docs: Bigtable fraud example update readme and convert scan to get (#…

…7367) * docs: Bigtable fraud example update readme and convert scan to get * fix lint line length
GoogleCloudPlatform · Oct 28, 2022 · 16213c7 · 16213c7
1 parent 7879314
commit 16213c7
Show file tree

Hide file tree

Showing 2 changed files with 34 additions and 31 deletions.
diff --git a/bigtable/use-cases/fraudDetection/README.md b/bigtable/use-cases/fraudDetection/README.md
@@ -158,22 +158,30 @@ The ML model is located in the path: **terraform/model**
 
 ### Prerequisites
 
-1) [Have a GCP project.](https://cloud.google.com/resource-manager/docs/creating-managing-projects)
-2) [Have a service account that contains the following permissions:](https://cloud.google.com/docs/authentication/production)
-    1) Bigtable Administrator
-    2) Cloud Dataflow Service Agent
-    3) Compute Admin
-    4) Dataflow Admin
-    5) Dataflow Worker
-    6) Datapipelines Service Agent
-    7) Storage Admin
-    8) Vertex AI User
-3) Set these environment variables:
+1. [Have a GCP project.](https://cloud.google.com/resource-manager/docs/creating-managing-projects)
+2. [Have a service account that contains the following permissions:](https://cloud.google.com/docs/authentication/production)
+    1. Bigtable Administrator
+    1. Cloud Dataflow Service Agent
+    1. Compute Admin
+    1. Dataflow Admin
+    1. Dataflow Worker
+    1. Datapipelines Service Agent
+    1. Storage Admin
+    1. Vertex AI User
+3. Set these environment variables:
+   ```
+   export GOOGLE_APPLICATION_CREDENTIALS={YOUR CREDS PATH}
+   export PROJECT_ID={YOUR PROJECT ID}
+   ```
+
+4. Enable the required APIs:
+   ```
+   gcloud services enable aiplatform.googleapis.com bigtable.googleapis.com
+   bigtableadmin.googleapis.com compute.googleapis.com dataflow.googleapis.com
+   pubsub.googleapis.com storage-api.googleapis.com
+   storage-component.googleapis.com
+   ```
 
-```
-export GOOGLE_APPLICATION_CREDENTIALS={YOUR CREDS PATH}
-export PROJECT_ID={YOUR PROJECT ID}
-```
 
 ### Running steps
 

diff --git a/bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/FraudDetection.java b/bigtable/use-cases/fraudDetection/src/main/java/bigtable/fraud/beam/FraudDetection.java
@@ -42,15 +42,15 @@
 import org.apache.beam.sdk.transforms.ParDo;
 import org.apache.beam.sdk.values.PCollection;
 import org.apache.hadoop.hbase.TableName;
+import org.apache.hadoop.hbase.client.Get;
 import org.apache.hadoop.hbase.client.Result;
-import org.apache.hadoop.hbase.client.ResultScanner;
-import org.apache.hadoop.hbase.client.Scan;
 import org.apache.hadoop.hbase.client.Table;
 import org.apache.hadoop.hbase.util.Bytes;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 public final class FraudDetection {
+
   private FraudDetection() {
   }
 
@@ -61,9 +61,8 @@ private FraudDetection() {
       FraudDetection.class);
 
   /**
-   * Set the field isFraud to true if the fraud_probability was >= 0.1.
-   * This is a configurable number that should be tuned depending on
-   * the ML model.
+   * Set the field isFraud to true if the fraud_probability was >= 0.1. This is
+   * a configurable number that should be tuned depending on the ML model.
    */
   private static final double FRAUD_PROBABILITY_THRESHOLD = 0.1d;
 
@@ -92,8 +91,8 @@ public static class ReadFromTableFn
       AbstractCloudBigtableTableDoFn<TransactionDetails, AggregatedData> {
 
     /**
-     * @param config the CloudBigtableConfiguration used in reading from
-     * Cloud Bigtable.
+     * @param config the CloudBigtableConfiguration used in reading from Cloud
+     * Bigtable.
      */
     public ReadFromTableFn(final CloudBigtableConfiguration config) {
       super(config);
@@ -115,20 +114,15 @@ public void processElement(
             + transactionDetails.getCustomerID());
 
         // Read the cells for that customer ID.
-        Scan scan =
-            new Scan()
-                .withStartRow(Bytes.toBytes(transactionDetails.getCustomerID()))
-                .setOneRowLimit()
-                .setMaxVersions();
         Table table = getConnection().getTable(
             TableName.valueOf(options.getCBTTableId()));
-        ResultScanner data = table.getScanner(scan);
-        Result row = data.next();
+        Result row = table.get(
+            new Get(Bytes.toBytes(transactionDetails.getCustomerID())));
+
         Preconditions.checkArgument(new String(row.getRow()).equals(
             transactionDetails.getCustomerID()));
 
-        CustomerProfile customerProfile = new CustomerProfile(
-            row);
+        CustomerProfile customerProfile = new CustomerProfile(row);
 
         // Generate an AggregatedData object.
         AggregatedData aggregatedData =
@@ -144,6 +138,7 @@ public void processElement(
 
   public static final class QueryMlModelFn
       extends DoFn<AggregatedData, RowDetails> {
+
     /**
      * The region of the ML model.
      */