Merge pull request #408 from GispoCoding/407-evaluationvalidation-met…

…rics-invalid-when-using-cli-tools Fix invalid scoring for classifier metrics
GispoCoding · Jun 18, 2024 · 813362c · 813362c
2 parents 8b8fccb + 40f7c1f
commit 813362c
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/eis_toolkit/evaluation/scoring.py b/eis_toolkit/evaluation/scoring.py
@@ -53,8 +53,10 @@ def score_predictions(
 def _score_predictions(
     y_true: Union[np.ndarray, pd.Series], y_pred: Union[np.ndarray, pd.Series], metric: str
 ) -> Number:
+    num_classes = len(np.unique(y_true))
+
     # Multiclass classification
-    if len(y_true) > 2:
+    if num_classes > 2:
         average_method = "micro"
     # Binary classification
     else:

diff --git a/tests/evaluation/scoring_test.py b/tests/evaluation/scoring_test.py
@@ -7,7 +7,7 @@
 
 X, y = make_classification(n_samples=200, n_features=20, n_informative=2, n_redundant=10, random_state=42)
 X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
-rf_model, history = random_forest_classifier_train(X_train, y_train)
+rf_model, history = random_forest_classifier_train(X_train, y_train, random_state=42)
 y_pred = predict_classifier(X_test, rf_model, include_probabilities=False)