1. Learn
  2. /
  3. Courses
  4. /
  5. Marketing Analytics: Predicting Customer Churn in Python

Exercise

Predicting whether a new customer will churn

As you saw in the video, to train a model using sklearn:

  • Import the model of interest - here, a Support Vector Classifier:
from sklearn.svm import SVC
  • Instantiate it:
svc = SVC()
  • Train it, or "fit it", to the data:
svc.fit(telco['data'], telco['target'])

Here, the first argument consists of the features, while the second argument is the label that we are trying to predict - whether or not the customer will churn. After you've fitted the model, you can use the model's .predict() method to predict the label of a new customer.

This process is true no matter which model you use, and sklearn has many! In this exercise, you'll use LogisticRegression.

Instructions 1/4

undefined XP
    1
    2
    3
    4
  • From sklearn.linear_model, import LogisticRegression.