表形式回帰のモデル評価を取得する
コレクションでコンテンツを整理
必要に応じて、コンテンツの保存と分類を行います。
get_model_evaluation メソッドを使用して、表形式回帰のモデル評価を取得します。
もっと見る
このコードサンプルを含む詳細なドキュメントについては、以下をご覧ください。
コードサンプル
特に記載のない限り、このページのコンテンツはクリエイティブ・コモンズの表示 4.0 ライセンスにより使用許諾されます。コードサンプルは Apache 2.0 ライセンスにより使用許諾されます。詳しくは、Google Developers サイトのポリシーをご覧ください。Java は Oracle および関連会社の登録商標です。
[[["わかりやすい","easyToUnderstand","thumb-up"],["問題の解決に役立った","solvedMyProblem","thumb-up"],["その他","otherUp","thumb-up"]],[["わかりにくい","hardToUnderstand","thumb-down"],["情報またはサンプルコードが不正確","incorrectInformationOrSampleCode","thumb-down"],["必要な情報 / サンプルがない","missingTheInformationSamplesINeed","thumb-down"],["翻訳に関する問題","translationIssue","thumb-down"],["その他","otherDown","thumb-down"]],[],[],[],null,["Gets a model evaluation for tabular regression using the get_model_evaluation method.\n\nExplore further\n\n\nFor detailed documentation that includes this code sample, see the following:\n\n- [Evaluate AutoML classification and regression models](/vertex-ai/docs/tabular-data/classification-regression/evaluate-model)\n\nCode sample \n\nJava\n\n\nBefore trying this sample, follow the Java setup instructions in the\n[Vertex AI quickstart using\nclient libraries](/vertex-ai/docs/start/client-libraries).\n\n\nFor more information, see the\n[Vertex AI Java API\nreference documentation](/java/docs/reference/google-cloud-aiplatform/latest/com.google.cloud.aiplatform.v1).\n\n\nTo authenticate to Vertex AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n\n import com.google.cloud.aiplatform.v1.ModelEvaluation;\n import com.google.cloud.aiplatform.v1.ModelEvaluationName;\n import com.google.cloud.aiplatform.v1.ModelServiceClient;\n import com.google.cloud.aiplatform.v1.ModelServiceSettings;\n import java.io.IOException;\n\n public class GetModelEvaluationTabularRegressionSample {\n\n public static void main(String[] args) throws IOException {\n // TODO(developer): Replace these variables before running the sample.\n // To obtain evaluationId run the code block below after setting modelServiceSettings.\n //\n // try (ModelServiceClient modelServiceClient = ModelServiceClient.create(modelServiceSettings))\n // {\n // String location = \"us-central1\";\n // ModelName modelFullId = ModelName.of(project, location, modelId);\n // ListModelEvaluationsRequest modelEvaluationsrequest =\n // ListModelEvaluationsRequest.newBuilder().setParent(modelFullId.toString()).build();\n // for (ModelEvaluation modelEvaluation :\n // modelServiceClient.listModelEvaluations(modelEvaluationsrequest).iterateAll()) {\n // System.out.format(\"Model Evaluation Name: %s%n\", modelEvaluation.getName());\n // }\n // }\n String project = \"YOUR_PROJECT_ID\";\n String modelId = \"YOUR_MODEL_ID\";\n String evaluationId = \"YOUR_EVALUATION_ID\";\n getModelEvaluationTabularRegression(project, modelId, evaluationId);\n }\n\n static void getModelEvaluationTabularRegression(\n String project, String modelId, String evaluationId) throws IOException {\n ModelServiceSettings modelServiceSettings =\n ModelServiceSettings.newBuilder()\n .setEndpoint(\"us-central1-aiplatform.googleapis.com:443\")\n .build();\n\n // Initialize client that will be used to send requests. This client only needs to be created\n // once, and can be reused for multiple requests. After completing all of your requests, call\n // the \"close\" method on the client to safely clean up any remaining background resources.\n try (ModelServiceClient modelServiceClient = ModelServiceClient.create(modelServiceSettings)) {\n String location = \"us-central1\";\n ModelEvaluationName modelEvaluationName =\n ModelEvaluationName.of(project, location, modelId, evaluationId);\n ModelEvaluation modelEvaluation = modelServiceClient.getModelEvaluation(modelEvaluationName);\n\n System.out.println(\"Get Model Evaluation Tabular Regression Response\");\n System.out.format(\"\\tName: %s\\n\", modelEvaluation.getName());\n System.out.format(\"\\tMetrics Schema Uri: %s\\n\", modelEvaluation.getMetricsSchemaUri());\n System.out.format(\"\\tMetrics: %s\\n\", modelEvaluation.getMetrics());\n System.out.format(\"\\tCreate Time: %s\\n\", modelEvaluation.getCreateTime());\n System.out.format(\"\\tSlice Dimensions: %s\\n\", modelEvaluation.getSliceDimensionsList());\n }\n }\n }\n\nNode.js\n\n\nBefore trying this sample, follow the Node.js setup instructions in the\n[Vertex AI quickstart using\nclient libraries](/vertex-ai/docs/start/client-libraries).\n\n\nFor more information, see the\n[Vertex AI Node.js API\nreference documentation](/nodejs/docs/reference/aiplatform/latest).\n\n\nTo authenticate to Vertex AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n /**\n * TODO(developer): Uncomment these variables before running the sample\n * (not necessary if passing values as arguments). To obtain evaluationId,\n * instantiate the client and run the following the commands.\n */\n // const parentName = `projects/${project}/locations/${location}/models/${modelId}`;\n // const evalRequest = {\n // parent: parentName\n // };\n // const [evalResponse] = await modelServiceClient.listModelEvaluations(evalRequest);\n // console.log(evalResponse);\n\n // const modelId = 'YOUR_MODEL_ID';\n // const evaluationId = 'YOUR_EVALUATION_ID';\n // const project = 'YOUR_PROJECT_ID';\n // const location = 'YOUR_PROJECT_LOCATION';\n\n // Imports the Google Cloud Model Service Client library\n const {ModelServiceClient} = require('@google-cloud/aiplatform');\n\n // Specifies the location of the api endpoint\n const clientOptions = {\n apiEndpoint: 'us-central1-aiplatform.googleapis.com',\n };\n\n // Instantiates a client\n const modelServiceClient = new ModelServiceClient(clientOptions);\n\n async function getModelEvaluationTabularRegression() {\n // Configure the parent resources\n const name = `projects/${project}/locations/${location}/models/${modelId}/evaluations/${evaluationId}`;\n const request = {\n name,\n };\n\n // Get model evaluation request\n const [response] = await modelServiceClient.getModelEvaluation(request);\n\n console.log('Get model evaluation tabular regression response');\n console.log(`\\tName : ${response.name}`);\n console.log(`\\tMetrics schema uri : ${response.metricsSchemaUri}`);\n console.log(`\\tMetrics : ${JSON.stringify(response.metrics)}`);\n console.log(`\\tCreate time : ${JSON.stringify(response.createTime)}`);\n console.log(`\\tSlice dimensions : ${response.sliceDimensions}`);\n\n const modelExplanation = response.modelExplanation;\n console.log('\\tModel explanation');\n if (!modelExplanation) {\n console.log('\\t\\t{}');\n } else {\n const meanAttributions = modelExplanation.meanAttributions;\n if (!meanAttributions) {\n console.log('\\t\\t\\t []');\n } else {\n for (const meanAttribution of meanAttributions) {\n console.log('\\t\\tMean attribution');\n console.log(\n `\\t\\t\\tBaseline output value : \\\n ${meanAttribution.baselineOutputValue}`\n );\n console.log(\n `\\t\\t\\tInstance output value : \\\n ${meanAttribution.instanceOutputValue}`\n );\n console.log(\n `\\t\\t\\tFeature attributions : \\\n ${JSON.stringify(meanAttribution.featureAttributions)}`\n );\n console.log(`\\t\\t\\tOutput index : ${meanAttribution.outputIndex}`);\n console.log(\n `\\t\\t\\tOutput display name : \\\n ${meanAttribution.outputDisplayName}`\n );\n console.log(\n `\\t\\t\\tApproximation error : \\\n ${meanAttribution.approximationError}`\n );\n }\n }\n }\n }\n getModelEvaluationTabularRegression();\n\nPython\n\n\nBefore trying this sample, follow the Python setup instructions in the\n[Vertex AI quickstart using\nclient libraries](/vertex-ai/docs/start/client-libraries).\n\n\nFor more information, see the\n[Vertex AI Python API\nreference documentation](/python/docs/reference/aiplatform/latest).\n\n\nTo authenticate to Vertex AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n from google.cloud import aiplatform\n\n\n def get_model_evaluation_tabular_regression_sample(\n project: str,\n model_id: str,\n evaluation_id: str,\n location: str = \"us-central1\",\n api_endpoint: str = \"us-central1-aiplatform.googleapis.com\",\n ):\n \"\"\"\n To obtain evaluation_id run the following commands where LOCATION\n is the region where the model is stored, PROJECT is the project ID,\n and MODEL_ID is the ID of your model.\n\n model_client = aiplatform.gapic.ModelServiceClient(\n client_options={\n 'api_endpoint':'LOCATION-aiplatform.googleapis.com'\n }\n )\n evaluations = model_client.list_model_evaluations(parent='projects/PROJECT/locations/LOCATION/models/MODEL_ID')\n print(\"evaluations:\", evaluations)\n \"\"\"\n # The AI Platform services require regional API endpoints.\n client_options = {\"api_endpoint\": api_endpoint}\n # Initialize client that will be used to create and send requests.\n # This client only needs to be created once, and can be reused for multiple requests.\n client = aiplatform.gapic.ModelServiceClient(client_options=client_options)\n name = client.model_evaluation_path(\n project=project, location=location, model=model_id, evaluation=evaluation_id\n )\n response = client.get_model_evaluation(name=name)\n print(\"response:\", response)\n\nWhat's next\n\n\nTo search and filter code samples for other Google Cloud products, see the\n[Google Cloud sample browser](/docs/samples?product=aiplatform)."]]