Session Ready
Exercise

Randomization effects

Random assignment plays a critical role in A/B testing. Imagine you are a Data Scientist setting up an experiment to test the effects of different checkout page designs on business metrics.

You will explore sampling a percentage of users to simulate random enrollment of traffic into the experiment and check the distributions of certain attributes across randomly assigned users in each group. This allows you to verify the ability to generalize to the general traffic population, and isolate the impact of the one variable we are changing across groups: the check out page design.

checkout DataFrame is loaded for you. Assume every row in the DataFrame corresponds to a unique user visiting the respective checkout_page along with their actions and additional attributes.

Instructions 1/4
undefined XP
  • 1
  • 2
  • 3
  • 4
  • Use the pandas .value_counts() method to determine the normalized distribution of browser counts in the dataset.
Loading