Examples with AnalyzeDataSourceRiskDetails com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails used on opensource projects

Example 1 with AnalyzeDataSourceRiskDetails

use of com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails in project java-docs-samples by GoogleCloudPlatform.

the class RiskAnalysis method categoricalStatsAnalysis.

// [END dlp_numerical_stats]
// [START dlp_categorical_stats]
/**
 * Calculate categorical statistics for a column in a BigQuery table using the DLP API.
 *
 * @param projectId The Google Cloud Platform project ID to run the API call under.
 * @param datasetId The BigQuery dataset to analyze.
 * @param tableId The BigQuery table to analyze.
 * @param columnName The name of the column to analyze, which need not contain numerical data.
 * @param topicId The name of the Pub/Sub topic to notify once the job completes
 * @param subscriptionId The name of the Pub/Sub subscription to use when listening for job
 *     completion status.
 */
private static void categoricalStatsAnalysis(String projectId, String datasetId, String tableId, String columnName, String topicId, String subscriptionId) {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        FieldId fieldId = FieldId.newBuilder().setName(columnName).build();
        CategoricalStatsConfig categoricalStatsConfig = CategoricalStatsConfig.newBuilder().setField(fieldId).build();
        BigQueryTable bigQueryTable = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
        PrivacyMetric privacyMetric = PrivacyMetric.newBuilder().setCategoricalStatsConfig(categoricalStatsConfig).build();
        ProjectTopicName topicName = ProjectTopicName.of(projectId, topicId);
        PublishToPubSub publishToPubSub = PublishToPubSub.newBuilder().setTopic(topicName.toString()).build();
        // Create action to publish job status notifications over Google Cloud Pub/Sub
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        RiskAnalysisJobConfig riskAnalysisJobConfig = RiskAnalysisJobConfig.newBuilder().setSourceTable(bigQueryTable).setPrivacyMetric(privacyMetric).addActions(action).build();
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setRiskJob(riskAnalysisJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        String dlpJobName = dlpJob.getName();
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.newBuilder().setProject(projectId).setSubscription(subscriptionId).build(), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJobName)) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (TimeoutException e) {
            System.out.println("Unable to verify job completion.");
        }
        // Retrieve completed job status
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJobName).build());
        System.out.println("Job status: " + completedJob.getState());
        AnalyzeDataSourceRiskDetails riskDetails = completedJob.getRiskDetails();
        AnalyzeDataSourceRiskDetails.CategoricalStatsResult result = riskDetails.getCategoricalStatsResult();
        for (CategoricalStatsHistogramBucket bucket : result.getValueFrequencyHistogramBucketsList()) {
            System.out.printf("Most common value occurs %d time(s).\n", bucket.getValueFrequencyUpperBound());
            System.out.printf("Least common value occurs %d time(s).\n", bucket.getValueFrequencyLowerBound());
            for (ValueFrequency valueFrequency : bucket.getBucketValuesList()) {
                System.out.printf("Value %s occurs %d time(s).\n", valueFrequency.getValue().toString(), valueFrequency.getCount());
            }
        }
    } catch (Exception e) {
        System.out.println("Error in categoricalStatsAnalysis: " + e.getMessage());
    }
}

Example 2 with AnalyzeDataSourceRiskDetails

use of com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails in project java-docs-samples by GoogleCloudPlatform.

the class RiskAnalysis method calculateLDiversity.

// [END dlp_k_anonymity]
// [START dlp_l_diversity]
/**
 * Calculate l-diversity for an attribute relative to quasi-identifiers in a BigQuery table.
 *
 * @param projectId The Google Cloud Platform project ID to run the API call under.
 * @param datasetId The BigQuery dataset to analyze.
 * @param tableId The BigQuery table to analyze.
 * @param sensitiveAttribute The name of the attribute to compare the quasi-ID against
 * @param quasiIds A set of column names that form a composite key ('quasi-identifiers').
 * @param topicId The name of the Pub/Sub topic to notify once the job completes
 * @param subscriptionId The name of the Pub/Sub subscription to use when listening for job
 *     completion status.
 */
private static void calculateLDiversity(String projectId, String datasetId, String tableId, String sensitiveAttribute, List<String> quasiIds, String topicId, String subscriptionId) throws Exception {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        FieldId sensitiveAttributeField = FieldId.newBuilder().setName(sensitiveAttribute).build();
        List<FieldId> quasiIdFields = quasiIds.stream().map(columnName -> FieldId.newBuilder().setName(columnName).build()).collect(Collectors.toList());
        LDiversityConfig ldiversityConfig = LDiversityConfig.newBuilder().addAllQuasiIds(quasiIdFields).setSensitiveAttribute(sensitiveAttributeField).build();
        BigQueryTable bigQueryTable = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
        PrivacyMetric privacyMetric = PrivacyMetric.newBuilder().setLDiversityConfig(ldiversityConfig).build();
        String topicName = String.format("projects/%s/topics/%s", projectId, topicId);
        PublishToPubSub publishToPubSub = PublishToPubSub.newBuilder().setTopic(topicName).build();
        // Create action to publish job status notifications over Google Cloud Pub/Sub
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        RiskAnalysisJobConfig riskAnalysisJobConfig = RiskAnalysisJobConfig.newBuilder().setSourceTable(bigQueryTable).setPrivacyMetric(privacyMetric).addActions(action).build();
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setRiskJob(riskAnalysisJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        String dlpJobName = dlpJob.getName();
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.newBuilder().setProject(projectId).setSubscription(subscriptionId).build(), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJobName)) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (TimeoutException e) {
            System.out.println("Unable to verify job completion.");
        }
        // retrieve completed job status
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJobName).build());
        System.out.println("Job status: " + completedJob.getState());
        AnalyzeDataSourceRiskDetails riskDetails = completedJob.getRiskDetails();
        LDiversityResult ldiversityResult = riskDetails.getLDiversityResult();
        for (LDiversityHistogramBucket result : ldiversityResult.getSensitiveValueFrequencyHistogramBucketsList()) {
            for (LDiversityEquivalenceClass bucket : result.getBucketValuesList()) {
                List<String> quasiIdValues = bucket.getQuasiIdsValuesList().stream().map(Value::toString).collect(Collectors.toList());
                System.out.println("\tQuasi-ID values: " + String.join(", ", quasiIdValues));
                System.out.println("\tClass size: " + bucket.getEquivalenceClassSize());
                for (ValueFrequency valueFrequency : bucket.getTopSensitiveValuesList()) {
                    System.out.printf("\t\tSensitive value %s occurs %d time(s).\n", valueFrequency.getValue().toString(), valueFrequency.getCount());
                }
            }
        }
    } catch (Exception e) {
        System.out.println("Error in calculateLDiversity: " + e.getMessage());
    }
}

Example 3 with AnalyzeDataSourceRiskDetails

use of com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails in project java-docs-samples by GoogleCloudPlatform.

the class RiskAnalysis method calculateKMap.

// [END dlp_l_diversity]
// [START dlp_k_map]
/**
 * Calculate k-map risk estimation for an attribute relative to quasi-identifiers in a BigQuery
 * table.
 *
 * @param projectId The Google Cloud Platform project ID to run the API call under.
 * @param datasetId The BigQuery dataset to analyze.
 * @param tableId The BigQuery table to analyze.
 * @param quasiIds A set of column names that form a composite key ('quasi-identifiers').
 * @param infoTypes The infoTypes corresponding to each quasi-id column
 * @param regionCode An ISO-3166-1 region code specifying the k-map distribution region
 * @param topicId The name of the Pub/Sub topic to notify once the job completes
 * @param subscriptionId The name of the Pub/Sub subscription to use when listening for job
 *     completion status.
 */
private static void calculateKMap(String projectId, String datasetId, String tableId, List<String> quasiIds, List<InfoType> infoTypes, String regionCode, String topicId, String subscriptionId) throws Exception {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        Iterator<String> quasiIdsIterator = quasiIds.iterator();
        Iterator<InfoType> infoTypesIterator = infoTypes.iterator();
        if (quasiIds.size() != infoTypes.size()) {
            throw new IllegalArgumentException("The numbers of quasi-IDs and infoTypes must be equal!");
        }
        ArrayList<TaggedField> taggedFields = new ArrayList();
        while (quasiIdsIterator.hasNext() || infoTypesIterator.hasNext()) {
            taggedFields.add(TaggedField.newBuilder().setField(FieldId.newBuilder().setName(quasiIdsIterator.next()).build()).setInfoType(infoTypesIterator.next()).build());
        }
        KMapEstimationConfig kmapConfig = KMapEstimationConfig.newBuilder().addAllQuasiIds(taggedFields).setRegionCode(regionCode).build();
        BigQueryTable bigQueryTable = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
        PrivacyMetric privacyMetric = PrivacyMetric.newBuilder().setKMapEstimationConfig(kmapConfig).build();
        String topicName = String.format("projects/%s/topics/%s", projectId, topicId);
        PublishToPubSub publishToPubSub = PublishToPubSub.newBuilder().setTopic(topicName).build();
        // Create action to publish job status notifications over Google Cloud Pub/Sub
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        RiskAnalysisJobConfig riskAnalysisJobConfig = RiskAnalysisJobConfig.newBuilder().setSourceTable(bigQueryTable).setPrivacyMetric(privacyMetric).addActions(action).build();
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setRiskJob(riskAnalysisJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        String dlpJobName = dlpJob.getName();
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.newBuilder().setProject(projectId).setSubscription(subscriptionId).build(), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJobName)) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (TimeoutException e) {
            System.out.println("Unable to verify job completion.");
        }
        // retrieve completed job status
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJobName).build());
        System.out.println("Job status: " + completedJob.getState());
        AnalyzeDataSourceRiskDetails riskDetails = completedJob.getRiskDetails();
        KMapEstimationResult kmapResult = riskDetails.getKMapEstimationResult();
        for (KMapEstimationHistogramBucket result : kmapResult.getKMapEstimationHistogramList()) {
            System.out.printf("\tAnonymity range: [%d, %d]\n", result.getMinAnonymity(), result.getMaxAnonymity());
            System.out.printf("\tSize: %d\n", result.getBucketSize());
            for (KMapEstimationQuasiIdValues valueBucket : result.getBucketValuesList()) {
                String quasiIdValues = valueBucket.getQuasiIdsValuesList().stream().map(v -> {
                    String s = v.toString();
                    return s.substring(s.indexOf(':') + 1).trim();
                }).collect(Collectors.joining(", "));
                System.out.printf("\tValues: {%s}\n", quasiIdValues);
                System.out.printf("\tEstimated k-map anonymity: %d\n", valueBucket.getEstimatedAnonymity());
            }
        }
    } catch (Exception e) {
        System.out.println("Error in calculateKMap: " + e.getMessage());
    }
}

Example 4 with AnalyzeDataSourceRiskDetails

use of com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails in project java-docs-samples by GoogleCloudPlatform.

the class RiskAnalysis method calculateKAnonymity.

// [END dlp_categorical_stats]
// [START dlp_k_anonymity]
/**
 * Calculate k-anonymity for quasi-identifiers in a BigQuery table using the DLP API.
 *
 * @param projectId The Google Cloud Platform project ID to run the API call under.
 * @param datasetId The BigQuery dataset to analyze.
 * @param tableId The BigQuery table to analyze.
 * @param quasiIds The names of columns that form a composite key ('quasi-identifiers').
 * @param topicId The name of the Pub/Sub topic to notify once the job completes
 * @param subscriptionId The name of the Pub/Sub subscription to use when listening for job
 *     completion status.
 */
private static void calculateKAnonymity(String projectId, String datasetId, String tableId, List<String> quasiIds, String topicId, String subscriptionId) throws Exception {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        List<FieldId> quasiIdFields = quasiIds.stream().map(columnName -> FieldId.newBuilder().setName(columnName).build()).collect(Collectors.toList());
        KAnonymityConfig kanonymityConfig = KAnonymityConfig.newBuilder().addAllQuasiIds(quasiIdFields).build();
        BigQueryTable bigQueryTable = BigQueryTable.newBuilder().setProjectId(projectId).setDatasetId(datasetId).setTableId(tableId).build();
        PrivacyMetric privacyMetric = PrivacyMetric.newBuilder().setKAnonymityConfig(kanonymityConfig).build();
        String topicName = String.format("projects/%s/topics/%s", projectId, topicId);
        PublishToPubSub publishToPubSub = PublishToPubSub.newBuilder().setTopic(topicName).build();
        // Create action to publish job status notifications over Google Cloud Pub/Sub
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        RiskAnalysisJobConfig riskAnalysisJobConfig = RiskAnalysisJobConfig.newBuilder().setSourceTable(bigQueryTable).setPrivacyMetric(privacyMetric).addActions(action).build();
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setRiskJob(riskAnalysisJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        String dlpJobName = dlpJob.getName();
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.newBuilder().setProject(projectId).setSubscription(subscriptionId).build(), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJobName)) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (TimeoutException e) {
            System.out.println("Unable to verify job completion.");
        }
        // Retrieve completed job status
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJobName).build());
        System.out.println("Job status: " + completedJob.getState());
        AnalyzeDataSourceRiskDetails riskDetails = completedJob.getRiskDetails();
        KAnonymityResult kanonymityResult = riskDetails.getKAnonymityResult();
        for (KAnonymityHistogramBucket result : kanonymityResult.getEquivalenceClassHistogramBucketsList()) {
            System.out.printf("Bucket size range: [%d, %d]\n", result.getEquivalenceClassSizeLowerBound(), result.getEquivalenceClassSizeUpperBound());
            for (KAnonymityEquivalenceClass bucket : result.getBucketValuesList()) {
                List<String> quasiIdValues = bucket.getQuasiIdsValuesList().stream().map(v -> v.toString()).collect(Collectors.toList());
                System.out.println("\tQuasi-ID values: " + String.join(", ", quasiIdValues));
                System.out.println("\tClass size: " + bucket.getEquivalenceClassSize());
            }
        }
    } catch (Exception e) {
        System.out.println("Error in calculateKAnonymity: " + e.getMessage());
    }
}

Example 5 with AnalyzeDataSourceRiskDetails

use of com.google.privacy.dlp.v2.AnalyzeDataSourceRiskDetails in project java-docs-samples by GoogleCloudPlatform.

the class RiskAnalysis method numericalStatsAnalysis.

// [START dlp_numerical_stats]
/**
 * Calculate numerical statistics for a column in a BigQuery table using the DLP API.
 *
 * @param projectId The Google Cloud Platform project ID to run the API call under.
 * @param datasetId The BigQuery dataset to analyze.
 * @param tableId The BigQuery table to analyze.
 * @param columnName The name of the column to analyze, which must contain only numerical data.
 * @param topicId The name of the Pub/Sub topic to notify once the job completes
 * @param subscriptionId The name of the Pub/Sub subscription to use when listening for job
 *     completion status.
 */
private static void numericalStatsAnalysis(String projectId, String datasetId, String tableId, String columnName, String topicId, String subscriptionId) throws Exception {
    // Instantiates a client
    try (DlpServiceClient dlpServiceClient = DlpServiceClient.create()) {
        BigQueryTable bigQueryTable = BigQueryTable.newBuilder().setTableId(tableId).setDatasetId(datasetId).setProjectId(projectId).build();
        FieldId fieldId = FieldId.newBuilder().setName(columnName).build();
        NumericalStatsConfig numericalStatsConfig = NumericalStatsConfig.newBuilder().setField(fieldId).build();
        PrivacyMetric privacyMetric = PrivacyMetric.newBuilder().setNumericalStatsConfig(numericalStatsConfig).build();
        String topicName = String.format("projects/%s/topics/%s", projectId, topicId);
        PublishToPubSub publishToPubSub = PublishToPubSub.newBuilder().setTopic(topicName).build();
        // Create action to publish job status notifications over Google Cloud Pub/Sub
        Action action = Action.newBuilder().setPubSub(publishToPubSub).build();
        RiskAnalysisJobConfig riskAnalysisJobConfig = RiskAnalysisJobConfig.newBuilder().setSourceTable(bigQueryTable).setPrivacyMetric(privacyMetric).addActions(action).build();
        CreateDlpJobRequest createDlpJobRequest = CreateDlpJobRequest.newBuilder().setParent(ProjectName.of(projectId).toString()).setRiskJob(riskAnalysisJobConfig).build();
        DlpJob dlpJob = dlpServiceClient.createDlpJob(createDlpJobRequest);
        String dlpJobName = dlpJob.getName();
        final SettableApiFuture<Boolean> done = SettableApiFuture.create();
        // Set up a Pub/Sub subscriber to listen on the job completion status
        Subscriber subscriber = Subscriber.newBuilder(ProjectSubscriptionName.newBuilder().setProject(projectId).setSubscription(subscriptionId).build(), (pubsubMessage, ackReplyConsumer) -> {
            if (pubsubMessage.getAttributesCount() > 0 && pubsubMessage.getAttributesMap().get("DlpJobName").equals(dlpJobName)) {
                // notify job completion
                done.set(true);
                ackReplyConsumer.ack();
            }
        }).build();
        subscriber.startAsync();
        // For long jobs, consider using a truly asynchronous execution model such as Cloud Functions
        try {
            done.get(1, TimeUnit.MINUTES);
            // Wait for the job to become available
            Thread.sleep(500);
        } catch (TimeoutException e) {
            System.out.println("Unable to verify job completion.");
        }
        // Retrieve completed job status
        DlpJob completedJob = dlpServiceClient.getDlpJob(GetDlpJobRequest.newBuilder().setName(dlpJobName).build());
        System.out.println("Job status: " + completedJob.getState());
        AnalyzeDataSourceRiskDetails riskDetails = completedJob.getRiskDetails();
        AnalyzeDataSourceRiskDetails.NumericalStatsResult result = riskDetails.getNumericalStatsResult();
        System.out.printf("Value range : [%.3f, %.3f]\n", result.getMinValue().getFloatValue(), result.getMaxValue().getFloatValue());
        int percent = 1;
        Double lastValue = null;
        for (Value quantileValue : result.getQuantileValuesList()) {
            Double currentValue = quantileValue.getFloatValue();
            if (lastValue == null || !lastValue.equals(currentValue)) {
                System.out.printf("Value at %s %% quantile : %.3f", percent, currentValue);
            }
            lastValue = currentValue;
        }
    } catch (Exception e) {
        System.out.println("Error in categoricalStatsAnalysis: " + e.getMessage());
    }
}