make changes according to review

Author: nmaarnio

eis_toolkit/prediction/machine_learning_predict.py

@@ -29,13 +29,13 @@ def predict_classifier(
             return labels, probabilities
         else:
             return labels
-    elif include_probabilities:
-        probabilities = model.predict_proba(data)
+    elif isinstance(model, BaseEstimator):
         labels = model.predict(data)
-        return labels, probabilities
-    else:
-        labels = model.predict(data)
-        return labels
+        if include_probabilities:
+            probabilities = model.predict_proba(data)
+            return labels, probabilities
+        else:
+            return labels
 
 
 @beartype

eis_toolkit/validation/classification_probability_evaluation.py

@@ -98,7 +98,7 @@ def plot_det_curve(
     """
     display = DetCurveDisplay.from_predictions(y_true, y_prob, ax=ax, **kwargs)
     out_ax = display.ax_
-    out_ax.set(xlabel="False positive rate", ylabel="True positive rate", title=plot_title)
+    out_ax.set(xlabel="False positive rate", ylabel="False negative rate", title=plot_title)
     return out_ax
 
 
@@ -129,7 +129,7 @@ def plot_precision_recall_curve(
     """
     display = PrecisionRecallDisplay.from_predictions(y_true, y_prob, plot_chance_level=True, ax=ax, **kwargs)
     out_ax = display.ax_
-    out_ax.set(xlabel="False positive rate", ylabel="True positive rate", title=plot_title)
+    out_ax.set(xlabel="Recall", ylabel="Precision", title=plot_title)
     return out_ax
 
 

eis_toolkit/validation/plot_prediction_area_curves.py

@@ -65,6 +65,8 @@ def plot_prediction_area_curves(
     Plots prediction area plot that can be used to evaluate mineral prospectivity maps and evidential layers. See e.g.,
     Yousefi and Carranza (2015).
 
+    The inputs needed for this tool can be obtained with calculate_base_metrics() tool.
+
     Args:
         true_positive_rate_values: True positive rate values.
         proportion_of_area_values: Proportion of area values.