This commit is contained in:
2026-04-10 15:06:59 +02:00
parent 3031b7153b
commit e5a4711004
7806 changed files with 1918528 additions and 335 deletions

View File

@@ -0,0 +1,37 @@
"""
Common utilities for testing clustering.
"""
import numpy as np
###############################################################################
# Generate sample data
def generate_clustered_data(
seed=0, n_clusters=3, n_features=2, n_samples_per_cluster=20, std=0.4
):
prng = np.random.RandomState(seed)
# the data is voluntary shifted away from zero to check clustering
# algorithm robustness with regards to non centered data
means = (
np.array(
[
[1, 1, 1, 0],
[-1, -1, 0, 1],
[1, -1, 1, 1],
[-1, 1, 1, 0],
]
)
+ 10
)
X = np.empty((0, n_features))
for i in range(n_clusters):
X = np.r_[
X,
means[i][:n_features] + std * prng.randn(n_samples_per_cluster, n_features),
]
return X