_value,
    DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
    CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      recurring_checks:
        monthly:
          numeric:
            monthly_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key
BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,

                analyzed_table.grouping_level_1,

                analyzed_table.grouping_level_2
,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    original_table."country" AS grouping_level_1,
    original_table."state" AS grouping_level_2,
    TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(CURRENT_TIMESTAMP AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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 non negative percent

Check description
Verifies that the percentage of non-negative values in a column does not exceed the maximum accepted percentage. Creates a separate data quality check (and an alert) for each daily partition.

Check name Check type Time scale Sensor definition Quality rule
daily_partition_non_negative_percent partitioned daily non_negative_percent max_percent

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_non_negative_percent
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=daily_partition_non_negative_percent
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_non_negative_percent
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_non_negative_percent
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_non_negative_percent
Check structure (Yaml)
      partitioned_checks:
        daily:
          numeric:
            daily_partition_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
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:
          numeric:
            daily_partition_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(analyzed_table.`` AS DATE) AS time_period,
    TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    TRUNC(CAST(original_table."" AS DATE)) AS time_period,
    CAST(TRUNC(CAST(original_table."" AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) AS actual_value,
    CAST(analyzed_table.[] AS date) AS time_period,
    CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY CAST(analyzed_table.[] AS date)

Configuration with data grouping

Click to see more

Sample configuration (Yaml)

# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
  timestamp_columns:
    event_timestamp_column: col_event_timestamp
    ingestion_timestamp_column: col_inserted_at
  incremental_time_window:
    daily_partitioning_recent_days: 7
    monthly_partitioning_recent_months: 1
  default_grouping_name: group_by_country_and_state
  groupings:
    group_by_country_and_state:
      level_1:
        source: column_value
        column: country
      level_2:
        source: column_value
        column: state
  columns:
    target_column:
      partitioned_checks:
        daily:
          numeric:
            daily_partition_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key
BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    CAST(analyzed_table.`` AS DATE) AS time_period,
    TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table.`country` AS grouping_level_1,
    analyzed_table.`state` AS grouping_level_2,
    DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
    FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,

                analyzed_table.grouping_level_1,

                analyzed_table.grouping_level_2
,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    original_table."country" AS grouping_level_1,
    original_table."state" AS grouping_level_2,
    TRUNC(CAST(original_table."" AS DATE)) AS time_period,
    CAST(TRUNC(CAST(original_table."" AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    analyzed_table."country" AS grouping_level_1,
    analyzed_table."state" AS grouping_level_2,
    CAST(analyzed_table."" AS date) AS time_period,
    TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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 non negative percent

Check description
Verifies that the percentage of non-negative values in a column does not exceed the maximum accepted percentage. Creates a separate data quality check (and an alert) for each monthly partition.

Check name Check type Time scale Sensor definition Quality rule
monthly_partition_non_negative_percent partitioned monthly non_negative_percent max_percent

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_non_negative_percent
Run check (Shell)
To run this check provide check name in check run command
dqo> check run -ch=monthly_partition_non_negative_percent
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_non_negative_percent
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_non_negative_percent
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_non_negative_percent
Check structure (Yaml)
      partitioned_checks:
        monthly:
          numeric:
            monthly_partition_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
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:
          numeric:
            monthly_partition_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested

BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH) AS time_period,
    TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    TRUNC(CAST(original_table."" AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(original_table."" AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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:
          numeric:
            monthly_partition_non_negative_percent:
              warning:
                max_percent: 100.0
              error:
                max_percent: 99.0
              fatal:
                max_percent: 95.0
      labels:
      - This is the column that is analyzed for data quality issues
    col_event_timestamp:
      labels:
      - optional column that stores the timestamp when the event/transaction happened
    col_inserted_at:
      labels:
      - optional column that stores the timestamp when row was ingested
    country:
      labels:
      - column used as the first grouping key
    state:
      labels:
      - column used as the second grouping key
BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.`target_column` < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) AS actual_value,

                analyzed_table.grouping_level_1,

                analyzed_table.grouping_level_2
,
    time_period,
    time_period_utc
    FROM(
        SELECT
                   original_table.*,
    original_table."country" AS grouping_level_1,
    original_table."state" AS grouping_level_2,
    TRUNC(CAST(original_table."" AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(original_table."" AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
                   FROM "<target_schema>"."<target_table>" original_table
         ) analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc

PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table."target_column" < 0 THEN 0
            ELSE 1
        END
    ) / COUNT(*) 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

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    100.0 * SUM(
        CASE
            WHEN {{ lib.render_target_column('analyzed_table') }} < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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
    100.0 * SUM(
        CASE
            WHEN analyzed_table.[target_column] < 0 THEN 0
            ELSE 1
        END
    ) / COUNT_BIG(*) 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)