最新的ML Data Scientist認證 Databricks-Machine-Learning-Professional考試題庫

問題1

A machine learning engineer is migrating a machine learning pipeline to use Data bricks Machine Learning. The pipeline needs to automatically refresh its model each time it runs.
They are using the following code block as part of their solution:

Assuming that this is the first time that the model is being run, which statement describes the impact of the registered_model_name=model_name parameter?

A. It registers the new version of the existing model_name model in the MLflow Model Registry.

B. It avoids the need to specify the model name in the subsequent required call to mflow.register_model.

C. It identifies the name of the logged model in the MLflow Experiment.

D. It registers a new model called model_name in the MLflow Model Registry.

正確答案: D

說明：（僅 VCESoft 成員可見）

問題2

Which approach is best for scoring large historical datasets?

A. Local Python script

B. Real-time REST API

C. Manual predictions

D. Batch inference with Spark

正確答案: D

說明：（僅 VCESoft 成員可見）

問題3

A Machine Learning Engineer needs to develop a custom anomaly detection model that monitors the internal IT infrastructure of their company. The model takes in compute metrics, logs, and user data and generates a binary prediction. The engineer plans to deploy it as a Databricks Model Serving endpoint. In production there will only be one client calling the endpoint once every
15 seconds. Leadership sees the model as an important part of their operational improvement strategy so maintaining consistent, stable, low latency inference is a requirement while minimizing infrastructure costs. The engineer plans to deploy the endpoint via the MLflow Deployment SDK.
Which endpoint config for the MLflow Deployment SDK should the engineer select?

A.

B.

C.

D.

正確答案: B

說明：（僅 VCESoft 成員可見）

問題4

A data scientist set up a machine learning pipeline to automatically log a data visualization with each run. They now want to view the visualizations in Databricks. Which location in Databricks will show these data visualizations?

A. Logged data visualizations cannot be viewed in Databricks

B. The Artifacts section of the MLflow Experiment page

C. The Artifacts section of the MLflow Run page

D. The Figures section of the MLflow Run page

E. The MLflow Model Registry Model paqe

正確答案: D

問題5

A Data Scientist is tasked with developing models to forecast product demand. The company offers 5000 different product types, and the Data Scientist must generate weekly forecasts for each type. They have access to two years of historical purchase data and are given ample project budget.
For their next project, they want to build 5000 separate Random Forest models, one for each product type. They aim to train all the models as quickly as possible with minimal setup.
Which approach meets these requirements?

A. Create a Databricks Workflow with 5000 tasks. Each task is configured to accept a product ID as a parameter which will then train a model based on the specified product ID.

B. Use the RandomForest method from MLlib. This will leverage Spark's parallel processing capability to train 5000 different models.

C. Use the DeepSpeed library to distribute the data by product across different nodes to enable the parallel training of multiple models.

D. Leverage the pandas function API (Grouped map) to group the data by product type and apply a custom model training function to each group.

正確答案: D

說明：（僅 VCESoft 成員可見）

問題6

A Machine Learning Engineer has deployed a fraud detection model in Databricks Model Serving to detect fraudulent transactions. The engineer wants to compare the model's predictions with the actual fraud classifications from the Fraud Ops team to monitor model performance. The Fraud Ops team uses a unique transaction_id to investigate fraudulent activity and persist their findings to a fraud_findings table. The engineer enabled inference tables on the endpoint, but they are not sure how to map the models' predictions to the Fraud Ops team's classifications. How can the engineer uniquely join the models' prediction to the fraud_findings table with the fewest code changes?

A. Store databricks_request_id returned from each model serving request and persist it to the fraud_findings table. Join the inference table with the fraud_findings table using databricks_request_id as the join key.

B. Modify the model to include an additional input: transaction_id. Log, register and deploy the new model. In the model serving request body, add transaction_id as an additional input feature. Join the inference table with the fraud_findings table using transaction_id as the join key.

C. Populate the client_request_id field with the transaction_id in the model serving request body.
Join the inference table with the fraud_findings table using client_request_id (which contains the transaction_id) as the join key.

D. Join the inference table with the fraud_findings table using timestamp_ms as the join key.

正確答案: C

說明：（僅 VCESoft 成員可見）

問題7

Which MLflow command logs a trained model?

A. mlflow.run()

B. mlflow.start_run()

C. mlflow.log_model()

D. mlflow.register_model()

正確答案: C

說明：（僅 VCESoft 成員可見）

問題8

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. Delta tables cannot be modified

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

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

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

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

正確答案: D

問題9

In order to connect an MLflow Model Registry Webhook to a Databricks Job, the Job ID must be provided to the code block used to create the webhook. Which approach can be used to obtain a Databricks Job ID?

A. All of these approaches

B. The Job ID field in the Job details section of the specific Job page in the UI

C. The Job ID field returned in a query using the Jobs API

D. The Job ID field in the Jobs page in the UI

正確答案: A

說明：（僅 VCESoft 成員可見）

問題10

A data scientist would like to enable MLflow Autologging for all machine learning libraries used in a notebook. They want to ensure that MLflow Autologging is used no matter what version of the Databricks Runtime for Machine Learning is used to run the notebook and no matter what workspace-wide configurations are selected in the Admin Console. Which of the following lines of code can they use to accomplish this task?

A. mlflow.autolog()

B. It is not possible to automatically log MLflow runs.

C. mlflow.sklearn.autolog()

D. mlflow.spark.autolog()

E. spark.conf.set("autologging", True)

正確答案: E

最新的Databricks Certified Machine Learning Professional - Databricks-Machine-Learning-Professional免費考試真題

最新更新

站內鏈接

聯系我們