Clustering

import numpy as np
from sklearn.cluster import KMeans, DBSCAN
from sklearn.mixture import GaussianMixture
from sklearn.metrics import silhouette_score
from sklearn.datasets import make_blobs

X, _ = make_blobs(n_samples=400, centers=4, cluster_std=0.6, random_state=42)

# KMeans
km = KMeans(n_clusters=4, random_state=42, n_init=10)
labels = km.fit_predict(X)
print("kmeans silhouette:", silhouette_score(X, labels))

# DBSCAN finds clusters of arbitrary shape and noise
db = DBSCAN(eps=0.5, min_samples=5).fit(X)
n_clusters = len(set(db.labels_)) - (1 if -1 in db.labels_ else 0)
print("dbscan clusters:", n_clusters)

# Gaussian mixture
gmm = GaussianMixture(n_components=4, random_state=42).fit(X)
gmm_labels = gmm.predict(X)

# Elbow method to pick k
inertias = [KMeans(k, n_init=10, random_state=42).fit(X).inertia_ for k in range(2, 8)]