Practice Questions — Unsupervised Learning - Clustering (K-Means, DBSCAN, Hierarchical)

from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
from sklearn.metrics import silhouette_score

X, _ = make_blobs(n_samples=300, centers=4, random_state=42)

best_k = 2
best_score = -1
for k in range(2, 9):
    km = KMeans(n_clusters=k, random_state=42, n_init=10)
    labels = km.fit_predict(X)
    score = silhouette_score(X, labels)
    print(f"K={k}: silhouette={score:.4f}")
    if score > best_score:
        best_score = score
        best_k = k

print(f"Best K: {best_k} with silhouette score: {best_score:.4f}")

from sklearn.cluster import DBSCAN
from sklearn.datasets import make_moons
from sklearn.preprocessing import StandardScaler

X, _ = make_moons(n_samples=300, noise=0.1, random_state=42)
X_scaled = StandardScaler().fit_transform(X)

db = DBSCAN(eps=0.3, min_samples=5)
labels = db.fit_predict(X_scaled)

n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
n_noise = list(labels).count(-1)

print(f"Clusters: {n_clusters}")
print(f"Noise points: {n_noise}")
print(f"Points per cluster:")
for lbl in sorted(set(labels)):
    name = "Noise" if lbl == -1 else f"Cluster {lbl}"
    print(f"  {name}: {list(labels).count(lbl)}")

import pandas as pd
from sklearn.cluster import KMeans
from sklearn.datasets import load_iris

iris = load_iris()
km = KMeans(n_clusters=3, random_state=42, n_init=10)
clusters = km.fit_predict(iris.data)

print("Cluster vs Actual Species:")
print(pd.crosstab(clusters, iris.target, rownames=['Cluster'], colnames=['Species']))

from sklearn.cluster import KMeans, AgglomerativeClustering
from sklearn.datasets import load_iris
from sklearn.metrics import silhouette_score
from sklearn.preprocessing import StandardScaler

iris = load_iris()
X = StandardScaler().fit_transform(iris.data)

km = KMeans(n_clusters=3, random_state=42, n_init=10)
km_labels = km.fit_predict(X)
km_sil = silhouette_score(X, km_labels)

agg = AgglomerativeClustering(n_clusters=3, linkage='ward')
agg_labels = agg.fit_predict(X)
agg_sil = silhouette_score(X, agg_labels)

print(f"K-Means silhouette: {km_sil:.4f}")
print(f"Agglomerative silhouette: {agg_sil:.4f}")
print(f"Winner: {'K-Means' if km_sil > agg_sil else 'Agglomerative'}")

from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
import numpy as np

X, _ = make_blobs(n_samples=300, centers=3, random_state=42)
km = KMeans(n_clusters=3, random_state=42, n_init=10)
labels = km.fit_predict(X)

print("Cluster sizes:")
for i in range(3):
    size = np.sum(labels == i)
    print(f"  Cluster {i}: {size} points")
print(f"Total: {len(labels)}")

from sklearn.cluster import KMeans, DBSCAN
from sklearn.datasets import make_circles
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import silhouette_score

X, _ = make_circles(n_samples=300, noise=0.05, factor=0.5, random_state=42)
X_scaled = StandardScaler().fit_transform(X)

# K-Means
km = KMeans(n_clusters=2, random_state=42, n_init=10)
km_labels = km.fit_predict(X_scaled)
km_sil = silhouette_score(X_scaled, km_labels)

# DBSCAN
db = DBSCAN(eps=0.3, min_samples=5)
db_labels = db.fit_predict(X_scaled)
mask = db_labels != -1
db_sil = silhouette_score(X_scaled[mask], db_labels[mask]) if len(set(db_labels[mask])) >= 2 else -1

print(f"K-Means silhouette: {km_sil:.4f}")
print(f"DBSCAN silhouette:  {db_sil:.4f}")
print(f"DBSCAN wins: {db_sil > km_sil}")

import numpy as np
from sklearn.neighbors import NearestNeighbors

def find_best_eps(X, min_samples):
    nn = NearestNeighbors(n_neighbors=min_samples)
    nn.fit(X)
    distances, _ = nn.kneighbors(X)
    k_distances = np.sort(distances[:, min_samples - 1])
    suggested_eps = np.percentile(k_distances, 90)
    return suggested_eps

# Test it
from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler

X, _ = make_blobs(n_samples=300, centers=3, random_state=42)
X_scaled = StandardScaler().fit_transform(X)
eps = find_best_eps(X_scaled, min_samples=5)
print(f"Suggested eps: {eps:.4f}")