PIG plot fix: avoiding the

exaggeration of avg_target differences if differences across bins and vs global avg target is small (issue #32).

Author: Sander Vanden Hautte

cobra/evaluation/pigs_tables.py

@@ -179,6 +179,24 @@ def plot_incidence(pig_tables: pd.DataFrame,
             ax.set_yticks(np.arange(0, max(df_plot['avg_target'])+0.05, 0.05))
             ax.yaxis.set_major_formatter(
                 FuncFormatter(lambda y, _: '{:.1%}'.format(y)))
+        elif model_type == "regression":
+            # If both the difference between the highest avg target of all bins
+            # versus the global avg target AND the difference between the
+            # lowest avg target versus the global avg target are both smaller
+            # than 25% of the global avg target itself, we increase the y
+            # axis range, to avoid that the minor avg target differences are
+            # spread out over the configure figure height, suggesting
+            # incorrectly that there are big differences in avg target across
+            # the bins and versus the global avg target.
+            # (Motivation for the AND above: if on one end there IS enough
+            # difference, the effect that we discuss here does not occur.)
+            global_avg_target = max(df_plot['global_avg_target']) # series of same number, for every bin.
+            if (np.abs((max(df_plot['avg_target']) - global_avg_target))
+                    / global_avg_target < 0.25) \
+                and (np.abs((min(df_plot['avg_target']) - global_avg_target))
+                    / global_avg_target < 0.25):
+                ax.set_ylim(global_avg_target * 0.75,
+                            global_avg_target * 1.25)
 
         # Remove ticks but keep the labels
         ax.tick_params(axis='both', which='both', length=0)