Examining the different cohorts
To finish this lesson, you're now going to plot by 'country' and then by 'device' and examine the results. Hopefully you will see the observed lift across all groups as designed. This would point to the change being the cause of the lift, not some other event impacting the purchase rate.
This exercise is part of the course
Customer Analytics and A/B Testing in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Plot the average first week purchases for each country by registration date
country_pivot.plot(x='____', y=['____', '____', '____', '____', '____', '____'])
plt.show()