/**
* Performs the test
*
* @throws IOException
*/
@Test
public void test() throws IOException {
final Data data = getDataObject(testCase);
// Create an instance of the anonymizer
final ARXAnonymizer anonymizer = new ARXAnonymizer();
testCase.config.setPracticalMonotonicity(testCase.practical);
// Warm up
System.out.println("Experiment:");
System.out.println(" - Dataset: " + testCase.dataset);
System.out.println(" - Utility measure: " + testCase.config.getMetric().toString());
System.out.println(" - Practical monotonicity: " + testCase.practical);
System.out.println(" - Suppression limit: " + testCase.config.getMaxOutliers());
System.out.println(" - Privacy model: " + getPrivacyModel(testCase.config));
System.out.println(" - Performing experiment:");
System.out.println(" * Warmup");
long time = System.currentTimeMillis();
ARXResult result = anonymizer.anonymize(data, testCase.config);
System.out.println(" * Performed in: " + (System.currentTimeMillis() - time) + " [ms]");
// Collect statistics
int[] statistics = new int[7];
for (ARXNode[] level : result.getLattice().getLevels()) {
for (ARXNode arxNode : level) {
statistics[0]++;
if (arxNode.isChecked()) {
statistics[1]++;
}
if (arxNode.getAnonymity() == Anonymity.ANONYMOUS) {
statistics[2]++;
}
if (arxNode.getAnonymity() == Anonymity.NOT_ANONYMOUS) {
statistics[3]++;
}
if (arxNode.getAnonymity() == Anonymity.PROBABLY_ANONYMOUS) {
statistics[4]++;
}
if (arxNode.getAnonymity() == Anonymity.PROBABLY_NOT_ANONYMOUS) {
statistics[5]++;
}
if (arxNode.getMaximumInformationLoss() == arxNode.getMinimumInformationLoss()) {
statistics[6]++;
}
}
}
System.out.println(getClassification(statistics));
// Repeat
time = System.currentTimeMillis();
for (int i = 0; i < 10; i++) {
System.out.println(" * Repetition " + (i + 1) + " of 10");
data.getHandle().release();
result = anonymizer.anonymize(data, testCase.config);
}
time = (System.currentTimeMillis() - time) / 10;
System.out.println(" -> Anonymization performed in: " + time + " [ms]");
}
/**
* Performs a test.
*
* @throws IOException
*/
@Test
public void testNullHierarchy() throws IOException {
try {
final ARXAnonymizer anonymizer = new ARXAnonymizer();
final Data data = provider.getData();
data.getDefinition().setAttributeType("age", (AttributeType) null);
final ARXConfiguration config = ARXConfiguration.create();
config.addCriterion(new KAnonymity(2));
config.setMaxOutliers(1.2d);
anonymizer.anonymize(data, config);
} catch (final NullPointerException e) {
return;
}
Assert.fail();
}
/**
* Performs a test.
*
* @throws IOException
*/
@Test
public void testEmptyDatasetWithAttributeDefinition() throws IOException {
try {
final ARXAnonymizer anonymizer = new ARXAnonymizer();
final Data data = Data.create();
data.getDefinition().setAttributeType("age", AttributeType.IDENTIFYING_ATTRIBUTE);
final ARXConfiguration config = ARXConfiguration.create();
config.addCriterion(new KAnonymity(2));
config.setMaxOutliers(1.2d);
anonymizer.anonymize(provider.getData(), config);
} catch (final IllegalArgumentException e) {
return;
}
Assert.fail();
}
/** @return */
private static Data getData() {
DefaultData data = Data.create();
data.add("zipcode", "disease1", "age", "disease2");
data.add("47677", "gastric ulcer", "29", "gastric ulcer");
data.add("47602", "gastritis", "22", "gastritis");
data.add("47678", "stomach cancer", "27", "stomach cancer");
data.add("47905", "gastritis", "43", "gastritis");
data.add("47909", "flu", "52", "flu");
data.add("47906", "bronchitis", "47", "bronchitis");
data.add("47605", "bronchitis", "30", "bronchitis");
data.add("47673", "pneumonia", "36", "pneumonia");
data.add("47607", "stomach cancer", "32", "stomach cancer");
return data;
}
/**
* Entry point.
*
* @param args the arguments
*/
public static void main(String[] args) throws IOException {
// Define data
Data data = getData();
// Define attribute types
data.getDefinition().setAttributeType("age", getHierarchyAge());
data.getDefinition().setAttributeType("zipcode", getHierarchyZipcode());
data.getDefinition().setAttributeType("disease1", AttributeType.SENSITIVE_ATTRIBUTE);
data.getDefinition().setAttributeType("disease2", AttributeType.SENSITIVE_ATTRIBUTE);
// Create an instance of the anonymizer
ARXAnonymizer anonymizer = new ARXAnonymizer();
ARXConfiguration config = ARXConfiguration.create();
config.addPrivacyModel(new KAnonymity(3));
config.addPrivacyModel(
new HierarchicalDistanceTCloseness("disease1", 0.6d, getHierarchyDisease()));
config.addPrivacyModel(new RecursiveCLDiversity("disease2", 3d, 2));
config.setMaxOutliers(0d);
config.setQualityModel(Metric.createEntropyMetric());
// Now anonymize
ARXResult result = anonymizer.anonymize(data, config);
// Print info
printResult(result, data);
// Process results
if (result.getGlobalOptimum() != null) {
System.out.println(" - Transformed data:");
Iterator<String[]> transformed = result.getOutput(false).iterator();
while (transformed.hasNext()) {
System.out.print(" ");
System.out.println(Arrays.toString(transformed.next()));
}
}
}
/**
* Performs a test.
*
* @throws IOException
*/
@Test
public void testEmptyDatasetWithoutAttributeDefinition() throws IOException {
try {
final ARXAnonymizer anonymizer = new ARXAnonymizer();
final Data data = Data.create();
final ARXConfiguration config = ARXConfiguration.create();
config.addCriterion(new KAnonymity(2));
config.setMaxOutliers(1.2d);
anonymizer.anonymize(data, config);
} catch (final IllegalArgumentException e) {
return;
}
Assert.fail();
}
/**
* Returns the test cases.
*
* @return
* @throws IOException
*/
@Parameters(name = "{index}:[{0}]")
public static Collection<Object[]> cases() throws IOException {
return Arrays.asList(
new Object[][] {
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createPrecomputedEntropyMetric(0.1d, false))
.addPrivacyModel(
new KMap(
3,
0.01d,
ARXPopulationModel.create(Region.USA),
CellSizeEstimator.ZERO_TRUNCATED_POISSON)),
"occupation",
"./data/adult.csv",
130804.5332092598,
new int[] {0, 0, 1, 1, 0, 2, 2, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createPrecomputedEntropyMetric(0.1d, false))
.addPrivacyModel(
new KMap(
1000,
0.01d,
ARXPopulationModel.create(Region.USA),
CellSizeEstimator.ZERO_TRUNCATED_POISSON)),
"occupation",
"./data/adult.csv",
151894.1394841501,
new int[] {0, 0, 1, 1, 1, 2, 1, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.0d, Metric.createAECSMetric())
.addPrivacyModel(
new KMap(
5,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
45.014925373134325,
new int[] {1, 0, 1, 2, 3, 2, 2, 1},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.0d, Metric.createPrecomputedEntropyMetric(0.1d, true))
.addPrivacyModel(
new KMap(
3,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
23387.494246375998,
new int[] {0, 0, 1, 2, 3, 2, 2, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.0d, Metric.createPrecomputedEntropyMetric(0.1d, false))
.addPrivacyModel(
new KMap(
5,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
28551.7222913157,
new int[] {1, 0, 1, 2, 3, 2, 2, 1},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createAECSMetric())
.addPrivacyModel(
new KMap(
20,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
11.424242424242424,
new int[] {1, 0, 1, 1, 3, 2, 1, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createPrecomputedEntropyMetric(0.1d, true))
.addPrivacyModel(
new KMap(
7,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
17075.7181747451,
new int[] {0, 0, 1, 1, 2, 2, 2, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createPrecomputedEntropyMetric(0.1d, false))
.addPrivacyModel(
new KMap(
3,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
15121.633326877098,
new int[] {0, 0, 1, 1, 1, 2, 1, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.0d, Metric.createAECSMetric())
.addPrivacyModel(
new KMap(
5,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
45.014925373134325,
new int[] {1, 0, 1, 2, 3, 2, 2, 1},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.0d, Metric.createPrecomputedEntropyMetric(0.1d, true))
.addPrivacyModel(
new KMap(
2,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
23108.1673304724,
new int[] {1, 0, 1, 1, 3, 2, 2, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.0d, Metric.createPrecomputedEntropyMetric(0.1d, false))
.addPrivacyModel(
new KMap(
10,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
30238.2081484441,
new int[] {0, 1, 1, 2, 3, 2, 2, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createAECSMetric())
.addPrivacyModel(
new KMap(
10,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
7.215311004784689,
new int[] {0, 0, 1, 1, 3, 2, 1, 0},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createPrecomputedEntropyMetric(0.1d, true))
.addPrivacyModel(
new KMap(
5,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
17053.8743069776,
new int[] {0, 0, 1, 0, 2, 2, 2, 1},
false)
},
{
new ARXAnonymizationTestCase(
ARXConfiguration.create(0.05d, Metric.createPrecomputedEntropyMetric(0.1d, false))
.addPrivacyModel(
new KMap(
3,
DataSubset.create(
Data.create("./data/adult.csv", StandardCharsets.UTF_8, ';'),
Data.create(
"./data/adult_subset.csv", StandardCharsets.UTF_8, ';')))),
"occupation",
"./data/adult.csv",
15121.633326877098,
new int[] {0, 0, 1, 1, 1, 2, 1, 0},
false)
},
});
}
/**
* Entry point.
*
* @param args the arguments
*/
public static void main(String[] args) throws IOException {
// Define data
DefaultData data = Data.create();
data.add("age", "gender", "zipcode");
data.add("45", "female", "81675");
data.add("34", "male", "81667");
data.add("66", "male", "81925");
data.add("70", "female", "81931");
data.add("34", "female", "81931");
data.add("70", "male", "81931");
data.add("45", "male", "81931");
// Define hierarchies
DefaultHierarchy age = Hierarchy.create();
age.add("34", "<50", "*");
age.add("45", "<50", "*");
age.add("66", ">=50", "*");
age.add("70", ">=50", "*");
DefaultHierarchy gender = Hierarchy.create();
gender.add("male", "*");
gender.add("female", "*");
// Only excerpts for readability
DefaultHierarchy zipcode = Hierarchy.create();
zipcode.add("81667", "8166*", "816**", "81***", "8****", "*****");
zipcode.add("81675", "8167*", "816**", "81***", "8****", "*****");
zipcode.add("81925", "8192*", "819**", "81***", "8****", "*****");
zipcode.add("81931", "8193*", "819**", "81***", "8****", "*****");
data.getDefinition().setAttributeType("age", age);
data.getDefinition().setAttributeType("gender", gender);
data.getDefinition().setAttributeType("zipcode", zipcode);
// Create an instance of the anonymizer
ARXAnonymizer anonymizer = new ARXAnonymizer();
ARXConfiguration config = ARXConfiguration.create();
config.addCriterion(new KAnonymity(2));
config.setMaxOutliers(0d);
ARXResult result = anonymizer.anonymize(data, config);
// Print info
printResult(result, data);
// Print input
System.out.println(" - Input data:");
Iterator<String[]> original = data.getHandle().iterator();
while (original.hasNext()) {
System.out.print(" ");
System.out.println(Arrays.toString(original.next()));
}
// Print results
System.out.println(" - Transformed data:");
Iterator<String[]> transformed = result.getOutput(false).iterator();
while (transformed.hasNext()) {
System.out.print(" ");
System.out.println(Arrays.toString(transformed.next()));
}
// Print frequencies
StatisticsFrequencyDistribution distribution;
System.out.println(" - Distribution of attribute 'age' in input:");
distribution = data.getHandle().getStatistics().getFrequencyDistribution(0, false);
System.out.println(" " + Arrays.toString(distribution.values));
System.out.println(" " + Arrays.toString(distribution.frequency));
// Print frequencies
System.out.println(" - Distribution of attribute 'age' in output:");
distribution = result.getOutput(false).getStatistics().getFrequencyDistribution(0, true);
System.out.println(" " + Arrays.toString(distribution.values));
System.out.println(" " + Arrays.toString(distribution.frequency));
// Print contingency tables
StatisticsContingencyTable contingency;
System.out.println(" - Contingency of attribute 'gender' and 'zipcode' in input:");
contingency = data.getHandle().getStatistics().getContingencyTable(0, true, 2, true);
System.out.println(" " + Arrays.toString(contingency.values1));
System.out.println(" " + Arrays.toString(contingency.values2));
while (contingency.iterator.hasNext()) {
Entry e = contingency.iterator.next();
System.out.println(" [" + e.value1 + ", " + e.value2 + ", " + e.frequency + "]");
}
// Print contingency tables
System.out.println(" - Contingency of attribute 'gender' and 'zipcode' in output:");
contingency = result.getOutput(false).getStatistics().getContingencyTable(0, true, 2, true);
System.out.println(" " + Arrays.toString(contingency.values1));
System.out.println(" " + Arrays.toString(contingency.values2));
while (contingency.iterator.hasNext()) {
Entry e = contingency.iterator.next();
System.out.println(" [" + e.value1 + ", " + e.value2 + ", " + e.frequency + "]");
}
}
/**
* Entry point.
*
* @param args the arguments
* @throws IOException
*/
public static void main(String[] args) throws IOException {
// Define data
DefaultData data = Data.create();
data.add("zipcode", "age", "disease");
data.add("47677", "29", "gastric ulcer");
data.add("47602", "22", "gastritis");
data.add("47678", "27", "stomach cancer");
data.add("47905", "43", "gastritis");
data.add("47909", "52", "flu");
data.add("47906", "47", "bronchitis");
data.add("47605", "30", "bronchitis");
data.add("47673", "36", "pneumonia");
data.add("47607", "32", "stomach cancer");
// Define hierarchies
DefaultHierarchy age = Hierarchy.create();
age.add("29", "<=40", "*");
age.add("22", "<=40", "*");
age.add("27", "<=40", "*");
age.add("43", ">40", "*");
age.add("52", ">40", "*");
age.add("47", ">40", "*");
age.add("30", "<=40", "*");
age.add("36", "<=40", "*");
age.add("32", "<=40", "*");
// Only excerpts for readability
DefaultHierarchy zipcode = Hierarchy.create();
zipcode.add("47677", "4767*", "476**", "47***", "4****", "*****");
zipcode.add("47602", "4760*", "476**", "47***", "4****", "*****");
zipcode.add("47678", "4767*", "476**", "47***", "4****", "*****");
zipcode.add("47905", "4790*", "479**", "47***", "4****", "*****");
zipcode.add("47909", "4790*", "479**", "47***", "4****", "*****");
zipcode.add("47906", "4790*", "479**", "47***", "4****", "*****");
zipcode.add("47605", "4760*", "476**", "47***", "4****", "*****");
zipcode.add("47673", "4767*", "476**", "47***", "4****", "*****");
zipcode.add("47607", "4760*", "476**", "47***", "4****", "*****");
// Define sensitive value hierarchy
DefaultHierarchy disease = Hierarchy.create();
disease.add(
"flu",
"respiratory infection",
"vascular lung disease",
"respiratory & digestive system disease");
disease.add(
"pneumonia",
"respiratory infection",
"vascular lung disease",
"respiratory & digestive system disease");
disease.add(
"bronchitis",
"respiratory infection",
"vascular lung disease",
"respiratory & digestive system disease");
disease.add(
"pulmonary edema",
"vascular lung disease",
"vascular lung disease",
"respiratory & digestive system disease");
disease.add(
"pulmonary embolism",
"vascular lung disease",
"vascular lung disease",
"respiratory & digestive system disease");
disease.add(
"gastric ulcer",
"stomach disease",
"digestive system disease",
"respiratory & digestive system disease");
disease.add(
"stomach cancer",
"stomach disease",
"digestive system disease",
"respiratory & digestive system disease");
disease.add(
"gastritis",
"stomach disease",
"digestive system disease",
"respiratory & digestive system disease");
disease.add(
"colitis",
"colon disease",
"digestive system disease",
"respiratory & digestive system disease");
disease.add(
"colon cancer",
"colon disease",
"digestive system disease",
"respiratory & digestive system disease");
data.getDefinition().setAttributeType("age", age);
data.getDefinition().setAttributeType("zipcode", zipcode);
data.getDefinition().setAttributeType("disease", AttributeType.SENSITIVE_ATTRIBUTE);
// Create an instance of the anonymizer
ARXAnonymizer anonymizer = new ARXAnonymizer();
ARXConfiguration config = ARXConfiguration.create();
config.addCriterion(new KAnonymity(3));
config.addCriterion(new HierarchicalDistanceTCloseness("disease", 0.6d, disease));
config.setMaxOutliers(0d);
config.setMetric(Metric.createEntropyMetric());
// Now anonymize
ARXResult result = anonymizer.anonymize(data, config);
// Print info
printResult(result, data);
// Process results
System.out.println(" - Transformed data:");
Iterator<String[]> transformed = result.getOutput(false).iterator();
while (transformed.hasNext()) {
System.out.print(" ");
System.out.println(Arrays.toString(transformed.next()));
}
}
