내용 |
iris 데이터 실루엣 계수 확인하기
소스코드
%matplotlib inline
%config InlineBackend.figure_format = 'retina'
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_samples, silhouette_score
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import numpy as np
import seaborn as sns
iris = sns.load_dataset("iris")
iris_x = iris.loc[:, ["petal_length", "petal_width"] ]
range_n_clusters = [2, 3, 4, 5, 6]
for n_clusters in range_n_clusters:
fig, (ax1, ax2) = plt.subplots(1, 2)
fig.set_size_inches(12, 6)
# ax1.set_xlim([-0.1, 1])
# ax1.set_ylim([0, len(iris_x) + (n_clusters + 1) * 10])
# 클러스터의 수만큼 KMeans 모형을 만들고 클러스터 레이블을 예측함
clusterer = KMeans(n_clusters=n_clusters, random_state=10)
cluster_labels = clusterer.fit_predict(iris_x)
# 모든 샘플에 대한 실루엣 스코어 평균값을 계산함
silhouette_avg = silhouette_score(iris_x, cluster_labels)
print("For n_clusters =", n_clusters,
"The average silhouette_score is :", silhouette_avg)
# 각 셈플에 대해서 실루엣 스코어를 계산함
sample_silhouette_values = silhouette_samples(iris_x, cluster_labels)
y_lower = 10
for i in range(n_clusters):
ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]
ith_cluster_silhouette_values.sort()
size_cluster_i = ith_cluster_silhouette_values.shape[0]
y_upper = y_lower + size_cluster_i
color = cm.nipy_spectral(float(i) / n_clusters)
ax1.fill_betweenx(np.arange(y_lower, y_upper),
0, ith_cluster_silhouette_values,
facecolor=color, edgecolor=color, alpha=0.7)
# Label the silhouette plots with their cluster numbers at the middle
ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
# Compute the new y_lower for next plot
y_lower = y_upper + 10 # 10 for the 0 samples
ax1.set_title("The silhouette plot for the various clusters.")
ax1.set_xlabel("The silhouette coefficient values")
ax1.set_ylabel("Cluster label")
# The vertical line for average silhouette score of all the values
ax1.axvline(x=silhouette_avg, color="red", linestyle="--")
ax1.set_yticks([]) # Clear the yaxis labels / ticks
ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])
# 2nd Plot showing the actual clusters formed
colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)
ax2.scatter(iris_x.iloc[:, 0], iris_x.iloc[:, 1], marker='.', s=30, lw=0, alpha=0.7,
c=colors, edgecolor='k')
# 클러스터 라벨링
centers = clusterer.cluster_centers_
# 클러스터 중앙에 태두리가 검정색인 하얀 원을 그림
ax2.scatter(centers[:, 0], centers[:, 1], marker='o',
c="white", alpha=1, s=200, edgecolor='k')
for i, c in enumerate(centers):
ax2.scatter(c[0], c[1], marker='$%d$' % i, alpha=1,
s=50, edgecolor='k')
ax2.set_title("The visualization of the clustered data.")
ax2.set_xlabel("Feature space for the 1st feature")
ax2.set_ylabel("Feature space for the 2nd feature")
plt.suptitle(("Silhouette analysis for KMeans clustering on sample data "
"with n_clusters = %d" % n_clusters),
fontsize=14, fontweight='bold')
plt.show()
|