test_cluster.py
2.51 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import pytest
import pandas as pd
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
from hdbscan import HDBSCAN
from bertopic import BERTopic
@pytest.mark.parametrize("cluster_model", ["hdbscan", "kmeans"])
@pytest.mark.parametrize(
"samples,features,centers",
[
(200, 500, 1),
(500, 200, 1),
(200, 500, 2),
(500, 200, 2),
(200, 500, 4),
(500, 200, 4),
],
)
def test_hdbscan_cluster_embeddings(cluster_model, samples, features, centers):
embeddings, _ = make_blobs(n_samples=samples, centers=centers, n_features=features, random_state=42)
documents = [str(i + 1) for i in range(embeddings.shape[0])]
old_df = pd.DataFrame({"Document": documents, "ID": range(len(documents)), "Topic": None})
if cluster_model == "kmeans":
cluster_model = KMeans(n_clusters=centers)
else:
cluster_model = HDBSCAN(
min_cluster_size=10,
metric="euclidean",
cluster_selection_method="eom",
prediction_data=True,
)
model = BERTopic(hdbscan_model=cluster_model)
new_df, _ = model._cluster_embeddings(embeddings, old_df)
assert len(new_df.Topic.unique()) == centers
assert "Topic" in new_df.columns
pd.testing.assert_frame_equal(old_df.drop("Topic", axis=1), new_df.drop("Topic", axis=1))
@pytest.mark.parametrize("cluster_model", ["hdbscan", "kmeans"])
@pytest.mark.parametrize(
"samples,features,centers",
[
(200, 500, 1),
(500, 200, 1),
(200, 500, 2),
(500, 200, 2),
(200, 500, 4),
(500, 200, 4),
],
)
def test_custom_hdbscan_cluster_embeddings(cluster_model, samples, features, centers):
embeddings, _ = make_blobs(n_samples=samples, centers=centers, n_features=features, random_state=42)
documents = [str(i + 1) for i in range(embeddings.shape[0])]
old_df = pd.DataFrame({"Document": documents, "ID": range(len(documents)), "Topic": None})
if cluster_model == "kmeans":
cluster_model = KMeans(n_clusters=centers)
else:
cluster_model = HDBSCAN(
min_cluster_size=10,
metric="euclidean",
cluster_selection_method="eom",
prediction_data=True,
)
model = BERTopic(hdbscan_model=cluster_model)
new_df, _ = model._cluster_embeddings(embeddings, old_df)
assert len(new_df.Topic.unique()) == centers
assert "Topic" in new_df.columns
pd.testing.assert_frame_equal(old_df.drop("Topic", axis=1), new_df.drop("Topic", axis=1))