From 2f425df5df65d0ca5b1c7d113aa9de5ed5d29222 Mon Sep 17 00:00:00 2001
From: zinwang <32264884+zinwang@users.noreply.github.com>
Date: Thu, 27 Jul 2023 13:34:58 +0800
Subject: [PATCH] Add showcase for computing t-closeness (#28)

---
 README.md                                     | 39 +++++++++++++++++++
 data/patient_anonymized.csv                   | 10 +++++
 .../patient_hierarchy_Age.csv                 |  9 +++++
 .../patient_hierarchy_Disease.csv             |  6 +++
 .../patient_hierarchy_ZIPCode.csv             |  9 +++++
 5 files changed, 73 insertions(+)
 create mode 100644 data/patient_anonymized.csv
 create mode 100644 data/patient_hierarchy/patient_hierarchy_Age.csv
 create mode 100644 data/patient_hierarchy/patient_hierarchy_Disease.csv
 create mode 100644 data/patient_hierarchy/patient_hierarchy_ZIPCode.csv

diff --git a/README.md b/README.md
index 08ed971..e1417fa 100644
--- a/README.md
+++ b/README.md
@@ -334,6 +334,45 @@ $ python3 l-diversity.py
 }
 ```
 
+#### Compute the t-closeness
+
+```python
+from PETWorks import PETValidation, report
+from PETWorks.attributetypes import (
+    SENSITIVE_ATTRIBUTE,
+    QUASI_IDENTIFIER,
+)
+
+anonymized = "data/patient_anonymized.csv"
+dataHierarchy = "data/patient_hierarchy"
+
+attributeTypes = {
+    "ZIPCode": QUASI_IDENTIFIER,
+    "Age": QUASI_IDENTIFIER,
+    "Disease": SENSITIVE_ATTRIBUTE,
+}
+
+result = PETValidation(
+    None,
+    anonymized,
+    "t-closeness",
+    dataHierarchy=dataHierarchy,
+    attributeTypes=attributeTypes,
+    tLimit=0.376,
+)
+report(result, "json")
+```
+
+Execution Result
+
+```  
+$ python3 t-closeness.py
+{
+    "t": 0.376,
+    "fulfill t-closeness": true
+}
+```
+
 #### Anonymize with the k-anonymity
 
 ```python
diff --git a/data/patient_anonymized.csv b/data/patient_anonymized.csv
new file mode 100644
index 0000000..7c68f1f
--- /dev/null
+++ b/data/patient_anonymized.csv
@@ -0,0 +1,10 @@
+ZIPCode;Age;Salary;Disease
+4767*;<=40;3;gastric ulcer
+4760*;<=40;4;gastritis
+4767*;<=40;5;stomach cancer
+4790*;>40;6;gastritis
+4790*;>40;11;flu
+4790*;>40;8;bronchitis
+4760*;<=40;7;bronchitis
+4767*;<=40;9;pneumonia
+4760*;<=40;10;stomach cancer
diff --git a/data/patient_hierarchy/patient_hierarchy_Age.csv b/data/patient_hierarchy/patient_hierarchy_Age.csv
new file mode 100644
index 0000000..256fd5e
--- /dev/null
+++ b/data/patient_hierarchy/patient_hierarchy_Age.csv
@@ -0,0 +1,9 @@
+29;[20,30[;*
+22;[20,30[;*
+27;[20,30[;*
+43;>=40;*
+52;>=40;*
+47;>=40;*
+30;[30,40[;*
+36;[30,40[;*
+32;[30,40[;*
diff --git a/data/patient_hierarchy/patient_hierarchy_Disease.csv b/data/patient_hierarchy/patient_hierarchy_Disease.csv
new file mode 100644
index 0000000..7ddaa27
--- /dev/null
+++ b/data/patient_hierarchy/patient_hierarchy_Disease.csv
@@ -0,0 +1,6 @@
+gastric ulcer;stomach disease;digestive system disease;respiratory&digestive disease
+gastritis;stomach disease;digestive system disease;respiratory&digestive disease
+flu;respiratory infection;vascular lung disease;respiratory&digestive disease
+bronchitis;respiratory infection;vascular lung disease;respiratory&digestive disease
+pneumonia;respiratory infection;vascular lung disease;respiratory&digestive disease
+stomach cancer;stomach disease;digestive system disease;respiratory&digestive disease
diff --git a/data/patient_hierarchy/patient_hierarchy_ZIPCode.csv b/data/patient_hierarchy/patient_hierarchy_ZIPCode.csv
new file mode 100644
index 0000000..6eba0c0
--- /dev/null
+++ b/data/patient_hierarchy/patient_hierarchy_ZIPCode.csv
@@ -0,0 +1,9 @@
+47677;4767*;476**;47***;4****;*****
+47602;4760*;476**;47***;4****;*****
+47678;4767*;476**;47***;4****;*****
+47905;4790*;479**;47***;4****;*****
+47909;4790*;479**;47***;4****;*****
+47906;4790*;479**;47***;4****;*****
+47605;4760*;476**;47***;4****;*****
+47673;4767*;476**;47***;4****;*****
+47607;4760*;476**;47***;4****;*****