Fixed low contamination issue in RANK

KulikDM · Dec 19, 2024 · 5d9b340 · 5d9b340
1 parent b097a2a
commit 5d9b340
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 2 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -86,3 +86,4 @@ v<0.3.7>, <08/18/2024> -- Fixed muli-peak error in FWFM
 v<0.3.7>, <08/18/2024> -- Updated time complexity benchmarks
 v<0.3.8>, <11/21/2024> -- Added factor arg to MAD and ZSCORE, contribution by @MalikAly
 v<0.3.8>, <12/15/2024> -- Removed matplotlib as core dependency
+v<0.3.9>, <12/19/2024> -- Fixed low contamination issue in RANK
diff --git a/pythresh/utils/rank.py b/pythresh/utils/rank.py
@@ -226,10 +226,13 @@ def _cdf_metric(self, scores, labels):
             scores1 = scores1 + np.linspace(1e-30, 2e-30, len(scores1))
 
         scores2 = scores[labels == 1]
+        if len(scores2) < 2:
+            return [-1e6, -1e6]
+
         if np.all(scores2 == scores2[0]):
             scores2 = scores2 - np.linspace(1e-30, 2e-30, len(scores2))
 
-        # Generate KDEs of scores for both classed
+        # Generate KDEs of scores for both classes
         kde1 = stats.gaussian_kde(scores1)
         kde2 = stats.gaussian_kde(scores2)
 

diff --git a/requirements-test.txt b/requirements-test.txt
@@ -1,7 +1,7 @@
 #pyclustering
 https://github.com/KulikDM/pyclustering/archive/Warning-Fix.zip
 joblib>=0.14.1
-numpy<=1.26.4
+numpy
 pandas
 pyod
 ruptures