from sklearn.preprocessing import StandardScaler import numpy as np import pandas as pd from sklearn.cluster import KMeans import sample as sp customers, purchases = sp.sample() array = pd.DataFrame([{'age':x['age'], 'income':x['income']} for x in customers]).to_numpy() def normalize_data(data): scaler = StandardScaler() scaled_data = scaler.fit_transform(data) return scaled_data model = kmeans = KMeans(n_clusters=3, random_state=42) result = kmeans.fit(normalize_data(array)) centroids = result.cluster_centers_.tolist()