Build 4-cluster solution
Perfect, you can see the the recommended number of clusters is somewhere between 3 and 4. Now, you will build the latter number of clusters in this exercise.
The normalized RFMT dataset is available as datamart_rfmt_normalized
, feel free to use the console to explore it.
This exercise is part of the course
Customer Segmentation in Python
Exercise instructions
- Import
KMeans
fromsklearn
library. - Initialize
KMeans
with 4 clusters and random state 1. - Fit k-means clustering on the normalized data set.
- Extract cluster labels and store them as
cluster_labels
object.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Import KMeans
from ____.____ import ____
# Initialize KMeans
kmeans = ____(____, ____)
# Fit k-means clustering on the normalized data set
____.____(____)
# Extract cluster labels
cluster_labels = ____.____