Class: Google::Cloud::Dlp::V2::PrivacyMetric

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/privacy/dlp/v2/dlp.rb

Overview

Privacy metric to compute for reidentification risk analysis.

Defined Under Namespace

Classes: CategoricalStatsConfig, DeltaPresenceEstimationConfig, KAnonymityConfig, KMapEstimationConfig, LDiversityConfig, NumericalStatsConfig

Instance Attribute Summary collapse

Instance Attribute Details

#categorical_stats_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::CategoricalStatsConfig

Returns Categorical stats.

Returns:



1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1395

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point number
    #     between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#delta_presence_estimation_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::DeltaPresenceEstimationConfig

Returns delta-presence.

Returns:



1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1395

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point number
    #     between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#k_anonymity_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::KAnonymityConfig

Returns K-anonymity.

Returns:



1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1395

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point number
    #     between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#k_map_estimation_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig

Returns k-map.

Returns:



1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1395

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point number
    #     between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#l_diversity_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::LDiversityConfig

Returns l-diversity.

Returns:



1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1395

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point number
    #     between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#numerical_stats_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::NumericalStatsConfig

Returns Numerical stats.

Returns:



1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1395

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point number
    #     between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can have the
  #     same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end