diff --git a/aiplatform/snippets/pom.xml b/aiplatform/snippets/pom.xml index 3fc4e24afa6..83953def3f0 100644 --- a/aiplatform/snippets/pom.xml +++ b/aiplatform/snippets/pom.xml @@ -62,6 +62,10 @@ proto-google-cloud-aiplatform-v1beta1 0.17.0 - + + com.google.cloud + google-cloud-bigquery + 2.13.6 + diff --git a/aiplatform/snippets/src/main/java/aiplatform/BatchCreateFeaturesSample.java b/aiplatform/snippets/src/main/java/aiplatform/BatchCreateFeaturesSample.java new file mode 100644 index 00000000000..8b948092798 --- /dev/null +++ b/aiplatform/snippets/src/main/java/aiplatform/BatchCreateFeaturesSample.java @@ -0,0 +1,128 @@ +/* + * Copyright 2022 Google LLC + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * + * + * Create features in bulk for an existing entity type. See + * https://cloud.google.com/vertex-ai/docs/featurestore/setup + * before running the code snippet + */ + +package aiplatform; + +// [START aiplatform_batch_create_features_sample] + +import com.google.api.gax.longrunning.OperationFuture; +import com.google.cloud.aiplatform.v1.BatchCreateFeaturesOperationMetadata; +import com.google.cloud.aiplatform.v1.BatchCreateFeaturesRequest; +import com.google.cloud.aiplatform.v1.BatchCreateFeaturesResponse; +import com.google.cloud.aiplatform.v1.CreateFeatureRequest; +import com.google.cloud.aiplatform.v1.EntityTypeName; +import com.google.cloud.aiplatform.v1.Feature; +import com.google.cloud.aiplatform.v1.Feature.ValueType; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceClient; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceSettings; +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; + +public class BatchCreateFeaturesSample { + + public static void main(String[] args) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + // TODO(developer): Replace these variables before running the sample. + String project = "YOUR_PROJECT_ID"; + String featurestoreId = "YOUR_FEATURESTORE_ID"; + String entityTypeId = "YOUR_ENTITY_TYPE_ID"; + String location = "us-central1"; + String endpoint = "us-central1-aiplatform.googleapis.com:443"; + int timeout = 300; + batchCreateFeaturesSample(project, featurestoreId, entityTypeId, location, endpoint, timeout); + } + + static void batchCreateFeaturesSample( + String project, + String featurestoreId, + String entityTypeId, + String location, + String endpoint, + int timeout) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + FeaturestoreServiceSettings featurestoreServiceSettings = + FeaturestoreServiceSettings.newBuilder().setEndpoint(endpoint).build(); + + // 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 (FeaturestoreServiceClient featurestoreServiceClient = + FeaturestoreServiceClient.create(featurestoreServiceSettings)) { + + List createFeatureRequests = new ArrayList<>(); + + Feature titleFeature = + Feature.newBuilder() + .setDescription("The title of the movie") + .setValueType(ValueType.STRING) + .build(); + Feature genresFeature = + Feature.newBuilder() + .setDescription("The genres of the movie") + .setValueType(ValueType.STRING) + .build(); + Feature averageRatingFeature = + Feature.newBuilder() + .setDescription("The average rating for the movie, range is [1.0-5.0]") + .setValueType(ValueType.DOUBLE) + .build(); + + createFeatureRequests.add( + CreateFeatureRequest.newBuilder().setFeature(titleFeature).setFeatureId("title").build()); + + createFeatureRequests.add( + CreateFeatureRequest.newBuilder() + .setFeature(genresFeature) + .setFeatureId("genres") + .build()); + + createFeatureRequests.add( + CreateFeatureRequest.newBuilder() + .setFeature(averageRatingFeature) + .setFeatureId("average_rating") + .build()); + + BatchCreateFeaturesRequest batchCreateFeaturesRequest = + BatchCreateFeaturesRequest.newBuilder() + .setParent( + EntityTypeName.of(project, location, featurestoreId, entityTypeId).toString()) + .addAllRequests(createFeatureRequests) + .build(); + + OperationFuture + batchCreateFeaturesFuture = + featurestoreServiceClient.batchCreateFeaturesAsync(batchCreateFeaturesRequest); + System.out.format( + "Operation name: %s%n", batchCreateFeaturesFuture.getInitialFuture().get().getName()); + System.out.println("Waiting for operation to finish..."); + BatchCreateFeaturesResponse batchCreateFeaturesResponse = + batchCreateFeaturesFuture.get(timeout, TimeUnit.SECONDS); + System.out.println("Batch Create Features Response"); + System.out.println(batchCreateFeaturesResponse); + featurestoreServiceClient.close(); + } + } +} +// [END aiplatform_batch_create_features_sample] diff --git a/aiplatform/snippets/src/main/java/aiplatform/BatchReadFeatureValuesSample.java b/aiplatform/snippets/src/main/java/aiplatform/BatchReadFeatureValuesSample.java new file mode 100644 index 00000000000..a76c3388d1e --- /dev/null +++ b/aiplatform/snippets/src/main/java/aiplatform/BatchReadFeatureValuesSample.java @@ -0,0 +1,135 @@ +/* + * Copyright 2022 Google LLC + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * + * + * Batch read feature values from a featurestore, as determined by your + * read instances list file, to export data. See + * https://cloud.google.com/vertex-ai/docs/featurestore/setup before running + * the code snippet + */ + +package aiplatform; + +// [START aiplatform_batch_read_feature_values_sample] + +import com.google.api.gax.longrunning.OperationFuture; +import com.google.cloud.aiplatform.v1.BatchReadFeatureValuesOperationMetadata; +import com.google.cloud.aiplatform.v1.BatchReadFeatureValuesRequest; +import com.google.cloud.aiplatform.v1.BatchReadFeatureValuesRequest.EntityTypeSpec; +import com.google.cloud.aiplatform.v1.BatchReadFeatureValuesResponse; +import com.google.cloud.aiplatform.v1.BigQueryDestination; +import com.google.cloud.aiplatform.v1.CsvSource; +import com.google.cloud.aiplatform.v1.FeatureSelector; +import com.google.cloud.aiplatform.v1.FeatureValueDestination; +import com.google.cloud.aiplatform.v1.FeaturestoreName; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceClient; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceSettings; +import com.google.cloud.aiplatform.v1.GcsSource; +import com.google.cloud.aiplatform.v1.IdMatcher; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; + +public class BatchReadFeatureValuesSample { + + public static void main(String[] args) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + // TODO(developer): Replace these variables before running the sample. + String project = "YOUR_PROJECT_ID"; + String featurestoreId = "YOUR_FEATURESTORE_ID"; + String entityTypeId = "YOUR_ENTITY_TYPE_ID"; + String inputCsvFile = "YOU_INPUT_CSV_FILE"; + String destinationTableUri = "YOUR_DESTINATION_TABLE_URI"; + List featureSelectorIds = Arrays.asList("title", "genres", "average_rating"); + String location = "us-central1"; + String endpoint = "us-central1-aiplatform.googleapis.com:443"; + int timeout = 300; + batchReadFeatureValuesSample( + project, + featurestoreId, + entityTypeId, + inputCsvFile, + destinationTableUri, + featureSelectorIds, + location, + endpoint, + timeout); + } + + static void batchReadFeatureValuesSample( + String project, + String featurestoreId, + String entityTypeId, + String inputCsvFile, + String destinationTableUri, + List featureSelectorIds, + String location, + String endpoint, + int timeout) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + FeaturestoreServiceSettings featurestoreServiceSettings = + FeaturestoreServiceSettings.newBuilder().setEndpoint(endpoint).build(); + + // 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 (FeaturestoreServiceClient featurestoreServiceClient = + FeaturestoreServiceClient.create(featurestoreServiceSettings)) { + + List entityTypeSpecs = new ArrayList<>(); + + FeatureSelector featureSelector = + FeatureSelector.newBuilder() + .setIdMatcher(IdMatcher.newBuilder().addAllIds(featureSelectorIds).build()) + .build(); + EntityTypeSpec entityTypeSpec = + EntityTypeSpec.newBuilder() + .setEntityTypeId(entityTypeId) + .setFeatureSelector(featureSelector) + .build(); + + entityTypeSpecs.add(entityTypeSpec); + + BigQueryDestination bigQueryDestination = + BigQueryDestination.newBuilder().setOutputUri(destinationTableUri).build(); + GcsSource gcsSource = GcsSource.newBuilder().addUris(inputCsvFile).build(); + BatchReadFeatureValuesRequest batchReadFeatureValuesRequest = + BatchReadFeatureValuesRequest.newBuilder() + .setFeaturestore(FeaturestoreName.of(project, location, featurestoreId).toString()) + .setCsvReadInstances(CsvSource.newBuilder().setGcsSource(gcsSource)) + .setDestination( + FeatureValueDestination.newBuilder().setBigqueryDestination(bigQueryDestination)) + .addAllEntityTypeSpecs(entityTypeSpecs) + .build(); + + OperationFuture + batchReadFeatureValuesFuture = + featurestoreServiceClient.batchReadFeatureValuesAsync(batchReadFeatureValuesRequest); + System.out.format( + "Operation name: %s%n", batchReadFeatureValuesFuture.getInitialFuture().get().getName()); + System.out.println("Waiting for operation to finish..."); + BatchReadFeatureValuesResponse batchReadFeatureValuesResponse = + batchReadFeatureValuesFuture.get(timeout, TimeUnit.SECONDS); + System.out.println("Batch Read Feature Values Response"); + System.out.println(batchReadFeatureValuesResponse); + featurestoreServiceClient.close(); + } + } +} +// [END aiplatform_batch_read_feature_values_sample] diff --git a/aiplatform/snippets/src/main/java/aiplatform/ExportFeatureValuesSample.java b/aiplatform/snippets/src/main/java/aiplatform/ExportFeatureValuesSample.java new file mode 100644 index 00000000000..6bb7b00d66e --- /dev/null +++ b/aiplatform/snippets/src/main/java/aiplatform/ExportFeatureValuesSample.java @@ -0,0 +1,119 @@ +/* + * Copyright 2022 Google LLC + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * + * + * Bulk export feature values from a featurestore. See + * https://cloud.google.com/vertex-ai/docs/featurestore/setup before running + * the code snippet + */ + +package aiplatform; + +// [START aiplatform_export_feature_values_sample] + +import com.google.api.gax.longrunning.OperationFuture; +import com.google.cloud.aiplatform.v1.BigQueryDestination; +import com.google.cloud.aiplatform.v1.EntityTypeName; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesOperationMetadata; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesRequest; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesRequest.FullExport; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesResponse; +import com.google.cloud.aiplatform.v1.FeatureSelector; +import com.google.cloud.aiplatform.v1.FeatureValueDestination; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceClient; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceSettings; +import com.google.cloud.aiplatform.v1.IdMatcher; +import java.io.IOException; +import java.util.Arrays; +import java.util.List; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; + +public class ExportFeatureValuesSample { + + public static void main(String[] args) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + // TODO(developer): Replace these variables before running the sample. + String project = "YOUR_PROJECT_ID"; + String featurestoreId = "YOUR_FEATURESTORE_ID"; + String entityTypeId = "YOUR_ENTITY_TYPE_ID"; + String destinationTableUri = "YOUR_DESTINATION_TABLE_URI"; + List featureSelectorIds = Arrays.asList("title", "genres", "average_rating"); + String location = "us-central1"; + String endpoint = "us-central1-aiplatform.googleapis.com:443"; + int timeout = 300; + exportFeatureValuesSample( + project, + featurestoreId, + entityTypeId, + destinationTableUri, + featureSelectorIds, + location, + endpoint, + timeout); + } + + static void exportFeatureValuesSample( + String project, + String featurestoreId, + String entityTypeId, + String destinationTableUri, + List featureSelectorIds, + String location, + String endpoint, + int timeout) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + FeaturestoreServiceSettings featurestoreServiceSettings = + FeaturestoreServiceSettings.newBuilder().setEndpoint(endpoint).build(); + + // 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 (FeaturestoreServiceClient featurestoreServiceClient = + FeaturestoreServiceClient.create(featurestoreServiceSettings)) { + + FeatureSelector featureSelector = + FeatureSelector.newBuilder() + .setIdMatcher(IdMatcher.newBuilder().addAllIds(featureSelectorIds).build()) + .build(); + + ExportFeatureValuesRequest exportFeatureValuesRequest = + ExportFeatureValuesRequest.newBuilder() + .setEntityType( + EntityTypeName.of(project, location, featurestoreId, entityTypeId).toString()) + .setDestination( + FeatureValueDestination.newBuilder() + .setBigqueryDestination( + BigQueryDestination.newBuilder().setOutputUri(destinationTableUri))) + .setFeatureSelector(featureSelector) + .setFullExport(FullExport.newBuilder()) + .build(); + + OperationFuture + exportFeatureValuesFuture = + featurestoreServiceClient.exportFeatureValuesAsync(exportFeatureValuesRequest); + System.out.format( + "Operation name: %s%n", exportFeatureValuesFuture.getInitialFuture().get().getName()); + System.out.println("Waiting for operation to finish..."); + ExportFeatureValuesResponse exportFeatureValuesResponse = + exportFeatureValuesFuture.get(timeout, TimeUnit.SECONDS); + System.out.println("Export Feature Values Response"); + System.out.println(exportFeatureValuesResponse); + featurestoreServiceClient.close(); + } + } +} +// [END aiplatform_export_feature_values_sample] diff --git a/aiplatform/snippets/src/main/java/aiplatform/ExportFeatureValuesSnapshotSample.java b/aiplatform/snippets/src/main/java/aiplatform/ExportFeatureValuesSnapshotSample.java new file mode 100644 index 00000000000..6d48d34d06c --- /dev/null +++ b/aiplatform/snippets/src/main/java/aiplatform/ExportFeatureValuesSnapshotSample.java @@ -0,0 +1,119 @@ +/* + * Copyright 2022 Google LLC + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * + * + * Bulk export feature values from a featurestore. See + * https://cloud.google.com/vertex-ai/docs/featurestore/setup before running + * the code snippet + */ + +package aiplatform; + +// [START aiplatform_export_feature_values_snapshot_sample] + +import com.google.api.gax.longrunning.OperationFuture; +import com.google.cloud.aiplatform.v1.BigQueryDestination; +import com.google.cloud.aiplatform.v1.EntityTypeName; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesOperationMetadata; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesRequest; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesRequest.SnapshotExport; +import com.google.cloud.aiplatform.v1.ExportFeatureValuesResponse; +import com.google.cloud.aiplatform.v1.FeatureSelector; +import com.google.cloud.aiplatform.v1.FeatureValueDestination; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceClient; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceSettings; +import com.google.cloud.aiplatform.v1.IdMatcher; +import java.io.IOException; +import java.util.Arrays; +import java.util.List; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; + +public class ExportFeatureValuesSnapshotSample { + + public static void main(String[] args) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + // TODO(developer): Replace these variables before running the sample. + String project = "YOUR_PROJECT_ID"; + String featurestoreId = "YOUR_FEATURESTORE_ID"; + String entityTypeId = "YOUR_ENTITY_TYPE_ID"; + String destinationTableUri = "YOUR_DESTINATION_TABLE_URI"; + List featureSelectorIds = Arrays.asList("title", "genres", "average_rating"); + String location = "us-central1"; + String endpoint = "us-central1-aiplatform.googleapis.com:443"; + int timeout = 300; + exportFeatureValuesSnapshotSample( + project, + featurestoreId, + entityTypeId, + destinationTableUri, + featureSelectorIds, + location, + endpoint, + timeout); + } + + static void exportFeatureValuesSnapshotSample( + String project, + String featurestoreId, + String entityTypeId, + String destinationTableUri, + List featureSelectorIds, + String location, + String endpoint, + int timeout) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + FeaturestoreServiceSettings featurestoreServiceSettings = + FeaturestoreServiceSettings.newBuilder().setEndpoint(endpoint).build(); + + // 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 (FeaturestoreServiceClient featurestoreServiceClient = + FeaturestoreServiceClient.create(featurestoreServiceSettings)) { + + FeatureSelector featureSelector = + FeatureSelector.newBuilder() + .setIdMatcher(IdMatcher.newBuilder().addAllIds(featureSelectorIds).build()) + .build(); + + ExportFeatureValuesRequest exportFeatureValuesRequest = + ExportFeatureValuesRequest.newBuilder() + .setEntityType( + EntityTypeName.of(project, location, featurestoreId, entityTypeId).toString()) + .setDestination( + FeatureValueDestination.newBuilder() + .setBigqueryDestination( + BigQueryDestination.newBuilder().setOutputUri(destinationTableUri))) + .setFeatureSelector(featureSelector) + .setSnapshotExport(SnapshotExport.newBuilder()) + .build(); + + OperationFuture + exportFeatureValuesFuture = + featurestoreServiceClient.exportFeatureValuesAsync(exportFeatureValuesRequest); + System.out.format( + "Operation name: %s%n", exportFeatureValuesFuture.getInitialFuture().get().getName()); + System.out.println("Waiting for operation to finish..."); + ExportFeatureValuesResponse exportFeatureValuesResponse = + exportFeatureValuesFuture.get(timeout, TimeUnit.SECONDS); + System.out.println("Snapshot Export Feature Values Response"); + System.out.println(exportFeatureValuesResponse); + featurestoreServiceClient.close(); + } + } +} +// [END aiplatform_export_feature_values_snapshot_sample] diff --git a/aiplatform/snippets/src/main/java/aiplatform/ImportFeatureValuesSample.java b/aiplatform/snippets/src/main/java/aiplatform/ImportFeatureValuesSample.java new file mode 100644 index 00000000000..405b05f54fb --- /dev/null +++ b/aiplatform/snippets/src/main/java/aiplatform/ImportFeatureValuesSample.java @@ -0,0 +1,122 @@ +/* + * Copyright 2022 Google LLC + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * + * + * Bulk import values into a featurestore for existing features. See + * https://cloud.google.com/vertex-ai/docs/featurestore/setup before running + * the code snippet + */ + +package aiplatform; + +// [START aiplatform_import_feature_values_sample] + +import com.google.api.gax.longrunning.OperationFuture; +import com.google.cloud.aiplatform.v1.AvroSource; +import com.google.cloud.aiplatform.v1.EntityTypeName; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceClient; +import com.google.cloud.aiplatform.v1.FeaturestoreServiceSettings; +import com.google.cloud.aiplatform.v1.GcsSource; +import com.google.cloud.aiplatform.v1.ImportFeatureValuesOperationMetadata; +import com.google.cloud.aiplatform.v1.ImportFeatureValuesRequest; +import com.google.cloud.aiplatform.v1.ImportFeatureValuesRequest.FeatureSpec; +import com.google.cloud.aiplatform.v1.ImportFeatureValuesResponse; +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; + +public class ImportFeatureValuesSample { + + public static void main(String[] args) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + // TODO(developer): Replace these variables before running the sample. + String project = "YOUR_PROJECT_ID"; + String featurestoreId = "YOUR_FEATURESTORE_ID"; + String entityTypeId = "YOUR_ENTITY_TYPE_ID"; + String entityIdField = "YOUR_ENTITY_FIELD_ID"; + String featureTimeField = "YOUR_FEATURE_TIME_FIELD"; + String gcsSourceUri = "YOUR_GCS_SOURCE_URI"; + int workerCount = 2; + String location = "us-central1"; + String endpoint = "us-central1-aiplatform.googleapis.com:443"; + int timeout = 300; + importFeatureValuesSample( + project, + featurestoreId, + entityTypeId, + gcsSourceUri, + entityIdField, + featureTimeField, + workerCount, + location, + endpoint, + timeout); + } + + static void importFeatureValuesSample( + String project, + String featurestoreId, + String entityTypeId, + String gcsSourceUri, + String entityIdField, + String featureTimeField, + int workerCount, + String location, + String endpoint, + int timeout) + throws IOException, InterruptedException, ExecutionException, TimeoutException { + FeaturestoreServiceSettings featurestoreServiceSettings = + FeaturestoreServiceSettings.newBuilder().setEndpoint(endpoint).build(); + + // 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 (FeaturestoreServiceClient featurestoreServiceClient = + FeaturestoreServiceClient.create(featurestoreServiceSettings)) { + List featureSpecs = new ArrayList<>(); + + featureSpecs.add(FeatureSpec.newBuilder().setId("title").build()); + featureSpecs.add(FeatureSpec.newBuilder().setId("genres").build()); + featureSpecs.add(FeatureSpec.newBuilder().setId("average_rating").build()); + ImportFeatureValuesRequest importFeatureValuesRequest = + ImportFeatureValuesRequest.newBuilder() + .setEntityType( + EntityTypeName.of(project, location, featurestoreId, entityTypeId).toString()) + .setEntityIdField(entityIdField) + .setFeatureTimeField(featureTimeField) + .addAllFeatureSpecs(featureSpecs) + .setWorkerCount(workerCount) + .setAvroSource( + AvroSource.newBuilder() + .setGcsSource(GcsSource.newBuilder().addUris(gcsSourceUri))) + .build(); + OperationFuture + importFeatureValuesFuture = + featurestoreServiceClient.importFeatureValuesAsync(importFeatureValuesRequest); + System.out.format( + "Operation name: %s%n", importFeatureValuesFuture.getInitialFuture().get().getName()); + System.out.println("Waiting for operation to finish..."); + ImportFeatureValuesResponse importFeatureValuesResponse = + importFeatureValuesFuture.get(timeout, TimeUnit.SECONDS); + System.out.println("Import Feature Values Response"); + System.out.println(importFeatureValuesResponse); + featurestoreServiceClient.close(); + } + } +} +// [END aiplatform_import_feature_values_sample] diff --git a/aiplatform/snippets/src/test/java/aiplatform/FeatureValuesSamplesTest.java b/aiplatform/snippets/src/test/java/aiplatform/FeatureValuesSamplesTest.java new file mode 100644 index 00000000000..56852503b09 --- /dev/null +++ b/aiplatform/snippets/src/test/java/aiplatform/FeatureValuesSamplesTest.java @@ -0,0 +1,278 @@ +/* + * Copyright 2022 Google LLC + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package aiplatform; + +import static com.google.common.truth.Truth.assertThat; +import static junit.framework.TestCase.assertNotNull; + +import com.google.cloud.bigquery.BigQuery; +import com.google.cloud.bigquery.BigQuery.DatasetDeleteOption; +import com.google.cloud.bigquery.BigQueryException; +import com.google.cloud.bigquery.BigQueryOptions; +import com.google.cloud.bigquery.Dataset; +import com.google.cloud.bigquery.DatasetId; +import com.google.cloud.bigquery.DatasetInfo; +import java.io.ByteArrayOutputStream; +import java.io.IOException; +import java.io.PrintStream; +import java.text.SimpleDateFormat; +import java.util.Arrays; +import java.util.Date; +import java.util.List; +import java.util.UUID; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeoutException; +import org.junit.After; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.JUnit4; + +@RunWith(JUnit4.class) +public class FeatureValuesSamplesTest { + + private static final String PROJECT_ID = System.getenv("UCAIP_PROJECT_ID"); + private static final int MIN_NODE_COUNT = 1; + private static final int MAX_NODE_COUNT = 5; + private static final String DESCRIPTION = "Test Description"; + private static final boolean USE_FORCE = true; + private static final String ENTITY_ID_FIELD = "movie_id"; + private static final String FEATURE_TIME_FIELD = "update_time"; + private static final String GCS_SOURCE_URI = + "gs://cloud-samples-data-us-central1/vertex-ai/feature-store/datasets/movies.avro"; + private static final int WORKER_COUNT = 2; + private static final String INPUT_CSV_FILE = + "gs://cloud-samples-data-us-central1/vertex-ai/feature-store/datasets/movie_prediction.csv"; + private static final List FEATURE_SELECTOR_IDS = + Arrays.asList("title", "genres", "average_rating"); + private static final String LOCATION = "us-central1"; + private static final String ENDPOINT = "us-central1-aiplatform.googleapis.com:443"; + private static final int TIMEOUT = 900; + private ByteArrayOutputStream bout; + private PrintStream out; + private PrintStream originalPrintStream; + private String featurestoreId; + private String destinationTableUri; + private Date date; + private SimpleDateFormat dateFormat; + private String datasetName; + private String destinationTableName; + + private static void requireEnvVar(String varName) { + String errorMessage = + String.format("Environment variable '%s' is required to perform these tests.", varName); + assertNotNull(errorMessage, System.getenv(varName)); + } + + @BeforeClass + public static void checkRequirements() { + requireEnvVar("GOOGLE_APPLICATION_CREDENTIALS"); + requireEnvVar("UCAIP_PROJECT_ID"); + } + + @Before + public void setUp() { + date = new Date(); + dateFormat = new SimpleDateFormat("yyyyMMddHHmmSSS"); + datasetName = "movie_predictions" + dateFormat.format(date); + destinationTableName = "training_data"; + bout = new ByteArrayOutputStream(); + out = new PrintStream(bout); + originalPrintStream = System.out; + System.setOut(out); + } + + static void createBigQueryDataset(String projectId, String datasetName, String location) { + try { + // Initialize client that will be used to send requests. This client only needs + // to be created + // once, and can be reused for multiple requests. + BigQuery bigquery = + BigQueryOptions.newBuilder() + .setLocation(location) + .setProjectId(projectId) + .build() + .getService(); + DatasetInfo datasetInfo = DatasetInfo.newBuilder(datasetName).build(); + + Dataset newDataset = bigquery.create(datasetInfo); + String newDatasetName = newDataset.getDatasetId().getDataset(); + System.out.println(newDatasetName + " created successfully"); + } catch (BigQueryException e) { + System.out.format("Dataset was not created. %n%s", e.toString()); + } + } + + static void deleteBigQueryDataset(String projectId, String datasetName, String location) { + try { + // Initialize client that will be used to send requests. This client only needs to be created + // once, and can be reused for multiple requests. + BigQuery bigquery = + BigQueryOptions.newBuilder() + .setLocation(location) + .setProjectId(projectId) + .build() + .getService(); + + DatasetId datasetId = DatasetId.of(projectId, datasetName); + boolean success = bigquery.delete(datasetId, DatasetDeleteOption.deleteContents()); + if (success) { + System.out.println("Dataset deleted successfully"); + } else { + System.out.println("Dataset was not found"); + } + } catch (BigQueryException e) { + System.out.format("Dataset was not deleted. %n%s", e.toString()); + } + } + + @After + public void tearDown() + throws InterruptedException, ExecutionException, IOException, TimeoutException { + + // Delete the featurestore + DeleteFeaturestoreSample.deleteFeaturestoreSample( + PROJECT_ID, featurestoreId, USE_FORCE, LOCATION, ENDPOINT, 300); + + // Assert + String deleteFeaturestoreResponse = bout.toString(); + assertThat(deleteFeaturestoreResponse).contains("Deleted Featurestore"); + + // Delete the big query dataset + deleteBigQueryDataset(PROJECT_ID, datasetName, LOCATION); + + // Assert + String deleteBigQueryResponse = bout.toString(); + assertThat(deleteBigQueryResponse).contains("Dataset deleted successfully"); + + System.out.flush(); + System.setOut(originalPrintStream); + } + + @Test + public void testFeatureValuesSamples() + throws IOException, InterruptedException, ExecutionException, TimeoutException { + // Create the featurestore + String tempUuid = UUID.randomUUID().toString().replaceAll("-", "_").substring(0, 26); + String id = String.format("temp_create_featurestore_test_%s", tempUuid); + CreateFeaturestoreSample.createFeaturestoreSample( + PROJECT_ID, id, MIN_NODE_COUNT, MAX_NODE_COUNT, LOCATION, ENDPOINT, 900); + + // Assert + String createFeaturestoreResponse = bout.toString(); + assertThat(createFeaturestoreResponse).contains("Create Featurestore Response"); + featurestoreId = + createFeaturestoreResponse.split("Name: ")[1].split("featurestores/")[1].split("\n")[0] + .trim(); + + // Create the entity type + String entityTypeId = "movies"; + CreateEntityTypeSample.createEntityTypeSample( + PROJECT_ID, featurestoreId, entityTypeId, DESCRIPTION, LOCATION, ENDPOINT, 900); + + // Assert + String createEntityTypeResponse = bout.toString(); + assertThat(createEntityTypeResponse).contains("Create Entity Type Response"); + + // Batch create features + BatchCreateFeaturesSample.batchCreateFeaturesSample( + PROJECT_ID, featurestoreId, entityTypeId, LOCATION, ENDPOINT, TIMEOUT); + + // Assert + String batchCreateFeaturesResponse = bout.toString(); + assertThat(batchCreateFeaturesResponse).contains("Batch Create Features Response"); + + // Import feature values + ImportFeatureValuesSample.importFeatureValuesSample( + PROJECT_ID, + featurestoreId, + entityTypeId, + GCS_SOURCE_URI, + ENTITY_ID_FIELD, + FEATURE_TIME_FIELD, + WORKER_COUNT, + LOCATION, + ENDPOINT, + TIMEOUT); + + // Assert + String importFeatureValuesResponse = bout.toString(); + assertThat(importFeatureValuesResponse).contains("Import Feature Values Response"); + + // Create the big query dataset + createBigQueryDataset(PROJECT_ID, datasetName, LOCATION); + destinationTableUri = + String.format("bq://%s.%s.%s_full", PROJECT_ID, datasetName, destinationTableName); + + // Assert + String createBigQueryDatasetResponse = bout.toString(); + assertThat(createBigQueryDatasetResponse).contains(datasetName + " created successfully"); + + // Export feature values + ExportFeatureValuesSample.exportFeatureValuesSample( + PROJECT_ID, + featurestoreId, + entityTypeId, + destinationTableUri, + FEATURE_SELECTOR_IDS, + LOCATION, + ENDPOINT, + TIMEOUT); + + // Assert + String exportFeatureValuesResponse = bout.toString(); + assertThat(exportFeatureValuesResponse).contains("Export Feature Values Response"); + + destinationTableUri = + String.format("bq://%s.%s.%s_snapshot", PROJECT_ID, datasetName, destinationTableName); + + // Snapshot export feature values + ExportFeatureValuesSnapshotSample.exportFeatureValuesSnapshotSample( + PROJECT_ID, + featurestoreId, + entityTypeId, + destinationTableUri, + FEATURE_SELECTOR_IDS, + LOCATION, + ENDPOINT, + TIMEOUT); + + // Assert + String snapshotResponse = bout.toString(); + assertThat(snapshotResponse).contains("Snapshot Export Feature Values Response"); + + destinationTableUri = + String.format("bq://%s.%s.%s_batchRead", PROJECT_ID, datasetName, destinationTableName); + + // Batch read feature values + BatchReadFeatureValuesSample.batchReadFeatureValuesSample( + PROJECT_ID, + featurestoreId, + entityTypeId, + INPUT_CSV_FILE, + destinationTableUri, + FEATURE_SELECTOR_IDS, + LOCATION, + ENDPOINT, + TIMEOUT); + + // Assert + String batchReadFeatureValuesResponse = bout.toString(); + assertThat(batchReadFeatureValuesResponse).contains("Batch Read Feature Values Response"); + } +}