如何绘制 dbscan 图

Question

我一直在尝试绘制DBSCAN 聚类图，但遇到了错误：

AttributeError: 'DBSCAN' object has no attribute 'labels'

代码：

from sklearn.cluster import DBSCAN
    
model = DBSCAN(eps=3)
X = dataset.data
model.fit(X)
df=pd.DataFrame(iris['data'])
df.head()
    print(model)
%matplotlib inline
# Visualize the results
import matplotlib.pyplot as plt
X = dataset.data
y_kmeans = model.fit_predict(X) # this give the cluster number of the nearest centroid

# scatter plot the petal length (column 2), petal width (column 3)
plt.scatter(X[:, 2], X[:, 3], c=y_kmeans, s=50, cmap='viridis')
# show centroid centres as grey circle opacity 50%
centers = model.labels
plt.scatter(centers[:, 2], centers[:, 3], c='black', s=200, alpha=0.5)

任何建议或替代方案都会有所帮助！

Answer 1

根据help 文件，标签位于model.labels_