简介
本实验展示了不同聚类算法在二维“有趣”数据集上的特性。这些数据集与算法对的参数已经过调整，以产生良好的聚类结果。虽然这些示例能让你对算法有一些直观认识，但这种直观认识可能不适用于非常高维的数据。
虚拟机使用提示
虚拟机启动完成后，点击左上角切换到“笔记本”标签，以访问 Jupyter Notebook 进行练习。
有时，你可能需要等待几秒钟让 Jupyter Notebook 完成加载。由于 Jupyter Notebook 的限制，操作验证无法自动化。
如果你在学习过程中遇到问题，随时向 Labby 提问。课程结束后提供反馈，我们会及时为你解决问题。
导入库
必要的库被导入到笔记本中。
import time
import warnings
import numpy as np
import matplotlib.pyplot as plt
from sklearn import cluster, datasets, mixture
from sklearn.neighbors import kneighbors_graph
from sklearn.preprocessing import StandardScaler
from itertools import cycle, islice
生成数据集
生成数据集用于测试和比较不同的聚类算法。生成了以下几种数据集：
- 带噪声的圆圈
- 带噪声的月亮
- 斑点
- 无结构数据
- 各向异性分布的数据
- 具有不同方差的斑点
n_samples = 500
noisy_circles = datasets.make_circles(n_samples=n_samples, factor=0.5, noise=0.05)
noisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05)
blobs = datasets.make_blobs(n_samples=n_samples, random_state=8)
no_structure = np.random.rand(n_samples, 2), None
random_state = 170
X, y = datasets.make_blobs(n_samples=n_samples, random_state=random_state)
transformation = [[0.6, -0.6], [-0.4, 0.8]]
X_aniso = np.dot(X, transformation)
aniso = (X_aniso, y)
varied = datasets.make_blobs(
n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state
)
设置聚类参数
定义了每种聚类算法的参数。
default_base = {
"quantile": 0.3,
"eps": 0.3,
"damping": 0.9,
"preference": -200,
"n_neighbors": 3,
"n_clusters": 3,
"min_samples": 7,
"xi": 0.05,
"min_cluster_size": 0.1,
"allow_single_cluster": True,
"hdbscan_min_cluster_size": 15,
"hdbscan_min_samples": 3,
}
datasets = [
(
noisy_circles,
{
"damping": 0.77,
"preference": -240,
"quantile": 0.2,
"n_clusters": 2,
"min_samples": 7,
"xi": 0.08,
},
),
(
noisy_moons,
{
"damping": 0.75,
"preference": -220,
"n_clusters": 2,
"min_samples": 7,
"xi": 0.1,
},
),
(
varied,
{
"eps": 0.18,
"n_neighbors": 2,
"min_samples": 7,
"xi": 0.01,
"min_cluster_size": 0.2,
},
),
(
aniso,
{
"eps": 0.15,
"n_neighbors": 2,
"min_samples": 7,
"xi": 0.1,
"min_cluster_size": 0.2,
},
),
(blobs, {"min_samples": 7, "xi": 0.1, "min_cluster_size": 0.2}),
(no_structure, {}),
]
创建聚类对象
为每种聚类算法创建聚类对象。
ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
two_means = cluster.MiniBatchKMeans(n_clusters=params["n_clusters"], n_init="auto")
ward = cluster.AgglomerativeClustering(
n_clusters=params["n_clusters"], linkage="ward", connectivity=connectivity
)
spectral = cluster.SpectralClustering(
n_clusters=params["n_clusters"],
eigen_solver="arpack",
affinity="nearest_neighbors",
)
dbscan = cluster.DBSCAN(eps=params["eps"])
hdbscan = cluster.HDBSCAN(
min_samples=params["hdbscan_min_samples"],
min_cluster_size=params["hdbscan_min_cluster_size"],
allow_single_cluster=params["allow_single_cluster"],
)
optics = cluster.OPTICS(
min_samples=params["min_samples"],
xi=params["xi"],
min_cluster_size=params["min_cluster_size"],
)
affinity_propagation = cluster.AffinityPropagation(
damping=params["damping"], preference=params["preference"], random_state=0
)
average_linkage = cluster.AgglomerativeClustering(
linkage="average",
metric="cityblock",
n_clusters=params["n_clusters"],
connectivity=connectivity,
)
birch = cluster.Birch(n_clusters=params["n_clusters"])
gmm = mixture.GaussianMixture(
n_components=params["n_clusters"], covariance_type="full"
)
绘制聚类结果
创建一个图表来展示不同聚类算法在数据集上的性能。
for i_dataset, (dataset, algo_params) in enumerate(datasets):
## 使用特定于数据集的值更新参数
params = default_base.copy()
params.update(algo_params)
X, y = dataset
## 标准化数据集以便于参数选择
X = StandardScaler().fit_transform(X)
## 估计均值漂移的带宽
bandwidth = cluster.estimate_bandwidth(X, quantile=params["quantile"])
## 用于结构化沃德聚类的连接矩阵
connectivity = kneighbors_graph(
X, n_neighbors=params["n_neighbors"], include_self=False
)
## 使连接矩阵对称
connectivity = 0.5 * (connectivity + connectivity.T)
clustering_algorithms = (
("MiniBatch\nKMeans", two_means),
("Affinity\nPropagation", affinity_propagation),
("MeanShift", ms),
("Spectral\nClustering", spectral),
("Ward", ward),
("Agglomerative\nClustering", average_linkage),
("DBSCAN", dbscan),
("HDBSCAN", hdbscan),
("OPTICS", optics),
("BIRCH", birch),
("Gaussian\nMixture", gmm),
)
for name, algorithm in clustering_algorithms:
t0 = time.time()
## 捕获与 kneighbors_graph 相关的警告
with warnings.catch_warnings():
warnings.filterwarnings(
"ignore",
message="the number of connected components of the "
+ "connectivity matrix is [0-9]{1,2}"
+ " > 1. Completing it to avoid stopping the tree early.",
category=UserWarning,
)
warnings.filterwarnings(
"ignore",
message="Graph is not fully connected, spectral embedding"
+ " may not work as expected.",
category=UserWarning,
)
algorithm.fit(X)
t1 = time.time()
if hasattr(algorithm, "labels_"):
y_pred = algorithm.labels_.astype(int)
else:
y_pred = algorithm.predict(X)
plt.subplot(len(datasets), len(clustering_algorithms), plot_num)
if i_dataset == 0:
plt.title(name, size=18)
colors = np.array(
list(
islice(
cycle(
[
"#377eb8",
"#ff7f00",
"#4daf4a",
"#f781bf",
"#a65628",
"#984ea3",
"#999999",
"#e41a1c",
"#dede00",
]
),
int(max(y_pred) + 1),
)
)
)
## 为异常值添加黑色（如果有）
colors = np.append(colors, ["#000000"])
plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[y_pred])
plt.xlim(-2.5, 2.5)
plt.ylim(-2.5, 2.5)
plt.xticks(())
plt.yticks(())
plt.text(
0.99,
0.01,
("%.2fs" % (t1 - t0)).lstrip("0"),
transform=plt.gca().transAxes,
size=15,
horizontalalignment="right",
)
plot_num += 1
plt.show()
总结
本实验展示了不同聚类算法在二维“有趣”数据集上的特点。比较了每种算法的性能并绘制图表以对比结果。