import numpy as np
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
# Sample data: customer_id, total_purchases, avg_time_between_purchases (hours)
customer_data = np.array([
[1, 25, 0.5],
[2, 10, 5],
[3, 15, 2],
[4, 30, 1],
[5, 7, 10],
[6, 20, 3],
[7, 12, 7],
[8, 28, 0.8],
[9, 6, 12],
[10, 18, 1.5]
])
# Extract customer IDs and feature data
customer_ids = customer_data[:, 0].astype(int)
features = customer_data[:, 1:]
# Perform k-means clustering
n_clusters = 2
kmeans = KMeans(n_clusters=n_clusters, random_state=42)
cluster_labels = kmeans.fit_predict(features)
# Find the cluster with the lowest average time between purchases
impulsive_cluster = np.argmin(kmeans.cluster_centers_[:, 1])
# Get the customer IDs in the impulsive cluster
impulsive_buyers = customer_ids[cluster_labels == impulsive_cluster]
print("Impulsive buyers:", impulsive_buyers)
# Visualize the clustering results (optional)
plt.scatter(features[:, 0], features[:, 1], c=cluster_labels, cmap='viridis')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], c='red', marker='x')
plt.xlabel('Total Purchases')
plt.ylabel('Average Time Between Purchases (hours)')
plt.show()
top of page
bottom of page
