Merge pull request #6734 from sinhrks/ind_nunique

ENH: added nunique function to Index

Author: jreback

doc/source/api.rst

@@ -348,16 +348,16 @@ Computations / Descriptive Stats
    Series.median
    Series.min
    Series.mode
-   Series.nunique
    Series.pct_change
    Series.prod
    Series.quantile
    Series.rank
    Series.skew
    Series.std
    Series.sum
-   Series.unique
    Series.var
+   Series.unique
+   Series.nunique
    Series.value_counts
 
 Reindexing / Selection / Label manipulation
@@ -1053,6 +1053,8 @@ Modifying and Computations
    Index.repeat
    Index.set_names
    Index.unique
+   Index.nunique
+   Index.value_counts
 
 Conversion
 ~~~~~~~~~~

doc/source/release.rst

@@ -159,6 +159,8 @@ API Changes
 - Arithmetic ops are now disallowed when passed two bool dtype Series or
   DataFrames (:issue:`6762`).
 
+- Added ``nunique`` and ``value_counts`` functions to ``Index`` for counting unique elements. (:issue:`6734`)
+
 Deprecations
 ~~~~~~~~~~~~
 

doc/source/v0.14.0.txt

@@ -199,6 +199,7 @@ API changes
 - ``Series.iteritems()`` is now lazy (returns an iterator rather than a list). This was the documented behavior prior to 0.14. (:issue:`6760`)
 - ``Panel.shift`` now uses ``NDFrame.shift``. It no longer drops the ``nan`` data and retains its original shape.  (:issue:`4867`)
 
+- Added ``nunique`` and ``value_counts`` functions to ``Index`` for counting unique elements. (:issue:`6734`)
 
 MultiIndexing Using Slicers
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~

pandas/core/base.py

@@ -269,6 +269,56 @@ def min(self):
         self._is_allowed_index_op('min')
         return self.values.min()
 
+    def value_counts(self, normalize=False, sort=True, ascending=False,
+                     bins=None):
+        """
+        Returns object containing counts of unique values. The resulting object
+        will be in descending order so that the first element is the most
+        frequently-occurring element. Excludes NA values.
+
+        Parameters
+        ----------
+        normalize : boolean, default False
+            If True then the object returned will contain the relative
+            frequencies of the unique values.
+        sort : boolean, default True
+            Sort by values
+        ascending : boolean, default False
+            Sort in ascending order
+        bins : integer, optional
+            Rather than count values, group them into half-open bins,
+            a convenience for pd.cut, only works with numeric data
+
+        Returns
+        -------
+        counts : Series
+        """
+        from pandas.core.algorithms import value_counts
+        return value_counts(self.values, sort=sort, ascending=ascending,
+                            normalize=normalize, bins=bins)
+
+    def unique(self):
+        """
+        Return array of unique values in the object. Significantly faster than
+        numpy.unique. Includes NA values.
+
+        Returns
+        -------
+        uniques : ndarray
+        """
+        from pandas.core.nanops import unique1d
+        return unique1d(self.values)
+
+    def nunique(self):
+        """
+        Return count of unique elements in the object. Excludes NA values.
+
+        Returns
+        -------
+        nunique : int
+        """
+        return len(self.value_counts())
+
     date = _field_accessor('date','Returns numpy array of datetime.date. The date part of the Timestamps')
     time = _field_accessor('time','Returns numpy array of datetime.time. The time part of the Timestamps')
     year = _field_accessor('year', "The year of the datetime")

pandas/core/index.py

@@ -1102,18 +1102,6 @@ def sym_diff(self, other, result_name=None):
         the_diff = sorted(set((self - other) + (other - self)))
         return Index(the_diff, name=result_name)
 
-    def unique(self):
-        """
-        Return array of unique values in the Index. Significantly faster than
-        numpy.unique
-
-        Returns
-        -------
-        uniques : ndarray
-        """
-        from pandas.core.nanops import unique1d
-        return unique1d(self.values)
-
     def get_loc(self, key):
         """
         Get integer location for requested label

pandas/core/series.py

@@ -1095,34 +1095,6 @@ def count(self, level=None):
 
         return notnull(_values_from_object(self)).sum()
 
-    def value_counts(self, normalize=False, sort=True, ascending=False,
-                     bins=None):
-        """
-        Returns Series containing counts of unique values. The resulting Series
-        will be in descending order so that the first element is the most
-        frequently-occurring element. Excludes NA values
-
-        Parameters
-        ----------
-        normalize : boolean, default False
-            If True then the Series returned will contain the relative
-            frequencies of the unique values.
-        sort : boolean, default True
-            Sort by values
-        ascending : boolean, default False
-            Sort in ascending order
-        bins : integer, optional
-            Rather than count values, group them into half-open bins,
-            a convenience for pd.cut, only works with numeric data
-
-        Returns
-        -------
-        counts : Series
-        """
-        from pandas.core.algorithms import value_counts
-        return value_counts(self.values, sort=sort, ascending=ascending,
-                            normalize=normalize, bins=bins)
-
     def mode(self):
         """Returns the mode(s) of the dataset.
 
@@ -1143,27 +1115,6 @@ def mode(self):
         from pandas.core.algorithms import mode
         return mode(self)
 
-    def unique(self):
-        """
-        Return array of unique values in the Series. Significantly faster than
-        numpy.unique
-
-        Returns
-        -------
-        uniques : ndarray
-        """
-        return nanops.unique1d(self.values)
-
-    def nunique(self):
-        """
-        Return count of unique elements in the Series
-
-        Returns
-        -------
-        nunique : int
-        """
-        return len(self.value_counts())
-
     def drop_duplicates(self, take_last=False, inplace=False):
         """
         Return Series with duplicate values removed