docs: In bigtable fraud demo, change "demographics" wording (#7336)

* docs: In bigtable fraud demo, change "demographics" to be "customer profiles"

* fix cf name

* Fix table formatting

Author: billyjacobson

bigtable/use-cases/fraudDetection/README.md

@@ -16,7 +16,7 @@
 package bigtable.fraud.beam;
 
 import bigtable.fraud.beam.utils.AggregatedData;
-import bigtable.fraud.beam.utils.CustomerDemographics;
+import bigtable.fraud.beam.utils.CustomerProfile;
 import bigtable.fraud.beam.utils.RowDetails;
 import bigtable.fraud.beam.utils.TransactionDetails;
 import bigtable.fraud.beam.utils.WriteCBTHelper;
@@ -127,12 +127,12 @@ public void processElement(
         Preconditions.checkArgument(new String(row.getRow()).equals(
             transactionDetails.getCustomerID()));
 
-        CustomerDemographics customerDemographics = new CustomerDemographics(
+        CustomerProfile customerProfile = new CustomerProfile(
             row);
 
         // Generate an AggregatedData object.
         AggregatedData aggregatedData =
-            new AggregatedData(customerDemographics, transactionDetails, row);
+            new AggregatedData(customerProfile, transactionDetails, row);
 
         c.output(aggregatedData);
       } catch (Exception e) {

bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/FraudDetection.java

@@ -15,7 +15,7 @@
  */
 package bigtable.fraud.beam;
 
-import bigtable.fraud.beam.utils.CustomerDemographics;
+import bigtable.fraud.beam.utils.CustomerProfile;
 import bigtable.fraud.beam.utils.TransactionDetails;
 import bigtable.fraud.beam.utils.RowDetails;
 import bigtable.fraud.beam.utils.WriteCBTHelper;
@@ -29,7 +29,7 @@
 import org.apache.beam.sdk.transforms.ParDo;
 import org.apache.beam.sdk.values.TypeDescriptor;
 
-// Load customer demographics and history into Cloud Bigtable.
+// Load customer profiles and history into Cloud Bigtable.
 public final class LoadDataset {
 
   /**
@@ -46,7 +46,7 @@ public static void main(final String[] args) throws
     LoadDatasetOptions options =
         PipelineOptionsFactory.fromArgs(args).withValidation()
             .as(LoadDatasetOptions.class);
-    options.setJobName("load-customer-demographics-" + options.getRandomUUID());
+    options.setJobName("load-customer-profiles-" + options.getRandomUUID());
 
     CloudBigtableTableConfiguration config =
         new CloudBigtableTableConfiguration.Builder()
@@ -55,21 +55,21 @@ public static void main(final String[] args) throws
             .withTableId(options.getCBTTableId())
             .build();
 
-    // Create a pipeline that reads the GCS demographics csv file
+    // Create a pipeline that reads the GCS customer profile csv file
     // and write it into CBT.
-    Pipeline pDemographics = Pipeline.create(options);
-    pDemographics
+    Pipeline pProfiles = Pipeline.create(options);
+    pProfiles
         .apply("ReadGCSFile",
-            TextIO.read().from(options.getDemographicsInputFile()))
+            TextIO.read().from(options.getCustomerProfileInputFile()))
         .apply(
             MapElements.into(TypeDescriptor.of(RowDetails.class))
-                .via(CustomerDemographics::new))
+                .via(CustomerProfile::new))
         .apply("TransformParsingsToBigtable",
             ParDo.of(WriteCBTHelper.MUTATION_TRANSFORM))
         .apply(
             "WriteToBigtable",
             CloudBigtableIO.writeToTable(config));
-    PipelineResult pDemographicsRun = pDemographics.run();
+    PipelineResult pProfilesRun = pProfiles.run();
 
     // Create a pipeline that reads the GCS history csv file and write
     // it into CBT
@@ -89,7 +89,7 @@ public static void main(final String[] args) throws
             CloudBigtableIO.writeToTable(config));
     PipelineResult pHistoryRun = pHistory.run();
 
-    pDemographicsRun.waitUntilFinish();
+    pProfilesRun.waitUntilFinish();
     pHistoryRun.waitUntilFinish();
   }
 }

bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/LoadDataset.java

@@ -58,15 +58,15 @@ public interface LoadDatasetOptions extends DataflowPipelineOptions {
   void setCBTTableId(String tableID);
 
   /**
-   * @return customer demographics input file.
+   * @return customer profile input file.
    */
-  @Description("The Cloud Storage path to the demographics CSV file.")
-  String getDemographicsInputFile();
+  @Description("The Cloud Storage path to the profile CSV file.")
+  String getCustomerProfileInputFile();
 
   /**
-   * @param location customer demographics file location.
+   * @param location customer profile file location.
    */
-  void setDemographicsInputFile(String location);
+  void setCustomerProfileInputFile(String location);
 
   /**
    * @return transactions history input file.

bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/LoadDatasetOptions.java

@@ -28,9 +28,9 @@ public final class AggregatedData {
    */
   private TransactionDetails transactionDetails;
   /**
-   * Stores the incoming transaction customer demographics.
+   * Stores the incoming transaction customer profile.
    */
-  private CustomerDemographics customerDemographics;
+  private CustomerProfile customerProfile;
   /**
    * Stores the time difference between this transaction and the last one in
    * minutes.
@@ -58,14 +58,14 @@ public final class AggregatedData {
   /**
    * Construct an AggregatedData object.
    *
-   * @param iCustomerDemographics the incoming customer demographic object.
+   * @param iCustomerProfile the incoming customer profile object.
    * @param iTransactionDetails the incoming transaction details object.
    * @param row a result row read from Cloud Bigtable.
    */
   public AggregatedData(
-      final CustomerDemographics iCustomerDemographics,
+      final CustomerProfile iCustomerProfile,
       final TransactionDetails iTransactionDetails, final Result row) {
-    this.customerDemographics = iCustomerDemographics;
+    this.customerProfile = iCustomerProfile;
     this.transactionDetails = iTransactionDetails;
 
     // Get last transaction.
@@ -162,8 +162,8 @@ public String getMLFeatures() {
     mlFeatures.add(String.valueOf(avgAmountSpentLastWeek));
     mlFeatures.add(String.valueOf(avgAmountSpentLastMonth));
     mlFeatures.add(String.valueOf(numOfTransactionLastDay));
-    mlFeatures.add(String.valueOf(customerDemographics.getId()));
-    mlFeatures.add(customerDemographics.getCcNumber());
+    mlFeatures.add(String.valueOf(customerProfile.getId()));
+    mlFeatures.add(customerProfile.getCcNumber());
     mlFeatures.add(String.valueOf(transactionDetails.getTransactionAmount()));
     mlFeatures.add(String.valueOf(transactionDetails.getMerchantID()));
 

bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/utils/AggregatedData.java

@@ -20,7 +20,7 @@
 import org.apache.hadoop.hbase.client.Result;
 
 @DefaultCoder(AvroCoder.class)
-public final class CustomerDemographics extends RowDetails {
+public final class CustomerProfile extends RowDetails {
 
   /**
    * The incoming request's customer id.
@@ -48,20 +48,20 @@ public final class CustomerDemographics extends RowDetails {
   private String accountNumber;
 
   /**
-   * Constructs CustomerDemographics object.
+   * Constructs CustomerProfile object.
    *
-   * @param line a CustomerDemographics comma-seperated line
+   * @param line a CustomerProfile comma-seperated line
    */
-  public CustomerDemographics(final String line) {
+  public CustomerProfile(final String line) {
     super(line);
   }
 
   /**
-   * Constructs CustomerDemographics object.
+   * Constructs CustomerProfile object.
    *
    * @param row a row result read from Cloud Bigtable.
    */
-  public CustomerDemographics(final Result row) {
+  public CustomerProfile(final Result row) {
     super(row);
   }
 
@@ -81,6 +81,6 @@ public String getCcNumber() {
 
   @Override
   public String getColFamily() {
-    return "demographics";
+    return "customer_profile";
   }
 }

…aud/beam/utils/CustomerDemographics.java …le/fraud/beam/utils/CustomerProfile.javabigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/utils/CustomerDemographics.java renamed to bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/utils/CustomerProfile.java bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/utils/CustomerDemographics.java renamed to bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/utils/CustomerProfile.java

@@ -15,7 +15,7 @@
  */
 
 /**
- * Classes that will hold customer demographics, transactions history, and
+ * Classes that will hold customer profiles, transactions history, and
  * aggregated data to be sent to the machine learning model.
  */
 package bigtable.fraud.beam.utils;

bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/utils/package-info.java

@@ -36,7 +36,7 @@ resource "google_bigtable_table" "tf-fd-table" {
   name          = "customer-information-${random_string.uuid.result}"
   instance_name = google_bigtable_instance.tf-fd-instance.name
   column_family {
-    family = "demographics"
+    family = "customer_profile"
   }
   column_family {
     family = "history"
@@ -116,7 +116,7 @@ resource "google_storage_bucket_object" "legit_transactions" {
   bucket = google_storage_bucket.tf-fd-bucket.name
 }
 
-# A CSV file that contains customers' demographics.
+# A CSV file that contains customers' profiles.
 resource "google_storage_bucket_object" "customers" {
   name   = "training_dataset/customers.csv"
   source = "./datasets/training_data/customers.csv"
@@ -170,7 +170,7 @@ module "dataflow_pipeline" {
   destroy_cmd_body       = "${var.region} ${random_string.uuid.result}"
 }
 
-# Load both demographics and historical data into Cloud Bigtable so that
+# Load both profiles and historical data into Cloud Bigtable so that
 # the dataflow pipeline can aggregate data properly before querying
 # the ML model.
 

bigtable/use-cases/fraudDetection/terraform/main.tf

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-# Load demographics and historical transactions data from GCS into CBT.
+# Load customer profiles and historical transactions data from GCS into CBT.
 
 PROJECT_ID=$1
 REGION=$2
@@ -18,6 +18,6 @@ echo "GCS_BUCKET=$GCS_BUCKET"
 mvn -f ../pom.xml compile exec:java -Dexec.mainClass=bigtable.fraud.beam.LoadDataset -Dexec.cleanupDaemonThreads=false \
 "-Dexec.args= --runner=DataflowRunner --project=$PROJECT_ID --projectID=$PROJECT_ID --region=$REGION \
 --gcpTempLocation=gs://$GCS_BUCKET/temp --CBTInstanceId=$CBT_INSTANCE --CBTTableId=$CBT_TABLE \
---demographicsInputFile=gs://$GCS_BUCKET/training_dataset/customers.csv \
+--customerProfileInputFile=gs://$GCS_BUCKET/training_dataset/customers.csv \
 --historyInputFile=gs://$GCS_BUCKET/training_dataset/transactions.csv \
 --randomUUID=$RANDOM_UUID"