Add note about special case with mode NA replacement

rhiever · Jan 18, 2017 · 5572555 · 5572555
1 parent 44bcd70
commit 5572555
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/datacleaner/datacleaner.py b/datacleaner/datacleaner.py
@@ -77,7 +77,9 @@ def autoclean(input_dataframe, drop_nans=False, copy=False, encoder=None,
             input_dataframe[column].fillna(input_dataframe[column].median(), inplace=True)
         except TypeError:
             most_frequent = input_dataframe[column].mode()
-            if len(most_frequent)>0:
+            # If the mode can't be computed, use the nearest valid value
+            # See https://github.com/rhiever/datacleaner/issues/8
+            if len(most_frequent) > 0:
                 input_dataframe[column].fillna(input_dataframe[column].mode()[0], inplace=True)
             else:
                 input_dataframe[column].fillna(method='bfill', inplace=True)