row count match

row count match checks

Description
Table level comparison check compares the row count of the current (parent) table to a reference table.

profile row count match

Check description
Verifies that the row count of the tested (parent) table matches the row count of the reference table. Compares each group of data with a GROUP BY clause.

Check name	Check type	Time scale	Sensor definition	Quality rule
profile_row_count_match	profiling		row_count	diff_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_row_count_match

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

dqo> check run -ch=profile_row_count_match

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_row_count_match

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_row_count_match

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_row_count_match

Check structure (Yaml)

  profiling_checks:
    comparisons:
      compare_to_source_of_truth_table:
        profile_row_count_match:
          warning:
            max_diff_percent: 0.0
          error:
            max_diff_percent: 1.0
          fatal:
            max_diff_percent: 5.0

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
  table_comparisons:
    compare_to_source_of_truth_table:
      reference_table_connection_name: <source_of_truth_connection_name>
      reference_table_schema_name: <source_of_truth_schema_name>
      reference_table_name: <source_of_truth_table_name>
      check_type: profiling
      grouping_columns:
      - compared_table_column_name: country
        reference_table_column_name: country_column_name_on_reference_table
      - compared_table_column_name: state
        reference_table_column_name: state_column_name_on_reference_table
  profiling_checks:
    comparisons:
      compare_to_source_of_truth_table:
        profile_row_count_match:
          warning:
            max_diff_percent: 0.0
          error:
            max_diff_percent: 1.0
          fatal:
            max_diff_percent: 5.0
  columns:
    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 for calculating aggregated values used
        for the table comparison
    state:
      labels:
      - column used as the first grouping key for calculating aggregated values used
        for the table comparison

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for OracleRendered SQL for Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections_reference('grouping_table') }}
    {{- lib.render_time_dimension_projection_reference('grouping_table') }}
FROM (
    SELECT 1 AS actual_value
        {{- lib.render_data_grouping_projections('analyzed_table') }}
        {{- lib.render_time_dimension_projection('analyzed_table') }}
    FROM {{ lib.render_target_table() }} analyzed_table
    {{- lib.render_where_clause() -}}
) grouping_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT 1 AS actual_value,
    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>" analyzed_table) grouping_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    COUNT_BIG(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT_BIG(*) 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

daily row count match

Check description
Verifies that the row count of the tested (parent) table matches the row count of the reference table. Compares each group of data with a GROUP BY clause. 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_row_count_match	recurring	daily	row_count	diff_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_row_count_match

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

dqo> check run -ch=daily_row_count_match

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_row_count_match

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_row_count_match

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_row_count_match

Check structure (Yaml)

  recurring_checks:
    daily:
      comparisons:
        compare_to_source_of_truth_table:
          daily_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0

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
  table_comparisons:
    compare_to_source_of_truth_table:
      reference_table_connection_name: <source_of_truth_connection_name>
      reference_table_schema_name: <source_of_truth_schema_name>
      reference_table_name: <source_of_truth_table_name>
      check_type: profiling
      grouping_columns:
      - compared_table_column_name: country
        reference_table_column_name: country_column_name_on_reference_table
      - compared_table_column_name: state
        reference_table_column_name: state_column_name_on_reference_table
  recurring_checks:
    daily:
      comparisons:
        compare_to_source_of_truth_table:
          daily_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0
  columns:
    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 for calculating aggregated values used
        for the table comparison
    state:
      labels:
      - column used as the first grouping key for calculating aggregated values used
        for the table comparison

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for OracleRendered SQL for Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections_reference('grouping_table') }}
    {{- lib.render_time_dimension_projection_reference('grouping_table') }}
FROM (
    SELECT 1 AS actual_value
        {{- lib.render_data_grouping_projections('analyzed_table') }}
        {{- lib.render_time_dimension_projection('analyzed_table') }}
    FROM {{ lib.render_target_table() }} analyzed_table
    {{- lib.render_where_clause() -}}
) grouping_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT 1 AS actual_value,
    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>" analyzed_table) grouping_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    CAST(LOCALTIMESTAMP AS date) AS time_period,
    CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    CAST(LOCALTIMESTAMP AS date) AS time_period,
    CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
    TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    COUNT_BIG(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT_BIG(*) 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

monthly row count match

Check description
Verifies that the row count of the tested (parent) table matches the row count of the reference table. Compares each group of data with a GROUP BY clause. Stores the most recent captured value for each month when the data quality check was evaluated.

Check name	Check type	Time scale	Sensor definition	Quality rule
monthly_row_count_match	recurring	monthly	row_count	diff_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_row_count_match

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

dqo> check run -ch=monthly_row_count_match

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_row_count_match

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_row_count_match

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_row_count_match

Check structure (Yaml)

  recurring_checks:
    monthly:
      comparisons:
        compare_to_source_of_truth_table:
          monthly_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0

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
  table_comparisons:
    compare_to_source_of_truth_table:
      reference_table_connection_name: <source_of_truth_connection_name>
      reference_table_schema_name: <source_of_truth_schema_name>
      reference_table_name: <source_of_truth_table_name>
      check_type: profiling
      grouping_columns:
      - compared_table_column_name: country
        reference_table_column_name: country_column_name_on_reference_table
      - compared_table_column_name: state
        reference_table_column_name: state_column_name_on_reference_table
  recurring_checks:
    monthly:
      comparisons:
        compare_to_source_of_truth_table:
          monthly_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0
  columns:
    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 for calculating aggregated values used
        for the table comparison
    state:
      labels:
      - column used as the first grouping key for calculating aggregated values used
        for the table comparison

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for OracleRendered SQL for Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections_reference('grouping_table') }}
    {{- lib.render_time_dimension_projection_reference('grouping_table') }}
FROM (
    SELECT 1 AS actual_value
        {{- lib.render_data_grouping_projections('analyzed_table') }}
        {{- lib.render_time_dimension_projection('analyzed_table') }}
    FROM {{ lib.render_target_table() }} analyzed_table
    {{- lib.render_where_clause() -}}
) grouping_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT 1 AS actual_value,
    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>" analyzed_table) grouping_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Snowflake

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
    TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

SQL Server

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    COUNT_BIG(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT_BIG(*) 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

daily partition row count match

Check description
Verifies that the row count of the tested (parent) table matches the row count of the reference table. Compares each group of data with a GROUP BY clause on the time period (the daily partition) and all other data grouping columns. Stores the most recent captured value for each daily partition that was analyzed.

Check name	Check type	Time scale	Sensor definition	Quality rule
daily_partition_row_count_match	partitioned	daily	row_count	diff_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_row_count_match

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

dqo> check run -ch=daily_partition_row_count_match

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_row_count_match

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_row_count_match

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_row_count_match

Check structure (Yaml)

  partitioned_checks:
    daily:
      comparisons:
        compare_to_source_of_truth_table:
          daily_partition_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0

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
  table_comparisons:
    compare_to_source_of_truth_table:
      reference_table_connection_name: <source_of_truth_connection_name>
      reference_table_schema_name: <source_of_truth_schema_name>
      reference_table_name: <source_of_truth_table_name>
      check_type: profiling
      grouping_columns:
      - compared_table_column_name: country
        reference_table_column_name: country_column_name_on_reference_table
      - compared_table_column_name: state
        reference_table_column_name: state_column_name_on_reference_table
  partitioned_checks:
    daily:
      comparisons:
        compare_to_source_of_truth_table:
          daily_partition_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0
  columns:
    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 for calculating aggregated values used
        for the table comparison
    state:
      labels:
      - column used as the first grouping key for calculating aggregated values used
        for the table comparison

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for OracleRendered SQL for Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections_reference('grouping_table') }}
    {{- lib.render_time_dimension_projection_reference('grouping_table') }}
FROM (
    SELECT 1 AS actual_value
        {{- lib.render_data_grouping_projections('analyzed_table') }}
        {{- lib.render_time_dimension_projection('analyzed_table') }}
    FROM {{ lib.render_target_table() }} analyzed_table
    {{- lib.render_where_clause() -}}
) grouping_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT 1 AS actual_value,
    TRUNC(CAST(analyzed_table."" AS DATE)) AS time_period,
    CAST(TRUNC(CAST(analyzed_table."" AS DATE)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
    FROM "<target_schema>"."<target_table>" analyzed_table) grouping_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    CAST(analyzed_table."" AS date) AS time_period,
    CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    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
    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)

monthly partition row count match

Check description
Verifies that the row count of the tested (parent) table matches the row count of the reference table, for each monthly partition (grouping rows by the time period, truncated to the month). Compares each group of data with a GROUP BY clause. Stores the most recent captured value for each monthly partition and optionally data groups.

Check name	Check type	Time scale	Sensor definition	Quality rule
monthly_partition_row_count_match	partitioned	monthly	row_count	diff_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_row_count_match

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

dqo> check run -ch=monthly_partition_row_count_match

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_row_count_match

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_row_count_match

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_row_count_match

Check structure (Yaml)

  partitioned_checks:
    monthly:
      comparisons:
        compare_to_source_of_truth_table:
          monthly_partition_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0

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
  table_comparisons:
    compare_to_source_of_truth_table:
      reference_table_connection_name: <source_of_truth_connection_name>
      reference_table_schema_name: <source_of_truth_schema_name>
      reference_table_name: <source_of_truth_table_name>
      check_type: profiling
      grouping_columns:
      - compared_table_column_name: country
        reference_table_column_name: country_column_name_on_reference_table
      - compared_table_column_name: state
        reference_table_column_name: state_column_name_on_reference_table
  partitioned_checks:
    monthly:
      comparisons:
        compare_to_source_of_truth_table:
          monthly_partition_row_count_match:
            warning:
              max_diff_percent: 0.0
            error:
              max_diff_percent: 1.0
            fatal:
              max_diff_percent: 5.0
  columns:
    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 for calculating aggregated values used
        for the table comparison
    state:
      labels:
      - column used as the first grouping key for calculating aggregated values used
        for the table comparison

BigQuery

Sensor template for BigQueryRendered SQL for BigQuery

{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for MySQLRendered SQL for MySQL

{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for OracleRendered SQL for Oracle

{% import '/dialects/oracle.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections_reference('grouping_table') }}
    {{- lib.render_time_dimension_projection_reference('grouping_table') }}
FROM (
    SELECT 1 AS actual_value
        {{- lib.render_data_grouping_projections('analyzed_table') }}
        {{- lib.render_time_dimension_projection('analyzed_table') }}
    FROM {{ lib.render_target_table() }} analyzed_table
    {{- lib.render_where_clause() -}}
) grouping_table
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    time_period,
    time_period_utc
FROM (
    SELECT 1 AS actual_value,
    TRUNC(CAST(analyzed_table."" AS DATE), 'MONTH') AS time_period,
    CAST(TRUNC(CAST(analyzed_table."" AS DATE), 'MONTH') AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
    FROM "<target_schema>"."<target_table>" analyzed_table) grouping_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

PostgreSQL

Sensor template for PostgreSQLRendered SQL for PostgreSQL

{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
    COUNT(*) AS actual_value
    {{- lib.render_data_grouping_projections('analyzed_table') }}
    {{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}

SELECT
    COUNT(*) AS actual_value,
    DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
    CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc

Redshift

Sensor template for RedshiftRendered SQL for Redshift

{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for SnowflakeRendered SQL for Snowflake

{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
    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
    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

Sensor template for SQL ServerRendered SQL for SQL Server

{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
    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
    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)