Skip to content

Commit

Permalink
samples: Translate automl test fixes (#1606)
Browse files Browse the repository at this point in the history 
* Update auto ml tests

* Update style format, slightly to see if that fixes tests

* Update to latest library and fix some syntax to fix the tests

* Address review comments
  • Loading branch information
@nnegrey @chingor13
nnegrey authored and chingor13 committed Aug 3, 2020
1 parent 53904e4 commit d2e9b4e
Show file tree
Hide file tree
Showing 5 changed files with 267 additions and 250 deletions.
247 changes: 124 additions & 123 deletions automl/snippets/src/main/java/com/google/cloud/translate/automl/DatasetApi.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@
import com.google.cloud.automl.v1beta1.Dataset;
import com.google.cloud.automl.v1beta1.DatasetName;
import com.google.cloud.automl.v1beta1.GcsSource;
import com.google.cloud.automl.v1beta1.GcsSource.Builder;
import com.google.cloud.automl.v1beta1.InputConfig;
import com.google.cloud.automl.v1beta1.ListDatasetsRequest;
import com.google.cloud.automl.v1beta1.LocationName;
Expand All @@ -30,6 +29,7 @@

import java.io.IOException;
import java.io.PrintStream;
import java.util.concurrent.ExecutionException;

import net.sourceforge.argparse4j.ArgumentParsers;
import net.sourceforge.argparse4j.inf.ArgumentParser;
Expand All @@ -54,53 +54,53 @@ public class DatasetApi {
* @param datasetName the name of the dataset to be created.
* @param source the Source language
* @param target the Target language
* @throws IOException on Input/Output errors.
*/
public static void createDataset(
String projectId, String computeRegion, String datasetName, String source, String target)
throws IOException {
// Instantiates a client
AutoMlClient client = AutoMlClient.create();

// A resource that represents Google Cloud Platform location.
LocationName projectLocation = LocationName.of(projectId, computeRegion);

// Specify the source and target language.
TranslationDatasetMetadata translationDatasetMetadata =
TranslationDatasetMetadata.newBuilder()
.setSourceLanguageCode(source)
.setTargetLanguageCode(target)
.build();

// Set dataset name and dataset metadata.
Dataset myDataset =
Dataset.newBuilder()
.setDisplayName(datasetName)
.setTranslationDatasetMetadata(translationDatasetMetadata)
.build();

// Create a dataset with the dataset metadata in the region.
Dataset dataset = client.createDataset(projectLocation, myDataset);

// Display the dataset information.
System.out.println(String.format("Dataset name: %s", dataset.getName()));
System.out.println(
String.format(
"Dataset id: %s",
dataset.getName().split("/")[dataset.getName().split("/").length - 1]));
System.out.println(String.format("Dataset display name: %s", dataset.getDisplayName()));
System.out.println("Translation dataset Metadata:");
System.out.println(
String.format(
"\tSource language code: %s",
dataset.getTranslationDatasetMetadata().getSourceLanguageCode()));
System.out.println(
String.format(
"\tTarget language code: %s",
dataset.getTranslationDatasetMetadata().getTargetLanguageCode()));
System.out.println("Dataset create time:");
System.out.println(String.format("\tseconds: %s", dataset.getCreateTime().getSeconds()));
System.out.println(String.format("\tnanos: %s", dataset.getCreateTime().getNanos()));
try (AutoMlClient client = AutoMlClient.create()) {

// A resource that represents Google Cloud Platform location.
LocationName projectLocation = LocationName.of(projectId, computeRegion);

// Specify the source and target language.
TranslationDatasetMetadata translationDatasetMetadata =
TranslationDatasetMetadata.newBuilder()
.setSourceLanguageCode(source)
.setTargetLanguageCode(target)
.build();

// Set dataset name and dataset metadata.
Dataset myDataset =
Dataset.newBuilder()
.setDisplayName(datasetName)
.setTranslationDatasetMetadata(translationDatasetMetadata)
.build();

// Create a dataset with the dataset metadata in the region.
Dataset dataset = client.createDataset(projectLocation, myDataset);

// Display the dataset information.
System.out.println(String.format("Dataset name: %s", dataset.getName()));
System.out.println(
String.format(
"Dataset id: %s",
dataset.getName().split("/")[dataset.getName().split("/").length - 1]));
System.out.println(String.format("Dataset display name: %s", dataset.getDisplayName()));
System.out.println("Translation dataset Metadata:");
System.out.println(
String.format(
"\tSource language code: %s",
dataset.getTranslationDatasetMetadata().getSourceLanguageCode()));
System.out.println(
String.format(
"\tTarget language code: %s",
dataset.getTranslationDatasetMetadata().getTargetLanguageCode()));
System.out.println("Dataset create time:");
System.out.println(String.format("\tseconds: %s", dataset.getCreateTime().getSeconds()));
System.out.println(String.format("\tnanos: %s", dataset.getCreateTime().getNanos()));
}
}
// [END automl_translate_create_dataset]

Expand All @@ -111,27 +111,69 @@ public static void createDataset(
* @param projectId the Google Cloud Project ID.
* @param computeRegion the Region name. (e.g., "us-central1").
* @param filter the Filter expression.
* @throws Exception on AutoML Client errors
*/
public static void listDatasets(String projectId, String computeRegion, String filter)
throws IOException {
// Instantiates a client
AutoMlClient client = AutoMlClient.create();
try (AutoMlClient client = AutoMlClient.create()) {

// A resource that represents Google Cloud Platform location.
LocationName projectLocation = LocationName.of(projectId, computeRegion);

ListDatasetsRequest request =
ListDatasetsRequest.newBuilder()
.setParent(projectLocation.toString())
.setFilter(filter)
.build();

// List all the datasets available in the region by applying filter.
System.out.println("List of datasets:");
for (Dataset dataset : client.listDatasets(request).iterateAll()) {
// Display the dataset information
System.out.println(String.format("\nDataset name: %s", dataset.getName()));
System.out.println(
String.format(
"Dataset id: %s",
dataset.getName().split("/")[dataset.getName().split("/").length - 1]));
System.out.println(String.format("Dataset display name: %s", dataset.getDisplayName()));
System.out.println("Translation dataset metadata:");
System.out.println(
String.format(
"\tSource language code: %s",
dataset.getTranslationDatasetMetadata().getSourceLanguageCode()));
System.out.println(
String.format(
"\tTarget language code: %s",
dataset.getTranslationDatasetMetadata().getTargetLanguageCode()));
System.out.println("Dataset create time:");
System.out.println(String.format("\tseconds: %s", dataset.getCreateTime().getSeconds()));
System.out.println(String.format("\tnanos: %s", dataset.getCreateTime().getNanos()));
}
}
}
// [END automl_translate_list_datasets]

// [START automl_translate_get_dataset]
/**
* Demonstrates using the AutoML client to get a dataset by ID.
*
* @param projectId the Google Cloud Project ID.
* @param computeRegion the Region name. (e.g., "us-central1").
* @param datasetId the Id of the dataset.
*/
public static void getDataset(String projectId, String computeRegion, String datasetId)
throws IOException {
// Instantiates a client
try (AutoMlClient client = AutoMlClient.create()) {

// A resource that represents Google Cloud Platform location.
LocationName projectLocation = LocationName.of(projectId, computeRegion);
// Get the complete path of the dataset.
DatasetName datasetFullId = DatasetName.of(projectId, computeRegion, datasetId);

ListDatasetsRequest request =
ListDatasetsRequest.newBuilder()
.setParent(projectLocation.toString())
.setFilter(filter)
.build();
// Get all the information about a given dataset.
Dataset dataset = client.getDataset(datasetFullId);

// List all the datasets available in the region by applying filter.
System.out.println("List of datasets:");
for (Dataset dataset : client.listDatasets(request).iterateAll()) {
// Display the dataset information
System.out.println(String.format("\nDataset name: %s", dataset.getName()));
System.out.println(String.format("Dataset name: %s", dataset.getName()));
System.out.println(
String.format(
"Dataset id: %s",
Expand All @@ -151,48 +193,6 @@ public static void listDatasets(String projectId, String computeRegion, String f
System.out.println(String.format("\tnanos: %s", dataset.getCreateTime().getNanos()));
}
}
// [END automl_translate_list_datasets]

// [START automl_translate_get_dataset]
/**
* Demonstrates using the AutoML client to get a dataset by ID.
*
* @param projectId the Google Cloud Project ID.
* @param computeRegion the Region name. (e.g., "us-central1").
* @param datasetId the Id of the dataset.
* @throws Exception on AutoML Client errors
*/
public static void getDataset(String projectId, String computeRegion, String datasetId)
throws Exception {
// Instantiates a client
AutoMlClient client = AutoMlClient.create();

// Get the complete path of the dataset.
DatasetName datasetFullId = DatasetName.of(projectId, computeRegion, datasetId);

// Get all the information about a given dataset.
Dataset dataset = client.getDataset(datasetFullId);

// Display the dataset information
System.out.println(String.format("Dataset name: %s", dataset.getName()));
System.out.println(
String.format(
"Dataset id: %s",
dataset.getName().split("/")[dataset.getName().split("/").length - 1]));
System.out.println(String.format("Dataset display name: %s", dataset.getDisplayName()));
System.out.println("Translation dataset metadata:");
System.out.println(
String.format(
"\tSource language code: %s",
dataset.getTranslationDatasetMetadata().getSourceLanguageCode()));
System.out.println(
String.format(
"\tTarget language code: %s",
dataset.getTranslationDatasetMetadata().getTargetLanguageCode()));
System.out.println("Dataset create time:");
System.out.println(String.format("\tseconds: %s", dataset.getCreateTime().getSeconds()));
System.out.println(String.format("\tnanos: %s", dataset.getCreateTime().getNanos()));
}
// [END automl_translate_get_dataset]

// [START automl_translate_import_data]
Expand All @@ -203,30 +203,31 @@ public static void getDataset(String projectId, String computeRegion, String dat
* @param computeRegion the Region name. (e.g., "us-central1").
* @param datasetId the Id of the dataset.
* @param path the remote Path of the training data csv file.
* @throws Exception on AutoML Client errors
*/
public static void importData(
String projectId, String computeRegion, String datasetId, String path) throws Exception {
String projectId, String computeRegion, String datasetId, String path)
throws IOException, InterruptedException, ExecutionException {
// Instantiates a client
AutoMlClient client = AutoMlClient.create();
try (AutoMlClient client = AutoMlClient.create()) {

// Get the complete path of the dataset.
DatasetName datasetFullId = DatasetName.of(projectId, computeRegion, datasetId);
// Get the complete path of the dataset.
DatasetName datasetFullId = DatasetName.of(projectId, computeRegion, datasetId);

Builder gcsSource = GcsSource.newBuilder();
GcsSource.Builder gcsSource = GcsSource.newBuilder();

// Get multiple Google Cloud Storage URIs to import data from
String[] inputUris = path.split(",");
for (String inputUri : inputUris) {
gcsSource.addInputUris(inputUri);
}
// Get multiple Google Cloud Storage URIs to import data from
String[] inputUris = path.split(",");
for (String inputUri : inputUris) {
gcsSource.addInputUris(inputUri);
}

// Import data from the input URI
InputConfig inputConfig = InputConfig.newBuilder().setGcsSource(gcsSource).build();
System.out.println("Processing import...");
// Import data from the input URI
InputConfig inputConfig = InputConfig.newBuilder().setGcsSource(gcsSource).build();
System.out.println("Processing import...");

Empty response = client.importDataAsync(datasetFullId, inputConfig).get();
System.out.println(String.format("Dataset imported. %s", response));
Empty response = client.importDataAsync(datasetFullId, inputConfig).get();
System.out.println(String.format("Dataset imported. %s", response));
}
}
// [END automl_translate_import_data]

Expand All @@ -237,20 +238,20 @@ public static void importData(
* @param projectId the Google Cloud Project ID.
* @param computeRegion the Region name. (e.g., "us-central1").
* @param datasetId the Id of the dataset.
* @throws Exception on AutoML Client errors
*/
public static void deleteDataset(String projectId, String computeRegion, String datasetId)
throws Exception {
throws IOException, InterruptedException, ExecutionException {
// Instantiates a client
AutoMlClient client = AutoMlClient.create();
try (AutoMlClient client = AutoMlClient.create()) {

// Get the full path of the dataset.
DatasetName datasetFullId = DatasetName.of(projectId, computeRegion, datasetId);
// Get the full path of the dataset.
DatasetName datasetFullId = DatasetName.of(projectId, computeRegion, datasetId);

// Delete a dataset.
Empty response = client.deleteDatasetAsync(datasetFullId).get();
// Delete a dataset.
Empty response = client.deleteDatasetAsync(datasetFullId).get();

System.out.println(String.format("Dataset deleted. %s", response));
System.out.println(String.format("Dataset deleted. %s", response));
}
}
// [END automl_translate_delete_dataset]

Expand Down Expand Up @@ -284,7 +285,7 @@ public static void argsHelper(String[] args, PrintStream out) throws Exception {
String projectId = System.getenv("PROJECT_ID");
String computeRegion = System.getenv("REGION_NAME");

Namespace ns = null;
Namespace ns;
try {
ns = parser.parseArgs(args);
if (ns.get("command").equals("create_dataset")) {
Expand Down
Loading

0 comments on commit d2e9b4e

Please sign in to comment.