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

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

Overview

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.

Defined Under Namespace

Classes: AuxiliaryTable, TaggedField

Instance Attribute Summary collapse

Instance Attribute Details

#auxiliary_tables ⇒ ::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>

Returns 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.

Returns:



1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1611

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

#quasi_ids ⇒ ::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>

Returns Required. Fields considered to be quasi-identifiers. No two columns can have the same tag.

Returns:



1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1611

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

#region_code ⇒ ::String

Returns 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.

Returns:

  • (::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.



1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1611

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