null count match
null count match checks
Description
Column level check that ensures that compares the count of null values in the tested column to the count of null values in a reference column from the reference table.
Compares the count of null values for each group of data. The data is grouped using a GROUP BY clause and groups are matched between the tested (parent) table and the reference table (the source of truth).
profile null count match
Check description
Verifies that percentage of the difference between the count of null values in a tested column in a parent table and the count of null values in a column in the reference table. The difference must be below defined percentage thresholds.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| profile_null_count_match | profiling | null_count | diff_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below 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 Check structure (Yaml)
profiling_checks:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
profile_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
# 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
columns:
target_column:
profiling_checks:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
profile_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
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 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
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.[target_column] IS NULL THEN 1
ELSE 0
END
) 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 null count match
Check description
Verifies that percentage of the difference between the count of null values in a tested column in a parent table and the count of null values in a column in the reference table. The difference must be below defined percentage thresholds. 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_null_count_match | recurring | daily | null_count | diff_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below 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 Check structure (Yaml)
recurring_checks:
daily:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
daily_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
# 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
columns:
target_column:
recurring_checks:
daily:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
daily_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
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 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
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.[target_column] IS NULL THEN 1
ELSE 0
END
) 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 null count match
Check description
Verifies that percentage of the difference between the count of null values in a tested column in a parent table and the count of null values in a column in the reference table. The difference must be below defined percentage thresholds. 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_null_count_match | recurring | monthly | null_count | diff_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below 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 Check structure (Yaml)
recurring_checks:
monthly:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
monthly_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
# 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
columns:
target_column:
recurring_checks:
monthly:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
monthly_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
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 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
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.[target_column] IS NULL THEN 1
ELSE 0
END
) 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 null count match
Check description
Verifies that percentage of the difference between the count of null values in a tested column in a parent table and the count of null values in a column in the reference table. The difference must be below defined percentage thresholds. Compares each daily partition (each day of data) between the compared table and the reference table (the source of truth).
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| daily_partition_null_count_match | partitioned | daily | null_count | diff_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below 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_null_count_match
partitioned_checks:
daily:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
daily_partition_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
# 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
columns:
target_column:
partitioned_checks:
daily:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
daily_partition_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
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 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
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.[target_column] IS NULL THEN 1
ELSE 0
END
) 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 null count match
Check description
Verifies that percentage of the difference between the count of null values in a tested column in a parent table and the count of null values in a column in the reference table. The difference must be below defined percentage thresholds. Compares each monthly partition (each month of data) between the compared table and the reference table (the source of truth).
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| monthly_partition_null_count_match | partitioned | monthly | null_count | diff_percent |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below 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_null_count_match
partitioned_checks:
monthly:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
monthly_partition_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
# 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
columns:
target_column:
partitioned_checks:
monthly:
comparisons:
compare_to_source_of_truth_table:
reference_column: source_of_truth_column_name
monthly_partition_null_count_match:
warning:
max_diff_percent: 0.0
error:
max_diff_percent: 1.0
fatal:
max_diff_percent: 5.0
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 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
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.`target_column` IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table."target_column" IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table')}} IS NULL THEN 1
ELSE 0
END
) 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
SUM(
CASE
WHEN analyzed_table.[target_column] IS NULL THEN 1
ELSE 0
END
) 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)