Implement mode(dropna), for #17534

Author: fulldecent

pandas/core/algorithms.py

@@ -634,14 +634,16 @@ def duplicated(values, keep='first'):
     return f(values, keep=keep)
 
 
-def mode(values):
+def mode(values, dropna=True):
     """
     Returns the mode(s) of an array.
 
     Parameters
     ----------
     values : array-like
-        Array over which to check for duplicate values.
+        Array over which to check for duplicate values
+    dropna : boolean, default True
+        Don't include NaN values.
 
     Returns
     -------
@@ -666,6 +668,7 @@ def mode(values):
         ndtype = 'object'
         values = _ensure_object(values)
 
+### TODO: IN HERE IMPLEMENT THE DROPNA PARAMETER
     f = getattr(htable, "mode_{dtype}".format(dtype=ndtype))
     result = f(values)
     try:

pandas/core/frame.py

@@ -5640,7 +5640,7 @@ def _get_agg_axis(self, axis_num):
         else:
             raise ValueError('Axis must be 0 or 1 (got %r)' % axis_num)
 
-    def mode(self, axis=0, numeric_only=False):
+    def mode(self, axis=0, numeric_only=False, dropna=True):
         """
         Gets the mode(s) of each element along the axis selected. Adds a row
         for each mode per label, fills in gaps with nan.
@@ -5658,6 +5658,8 @@ def mode(self, axis=0, numeric_only=False):
             * 1 or 'columns' : get mode of each row
         numeric_only : boolean, default False
             if True, only apply to numeric columns
+        dropna : boolean, default True
+            Don't include NaN values.
 
         Returns
         -------
@@ -5674,7 +5676,7 @@ def mode(self, axis=0, numeric_only=False):
         data = self if not numeric_only else self._get_numeric_data()
 
         def f(s):
-            return s.mode()
+            return s.mode(dropna=dropna)
 
         return data.apply(f, axis=axis)
 

pandas/core/series.py

@@ -1236,11 +1236,16 @@ def count(self, level=None):
         return self._constructor(out, index=lev,
                                  dtype='int64').__finalize__(self)
 
-    def mode(self):
+    def mode(self, dropna=True):
         """Return the mode(s) of the dataset.
 
         Always returns Series even if only one value is returned.
 
+        Parameters
+        ----------
+        dropna : boolean, default True
+            Don't include NaN values.
+
         Returns
         -------
         modes : Series (sorted)