Muxammad al xorazmiy nomidagi toshkent axborot texnologiyalari universiteti

# A list holds the silhouette coefficients for each k

silhouette_coefficients = []

# Notice we start at 2 clusters for silhouette coefficient

for k in range(2, 11):

kmeans = KMeans(n_clusters=k, **kmeans_kwargs)

kmeans.fit(scaled_features)

score = silhouette_score(scaled_features, kmeans.labels_)

silhouette_coefficients.append(score)

In [18]:

plt.style.use("fivethirtyeight")

plt.plot(range(2, 11), silhouette_coefficients)

plt.xticks(range(2, 11))

plt.xlabel("Number of Clusters")

plt.ylabel("Silhouette Coefficient")

plt.show()
Advanced Clustering Evaluation

In [19]:

from sklearn.cluster import DBSCAN

from sklearn.datasets import make_moons

from sklearn.metrics import adjusted_rand_score

In [20]:

features, true_labels = make_moons(

n_samples=250, noise=0.05, random_state=42

)

scaled_features = scaler.fit_transform(features)

In [21]:

# Instantiate k-means and dbscan algorithms

kmeans = KMeans(n_clusters=2)

dbscan = DBSCAN(eps=0.3)
# Fit the algorithms to the features

kmeans.fit(scaled_features)

dbscan.fit(scaled_features)
# Compute the silhouette scores for each algorithm

kmeans_silhouette = silhouette_score(

scaled_features, kmeans.labels_

).round(2)

dbscan_silhouette = silhouette_score(

scaled_features, dbscan.labels_

).round (2)

In [22]:

kmeans_silhouette

Out[22]:

0.5

In [23]:

dbscan_silhouette

Out[23]:

0.38

In [24]:

# Plot the data and cluster silhouette comparison

fig, (ax1, ax2) = plt.subplots(

1, 2, figsize=(8, 6), sharex=True, sharey=True

)

fig.suptitle(f"Clustering Algorithm Comparison: Crescents", fontsize=16)

fte_colors = {

0: "#008fd5",

1: "#fc4f30",

}

# The k-means plot

km_colors = [fte_colors[label] for label in kmeans.labels_]

ax1.scatter(scaled_features[:, 0], scaled_features[:, 1], c=km_colors)

ax1.set_title(

f"k-means\nSilhouette: {kmeans_silhouette}", fontdict={"fontsize": 12}

)
# The dbscan plot

db_colors = [fte_colors[label] for label in dbscan.labels_]

ax2.scatter(scaled_features[:, 0], scaled_features[:, 1], c=db_colors)

ax2.set_title(

f"DBSCAN\nSilhouette: {dbscan_silhouette}", fontdict={"fontsize": 12}

)

plt.show()

In [25]:

ari_kmeans = adjusted_rand_score(true_labels, kmeans.labels_)

ari_dbscan = adjusted_rand_score(true_labels, dbscan.labels_)

In [26]:

round(ari_kmeans, 2)

Out[26]:

0.47

In [27]:

round(ari_dbscan, 2)

Out[27]:

1.0