Databricks-Machine-Learning-Professional無料問題集「Databricks Certified Machine Learning Professional」

質問 1

A machine learning engineer has developed the following custom model class with preprocessing logic to combine two columns:

However, instances of this class are unable to compute predictions.
Which set of changes will update the class so predictions can be computed while continuing to apply the preprocessing logic?

（A）Replace model_input.copy() with self.preprocess_input(model_input.copy()) in the predict method

（B）Replace self.rf_model.predict(input) with self.predict(input) in the predict method

（C）Replace model_input.copy() with self.preprocess_input(model_input.copy()) in the preprocess_input method

（D）Remove the self.rf_model = rf_model line from the fit method

正解：A 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 2

Concept drift is when there is a change in which element?

（A）The distribution of the predicted target given by the model

（B）The distribution of a target variable

（C）The relationship between input variables and target variables

（D）The distribution of an input variable

正解：C 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 3

A Machine Learning Engineer needs to build a credit risk model using Databricks. Due to strict data governance, production data cannot be accessed from development or staging environments. To manage MLOps, the engineer uses a "deploy code" strategy with separate development, staging, and production environments mapped to different catalogs in Unity Catalog. The CI/CD pipeline automates environment transitions. What is the primary architectural component promoted from staging to production to generate the final, production-ready model in this scenario?

（A）The model artifact trained and validated in the staging environment on a subset of the data.

（B）The model version entry in the Unity Catalog that has been transitioned from the "Staging" to the
"Production" alias.

（C）The CI/CD-approved model training source code, which will be executed in the production environment on the full production dataset.

（D）A containerized image of the complete inference pipeline, including feature transformations.

正解：C 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 4

A machine learning engineer has a machine learning pipeline where predictions are updated annually. The final prediction dataset contains millions of rows, and that dataset is irregularly accessed. Which solution should the machine learning engineer use to maintain cost efficiency?

（A）Cloud-based low latency database

（B）On-premises low-latency database

（C）Cloud-based object storage

（D）Cloud-based in-memory instance of a Spark DataFrame

正解：C 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 5

Which of the following statements about built-in library-specific MLflow Model flavors is true?

（A）Built-in library-specific flavors allow models to be exported as library objects

（B）Built-in library-specific flavors can only be used for logging models

（C）Built-in library-specific flavors are required for model signature use

（D）Built-in library-specific flavors allow models to be used with any library/span>

正解：A 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 6

A Machine Learning Engineer has deployed a customer churn prediction model to production three months ago. The model serves real-time predictions via a Databricks endpoint with inference logging enabled. They notice declining model accuracy in recent weeks and suspect data drift in customer demographics. They need to implement monitoring to track model performance degradation and input feature drift over time. Which monitoring profile type should they use?

（A）Inference profile - Monitor the inference table to track model performance metrics, prediction drift, and input feature drift across time windows.

（B）Snapshot profile - Monitor the complete inference table to compare current model performance against the baseline established at deployment.

（C）Custom profile - Create a hybrid monitoring approach combining snapshot and time series profiles to capture both baseline comparisons and temporal trends.

（D）Time series profile - Monitor the inference table using timestamp-based windows to track model performance and input drift over time.

正解：A 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 7

Which Spark ML class supports automated hyperparameter tuning?

（A）PipelineModel

（B）BinaryClassificationEvaluator

（C）CrossValidator

（D）ParamGridBuilder

正解：C 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 8

Which of the following describes the concept of MLflow Model flavors?

（A）A convention that MLflow Model Registry can use to version models

（B）A convention that deployment tools can use to understand the model

（C）A convention that MLflow Model Registry can use to organize its Models by project

（D）A convention that MLflow Experiments can use to organize their Runs by project

（E）A convention that deployment tools can use to wrap preprocessing logic into a Model

正解：D 解答を投票する

質問 9

A machine learning engineer is manually refreshing a model in an existing machine learning pipeline. The pipeline uses the MLflow Model Registry model "project". The machine learning engineer would like to add a new version of the model to "project". Which MLflow operation can the machine learning engineer use to accomplish this task?

（A）The machine learning engineer needs to create an entirely new MLflow Model Registry model

（B）MlflowClient.get_model_version

（C）mlflow.register_model

（D）MlflowClient.update_registered_model

（E）mlflow.add_model_version

正解：D 解答を投票する

Databricks-Machine-Learning-Professional 無料問題集「Databricks Certified Machine Learning Professional」

弊社を連絡する

関連リンク

トップ試験