RiskProfile¶
RiskProfile encapsulates the re-identification risks associated with a given Dataset
RiskProfile contains two main properties¶
Re-Identification Risks
- Lowest prosecutor re-identification risk.
- Individuals affected by lowest risk.
- Highest prosecutor re-identification risk.
- Individuals affected by highest risk.
- Average prosecutor re-identification risk.
- Fraction of unique records.
- Attacker success rate against the re-identification risk.
- Population Model name
- Quasi-identifiers
Distribution of Risks
The distribution of re-identification risks amongst the records of the dataset
-
class
pyarxaas.models.risk_profile.RiskProfile(metrics: collections.abc.Mapping)[source]¶ Represents the re-identification risks associated with a Dataset
-
attacker_success_rate¶ Attacker success rates against re-identification for a given Dataset
Returns: dict containing the attacker success rate.
-
distribution_of_risk¶ Distribution of risk for a given Dataset
Returns: dict containing the distribution of risks in a given Dataset
-
distribution_of_risk_dataframe() → pandas.core.frame.DataFrame[source]¶ Distribution of risk as a pandas.DataFrame
Returns: pandas.DataFrame
-
population_model¶ Population model used to analyze a given Dataset
Returns: The Population model name used to analyze a given Dataset
-
quasi_identifiers¶ Quasi-identifiers for a given Dataset
Returns: dict containing a list of all the quasi-identifying attribute in a a given Dataset
-
re_identification_risk¶ Re-identification risk metrics for a given Dataset
Returns: dict containing re-identification metrics
-