DBSCANDensity-Based Spatial Clustering of Applications with Noise
Overview
DBSCANdensity-based spatial clustering of applications with noiseDBSCANDBSCANk-means

Coding
DBSCAN
from sklearn.datasets import make_blobs
from sklearn.cluster import DBSCAN
X, y = make_blobs(random_state=0, n_samples=12)
dbscan = DBSCAN()
clusters = dbscan.fit_predict(X)
print("Cluster memberships:\n{}".format(clusters))
--------------------------------------------------------------------------
Cluster memberships:
[-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
--------------------------------------------------------------------------

-1epsmin_samplesepsmin_samples

mglearn.plots.plot_dbscan()
--------------------------------------------------------------------------
min_samples: 2 eps: 1.000000 cluster: [-1 0 0 -1 0 -1 1 1 0 1 -1 -1]
min_samples: 2 eps: 1.500000 cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 2 eps: 2.000000 cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 2 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 3 eps: 1.000000 cluster: [-1 0 0 -1 0 -1 1 1 0 1 -1 -1]
min_samples: 3 eps: 1.500000 cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 3 eps: 2.000000 cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 3 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 5 eps: 1.000000 cluster: [-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
min_samples: 5 eps: 1.500000 cluster: [-1 0 0 0 0 -1 -1 -1 0 -1 -1 -1]
min_samples: 5 eps: 2.000000 cluster: [-1 0 0 0 0 -1 -1 -1 0 -1 -1 -1]
min_samples: 5 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
--------------------------------------------------------------------------


epsmin_samples

eps

two_moonsStandardScalerDBSCAN
import matplotlib.pyplot as plt
import mglearn
from sklearn.datasets import make_moons
from sklearn.preprocessing import StandardScaler
X, y = make_moons(n_samples=200, noise=0.05, random_state=0)
# 01
scaler = StandardScaler()
scaler.fit(X)
X_scaled = scaler.transform(X)
dbscan = DBSCAN()
clusters = dbscan.fit_predict(X_scaled)
plt.scatter(X_scaled[:, 0], X_scaled[:, 1], c=clusters, cmap=mglearn.cm2, s=60)
plt.xlabel("Feature 0")
plt.ylabel("Feature 1")