hierarchies

README.md

@@ -33,22 +33,28 @@ Attribute        | Classification
 
 Table: Attribute classifications
 
+
 ## Justifications
 
 The vast majority of attributes present low values of distinction. This is consistent with the nature of
 the dataset, considering that `fnlwgt` should indicate the quantity of individuals that present the same
 set of attributes.
 
+
 ### `age`
 
 According to HIPPA recommendations, and together with it's very high separation value (99.87%), we classify
 this attribute as a QID.
 
+![Hierarchy for attribute `age`](coding-model/hierarchies/age/age.png){width=14cm}
+
+
 ### `workclass`
 
 This attribute presents a relatively low separation value (49.71%), and given how generic it is, it's
 deemed Insensitive.
 
+
 ### `fnlwgt`
 
 Despite high values of distinction (66.48%) and separation (99.99%) the `fnlwgt` column is not a QID
@@ -75,10 +81,14 @@ U.S.A., the origin of the dataset, which implies this attribute is not a count,
 
 We also note there are substantially more Male than Female records (more than double the `fnlwgt`).
 
+
 ### `education`
 
 This attribute presents a separation of 80.96%, which is quite high, thus we classified it as a QID.
 
+![Hierarchy for attribute `education`](coding-model/hierarchies/education/education.png){width=14cm}
+
+
 ### `education-num`
 
 We exported the anonymized dataset and used the following command to verify there weren't any discrepencies
@@ -93,25 +103,40 @@ representation of the `education` attribute. As such, this attribute
 recieves the same classification, which is backed by the equally high
 separation value of 80.96%, so it's classified as a QID.
 
+![Hierarchy for attribute `education-num`](coding-model/hierarchies/education/education-num.png){width=14cm}
+
+
 ### `marital-status`
 
 With a relatively high separation value of 66.01%, together with the fact that it could be cross
 referenced with other available datasets, we classify this attribute as a QID.
 
+![Hierarchy for attribute `marital-status`](coding-model/hierarchies/marital-status/marital-status.png){width=14cm}
+
+
 ### `occupation`
 
 With a separation of 90.02%, this attribute is classified as a QID.
 
+![Hierarchy for attribute `occupation`](coding-model/hierarchies/occupation.png){width=14cm}
+
+
 ### `relationship`
 
 Given it's separation value of 73.21%, this attribute is classified as a QID.
 
+![Hierarchy for attribute `relationship`](coding-model/hierarchies/relationship/relationship.png){width=14cm}
+
+
 ### `race`
 
 This collumn presents some weirdly specific values (Amer-Indian-Eskimo), but has a separation of 25.98%; given the fact
 that this attribute could be cross referenced with other datases, it is classified as a QID, so
 it may be transformed into more generic values.
 
+![Hierarchy for attribute `race`](coding-model/hierarchies/race.png)
+
+
 ### `sex`
 
 Despite the low separation value of 44.27%, this attribute is canonically classified as a QID, since
@@ -140,6 +165,9 @@ Doctorate	 |	   86 |	 327
 
 Table: Number of records with each `education` for each `sex`
 
+![Hierarchy for attribute `sex`](coding-model/hierarchies/sex.png)
+
+
 ### `capital-gain` & `capital-loss`
 
 With a separation of 15.93% and 9.15% respectively, these attributes are not QIDs. They're qualified as
@@ -150,20 +178,24 @@ A t-closeness privacy model was chosen for these attributes, with a
 value of t of 0.2. This reasoning is discussed in Applying
 anonymization models > k-Anonymity > Effect of parameters
 
+
 ### `hours-per-week`
 
 This attribute has a relatively high separation (76.24%) and since it had really unique values, it
 could be cross referenced with another dataset to help identify individuals, so it's classified as QID.
 
+
 ### `native-country`
 
 While this attribute might be regarded as a QID, it presents really low separation values (19.65%) in this
 dataset, so it's qualified as Insensitive.
 
+
 ### `prediction`
 
 This is the target attribute, the attribute the other attributes predict, and is therefore Insensitive.
 
+
 # Privacy risks in the original dataset
 
 In the original dataset, nearly 40% of records have a more than 50% risk of re-identification by
@@ -179,8 +211,10 @@ it's potentially easier to re-identify the individuals in question.
 
 All attacker models show a success rate of more than 50%, which is not acceptable.
 
+
 # Applying anonymization models
 
+
 ## k-Anonymity
 
 We opted for 8-anonymity, for it's tradeoff between maximal risk and suppression.
@@ -188,12 +222,14 @@ We opted for 8-anonymity, for it's tradeoff between maximal risk and suppression
 t-closeness was chosen for `capital-gain` and `capital-loss`
 (sensitive attributes).
 
+
 ### Re-identification risk
 
 The average re-identification risk dropped to nearly 0%, whereas the
 maximal risk dropped to 12.5%. The success rate for all attacker
 models was reduced drastically, to 1.3%.
 
+
 ### Utility
 
 The original Classification Performance, a measure of how well the attributes
@@ -205,6 +241,7 @@ value being equal across all atributes suggests entire rows were
 removed, rather than select values from separate rows. The only
 exception is the `occupation` attribute, which was entirely removed.
 
+
 ### Effect of parameters
 
 At a suppression limit of 0%, the same accuracy is maintained, but the
@@ -242,15 +279,18 @@ increased Generalization Intensity values.
 
 Adjusting the coding model had no significant effects.
 
+
 ## $(\epsilon, \delta)$-Differential Privacy
 
 With the default $\epsilon$ value of 2 and a $\delta$ value of
 $10^{-6}$, the performance was really good.
 
+
 ### Re-identification risk
 
 All indicators for risk by each attacker model was between 0.1% and 0.9%.
 
+
 ### Utility
 
 The original Classification Performance was 83.24% and it remained
@@ -259,6 +299,7 @@ at 80.97%.
 Nearly 16% of attributes are missing, with the expection of `age` and
 `education-num`, which are 100% missing.
 
+
 ### Effect of parameters
 
 An $\epsilon$ value of 3 maintained the accuracy at 80.5% with
@@ -270,12 +311,14 @@ performance of 82.05% and a missings value of 21.02% for all attributes.
 A further increase of $\delta$ to $10^{-4}$ resulted in an increased
 accuracy of 82.32%, but a maximal risk of 1.25%.
 
+
 # Results
 
 The 8-anonymity model was chosen as it resulted in a broader
 distribution of attribute values like `age`, whereas with Differential
 Privacy, they were split into only 2 categories.
 
+
 # Observations
 
 We noted that the contingency between `sex` and `relationship` maintained