De-identify tabular data through bucketing

This sample replaces the values within each bucket with predefined replacement values.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

C#

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


using System;
using Google.Api.Gax.ResourceNames;
using Google.Cloud.Dlp.V2;

public class DeidentifyTableWithPrimitiveBucketing
{
    public static Table DeidentifyData(
        string projectId,
        Table tableToInspect = null)
    {
        // Instantiate dlp client.
        var dlp = DlpServiceClient.Create();

        // Construct the table if null.
        if (tableToInspect == null)
        {
            var row1 = new Value[]
            {
                new Value { IntegerValue = 1 },
                new Value { IntegerValue = 95 }
            };
            var row2 = new Value[]
            {
                new Value { IntegerValue = 2 },
                new Value { IntegerValue = 61 }
            };
            var row3 = new Value[]
            {
                new Value { IntegerValue = 3 },
                new Value { IntegerValue = 22 }
            };

            tableToInspect = new Table
            {
                Headers =
                {
                    new FieldId { Name = "user_id" },
                    new FieldId { Name = "score" }
                },
                Rows =
                {
                    new Table.Types.Row { Values = { row1 } },
                    new Table.Types.Row { Values = { row2 } },
                    new Table.Types.Row { Values = { row3 } }
                }
            };
        }

        // Specify the table and construct the content item.
        var contentItem = new ContentItem { Table = tableToInspect };

        // Specify how the content should be de-identified.
        var bucketingConfig = new BucketingConfig
        {
            Buckets =
            {
                new BucketingConfig.Types.Bucket
                {
                    Min = new Value { IntegerValue = 0 },
                    Max = new Value { IntegerValue = 25 },
                    ReplacementValue = new Value { StringValue = "Low" }
                },
                new BucketingConfig.Types.Bucket
                {
                    Min = new Value { IntegerValue = 25 },
                    Max = new Value { IntegerValue = 75 },
                    ReplacementValue = new Value { StringValue = "Medium" }
                },
                new BucketingConfig.Types.Bucket
                {
                    Min = new Value { IntegerValue = 75 },
                    Max = new Value { IntegerValue = 100 },
                    ReplacementValue = new Value { StringValue = "High" }
                }
            }
        };

        // Specify the fields to be encrypted.
        var fields = new FieldId[] { new FieldId { Name = "score" } };


        // Associate the de-identification with the specified field.
        var fieldTransformation = new FieldTransformation
        {
            PrimitiveTransformation = new PrimitiveTransformation
            {
                BucketingConfig = bucketingConfig
            },
            Fields = { fields }
        };

        // Construct the de-identify config.
        var deidentifyConfig = new DeidentifyConfig
        {
            RecordTransformations = new RecordTransformations
            {
                FieldTransformations = { fieldTransformation }
            }
        };

        // Construct the request.
        var request = new DeidentifyContentRequest
        {
            ParentAsLocationName = new LocationName(projectId, "global"),
            DeidentifyConfig = deidentifyConfig,
            Item = contentItem,
        };

        // Call the API.
        DeidentifyContentResponse response = dlp.DeidentifyContent(request);

        // Inspect the response.
        Console.WriteLine(response.Item.Table);

        return response.Item.Table;
    }
}

Go

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import (
	"context"
	"fmt"
	"io"

	dlp "cloud.google.com/go/dlp/apiv2"
	"cloud.google.com/go/dlp/apiv2/dlppb"
)

// deIdentifyTablePrimitiveBucketing bucket sensitive data by grouping numerical values into
// predefined ranges to generalize and protect user information.
func deIdentifyTablePrimitiveBucketing(w io.Writer, projectID string) error {
	// projectId := "your-project-id"

	row1 := &dlppb.Table_Row{
		Values: []*dlppb.Value{
			{Type: &dlppb.Value_StringValue{StringValue: "22"}},
			{Type: &dlppb.Value_StringValue{StringValue: "Jane Austen"}},
			{Type: &dlppb.Value_StringValue{StringValue: "21"}},
		},
	}

	row2 := &dlppb.Table_Row{
		Values: []*dlppb.Value{
			{Type: &dlppb.Value_StringValue{StringValue: "101"}},
			{Type: &dlppb.Value_StringValue{StringValue: "Charles Dickens"}},
			{Type: &dlppb.Value_StringValue{StringValue: "95"}},
		},
	}

	row3 := &dlppb.Table_Row{
		Values: []*dlppb.Value{
			{Type: &dlppb.Value_StringValue{StringValue: "55"}},
			{Type: &dlppb.Value_StringValue{StringValue: "Mark Twain"}},
			{Type: &dlppb.Value_StringValue{StringValue: "75"}},
		},
	}

	tableToDeidentify := &dlppb.Table{
		Headers: []*dlppb.FieldId{
			{Name: "AGE"},
			{Name: "PATIENT"},
			{Name: "HAPPINESS SCORE"},
		},
		Rows: []*dlppb.Table_Row{
			{Values: row1.Values},
			{Values: row2.Values},
			{Values: row3.Values},
		},
	}
	ctx := context.Background()

	// Initialize a client once and reuse it to send multiple requests. Clients
	// are safe to use across goroutines. When the client is no longer needed,
	// call the Close method to cleanup its resources.
	client, err := dlp.NewClient(ctx)
	if err != nil {
		return err
	}

	// Closing the client safely cleans up background resources.
	defer client.Close()

	// Specify what content you want the service to de-identify.
	contentItem := &dlppb.ContentItem{
		DataItem: &dlppb.ContentItem_Table{
			Table: tableToDeidentify,
		},
	}

	// Specify how the content should be de-identified.
	buckets := []*dlppb.BucketingConfig_Bucket{
		{
			Min: &dlppb.Value{
				Type: &dlppb.Value_IntegerValue{
					IntegerValue: 0,
				},
			},
			Max: &dlppb.Value{
				Type: &dlppb.Value_IntegerValue{
					IntegerValue: 25,
				},
			},
			ReplacementValue: &dlppb.Value{
				Type: &dlppb.Value_StringValue{
					StringValue: "low",
				},
			},
		},
		{
			Min: &dlppb.Value{
				Type: &dlppb.Value_IntegerValue{
					IntegerValue: 25,
				},
			},
			Max: &dlppb.Value{
				Type: &dlppb.Value_IntegerValue{
					IntegerValue: 75,
				},
			},
			ReplacementValue: &dlppb.Value{
				Type: &dlppb.Value_StringValue{
					StringValue: "Medium",
				},
			},
		},
		{
			Min: &dlppb.Value{
				Type: &dlppb.Value_IntegerValue{
					IntegerValue: 75,
				},
			},
			Max: &dlppb.Value{
				Type: &dlppb.Value_IntegerValue{
					IntegerValue: 100,
				},
			},
			ReplacementValue: &dlppb.Value{
				Type: &dlppb.Value_StringValue{
					StringValue: "High",
				},
			},
		},
	}

	// Specify the BucketingConfig in primitive transformation.
	primitiveTransformation := &dlppb.PrimitiveTransformation_BucketingConfig{
		BucketingConfig: &dlppb.BucketingConfig{
			Buckets: buckets,
		},
	}

	// Specify the field of the table to be de-identified
	feildId := &dlppb.FieldId{
		Name: "HAPPINESS SCORE",
	}

	// Specify the field transformation which apply to input field(s) on which you want to transform.
	fieldTransformation := &dlppb.FieldTransformation{
		Transformation: &dlppb.FieldTransformation_PrimitiveTransformation{
			PrimitiveTransformation: &dlppb.PrimitiveTransformation{
				Transformation: primitiveTransformation,
			},
		},
		Fields: []*dlppb.FieldId{
			feildId,
		},
	}
	// Specify the record transformation to transform the record by applying various field transformations
	transformation := &dlppb.RecordTransformations{
		FieldTransformations: []*dlppb.FieldTransformation{
			fieldTransformation,
		},
	}
	// Specify the deidentification config.
	deidentifyConfig := &dlppb.DeidentifyConfig{
		Transformation: &dlppb.DeidentifyConfig_RecordTransformations{
			RecordTransformations: transformation,
		},
	}

	// Construct the de-identification request to be sent by the client.
	req := &dlppb.DeidentifyContentRequest{
		Parent:           fmt.Sprintf("projects/%s/locations/global", projectID),
		DeidentifyConfig: deidentifyConfig,
		Item:             contentItem,
	}

	// Send the request.
	resp, err := client.DeidentifyContent(ctx, req)
	if err != nil {
		return err
	}

	// Print the results.
	fmt.Fprintf(w, "Table after de-identification : %v", resp.GetItem().GetTable())
	return nil
}

Java

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


import com.google.cloud.dlp.v2.DlpServiceClient;
import com.google.privacy.dlp.v2.BucketingConfig;
import com.google.privacy.dlp.v2.ContentItem;
import com.google.privacy.dlp.v2.DeidentifyConfig;
import com.google.privacy.dlp.v2.DeidentifyContentRequest;
import com.google.privacy.dlp.v2.DeidentifyContentResponse;
import com.google.privacy.dlp.v2.FieldId;
import com.google.privacy.dlp.v2.FieldTransformation;
import com.google.privacy.dlp.v2.LocationName;
import com.google.privacy.dlp.v2.PrimitiveTransformation;
import com.google.privacy.dlp.v2.RecordTransformations;
import com.google.privacy.dlp.v2.Table;
import com.google.privacy.dlp.v2.Value;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DeIdentifyTableWithBucketingConfig {
  public static void main(String[] args) throws Exception {

    // TODO(developer): Replace these variables before running the sample.
    // The Google Cloud project id to use as a parent resource.
    String projectId = "your-project-id";
    // Specify the table to be considered for de-identification.
    Table tableToDeIdentify =
        Table.newBuilder()
            .addHeaders(FieldId.newBuilder().setName("AGE").build())
            .addHeaders(FieldId.newBuilder().setName("PATIENT").build())
            .addHeaders(FieldId.newBuilder().setName("HAPPINESS SCORE").build())
            .addRows(
                Table.Row.newBuilder()
                    .addValues(Value.newBuilder().setStringValue("101").build())
                    .addValues(Value.newBuilder().setStringValue("Charles Dickens").build())
                    .addValues(Value.newBuilder().setIntegerValue(95).build())
                    .build())
            .addRows(
                Table.Row.newBuilder()
                    .addValues(Value.newBuilder().setStringValue("22").build())
                    .addValues(Value.newBuilder().setStringValue("Jane Austen").build())
                    .addValues(Value.newBuilder().setIntegerValue(21).build())
                    .build())
            .addRows(
                Table.Row.newBuilder()
                    .addValues(Value.newBuilder().setStringValue("55").build())
                    .addValues(Value.newBuilder().setStringValue("Mark Twain").build())
                    .addValues(Value.newBuilder().setIntegerValue(75).build())
                    .build())
            .build();

    deIdentifyTableBucketing(projectId, tableToDeIdentify);
  }

  // Performs data de-identification on a table by replacing the values within each bucket with
  // predefined replacement values.
  public static Table deIdentifyTableBucketing(String projectId, Table tableToDeIdentify)
      throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (DlpServiceClient dlp = DlpServiceClient.create()) {
      // Specify what content you want the service to de-identify.
      ContentItem contentItem = ContentItem.newBuilder().setTable(tableToDeIdentify).build();

      List<BucketingConfig.Bucket> buckets = new ArrayList<>();
      buckets.add(
          BucketingConfig.Bucket.newBuilder()
              .setMin(Value.newBuilder().setIntegerValue(0).build())
              .setMax(Value.newBuilder().setIntegerValue(25).build())
              .setReplacementValue(Value.newBuilder().setStringValue("low").build())
              .build());
      buckets.add(
          BucketingConfig.Bucket.newBuilder()
              .setMin(Value.newBuilder().setIntegerValue(25).build())
              .setMax(Value.newBuilder().setIntegerValue(75).build())
              .setReplacementValue(Value.newBuilder().setStringValue("Medium").build())
              .build());
      buckets.add(
          BucketingConfig.Bucket.newBuilder()
              .setMin(Value.newBuilder().setIntegerValue(75).build())
              .setMax(Value.newBuilder().setIntegerValue(100).build())
              .setReplacementValue(Value.newBuilder().setStringValue("High").build())
              .build());

      BucketingConfig bucketingConfig = BucketingConfig.newBuilder().addAllBuckets(buckets).build();

      PrimitiveTransformation primitiveTransformation =
          PrimitiveTransformation.newBuilder().setBucketingConfig(bucketingConfig).build();

      // Specify the field of the table to be de-identified.
      FieldId fieldId = FieldId.newBuilder().setName("HAPPINESS SCORE").build();

      FieldTransformation fieldTransformation =
          FieldTransformation.newBuilder()
              .setPrimitiveTransformation(primitiveTransformation)
              .addFields(fieldId)
              .build();
      RecordTransformations transformations =
          RecordTransformations.newBuilder().addFieldTransformations(fieldTransformation).build();

      DeidentifyConfig deidentifyConfig =
          DeidentifyConfig.newBuilder().setRecordTransformations(transformations).build();

      // Combine configurations into a request for the service.
      DeidentifyContentRequest request =
          DeidentifyContentRequest.newBuilder()
              .setParent(LocationName.of(projectId, "global").toString())
              .setItem(contentItem)
              .setDeidentifyConfig(deidentifyConfig)
              .build();

      // Send the request and receive response from the service.
      DeidentifyContentResponse response = dlp.deidentifyContent(request);

      // Print the results.
      System.out.println("Table after de-identification: " + response.getItem().getTable());
      return response.getItem().getTable();
    }
  }
}

Node.js

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

// Imports the Google Cloud client library
const DLP = require('@google-cloud/dlp');
// Instantiates a client
const dlp = new DLP.DlpServiceClient();

// The project ID to run the API call under
// const projectId = 'your-project-id';

// Construct the tabular data
const tablularData = {
  headers: [{name: 'AGE'}, {name: 'PATIENT'}, {name: 'HAPPINESS SCORE'}],
  rows: [
    {
      values: [
        {stringValue: '101'},
        {stringValue: 'Charles Dickens'},
        {integerValue: 95},
      ],
    },
    {
      values: [
        {stringValue: '22'},
        {stringValue: 'Jane Austen'},
        {integerValue: 21},
      ],
    },
    {
      values: [
        {stringValue: '55'},
        {stringValue: 'Mark Twain'},
        {integerValue: 75},
      ],
    },
  ],
};

async function deIdentifyTableBucketing() {
  // Construct bucket confiugrations
  const buckets = [
    {
      min: {integerValue: 0},
      max: {integerValue: 25},
      replacementValue: {stringValue: 'Low'},
    },
    {
      min: {integerValue: 25},
      max: {integerValue: 75},
      replacementValue: {stringValue: 'Medium'},
    },
    {
      min: {integerValue: 75},
      max: {integerValue: 100},
      replacementValue: {stringValue: 'High'},
    },
  ];

  const bucketingConfig = {
    buckets: buckets,
  };

  // The list of fields to be transformed.
  const fieldIds = [{name: 'HAPPINESS SCORE'}];

  // Associate fields with bucketing configuration.
  const fieldTransformations = [
    {
      primitiveTransformation: {bucketingConfig: bucketingConfig},
      fields: fieldIds,
    },
  ];

  // Specify de-identify configuration using transformation object.
  const deidentifyConfig = {
    recordTransformations: {
      fieldTransformations: fieldTransformations,
    },
  };

  // Combine configurations into a request for the service.
  const request = {
    parent: `projects/${projectId}/locations/global`,
    deidentifyConfig: deidentifyConfig,
    item: {
      table: tablularData,
    },
  };
  // Send the request and receive response from the service.
  const [response] = await dlp.deidentifyContent(request);

  // Print the results.
  console.log(
    `Table after de-identification: ${JSON.stringify(
      response.item.table,
      null,
      2
    )}`
  );
}
deIdentifyTableBucketing();

PHP

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


use Google\Cloud\Dlp\V2\BucketingConfig;
use Google\Cloud\Dlp\V2\BucketingConfig\Bucket;
use Google\Cloud\Dlp\V2\Client\DlpServiceClient;
use Google\Cloud\Dlp\V2\ContentItem;
use Google\Cloud\Dlp\V2\DeidentifyConfig;
use Google\Cloud\Dlp\V2\DeidentifyContentRequest;
use Google\Cloud\Dlp\V2\FieldId;
use Google\Cloud\Dlp\V2\FieldTransformation;
use Google\Cloud\Dlp\V2\PrimitiveTransformation;
use Google\Cloud\Dlp\V2\RecordTransformations;
use Google\Cloud\Dlp\V2\Table;
use Google\Cloud\Dlp\V2\Table\Row;
use Google\Cloud\Dlp\V2\Value;

/**
 * De-identify data using primitive bucketing.
 * https://cloud.google.com/dlp/docs/concepts-bucketing#bucketing_scenario_1
 *
 * @param string $callingProjectId      The Google Cloud project id to use as a parent resource.
 * @param string $inputCsvFile          The input file(csv) path to deidentify.
 * @param string $outputCsvFile         The oupt file path to save deidentify content.
 *
 */
function deidentify_table_primitive_bucketing(
    // TODO(developer): Replace sample parameters before running the code.
    string $callingProjectId,
    string $inputCsvFile = './test/data/table4.csv',
    string $outputCsvFile = './test/data/deidentify_table_primitive_bucketing_output.csv'
): void {
    // Instantiate a client.
    $dlp = new DlpServiceClient();

    // Read a CSV file.
    $csvLines = file($inputCsvFile, FILE_IGNORE_NEW_LINES);
    $csvHeaders = explode(',', $csvLines[0]);
    $csvRows = array_slice($csvLines, 1);

    // Convert CSV file into protobuf objects.
    $tableHeaders = array_map(function ($csvHeader) {
        return (new FieldId)->setName($csvHeader);
    }, $csvHeaders);

    $tableRows = array_map(function ($csvRow) {
        $rowValues = array_map(function ($csvValue) {
            return (new Value())
                ->setStringValue($csvValue);
        }, explode(',', $csvRow));
        return (new Row())
            ->setValues($rowValues);
    }, $csvRows);

    // Construct the table object.
    $tableToDeIdentify = (new Table())
        ->setHeaders($tableHeaders)
        ->setRows($tableRows);

    // Specify what content you want the service to de-identify.
    $contentItem = (new ContentItem())
        ->setTable($tableToDeIdentify);

    // Specify how the content should be de-identified.
    $buckets = [
        (new Bucket())
            ->setMin((new Value())
                ->setIntegerValue(0))
            ->setMax((new Value())
                ->setIntegerValue(25))
            ->setReplacementValue((new Value())
                ->setStringValue('LOW')),
        (new Bucket())
            ->setMin((new Value())
                ->setIntegerValue(25))
            ->setMax((new Value())
                ->setIntegerValue(75))
            ->setReplacementValue((new Value())
                ->setStringValue('Medium')),
        (new Bucket())
            ->setMin((new Value())
                ->setIntegerValue(75))
            ->setMax((new Value())
                ->setIntegerValue(100))
            ->setReplacementValue((new Value())
                ->setStringValue('High')),
    ];

    $bucketingConfig = (new BucketingConfig())
        ->setBuckets($buckets);

    $primitiveTransformation = (new PrimitiveTransformation())
        ->setBucketingConfig($bucketingConfig);

    // Specify the field of the table to be de-identified.
    $fieldId = (new FieldId())
        ->setName('score');

    $fieldTransformation = (new FieldTransformation())
        ->setPrimitiveTransformation($primitiveTransformation)
        ->setFields([$fieldId]);

    $recordTransformations = (new RecordTransformations())
        ->setFieldTransformations([$fieldTransformation]);

    // Create the deidentification configuration object.
    $deidentifyConfig = (new DeidentifyConfig())
        ->setRecordTransformations($recordTransformations);

    $parent = "projects/$callingProjectId/locations/global";

    // Send the request and receive response from the service.
    $deidentifyContentRequest = (new DeidentifyContentRequest())
        ->setParent($parent)
        ->setDeidentifyConfig($deidentifyConfig)
        ->setItem($contentItem);
    $response = $dlp->deidentifyContent($deidentifyContentRequest);

    // Print the results.
    $csvRef = fopen($outputCsvFile, 'w');
    fputcsv($csvRef, $csvHeaders);
    foreach ($response->getItem()->getTable()->getRows() as $tableRow) {
        $values = array_map(function ($tableValue) {
            return $tableValue->getStringValue();
        }, iterator_to_array($tableRow->getValues()));
        fputcsv($csvRef, $values);
    };
    printf('Table after deidentify (File Location): %s', $outputCsvFile);
}

Python

To learn how to install and use the client library for Sensitive Data Protection, see Sensitive Data Protection client libraries.

To authenticate to Sensitive Data Protection, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import google.cloud.dlp


def deidentify_table_primitive_bucketing(
    project: str,
) -> None:
    """Uses the Data Loss Prevention API to de-identify sensitive data in
    a table by replacing them with generalized bucket labels.
    Args:
        project: The Google Cloud project id to use as a parent resource.
    """

    # Instantiate a client.
    dlp = google.cloud.dlp_v2.DlpServiceClient()

    # Convert the project id into a full resource id.
    parent = f"projects/{project}/locations/global"

    # Dictionary representing table to de-identify.
    # The table can also be taken as input to the function.
    table_to_deid = {
        "header": ["age", "patient", "happiness_score"],
        "rows": [
            ["101", "Charles Dickens", "95"],
            ["22", "Jane Austen", "21"],
            ["90", "Mark Twain", "75"],
        ],
    }

    # Construct the `table`. For more details on the table schema, please see
    # https://cloud.google.com/dlp/docs/reference/rest/v2/ContentItem#Table
    headers = [{"name": val} for val in table_to_deid["header"]]
    rows = []
    for row in table_to_deid["rows"]:
        rows.append({"values": [{"string_value": cell_val} for cell_val in row]})

    table = {"headers": headers, "rows": rows}

    # Construct the `item` for table to de-identify.
    item = {"table": table}

    # Construct generalised bucket configuration.
    buckets_config = [
        {
            "min_": {"integer_value": 0},
            "max_": {"integer_value": 25},
            "replacement_value": {"string_value": "Low"},
        },
        {
            "min_": {"integer_value": 25},
            "max_": {"integer_value": 75},
            "replacement_value": {"string_value": "Medium"},
        },
        {
            "min_": {"integer_value": 75},
            "max_": {"integer_value": 100},
            "replacement_value": {"string_value": "High"},
        },
    ]

    # Construct de-identify configuration that groups values in a table field and replace those with bucket labels.
    deidentify_config = {
        "record_transformations": {
            "field_transformations": [
                {
                    "fields": [{"name": "happiness_score"}],
                    "primitive_transformation": {
                        "bucketing_config": {"buckets": buckets_config}
                    },
                }
            ]
        }
    }

    # Call the API to deidentify table data through primitive bucketing.
    response = dlp.deidentify_content(
        request={
            "parent": parent,
            "deidentify_config": deidentify_config,
            "item": item,
        }
    )

    # Print the results.
    print(f"Table after de-identification: {response.item.table}")

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.