通过k-聚类处理Iris数据集

from sklearn.cluster import KMeans
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt

# 加载Iris数据集
iris = load_iris()
X = iris.data

# 应用K-means算法
kmeans = KMeans(n_clusters=3, random_state=0)
kmeans.fit(X)

# 预测每个样本的簇标签
labels = kmeans.predict(X)

# 可视化结果
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='red', marker='x')
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.title('K-means Clustering on Iris Dataset')
plt.show()

from sklearn.metrics import silhouette_score

# 肘部法则示例
inertia = []
for k in range(1, 11):
    kmeans = KMeans(n_clusters=k, random_state=0)
    kmeans.fit(X)
    inertia.append(kmeans.inertia_)

plt.plot(range(1, 11), inertia, marker='o')
plt.xlabel('Number of clusters')
plt.ylabel('Inertia')
plt.title('Elbow Method For Optimal k')
plt.show()

# 轮廓系数示例
silhouette_scores = []
for k in range(2, 11):
    kmeans = KMeans(n_clusters=k, random_state=0)
    labels = kmeans.fit_predict(X)
    score = silhouette_score(X, labels)
    silhouette_scores.append(score)

plt.plot(range(2, 11), silhouette_scores, marker='o')
plt.xlabel('Number of clusters')
plt.ylabel('Silhouette Score')
plt.title('Silhouette Score For Optimal k')
plt.show()

kmeans = KMeans(n_clusters=3, init='k-means++', random_state=0)
kmeans.fit(X)