DBSCAN：核心点、边界点与噪声点
您将配置 eps 和 min_samples，在月牙形数据集上识别核心点、边界点和噪声点，并观察 DBSCAN 找出 K-Means 无法发现的非凸簇。
DBSCAN：核心点、边界点与噪声点 是 CoddyKit 上的免费 Machine Learning Academy 课时。 这是第 3 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 Machine Learning Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Machine Learning Academy 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
Why K-Means Fails on Arbitrary Shapes
K-Means assumes clusters are convex and roughly spherical. It fails on crescent, ring, or elongated shapes because it partitions by distance to centroids. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) overcomes this by defining clusters as dense regions separated by low-density areas, discovering clusters of any shape.
Two Key Hyperparameters: eps and min_samples
DBSCAN is controlled by two parameters: eps (epsilon) defines the radius of a neighbourhood around a point, and min_samples sets the minimum number of points (including the point itself) required within that radius to be considered a dense region. Together they determine which points are cores, borders, or noise.
Core Points: The Anchors of Dense Regions
A point is a core point if at least min_samples points (including itself) lie within distance eps. Core points are the seeds from which clusters grow. Every point within the core's neighbourhood is directly reachable from it — the foundation for expanding the cluster.
from sklearn.neighbors import BallTree
import numpy as np
X = np.array([[0, 0], [0.3, 0], [0.6, 0],
[5, 5], [10, 10]])
eps = 1.0
min_samples = 3
tree = BallTree(X)
counts = tree.query_radius(X, r=eps, count_only=True)
core_mask = counts >= min_samples
print('Core points:', np.where(core_mask)[0]) # indices 0, 1, 2Border Points and Density-Reachability
A border point has fewer than min_samples neighbours within eps but lies within the eps-neighbourhood of a core point. It belongs to the cluster of its core point but does not expand the cluster further. A point is density-connected to another if there is a chain of directly-reachable steps linking them through core points.
Noise Points: Outlier Detection for Free
Points that are neither core nor border — isolated points with too few neighbours — are labelled noise (label = -1 in scikit-learn). This makes DBSCAN a natural outlier detector: anomalies that do not belong to any dense cluster are automatically flagged as noise without any extra configuration.
Running DBSCAN in scikit-learn
Use sklearn.cluster.DBSCAN. After fitting, db.labels_ contains integer cluster IDs starting at 0, with -1 for noise. db.core_sample_indices_ lists which samples are core points. The number of clusters is determined automatically — no k needed upfront.
from sklearn.cluster import DBSCAN
from sklearn.datasets import make_moons
import numpy as np
X, _ = make_moons(n_samples=200, noise=0.05, random_state=0)
db = DBSCAN(eps=0.3, min_samples=5)
db.fit(X)
n_clusters = len(set(db.labels_)) - (1 if -1 in db.labels_ else 0)
n_noise = (db.labels_ == -1).sum()
print('Clusters found:', n_clusters)
print('Noise points:', n_noise)
print('Labels (first 10):', db.labels_[:10])DBSCAN on Non-Convex Shapes
DBSCAN excels on datasets like two interlocking moons or concentric rings — shapes where K-Means completely fails. Because DBSCAN expands clusters along density chains, it naturally follows the curved manifold of the data. This is a fundamental algorithmic advantage for geospatial data, biological cell clusters, and anomaly-embedded datasets.
import matplotlib.pyplot as plt
from sklearn.cluster import DBSCAN, KMeans
from sklearn.datasets import make_moons
X, _ = make_moons(n_samples=300, noise=0.05, random_state=0)
db_labels = DBSCAN(eps=0.25, min_samples=5).fit_predict(X)
km_labels = KMeans(n_clusters=2, random_state=0, n_init=10).fit_predict(X)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
ax1.scatter(X[:, 0], X[:, 1], c=db_labels, cmap='tab10')
ax1.set_title('DBSCAN')
ax2.scatter(X[:, 0], X[:, 1], c=km_labels, cmap='tab10')
ax2.set_title('K-Means')
plt.show()Choosing eps: The K-Distance Plot
A practical way to choose eps is to plot the k-distance graph: compute the distance of each point to its kth nearest neighbour (where k = min_samples), sort these distances, and look for the knee. The distance at the knee is a good eps candidate. Points above the knee are in sparse regions (noise); below the knee are in dense regions.
from sklearn.neighbors import NearestNeighbors
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_moons
X, _ = make_moons(n_samples=200, noise=0.05, random_state=0)
min_samples = 5
nn = NearestNeighbors(n_neighbors=min_samples)
nn.fit(X)
distances, _ = nn.kneighbors(X)
k_distances = np.sort(distances[:, -1])[::-1]
plt.plot(k_distances)
plt.xlabel('Points sorted by distance')
plt.ylabel(f'{min_samples}-th nearest neighbour distance')
plt.title('K-Distance Plot for eps selection')
plt.show()Effect of eps and min_samples on Results
Increasing eps merges clusters (eventually everything becomes one cluster). Decreasing eps creates more clusters and more noise. Increasing min_samples requires denser cores, making it harder to form clusters and generating more noise points. Tuning both parameters together is needed — the k-distance plot guides eps while min_samples is typically set to the dimensionality of the data plus one as a starting point.
DBSCAN vs K-Means: When to Use Each
Use DBSCAN when: clusters have irregular shapes, you do not know k in advance, outlier detection is important, or data has varying density. Use K-Means when: clusters are roughly spherical, the dataset is very large (DBSCAN scales as O(n log n) with a spatial index), or you need a specific number of clusters for business reasons like market segmentation into exactly 5 regions.
DBSCAN for Geospatial Clustering
DBSCAN is particularly popular for geospatial clustering (finding hotspots in GPS data) because it naturally identifies dense urban areas while marking sparse rural points as noise. Use metric='haversine' and convert coordinates to radians to cluster by great-circle distance on Earth's surface. The result is geographically meaningful clusters without needing to specify their number.
import numpy as np
from sklearn.cluster import DBSCAN
# Sample GPS coords: (lat, lon) in radians
coords = np.radians([
[40.7128, -74.0060], # NYC
[40.6892, -74.0445], # nearby
[40.7282, -73.7949], # Queens
[51.5074, -0.1278], # London
])
# eps in radians: 1km / earth radius
eps_rad = 1.0 / 6371.0
db = DBSCAN(eps=eps_rad, min_samples=2, metric='haversine')
db.fit(coords)
print('Cluster labels:', db.labels_)Quick Check
Test your understanding of DBSCAN concepts from this lesson.
Lesson Recap
In this lesson you learned: DBSCAN classifies points as core, border, or noise based on the eps radius and min_samples threshold, it discovers clusters of arbitrary shape by chaining density-reachable core points, and noise points (label -1) are automatic outliers — a feature K-Means does not provide. Next up we apply clustering end-to-end in a customer segmentation project.
常见问题解答
「DBSCAN：核心点、边界点与噪声点」课时是免费的吗？
是的 — 「DBSCAN：核心点、边界点与噪声点」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Machine Learning Academy 课程的其余内容，请升级到 CoddyKit PRO。 Machine Learning Academy 课程共包含 4 节课。
「DBSCAN：核心点、边界点与噪声点」这节课中我会学到什么？
您将配置 eps 和 min_samples，在月牙形数据集上识别核心点、边界点和噪声点，并观察 DBSCAN 找出 K-Means 无法发现的非凸簇。 你通过在浏览器中直接运行的动手代码来练习 Machine Learning Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 Machine Learning Academy 需要有经验吗？
无需任何先前经验。CoddyKit 上的 Machine Learning Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 3 节课，共 4 节。
「DBSCAN：核心点、边界点与噪声点」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 Machine Learning Academy 课中编写并运行代码吗？
能。每节 Machine Learning Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。
此课程中的所有课时
- K-Means：质心、分配与更新步骤
- 选择 K：肘部法与轮廓系数
- DBSCAN：核心点、边界点与噪声点
- 用于客户细分的聚类：端到端示例