Python数据挖掘：聚类

Python数据挖掘：聚类

数据挖掘第三周作业
#波士顿房价数据集聚类
#1.k均值聚类，按照类别涂色；
#2.层次聚类，绘制聚类结果的基础上，绘制出层次树。

课堂聚类例子

#############################################################################
#聚类包和数据准备
import numpy as np
import matplotlib.pyplot as plt

from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering
from sklearn.datasets import make_blobs

plt.figure(figsize=(12, 12))

n_samples = 500
random_state = 170
#centers = [[5, 5], [-5, -5], [5, -5]]  centers=centers,
X, y = make_blobs(n_samples=n_samples, random_state=random_state)

#########################################################################
#对比k均值和层次聚类
# Incorrect number of clusters
y_pred = KMeans(n_clusters=2, random_state=random_state).fit_predict(X)

#clustering = AgglomerativeClustering(n_clusters=3).fit(X)
#y_pred=clustering.labels_


plt.subplot(221)
plt.scatter(X[:, 0], X[:, 1], c=y_pred)
plt.title("Incorrect Number of Blobs")

#########################################################################
#对比k均值和密度聚类
# Anisotropicly distributed data
transformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]
X_aniso = np.dot(X, transformation)
y_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_aniso)

#db = DBSCAN(eps=0.3, min_samples=10).fit(X_aniso)
#labels = db.labels_

plt.subplot(222)
plt.scatter(X_aniso[:, 0], X_aniso[:, 1], c=y_pred)
plt.title("Anisotropicly Distributed Blobs")

#检验生成不同特征的模拟数据集并进行聚类
# Different variance
X_varied, y_varied = make_blobs(n_samples=n_samples,
                                cluster_std=[1.0, 2.5, 0.5],
                                random_state=random_state)
y_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_varied)

plt.subplot(223)
plt.scatter(X_varied[:, 0], X_varied[:, 1], c=y_pred)
plt.title("Unequal Variance")

# Unevenly sized blobs
X_filtered = np.vstack((X[y == 0][:100], X[y == 1][:50], X[y == 2][:10]))
y_pred = KMeans(n_clusters=3,
                random_state=random_state).fit_predict(X_filtered)

plt.subplot(224)
plt.scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_pred)
plt.title("Unevenly Sized Blobs")

plt.show()

运行结果：