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:



1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1736

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.
  #
  #     Note: The following fields are mutually exclusive: `info_type`, `custom_tag`, `inferred`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!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).
  #
  #     Note: The following fields are mutually exclusive: `custom_tag`, `info_type`, `inferred`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!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
  #
  #     Note: The following fields are mutually exclusive: `inferred`, `info_type`, `custom_tag`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  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:



1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1736

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.
  #
  #     Note: The following fields are mutually exclusive: `info_type`, `custom_tag`, `inferred`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!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).
  #
  #     Note: The following fields are mutually exclusive: `custom_tag`, `info_type`, `inferred`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!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
  #
  #     Note: The following fields are mutually exclusive: `inferred`, `info_type`, `custom_tag`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  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.



1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1736

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.
  #
  #     Note: The following fields are mutually exclusive: `info_type`, `custom_tag`, `inferred`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!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).
  #
  #     Note: The following fields are mutually exclusive: `custom_tag`, `info_type`, `inferred`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!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
  #
  #     Note: The following fields are mutually exclusive: `inferred`, `info_type`, `custom_tag`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  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