Merge pull request #7 from IFCA-Advanced-Computing/develop

Update docs and add new tests

CITATION.cff

@@ -9,5 +9,10 @@ authors:
   orcid: "https://orcid.org/0000-0002-0013-4602"
 title: "ANJANA"
 version: 0.2.1
-date-released: 2024-04-18
+date-released: 2024-05-13
 url: "https://github.com/IFCA-Advanced-Computing/anjana"
+identifiers:
+  - type: doi
+    value: 10.5281/zenodo.11186382
+
+

docs/source/getting_started.rst

@@ -124,6 +124,29 @@ Then, in order to create the hierarchies we can define the following dictionary:
                 1: np.array(["*"] * len(data["city"].values))} # Suppression
    }
 
+In addition, we can also use the function _generate_intervals()_ from _utils_ for creating the interval-based hierarchy as follows:
+
+.. code-block:: python
+
+    import numpy as np
+    from anjana.anonymity import utils
+
+    age = data['age'].values
+
+    hierarchies = {
+        "age": {
+            0: data["age"].values,
+            1: utils.generate_intervals(data["age"].values, 0, 100, 5),
+            2: utils.generate_intervals(data["age"].values, 0, 100, 10),
+        },
+        "gender": {
+            0: data["gender"].values,
+            1: np.array(["*"] * len(data["gender"].values)) # Suppression
+        },
+        "city": {0: data["city"].values,
+                 1: np.array(["*"] * len(data["city"].values))} # Suppression
+    }
+
 
 .. _adult dataset: https://archive.ics.uci.edu/ml/datasets/adult
 .. _examples folder of the repository: https://gitlab.ifca.es/privacy-security/siesta-anonymity/-/tree/main/examples

docs/source/index.rst

@@ -1,9 +1,9 @@
 ANJANA
 =============================================================================
 
-|License| |codecov| |DOI| |PyPI| |Downloads| |Documentation Status|
+|License| |codecov| |DOI| |Downloads| |Documentation Status|
 |release-please| |Publish Package in PyPI| |CI/CD Pipeline| |Code Coverage|
-|Python version|
+|Python version| |PyPI|
 
 ANJANA is a `Python`_ library which allows the application of different anonymity
 techniques based on a set of identifiers, quasi-identifiers (QI) and a sensitive 

examples/hospital.py

@@ -16,7 +16,7 @@
 
 import numpy as np
 import pandas as pd
-from anjana.anonymity import k_anonymity, l_diversity, utils
+from anjana.anonymity import k_anonymity, l_diversity, utils, basic_beta_likeness
 
 data = pd.read_csv("data/hospital_extended.csv")
 

tests/test_anonymity.py

@@ -188,6 +188,21 @@ def test_entropy_l(self):
         )
         assert len(data_anon) == 0
 
+    def test_entropy_l1(self):
+        data_anon = anonymity.entropy_l_diversity(
+            self.data,
+            self.ident,
+            self.quasi_ident,
+            self.sens_att,
+            self.k,
+            1,
+            self.supp_level,
+            self.hierarchies,
+        )
+        assert 1 == pycanon.anonymity.entropy_l_diversity(
+            data_anon, self.quasi_ident, [self.sens_att]
+        )
+
     def test_rec_c_l(self):
         data_anon = anonymity.recursive_c_l_diversity(
             self.data,
@@ -365,7 +380,11 @@ class TestHospital:
     l_div = 2
     supp_level = 0
     hierarchies = {
-        "age": dict(pd.read_csv("./examples/hierarchies/age.csv", header=None)),
+        "age": {
+            0: data["age"].values,
+            1: utils.generate_intervals(data["age"].values, 0, 100, 5),
+            2: utils.generate_intervals(data["age"].values, 0, 100, 10),
+        },
         "gender": {
             0: data["gender"].values,
             1: np.array(["*"] * len(data["gender"].values)),
@@ -392,6 +411,18 @@ def test_k_anon(self):
         data_anon_real["age"] = hierarchy_age[2].values[pos]
         assert data_anon_real.equals(data_anon)
 
+    def test_k_anon_big(self):
+        data_anon = anonymity.k_anonymity(
+            self.data,
+            self.ident,
+            self.quasi_ident,
+            30,
+            self.supp_level,
+            self.hierarchies,
+        )
+
+        assert data_anon.equals(pd.DataFrame())
+
     def test_l_div(self):
         data_anon = anonymity.l_diversity(
             self.data,
@@ -414,6 +445,32 @@ def test_l_div(self):
         data_anon_real["city"] = "*"
         assert data_anon_real.equals(data_anon)
 
+    def test_basic_beta0_supp0(self):
+        data_anon = anonymity.basic_beta_likeness(
+            self.data,
+            self.ident,
+            self.quasi_ident,
+            self.sens_att,
+            self.k,
+            0,
+            0,
+            self.hierarchies,
+        )
+        assert data_anon.equals(pd.DataFrame())
+
+    def test_enhanced_beta0_supp0(self):
+        data_anon = anonymity.enhanced_beta_likeness(
+            self.data,
+            self.ident,
+            self.quasi_ident,
+            self.sens_att,
+            self.k,
+            0,
+            0,
+            self.hierarchies,
+        )
+        assert data_anon.equals(pd.DataFrame())
+
     def test_get_transformation(self):
         data_anon = anonymity.k_anonymity(
             self.data,
@@ -431,7 +488,15 @@ def test_get_transformation(self):
 
     def test_get_transformation_2qi(self):
         hierarchies = {
-            "age": dict(pd.read_csv("./examples/hierarchies/age.csv", header=None)),
+            "age": {
+                0: self.data["age"].values,
+                1: utils.generate_intervals(
+                    self.data["age"].values, 0, 100, 5
+                ),
+                2: utils.generate_intervals(
+                    self.data["age"].values, 0, 100, 10
+                ),
+            },
             "city": {
                 0: self.data["city"].values,
                 1: np.array(["*"] * len(self.data["city"].values)),
@@ -447,7 +512,7 @@ def test_get_transformation_2qi(self):
         )
 
         transformation = utils.get_transformation(
-            data_anon, self.quasi_ident, self.hierarchies
+            data_anon, self.quasi_ident, hierarchies
         )
         assert [2, 0, 0] == transformation