Probabilities
There are four main ways of expressing the prediction from a logistic regression model – we'll look at each of them over the next four exercises. Firstly, since the response variable is either "yes" or "no", you can make a prediction of the probability of a "yes". Here, you'll calculate and visualize these probabilities.
Two variables are available:
mdl_churn_vs_relationship
is the fitted logistic regression model ofhas_churned
versustime_since_first_purchase
.explanatory_data
is a DataFrame of explanatory values.
This exercise is part of the course
Introduction to Regression with statsmodels in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create prediction_data
prediction_data = explanatory_data.assign(
____
)
# Print the head
print(____)