데이터 품질 태스크 사용

샘플 1

다음 코드 샘플에서는 이러한 값을 검증하기 위한 데이터 품질 확인을 만듭니다.

• amount: 값은 0 또는 양수입니다.
• item_id: 5자리 영문자 다음에 15자리 숫자가 이어지는 영숫자 문자열입니다.
• transaction_currency: 정적 목록에서 정의된 허용되는 통화 유형입니다. 이 샘플의 정적 목록은 통화 유형으로 GBP 및 JPY를 허용합니다. 이 검증은 국제로 표시된 행에만 적용됩니다.

# The following `NONE` row filter is required.
row_filters:
 NONE:
   filter_sql_expr: |-
      True
 # This filters for rows marked as international (INTNL).
 INTERNATIONAL_ITEMS:
   filter_sql_expr: |-
      REGEXP_CONTAINS(item_id, 'INTNL')

# Rule dimensions are optional but let you aggregate reporting.
rule_dimensions:
  - consistency
  - correctness
  - duplication
  - completeness
  - conformance
  - integrity

# Rules can apply to multiple tables or columns.
rules:
 VALUE_ZERO_OR_POSITIVE:
   rule_type: CUSTOM_SQL_EXPR
   dimension: correctness
   params:
     custom_sql_expr: |-
       $column >= 0

 VALID_ITEM_ID:
   rule_type: REGEX
   dimension: conformance
   params:
     pattern: |-
       [A-Z]{5}[0-9]{15}

 VALID_CURRENCY_ID:
   rule_type: CUSTOM_SQL_EXPR
   dimension: integrity
   params:
     custom_sql_expr: |-
      $column in ('GBP', 'JPY')

# Rule bindings associate rules to columns within tables.
rule_bindings:
  TRANSACTION_AMOUNT_VALID:
   entity_uri: bigquery://projects/PROJECT_ID/datasets/DATASET_ID/tables/sales_orders
   column_id: amount
   row_filter_id: NONE
   rule_ids:
     - VALUE_ZERO_OR_POSITIVE

  TRANSACTION_VALID_ITEM_ID:
   entity_uri: bigquery://projects/PROJECT_ID/datasets/DATASET_ID/tables/sales_orders
   column_id: item_id
   row_filter_id: NONE
   rule_ids:
     - VALID_ITEM_ID

  TRANSACTION_CURRENCY_VALID:
   entity_uri: bigquery://projects/PROJECT_ID/datasets/DATASET_ID/tables/sales_orders
   column_id: transaction_currency
   row_filter_id: INTERNATIONAL_ITEMS
   rule_ids:
     - VALID_CURRENCY_ID

다음을 바꿉니다.

• PROJECT_ID: 프로젝트 ID입니다.
• DATASET_ID: 데이터 세트 ID입니다.

샘플 2

확인할 테이블이 Dataplex 레이크의 일부인 경우 레이크 또는 영역 표기법을 사용하여 테이블을 지정할 수 있습니다. 이렇게 하면 레이크 또는 영역별로 결과를 집계할 수 있습니다. 예를 들어 영역 수준 점수를 생성할 수 있습니다.

이 샘플을 사용하려면 레이크 ID가 operations이고 영역 ID가 procurement인 Dataplex 레이크를 만듭니다. 그런 다음 영역에 sales_orders 테이블을 애셋으로 추가합니다.

# This is a convenience section that allows you to shorten the entity_uri
metadata_registry_defaults:
 dataplex:
   projects: PROJECT_ID
   locations: REGION_ID
   lakes: operations
   zones: procurement

# You have to define a NONE row filter
row_filters:
 NONE:
   filter_sql_expr: |-
      True
 INTERNATIONAL_ITEMS:
   filter_sql_expr: |-
      REGEXP_CONTAINS(item_id, 'INTNL')

# rule dimensions are optional but allow you to aggregate reporting.
rule_dimensions:
  - consistency
  - correctness
  - duplication
  - completeness
  - conformance
  - integrity

# Rules can be shared across tables or columns.
rules:
 VALUE_ZERO_OR_POSITIVE:
   rule_type: CUSTOM_SQL_EXPR
   dimension: correctness
   params:
     custom_sql_expr: |-
       $column >= 0

 VALID_ITEM_ID:
   rule_type: REGEX
   dimension: conformance
   params:
     pattern: |-
       [A-Z]{5}[0-9]{15}

 VALID_CURRENCY_ID:
   rule_type: CUSTOM_SQL_EXPR
   dimension: integrity
   params:
     custom_sql_expr: |-
      $column in ('GBP', 'JPY')

#rule bindings associate rules to {table, column}
rule_bindings:
 TRANSACTION_AMOUNT_VALID:
   entity_uri: dataplex://projects/PROJECT_ID/locations/REGION_ID/lakes/operations/zones/procurement/entities/sales_orders
   column_id: amount
   row_filter_id: NONE
   rule_ids:
     - VALUE_ZERO_OR_POSITIVE

 TRANSACTION_VALID_ITEM_ID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders # omitting projects/locations/lakes from uri path to use the default values specified in metadata_registry_defaults
   column_id: item_id
   row_filter_id: NONE
   rule_ids:
     - VALID_ITEM_ID

 TRANSACTION_CURRENCY_VALID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders
   column_id: transaction_currency
   row_filter_id: INTERNATIONAL_ITEMS
   rule_ids:
     - VALID_CURRENCY_ID

다음을 바꿉니다.

• PROJECT_ID: 프로젝트 ID입니다.
• REGION_ID: 테이블이 있는 Dataplex 레이크의 리전 ID입니다(예: us-central1).

샘플 3

이 예시에서는 ID 값이 고유한지 확인하는 커스텀 SQL 확인을 추가하여 샘플 2를 개선합니다.

# This is a convenience section that allows you to shorten the entity_uri
metadata_registry_defaults:
 dataplex:
   projects: PROJECT_ID
   locations: REGION_ID
   lakes: operations
   zones: procurement

# You have to define a NONE row filter
row_filters:
 NONE:
   filter_sql_expr: |-
      True
 INTERNATIONAL_ITEMS:
   filter_sql_expr: |-
      REGEXP_CONTAINS(item_id, 'INTNL')

# rule dimensions are optional but allow you to aggregate reporting.
rule_dimensions:
  - consistency
  - correctness
  - duplication
  - completeness
  - conformance
  - integrity

# Rules can be shared across tables or columns.
rules:
# This rule is parameterized with column_names as parameter
 NO_DUPLICATES_IN_COLUMN_GROUPS:
   rule_type: CUSTOM_SQL_STATEMENT
   dimension: duplication
   params:
     custom_sql_arguments:
       - column_names
     custom_sql_statement: |-
       select a.*
       from data a
       inner join (
         select
           $column_names
         from data
         group by $column_names
         having count(*) > 1
       ) duplicates
       using ($column_names)

 VALUE_ZERO_OR_POSITIVE:
   rule_type: CUSTOM_SQL_EXPR
   dimension: correctness
   params:
     custom_sql_expr: |-
       $column >= 0

 VALID_ITEM_ID:
   rule_type: REGEX
   dimension: conformance
   params:
     pattern: |-
       [A-Z]{5}[0-9]{15}

 VALID_CURRENCY_ID:
   rule_type: CUSTOM_SQL_EXPR
   dimension: integrity
   params:
     custom_sql_expr: |-
      $column in ('GBP', 'JPY')

#rule bindings associate rules to {table, column}

rule_bindings:
 TRANSACTIONS_UNIQUE:
   entity_uri: dataplex://projects/PROJECT_ID/locations/REGION_ID/lakes/operations/zones/procurement/entities/sales_orders
   column_id: id
   row_filter_id: NONE
   rule_ids:
     - NO_DUPLICATES_IN_COLUMN_GROUPS:
         column_names: "id"

 TRANSACTION_AMOUNT_VALID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders # omitting projects/locations/lakes from uri path to use the default values specified in metadata_registry_defaults
   column_id: amount
   row_filter_id: NONE
   rule_ids:
     - VALUE_ZERO_OR_POSITIVE

 TRANSACTION_VALID_ITEM_ID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders
   column_id: item_id
   row_filter_id: NONE
   rule_ids:
     - VALID_ITEM_ID

 TRANSACTION_CURRENCY_VALID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders
   column_id: transaction_currency
   row_filter_id: INTERNATIONAL_ITEMS
   rule_ids:
     - VALID_CURRENCY_ID

샘플 4

이 예시에서는 last_modified_timestamp 열을 사용하여 점진적 검증을 추가하여 샘플 3을 개선합니다. 하나 이상의 규칙 결합에 대한 점진적 검증을 추가할 수 있습니다.

# This is a convenience section that allows you to shorten the entity_uri
metadata_registry_defaults:
 dataplex:
   projects: PROJECT_ID
   locations: REGION_ID
   lakes: operations
   zones: procurement

# You have to define a NONE row filter
row_filters:
 NONE:
   filter_sql_expr: |-
      True
 INTERNATIONAL_ITEMS:
   filter_sql_expr: |-
      REGEXP_CONTAINS(item_id, 'INTNL')

# rule dimensions are optional but allow you to aggregate reporting.
rule_dimensions:
  - consistency
  - correctness
  - duplication
  - completeness
  - conformance
  - integrity

# Rules can be shared across tables or columns.
rules:
# This rule is parameterized with column_names as parameter
 NO_DUPLICATES_IN_COLUMN_GROUPS:
   rule_type: CUSTOM_SQL_STATEMENT
   dimension: duplication
   params:
     custom_sql_arguments:
       - column_names
     custom_sql_statement: |-
       select a.*
       from data a
       inner join (
         select
           $column_names
         from data
         group by $column_names
         having count(*) > 1
       ) duplicates
       using ($column_names)

 VALUE_ZERO_OR_POSITIVE:
   rule_type: CUSTOM_SQL_EXPR
   dimension: correctness
   params:
     custom_sql_expr: |-
       $column >= 0

 VALID_ITEM_ID:
   rule_type: REGEX
   dimension: conformance
   params:
     pattern: |-
       [A-Z]{5}[0-9]{15}

 VALID_CURRENCY_ID:
   rule_type: CUSTOM_SQL_EXPR
   dimension: integrity
   params:
     custom_sql_expr: |-
      $column in ('GBP', 'JPY')

#rule bindings associate rules to {table, column}

rule_bindings:
 TRANSACTIONS_UNIQUE:
   entity_uri: dataplex://projects/PROJECT_ID/locations/REGION_ID/lakes/operations/zones/procurement/entities/sales_orders
   column_id: id
   row_filter_id: NONE
   incremental_time_filter_column_id: last_modified_timestamp
   rule_ids:
     - NO_DUPLICATES_IN_COLUMN_GROUPS:
         column_names: "id"

 TRANSACTION_AMOUNT_VALID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders # omitting projects/locations/lakes from uri path to use the default values specified in metadata_registry_defaults
   column_id: amount
   row_filter_id: NONE
   incremental_time_filter_column_id: last_modified_timestamp
   rule_ids:
     - VALUE_ZERO_OR_POSITIVE

 TRANSACTION_VALID_ITEM_ID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders
   column_id: item_id
   row_filter_id: NONE
   incremental_time_filter_column_id: last_modified_timestamp
   rule_ids:
     - VALID_ITEM_ID

 TRANSACTION_CURRENCY_VALID:
   entity_uri: dataplex://zones/procurement/entities/sales_orders
   column_id: transaction_currency
   row_filter_id: INTERNATIONAL_ITEMS
   incremental_time_filter_column_id: last_modified_timestamp
   rule_ids:
     - VALID_CURRENCY_ID