Merge pull request #53 from Blue-Yonder-OSS/analysis_plots_bin_occupa…

…ncies bin occupancy plots
Blue-Yonder-OSS · Oct 16, 2023 · 0203e88 · 0203e88
2 parents 550760c + c01bb1c
commit 0203e88
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 9 deletions.
diff --git a/cyclic_boosting/base.py b/cyclic_boosting/base.py
@@ -800,7 +800,6 @@ def prepare_plots(self, X: np.ndarray, y: np.ndarray, prediction: np.ndarray) ->
                 mean_prediction_finite = np.mean(prediction)
 
             mean_prediction_binned = (sum_pw + 1) / (sum_w + 1)
-            feature.unbind_data()
 
             if isinstance(self, IdentityLinkMixin):
                 feature.mean_dev = mean_prediction_binned - mean_target_binned

diff --git a/cyclic_boosting/plots/__init__.py b/cyclic_boosting/plots/__init__.py
@@ -187,7 +187,6 @@ def plot_analysis(
     dpi = 200
     with contextlib.closing(PdfPages(filepath_or_object)) as pdf_pages:
         plot_observer.check_fitted()
-        means, bin_centers, errors, _ = plot_observer.histograms
 
         # do not show for nbinom width mode
         if plot_observer.link_function.__class__ != CBNBinomC:
@@ -283,13 +282,28 @@ def _format_groupname_with_type(feature_group, feature_type):
 def _plot_one_feature_group(plot_observer, grid_item, feature, binners=None, use_tightlayout=True, plot_yp=True):
     if len(feature.feature_group) == 1:
         # treatment of one-dimensional features
-        plt.subplot(grid_item)
-        plot_factor_1d(
-            feature,
-            bin_bounds=get_bin_bounds(binners, feature.feature_group[0]),
-            link_function=plot_observer.link_function,
-            plot_yp=plot_yp,
-        )
+        # no bin occupancy plot for too many bins
+        if len(feature.factors_link) > 400:
+            plt.subplot(grid_item)
+            plot_factor_1d(
+                feature,
+                bin_bounds=get_bin_bounds(binners, feature.feature_group[0]),
+                link_function=plot_observer.link_function,
+                plot_yp=plot_yp,
+            )
+        else:
+            gs = gridspec.GridSpecFromSubplotSpec(2, 1, subplot_spec=grid_item, height_ratios=[2.5, 0.4])
+            factor_plot = plt.subplot(gs[0, 0])
+            plot_factor_1d(
+                feature,
+                bin_bounds=get_bin_bounds(binners, feature.feature_group[0]),
+                link_function=plot_observer.link_function,
+                plot_yp=plot_yp,
+            )
+            plt.subplot(gs[1, 0], sharex=factor_plot)
+            bin_occupancies = np.bincount(feature.lex_binned_data)
+            plt.plot(range(len(bin_occupancies)), bin_occupancies)
+            plt.xticks(size="xx-small", rotation="vertical")
         plt.grid(True, which="both")
 
     elif len(feature.feature_group) == 2: