dbscan 对少量点没有意义

Question

我正在玩一个 dbscan 示例，看看它是否适合我。在我的情况下，我有几个点（3-5）的集群靠近在一起，集群之间的距离相当长。我试图在下面的代码中复制这种情况。我认为使用低 epsilon 和低 min_samples，这应该可以工作，但它告诉我它只看到 1 个组（和 20 个噪声点？）。我是在错误地使用它，还是 dbscan 不适合这类问题。我选择了 dbscan 而不是 kmeans，因为我事先不知道会有多少个集群 (1-5)。

from sklearn.datasets import make_blobs
from sklearn.cluster import DBSCAN
import numpy as np
import matplotlib.pyplot as plt

# Configuration options
num_samples_total = 20
cluster_centers = [(3,3), (7,7),(7,3),(3,7),(5,5)]
num_classes = len(cluster_centers)
#epsilon = 1.0
epsilon = 1e-5
#min_samples = 13
min_samples = 2

# Generate data
X, y = make_blobs(n_samples = num_samples_total, centers = cluster_centers, n_features = num_classes, center_box=(0, 1), cluster_std = 0.05)

np.save('./clusters.npy', X)
X = np.load('./clusters.npy')

# Compute DBSCAN
db = DBSCAN(eps=epsilon, min_samples=min_samples).fit(X)
labels = db.labels_

no_clusters = len(np.unique(labels) )
no_noise = np.sum(np.array(labels) == -1, axis=0)

print('Estimated no. of clusters: %d' % no_clusters)
print('Estimated no. of noise points: %d' % no_noise)

# Generate scatter plot for training data
colors = list(map(lambda x: '#3b4cc0' if x == 1 else '#b40426', labels))                #only set for 2 colors
plt.scatter(X[:,0], X[:,1], c=colors, marker="o", picker=True)
plt.title('Two clusters with data')
plt.xlabel('Axis X[0]')
plt.ylabel('Axis X[1]')
plt.show()

Answer 1

最终选择了 kmeans 并进行了改进的肘部方法：

print(__doc__)

# Author: Phil Roth <mr.phil.roth@gmail.com>
# License: BSD 3 clause

import numpy as np
import matplotlib.pyplot as plt

from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs

# Configuration options
num_samples_total = 20
cluster_centers = [(3,3), (7,7),(7,3),(3,7),(5,5)]
num_classes = len(cluster_centers)
#epsilon = 1.0
epsilon = 1e-5
#min_samples = 13
min_samples = 2

# Generate data
X, y = make_blobs(n_samples = num_samples_total, centers = cluster_centers, n_features = num_classes, center_box=(0, 1), cluster_std = 0.05)
random_state = 170

#y_pred = KMeans(n_clusters=5, random_state=random_state).fit_predict(X)
#plt.scatter(X[:, 0], X[:, 1], c=y_pred)
#kmeans = KMeans(n_clusters=2, random_state=0).fit(X)
#maybe I dont have to look for an elbow, just go until the value drops below 1.
#also if I do go too far, it just means that the same shape will be shown twice.
clusterIdx = 0
inertia = 100
while inertia > 1:
    clusterIdx = clusterIdx + 1
    kmeans = KMeans(n_clusters=clusterIdx, random_state=0).fit(X)
    inertia = kmeans.inertia_
    print(inertia)
plt.scatter(X[:, 0], X[:, 1], c=kmeans.labels_)
print(clusterIdx)
plt.show()