Databricks-Machine-Learning-Professional Exam Dumps | A Data Scientist is tasked with developing models to forecast product demand. The company offers 5000

<< Prev Question Next Question >>

Question 48/96

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

B. 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.

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

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

Question 48/96

LEAVE A REPLY

Download PDF File