Certified Machine Learning Professional Practice Test

Certified Machine Learning Professional Practice Test practice questions, page 8 of 9, with answer review and explanations.

Question 36

A data scientist has developed a scikit-learn model sklearn_model and they want to log the model using MLflow. They write the following incomplete code block: Which of the following lines of code can be used to fill in the blank so the code block can successfully complete the task?

  1. mlflow.spark.track_model(sklearn_model, "model")
  2. mlflow.sklearn.log_model(sklearn_model, "model")
  3. mlflow.spark.log_model(sklearn_model, "model")
  4. mlflow.sklearn.load_model("model")
  5. mlflow.sklearn.track_model(sklearn_model, "model")

Question 37

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

  1. A convention that deployment tools can use to wrap preprocessing logic into a Model
  2. A convention that MLflow Model Registry can use to version models
  3. A convention that MLflow Experiments can use to organize their Runs by project
  4. A convention that deployment tools can use to understand the model
  5. A convention that MLflow Model Registry can use to organize its Models by project

Question 38

In a continuous integration, continuous deployment (CI/CD) process for machine learning pipelines, which of the following events commonly triggers the execution of automated testing?

  1. The launch of a new cost-efficient SQL endpoint
  2. CI/CD pipelines are not needed for machine learning pipelines
  3. The arrival of a new feature table in the Feature Store
  4. The launch of a new cost-efficient job cluster
  5. The arrival of a new model version in the MLflow Model Registry

Question 39

A machine learning engineering team has written predictions computed in a batch job to a Delta table for querying. However, the team has noticed that the querying is running slowly. The team has already tuned the size of the data files. Upon investigating, the team has concluded that the rows meeting the query condition are sparsely located throughout each of the data files. Based on the scenario, which of the following optimization techniques could speed up the query by colocating similar records while considering values in multiple columns?

  1. Z-Ordering
  2. Bin-packing
  3. Write as a Parquet file
  4. Data skipping
  5. Tuning the file size

Question 40

A machine learning engineer needs to deliver predictions of a machine learning model in real-time. However, the feature values needed for computing the predictions are available one week before the query time. Which of the following is a benefit of using a batch serving deployment in this scenario rather than a real-time serving deployment where predictions are computed at query time?

  1. Batch serving has built-in capabilities in Databricks Machine Learning
  2. There is no advantage to using batch serving deployments over real-time serving deployments
  3. Computing predictions in real-time provides more up-to-date results
  4. Testing is not possible in real-time serving deployments
  5. Querying stored predictions can be faster than computing predictions in real-time