Feature exploration
Using the same Avazu dataset, you will explore how the values of device_type
and banner_pos
are distributed, as well as how CTR varies based on them.
Sample data in DataFrame form is loaded as df
. The X
and y
variables that you created in the last exercise are available in your workspace. pandas
as pd
are also available in your workspace.
This exercise is part of the course
Predicting CTR with Machine Learning in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Distribution of values for device type
print("Distribution of device type: ")
print(X.device_type.____()/len(X))
# Sample CTR by device type
print("CTR by device type: ")
print(df.____('device_type')['click'].____/len(y))