ENH: mode(dropna=False) (pandas-dev#17534)

Author: reidy-p

pandas/_libs/hashtable_func_helper.pxi.in

@@ -39,20 +39,23 @@ cdef build_count_table_{{dtype}}({{dtype}}_t[:] values,
         int ret = 0
 
     {{if dtype == 'object'}}
+    print('object way')
     kh_resize_{{ttype}}(table, n // 10)
 
     for i in range(n):
         val = values[i]
 
         if not checknull(val) or not dropna:
             k = kh_get_{{ttype}}(table, <PyObject*> val)
+            print(k, val, table.n_buckets)
             if k != table.n_buckets:
                 table.vals[k] += 1
             else:
                 k = kh_put_{{ttype}}(table, <PyObject*> val, &ret)
                 table.vals[k] = 1
     {{else}}
     with nogil:
+    #print('non-object way')
         kh_resize_{{ttype}}(table, n)
 
         for i in range(n):
@@ -288,25 +291,25 @@ def ismember_{{dtype}}({{scalar}}[:] arr, {{scalar}}[:] values, bint hasnans=0):
 {{py:
 
 # dtype, ctype, table_type, npy_dtype
-dtypes = [('int64', 'int64_t', 'int64', 'int64'),
+dtypes = [('float64', 'float64_t', 'float64', 'float64'),
+          ('int64', 'int64_t', 'int64', 'int64'),
           ('uint64', 'uint64_t', 'uint64', 'uint64'),
           ('object', 'object', 'pymap', 'object_')]
 }}
 
 {{for dtype, ctype, table_type, npy_dtype in dtypes}}
 
-
 @cython.wraparound(False)
 @cython.boundscheck(False)
 
 {{if dtype == 'object'}}
 
 
-def mode_{{dtype}}(ndarray[{{ctype}}] values):
+def mode_{{dtype}}(ndarray[{{ctype}}] values, bint dropna):
 {{else}}
 
 
-def mode_{{dtype}}({{ctype}}[:] values):
+def mode_{{dtype}}({{ctype}}[:] values, bint dropna):
 {{endif}}
     cdef:
         int count, max_count = 1
@@ -317,9 +320,9 @@ def mode_{{dtype}}({{ctype}}[:] values):
 
     table = kh_init_{{table_type}}()
     {{if dtype == 'object'}}
-    build_count_table_{{dtype}}(values, table, 1)
+    build_count_table_{{dtype}}(values, table, dropna)
     {{else}}
-    build_count_table_{{dtype}}(values, table, 0)
+    build_count_table_{{dtype}}(values, table, dropna)
     {{endif}}
 
     modes = np.empty(table.n_buckets, dtype=np.{{npy_dtype}})
@@ -329,7 +332,6 @@ def mode_{{dtype}}({{ctype}}[:] values):
         for k in range(table.n_buckets):
             if kh_exist_{{table_type}}(table, k):
                 count = table.vals[k]
-
                 if count == max_count:
                     j += 1
                 elif count > max_count:
@@ -342,6 +344,7 @@ def mode_{{dtype}}({{ctype}}[:] values):
     {{else}}
     for k in range(table.n_buckets):
         if kh_exist_{{table_type}}(table, k):
+            print(<object> table.keys[k], table.vals[k])
             count = table.vals[k]
 
             if count == max_count:

pandas/core/algorithms.py

@@ -791,7 +791,7 @@ 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.
 
@@ -803,6 +803,8 @@ def mode(values):
     Returns
     -------
     mode : Series
+    dropna : boolean, default True
+        Don't include counts of NaN.
     """
     from pandas import Series
 
@@ -818,13 +820,15 @@ def mode(values):
 
     values, dtype, ndtype = _ensure_data(values)
 
-    # TODO: this should support float64
-    if ndtype not in ['int64', 'uint64', 'object']:
-        ndtype = 'object'
-        values = _ensure_object(values)
+    print('dtype', values.dtype)
+    ## TODO: this should support float64
+    #if ndtype not in ['int64', 'uint64', 'object']:
+    #    ndtype = 'object'
+    #    values = _ensure_object(values)
 
     f = getattr(htable, "mode_{dtype}".format(dtype=ndtype))
-    result = f(values)
+    print('dtype', values.dtype)
+    result = f(values, dropna=dropna)
     try:
         result = np.sort(result)
     except TypeError as e:

pandas/core/arrays/categorical.py

@@ -2044,7 +2044,7 @@ def max(self, numeric_only=None, **kwargs):
         else:
             return self.categories[pointer]
 
-    def mode(self):
+    def mode(self, dropna=True):
         """
         Returns the mode(s) of the Categorical.
 
@@ -2053,11 +2053,16 @@ def mode(self):
         Returns
         -------
         modes : `Categorical` (sorted)
+        dropna : boolean, default True
+            Don't include counts of NaN.
         """
 
         import pandas._libs.hashtable as htable
-        good = self._codes != -1
-        values = sorted(htable.mode_int64(_ensure_int64(self._codes[good])))
+        #if dropna:
+        #    good = self._codes != -1
+        #    values = sorted(htable.mode_int64(_ensure_int64(self._codes[good]), dropna))
+        #else:
+        values = sorted(htable.mode_int64(_ensure_int64(self._codes), dropna))
         result = self._constructor(values=values, categories=self.categories,
                                    ordered=self.ordered, fastpath=True)
         return result

pandas/core/frame.py

@@ -6992,7 +6992,7 @@ 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.
@@ -7010,6 +7010,8 @@ 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 counts of NaN.
 
         Returns
         -------
@@ -7026,7 +7028,7 @@ 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

@@ -1420,17 +1420,19 @@ 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.
 
         Returns
         -------
         modes : Series (sorted)
+
+
         """
         # TODO: Add option for bins like value_counts()
-        return algorithms.mode(self)
+        return algorithms.mode(self, dropna=dropna)
 
     def unique(self):
         """

pandas/tests/series/test_analytics.py

@@ -321,6 +321,18 @@ def test_mode(self):
         exp = Series(exp, dtype='category')
         tm.assert_series_equal(Series(c).mode(), exp)
 
+    @pytest.mark.parametrize('data, expected', [
+        ([np.nan, np.nan, 1], [np.nan]), 
+        ([np.nan, np.nan, 'a'], np.array([np.nan], dtype=object)),
+        (Categorical([np.nan, np.nan, 'a']), 
+         Categorical([np.nan], categories=['a']))
+    ])
+    def test_mode_dropna(self, data, expected):
+        
+        result = Series(data).mode(dropna=False)
+        expected = Series(expected) 
+        tm.assert_series_equal(result, expected) 
+
     def test_prod(self):
         self._check_stat_op('prod', np.prod)