Objective 2.1 Gather Data Sets CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 3)

Questions 11–15

1. 11application · medium

   A data scientist wants to use an open-source dataset from a government repository for a machine learning project. The dataset is licensed under CC BY 4.0. What is the most important requirement for using this data?

   • AThey must obtain written permission from the government agency before using the data.
   • BThey must attribute the source of the data in any publication or model documentation.
   • CThey must not use the data for commercial purposes.
   • DThey must share any derived datasets under the same license.
   Reveal Solution Discussion Select an answer first
2. 12foundation · easy

   Which SQL clause is used to combine rows from two or more tables based on a related column?

   • AUNION
   • BJOIN
   • CORDER BY
   • DGROUP BY
   Reveal Solution Discussion Select an answer first
4. 13foundation · easy

   What is the purpose of an API key in RESTful API authentication?

   • ATo encrypt the data being sent to the API.
   • BTo identify the client making the request and authorize access to the API.
   • CTo format the data in JSON.
   • DTo compress the data being sent to the API.
   Reveal Solution Discussion Select an answer first
5. 14foundation · easy

   When using open-source data, what should you check before using it in a commercial project?

   • AThe licensing terms and any usage restrictions
   • BThe color of the data provider's logo
   • CThe file size of the data
   • DThe number of downloads the data has received
   Reveal Solution Discussion Select an answer first
6. 15application · medium

   A data science team wants to augment a small dataset of images for training a deep learning model. They plan to use a generative adversarial network (GAN) to create additional images. What is the primary advantage of using a GAN over traditional data augmentation techniques like rotation and flipping?

   • AGANs can generate entirely new images that are not just transformations of existing ones, increasing the diversity of the training set.
   • BGANs guarantee that the generated images are perfectly realistic.
   • CGANs are faster to train than traditional augmentation methods.
   • DGANs do not require any training data.
   Reveal Solution Discussion Select an answer first