API: add DataFrame.nunique() and DataFrameGroupBy.nunique()

Author: xflr6

doc/source/whatsnew/v0.20.0.txt

@@ -97,6 +97,9 @@ Other enhancements
 ^^^^^^^^^^^^^^^^^^
 - ``Series.sort_index`` accepts parameters ``kind`` and ``na_position`` (:issue:`13589`, :issue:`14444`)
 
+- ``DataFrame`` has gained a ``nunique()`` method as short-cut for ``.apply(lambda x: x.nunique())`` (counting the distinct values over an axis) (:issue:`14336`).
+- New ``DataFrame.groupby().nunique()`` method as short-cut for ``.apply(lambda g: g.apply(lambda x: x.nunique()))`` (counting the distinct values for all columns within each group) (:issue:`14336`).
+
 - ``pd.read_excel`` now preserves sheet order when using ``sheetname=None`` (:issue:`9930`)
 - Multiple offset aliases with decimal points are now supported (e.g. '0.5min' is parsed as '30s') (:issue:`8419`)
 

pandas/core/frame.py

@@ -4969,6 +4969,27 @@ def f(x):
 
         return Series(result, index=labels)
 
+    def nunique(self, axis=0, dropna=True):
+        """
+        Return Series with number of distinct observations over requested
+        axis.
+
+        .. versionadded:: 0.20.0
+
+        Parameters
+        ----------
+        axis : {0 or 'index', 1 or 'columns'}, default 0
+            0 or 'index' for row-wise, 1 or 'columns' for column-wise
+        dropna : boolean, default True
+            Don't include NaN in the counts.
+
+        Returns
+        -------
+        nunique : Series
+        """
+        func = functools.partial(Series.nunique, dropna=dropna)
+        return self.apply(func, axis=axis)
+
     def idxmin(self, axis=0, skipna=True):
         """
         Return index of first occurrence of minimum over requested axis.

pandas/core/groupby.py

@@ -3899,6 +3899,21 @@ def count(self):
 
         return self._wrap_agged_blocks(data.items, list(blk))
 
+    def nunique(self, dropna=True):
+        """
+        Return Series with number of distinct observations per group.
+
+        .. versionadded:: 0.20.0
+
+        Parameters
+        ----------
+        dropna : boolean, default True
+            Don't include NaN in the counts.
+        """
+        from functools import partial
+        func = partial(Series.nunique, dropna=dropna)
+        return self.apply(lambda g: g.apply(func))
+
 
 from pandas.tools.plotting import boxplot_frame_groupby  # noqa
 DataFrameGroupBy.boxplot = boxplot_frame_groupby

pandas/tests/frame/test_analytics.py

@@ -410,6 +410,11 @@ def test_count(self):
         expected = Series(0, index=[])
         tm.assert_series_equal(result, expected)
 
+    def test_nunique(self):
+        f = lambda s: len(nanops.unique1d(s.dropna()))
+        self._check_stat_op('nunique', f, has_skipna=False,
+                            check_dtype=False, check_dates=True)
+
     def test_sum(self):
         self._check_stat_op('sum', np.sum, has_numeric_only=True)
 

pandas/tests/groupby/test_groupby.py

@@ -2800,6 +2800,16 @@ def test_count_cross_type(self):  # GH8169
             result = df.groupby(['c', 'd']).count()
             tm.assert_frame_equal(result, expected)
 
+    def test_nunique(self):
+        df = DataFrame({
+            'A': list('abbacc'),
+            'B': list('abxacc'),
+            'C': list('abbacx'),
+        })
+        expected = DataFrame({'A': [1] * 3, 'B': [1, 2, 1], 'C': [1, 1, 2]})
+        result = df.groupby('A', as_index=False).nunique()
+        tm.assert_frame_equal(result, expected)
+
     def test_non_cython_api(self):
 
         # GH5610
@@ -5150,11 +5160,11 @@ def test_tab_completion(self):
              'first', 'get_group', 'groups', 'hist', 'indices', 'last', 'max',
              'mean', 'median', 'min', 'name', 'ngroups', 'nth', 'ohlc', 'plot',
              'prod', 'size', 'std', 'sum', 'transform', 'var', 'sem', 'count',
-             'head', 'irow', 'describe', 'cummax', 'quantile', 'rank',
-             'cumprod', 'tail', 'resample', 'cummin', 'fillna', 'cumsum',
-             'cumcount', 'all', 'shift', 'skew', 'bfill', 'ffill', 'take',
-             'tshift', 'pct_change', 'any', 'mad', 'corr', 'corrwith', 'cov',
-             'dtypes', 'ndim', 'diff', 'idxmax', 'idxmin',
+             'nunique', 'head', 'irow', 'describe', 'cummax', 'quantile',
+             'rank', 'cumprod', 'tail', 'resample', 'cummin', 'fillna',
+             'cumsum', 'cumcount', 'all', 'shift', 'skew', 'bfill', 'ffill',
+             'take', 'tshift', 'pct_change', 'any', 'mad', 'corr', 'corrwith',
+             'cov', 'dtypes', 'ndim', 'diff', 'idxmax', 'idxmin',
              'ffill', 'bfill', 'pad', 'backfill', 'rolling', 'expanding'])
         self.assertEqual(results, expected)