denominator safety in stat calculation

Author: JohnMount

pkg/build/lib/wvpy/util.py

@@ -429,20 +429,20 @@ def threshold_statistics(
 
     # basic cumulative facts
     sorted_frame["count"] = sorted_frame["one"].cumsum()  # predicted true so far
-    sorted_frame["fraction"] = sorted_frame["count"] / sorted_frame["one"].sum()
-    sorted_frame["precision"] = sorted_frame["truth"].cumsum() / sorted_frame["count"]
+    sorted_frame["fraction"] = sorted_frame["count"] / max(1, sorted_frame["one"].sum())
+    sorted_frame["precision"] = sorted_frame["truth"].cumsum() / sorted_frame["count"].clip(lower=1)
     sorted_frame["true_positive_rate"] = (
-        sorted_frame["truth"].cumsum() / sorted_frame["truth"].sum()
+        sorted_frame["truth"].cumsum() / max(1, sorted_frame["truth"].sum())
     )
     sorted_frame["false_positive_rate"] = (
-        sorted_frame["notY"].cumsum() / sorted_frame["notY"].sum()
+        sorted_frame["notY"].cumsum() / max(1, sorted_frame["notY"].sum())
     )
     sorted_frame["true_negative_rate"] = (
         sorted_frame["notY"].sum() - sorted_frame["notY"].cumsum()
-    ) / sorted_frame["notY"].sum()
+    ) / max(1, sorted_frame["notY"].sum())
     sorted_frame["false_negative_rate"] = (
         sorted_frame["truth"].sum() - sorted_frame["truth"].cumsum()
-    ) / sorted_frame["truth"].sum()
+    ) / max(1, sorted_frame["truth"].sum())
 
     # derived facts and synonyms
     sorted_frame["recall"] = sorted_frame["true_positive_rate"]

pkg/dist/wvpy-0.2.2-py3-none-any.whl

@@ -13,7 +13,7 @@ def test_stats1():
             "threshold": [0.999999, 1.0, 2.0, 3.0, 4.0, 5.0, 5.000001],
             "count": [5, 5, 4, 3, 2, 1, 0],
             "fraction": [1.0, 1.0, 0.8, 0.6, 0.4, 0.2, 0.0],
-            "precision": [0.4, 0.4, 0.5, 0.6666666666666666, 0.5, 0.0, None],
+            "precision": [0.4, 0.4, 0.5, 0.6666666666666666, 0.5, 0.0, 0.0],
             "true_positive_rate": [1.0, 1.0, 1.0, 1.0, 0.5, 0.0, 0.0],
             "false_positive_rate": [
                 1.0,

pkg/dist/wvpy-0.2.2.tar.gz

@@ -429,20 +429,20 @@ def threshold_statistics(
 
     # basic cumulative facts
     sorted_frame["count"] = sorted_frame["one"].cumsum()  # predicted true so far
-    sorted_frame["fraction"] = sorted_frame["count"] / sorted_frame["one"].sum()
-    sorted_frame["precision"] = sorted_frame["truth"].cumsum() / sorted_frame["count"]
+    sorted_frame["fraction"] = sorted_frame["count"] / max(1, sorted_frame["one"].sum())
+    sorted_frame["precision"] = sorted_frame["truth"].cumsum() / sorted_frame["count"].clip(lower=1)
     sorted_frame["true_positive_rate"] = (
-        sorted_frame["truth"].cumsum() / sorted_frame["truth"].sum()
+        sorted_frame["truth"].cumsum() / max(1, sorted_frame["truth"].sum())
     )
     sorted_frame["false_positive_rate"] = (
-        sorted_frame["notY"].cumsum() / sorted_frame["notY"].sum()
+        sorted_frame["notY"].cumsum() / max(1, sorted_frame["notY"].sum())
     )
     sorted_frame["true_negative_rate"] = (
         sorted_frame["notY"].sum() - sorted_frame["notY"].cumsum()
-    ) / sorted_frame["notY"].sum()
+    ) / max(1, sorted_frame["notY"].sum())
     sorted_frame["false_negative_rate"] = (
         sorted_frame["truth"].sum() - sorted_frame["truth"].cumsum()
-    ) / sorted_frame["truth"].sum()
+    ) / max(1, sorted_frame["truth"].sum())
 
     # derived facts and synonyms
     sorted_frame["recall"] = sorted_frame["true_positive_rate"]