Use right=False in pandas.cut.

Histograms by default include the left endpoint of each interval, and so we need to use right=False when calling pandas.cut.
fbdesignpro · Oct 1, 2021 · c027b2a · c027b2a
1 parent a86686a
commit c027b2a
Showing 1 changed file with 12 additions and 8 deletions.
diff --git a/sweetviz/graph_numeric.py b/sweetviz/graph_numeric.py
@@ -91,8 +91,9 @@ def __init__(self, which_graph: str, to_process: FeatureToProcess):
                 # TODO: possible 1-off bug in counts from cut in lower bin
                 source_bins_series = pd.cut(to_process.source,
                                             bins=bin_limits,
-                                            labels=False)
-                source_bins_series = source_bins_series.fillna(0)
+                                            labels=False,
+                                            right=False)
+                source_bins_series = source_bins_series.fillna(num_bins-1)
                 # Create empty bin_averages, then fill in with values
                 bin_averages = [None] * num_bins
                 for b in range(0, num_bins):
@@ -111,8 +112,9 @@ def __init__(self, which_graph: str, to_process: FeatureToProcess):
                     # TARGET NUMERIC: with compare TARGET
                     compare_bins_series = pd.cut(to_process.compare,
                                                 bins=bin_limits,
-                                                labels=False)
-                    compare_bins_series = compare_bins_series.fillna(0)
+                                                labels=False,
+                                                right=False)
+                    source_bins_series = source_bins_series.fillna(num_bins-1)
                     bin_averages = [None] * num_bins
                     for b in range(0, num_bins):
                         bin_averages[b] = \
@@ -124,8 +126,9 @@ def __init__(self, which_graph: str, to_process: FeatureToProcess):
                 source_true = to_process.source[to_process.source_target == 1]
                 source_bins_series = pd.cut(source_true,
                                             bins=bin_limits,
-                                            labels=False)
-                source_bins_series = source_bins_series.fillna(0)
+                                            labels=False,
+                                            right=False)
+                source_bins_series = source_bins_series.fillna(num_bins-1)
                 total_counts_source = bin_counts[0] if to_process.compare is not None else bin_counts
                 total_counts_source = total_counts_source * len(cleaned_source)
                 bin_true_counts_source = [None] * num_bins
@@ -156,8 +159,9 @@ def __init__(self, which_graph: str, to_process: FeatureToProcess):
                     # TODO: possible 1-off bug in counts from cut in lower bin
                     compare_bins_series = pd.cut(compare_true,
                                                 bins=bin_limits,
-                                                labels=False)
-                    compare_bins_series = compare_bins_series.fillna(0)
+                                                labels=False,
+                                                right=False)
+                    source_bins_series = source_bins_series.fillna(num_bins-1)
                     total_counts_compare = bin_counts[1] * len(cleaned_compare)
                     bin_true_counts_compare = [None] * num_bins
                     for b in range(0, num_bins):