Databricks Machine Learning Associate exam dumps

Databricks Machine Learning Associate practice question 85 of 656

Databricks Certified Machine Learning Associate. Associate level, Databricks. Free question with the correct answer and a full explanation.

Databricks Machine Learning Associate Question 85

Select 3

You are working on a machine learning project in Databricks to predict customer churn. The relevant features are stored in a Delta table registered as a Feature Store table named 'customer_features'. You need to train a model using these features. Which of the following steps are required to train the model while ensuring the feature lineage is maintained?

  1. A

    Use the Feature Store library to load the features into a DataFrame.

  2. B

    Directly query the Delta table using Spark SQL to retrieve the features.

  3. C

    Create a training set using the feature_store.create_training_set method.

  4. D

    Log the model using the Feature Store API after training.

  5. E

    Use the spark.read.format('delta').load method to load the features for training.

Show answer and explanation

Correct answers: A, C, D

Explanation

To train a model with features from a Feature Store table in Databricks, it is essential to utilize the Feature Store library to ensure feature lineage is maintained. The process involves loading the features using the Feature Store library, creating a training set with the feature_store.create_training_set method, and logging the trained model with the Feature Store API to maintain feature dependencies. Directly querying the Delta table or loading it using Spark's Delta API bypasses the Feature Store's capabilities and should be avoided in this scenario.

  • A. Correct.

    Correct. Using the Feature Store library is necessary to ensure the features are retrieved with lineage information, which is a key advantage of the Feature Store.

  • B. Incorrect.

    Incorrect. While you can query the Delta table directly using Spark SQL, this approach does not maintain feature lineage information, which is critical for reproducibility and tracking.

  • C. Correct.

    Correct. The feature_store.create_training_set method is required to prepare the training data while maintaining metadata and lineage from the Feature Store.

  • D. Correct.

    Correct. Logging the model using the Feature Store API ensures that the model's dependencies on the features are tracked, enabling reproducibility.

  • E. Incorrect.

    Incorrect. Loading the Delta table using spark.read.format('delta').load retrieves the data but does not leverage the Feature Store's capabilities for tracking lineage and metadata.

Timed practice exam

Take a Databricks Machine Learning Associate practice test under exam conditions

48 questions in 90 minutes, drawn from this bank, with a score report and a per-question review when you finish.

Start timed exam

More Databricks Machine Learning Associate practice questions

  1. 86.You are tasked with building a machine learning model to predict customer churn using a feature...
  2. 87.You are tasked with training a machine learning model in Databricks to predict customer churn. The...
  3. 88.You are tasked with training a machine learning model to predict customer churn using features...
  4. 89.You are tasked with training a machine learning model in Databricks using features stored in a...
  5. 90.You are tasked with scoring a machine learning model that predicts customer churn using features...
Back to the Databricks Machine Learning Associate exam dumps