scikit-learn/scikit-learn
Agglomerative clustering training error for seuclidean/mahalanobis affinity and single linkage
開放
#26,961 建立於 2023年8月1日
Bughelp wanted
倉庫指標
- 星標
- (66,084 顆星)
- PR 合併指標
- (平均合併 10天) (30 天內合併 90 個 PR)
描述
Describe the bug
When trying Agglomerative clustering model training with the affinity as 'seuclidean' or 'mahalanobis' and the linkage as 'single' the training fails. The same affinity values along with other linkage such as 'average' options executes for model training. There's no specification given for this issue. Also, in the code I can see the handling for the single linkage is different and there is some cython code which is not accessible.
Steps/Code to Reproduce
from sklearn.cluster import AgglomerativeClustering
from sklearn.datasets import load_iris
model = AgglomerativeClustering(affinity='mahalanobis', linkage='average')
data = load_iris(as_frame=True)['data']
model.fit(data)
Expected Results
No error should be thrown sig
Actual Results
Versions
System:
python: 3.8.17 (default, Jul 5 2023, 21:04:15) [GCC 11.2.0]
executable: /home/albint/miniconda3/envs/myenv/bin/python
machine: Linux-5.15.0-78-generic-x86_64-with-glibc2.17
Python dependencies:
sklearn: 1.3.0
pip: 23.1.2
setuptools: 67.8.0
numpy: 1.24.4
scipy: 1.10.1
Cython: 3.0.0
pandas: 2.0.3
matplotlib: 3.7.2
joblib: 1.3.1
threadpoolctl: 3.2.0
Built with OpenMP: True
threadpoolctl info:
user_api: blas
internal_api: openblas
num_threads: 8
prefix: libopenblas
filepath: /home/albint/miniconda3/envs/myenv/lib/python3.8/site-packages/numpy.libs/libopenblas64_p-r0-15028c96.3.21.so
version: 0.3.21
threading_layer: pthreads
architecture: Haswell
user_api: blas
internal_api: openblas
num_threads: 8
prefix: libopenblas
filepath: /home/albint/miniconda3/envs/myenv/lib/python3.8/site-packages/scipy.libs/libopenblasp-r0-41284840.3.18.so
version: 0.3.18
threading_layer: pthreads
architecture: Haswell
user_api: openmp
internal_api: openmp
num_threads: 8
prefix: libgomp
filepath: /home/albint/miniconda3/envs/myenv/lib/python3.8/site-packages/scikit_learn.libs/libgomp-a34b3233.so.1.0.0
version: None