Databricks-Machine-Learning-Professional試験無料問題集（193題）「Databricks Certified Machine Learning Professional 認定」

出題：1

A data scientist wants to remove the star_rating column from the Delta table at the location path.
To do this, they need to load in data and drop the star_rating column. Which of the following code blocks accomplishes this task?

A. spark.read.format("delta").load(path).drop("star_rating")

B. spark.read.format("delta").table(path).drop("star_rating")

C. spark.read.table(path).drop("star_rating")

D. spark.sql("SELECT * EXCEPT star_rating FROM path")

E. Delta tables cannot be modified

正解：C 解答を投票する

出題：2

What is the purpose of ParamGridBuilder?

A. Feature storage

B. Tracking metrics

C. Creating hyperparameter combinations

D. Model deployment

正解：C 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：3

A Data Scientist is building a machine learning pipeline to classify raw text using a Logistic Regression model in Spark using Spark MLlib's Pipelines. This pipeline has three stages: the Tokenizer (to split the raw text in tokens), a HashingTF (to transform tokens into hashes) and the Logistic Regression itself (to perform the classification of texts). The Spark DataFrame with the training data is called trainingDF and the one with the test data is called testDF.
In order to do this, they use the following incomplete piece of code:

Which option correctly states:
(i) The complete command to run model training;
(ii) The complete command to execute the prediction on test data;
(iii) The object type of the model object returned by the model
training command.

A.

B.

C.

D.

正解：A 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：4

Which of the following describes batch deployment for machine learning projects?

A. Predictions are computed immediately as data arrives and stored for later querying

B. Predictions are computed prior to delivery and stored for later querying

C. Predictions are computed and delivered as soon as feature values are available

D. None of these describe batch deployment for machine learning projects

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：5

Why is Apache Spark useful for machine learning training?

A. Data visualization

B. Distributed data processing

C. GPU rendering

D. Web serving

正解：B 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：6

A machine learning engineer has deployed a model recommender using MLflow Model Serving.
They now want to query the version of that model that is in the Staging stage of the MLflow Model Registry. Which model URI can be used to query the described model version?

A. It is not possible to query a model version in the Staging stage.

B. The version number of the model version in Production is necessary to complete this task.

C. https://<databricks-instance>/model-serving/recommender/Staging/invocations

D. https://<databricks-instance>/model/recommender/Staging/invocations

正解：D 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：7

A machine learning engineer wants to log feature importance data from a CSV file at path importance_path with an MLflow run for model model. Which code block will accomplish this task inside of an existing MLflow run block?

A. None of these code blocks tan accomplish the task.

B.

C. mlflow.log_artifact(importance_path, "feature-importance.csv")

D.

E. mlflow.log_data(importance_path, "feature-importance.csv")

正解：B 解答を投票する

出題：8

Which deployment paradigm can centrally compute predictions for a single record with exceedingly fast results?

A. Streaming

B. Batch

C. Real-time

D. None of these strategies will accomplish the task.

E. Edge/on-device

正解：C 解答を投票する

出題：9

A Machine Learning Engineer has a large dataset with a customer_region column and wants to train separate models for each region, then generate predictions. They need to parallelize this group-specific model training process using Databricks and the Pandas Function API. Which approach will implement this solution?

A. Use mapInPandas() to apply the training function across all partitions without grouping.

B. Use foreachBatch() to sequentially process each region's data.

C. Use groupBy("customer_region") and apply a training function with applyInPandas().

D. Use collect() to gather all data and process regions using standard pandas groupby.

正解：C 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：10

A data scientist wants to log outlier feature data from a CSV file at path outlier_path with an MLflow run for model model. Which code block will accomplish this task inside of an existing MLflow run block?

A.

B. mlflow.log_data(outlier_path, "outlier-features.csv")

C. mlflow.log_artifact(outlier_path, "outlier-features.csv")

D.

正解：C 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：11

A Machine Learning Engineer has automated a model retraining job in Databricks. Each scheduled run trains multiple candidate models with new sales data and logs all runs with MLflow.
The goal is to select and register the best-performing model at the end of each cycle to ensure optimal forecast accuracy. Which approach will meet this goal?

A. Register all models from the run since all of them are trained on newer data and hence will be more accurate.

B. Register the model with the lowest training loss regardless of validation metrics.

C. Register the first model that has an evaluation metric better than the previously deployed model.

D. Register the best model based on the primary evaluation metric.

正解：D 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

出題：12

A Machine Learning Engineer is implementing integration tests for an ML pipeline in Databricks.
The current integration test runs the complete workflow but takes four hours to execute due to large dataset processing and extensive model training. They need to select an approach that will be the most effective for optimizing integration test execution while maintaining test reliability. The approach should also be based on MLOps best practices. Which approach will do this?

A. Replace integration tests with unit tests for each pipeline component to reduce execution time and focus on individual component validation in a staging environment that closely matches production.

B. Skip the model training phase entirely and only test data transformations and API endpoints using mock model predictions.

C. Use small subsets of production-like data and reduce training iterations while maintaining the same pipeline structure and validation checkpoints in a staging environment that closely matches production.

D. Run integration tests only in the production environment using full datasets to ensure complete accuracy of the testing process.

正解：C 解答を投票する

解説: (GoShiken メンバーにのみ表示されます)

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