ENH: add .ngroup() method to groupby objects (#14026) (#14026)

(cherry picked from commit 72e0d1f)

Author: dsm054

doc/source/api.rst

@@ -1707,6 +1707,7 @@ Computations / Descriptive Stats
    GroupBy.mean
    GroupBy.median
    GroupBy.min
+   GroupBy.ngroup
    GroupBy.nth
    GroupBy.ohlc
    GroupBy.prod

doc/source/groupby.rst

@@ -1122,12 +1122,36 @@ To see the order in which each row appears within its group, use the
 
 .. ipython:: python
 
-   df = pd.DataFrame(list('aaabba'), columns=['A'])
-   df
+   dfg = pd.DataFrame(list('aaabba'), columns=['A'])
+   dfg
+
+   dfg.groupby('A').cumcount()
+
+   dfg.groupby('A').cumcount(ascending=False)
+
+.. _groupby.ngroup:
+
+Enumerate groups
+~~~~~~~~~~~~~~~~
+
+.. versionadded:: 0.20.2
+
+To see the ordering of the groups (as opposed to the order of rows
+within a group given by ``cumcount``) you can use the ``ngroup``
+method.
+
+Note that the numbers given to the groups match the order in which the
+groups would be seen when iterating over the groupby object, not the
+order they are first observed.
+
+.. ipython:: python
 
-   df.groupby('A').cumcount()
+   dfg = pd.DataFrame(list('aaabba'), columns=['A'])
+   dfg
 
-   df.groupby('A').cumcount(ascending=False)  # kwarg only
+   dfg.groupby('A').ngroup()
+
+   dfg.groupby('A').ngroup(ascending=False)
 
 Plotting
 ~~~~~~~~
@@ -1176,14 +1200,41 @@ Regroup columns of a DataFrame according to their sum, and sum the aggregated on
    df
    df.groupby(df.sum(), axis=1).sum()
 
+.. _groupby.multicolumn_factorization
+
+Multi-column factorization
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By using ``.ngroup()``, we can extract information about the groups in
+a way similar to :func:`factorize` (as described further in the
+:ref:`reshaping API <reshaping.factorization>`) but which applies
+naturally to multiple columns of mixed type and different
+sources. This can be useful as an intermediate categorical-like step
+in processing, when the relationships between the group rows are more
+important than their content, or as input to an algorithm which only
+accepts the integer encoding. (For more information about support in
+pandas for full categorical data, see the :ref:`Categorical
+introduction <categorical>` and the
+:ref:`API documentation <api.categorical>`.)
+
+.. ipython:: python
+
+    dfg = pd.DataFrame({"A": [1, 1, 2, 3, 2], "B": list("aaaba")})
+
+    dfg
+
+    dfg.groupby(["A", "B"]).ngroup()
+
+    dfg.groupby(["A", [0, 0, 0, 1, 1]]).ngroup()
+
 Groupby by Indexer to 'resample' data
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Resampling produces new hypothetical samples(resamples) from already existing observed data or from a model that generates data. These new samples are similar to the pre-existing samples.
+Resampling produces new hypothetical samples (resamples) from already existing observed data or from a model that generates data. These new samples are similar to the pre-existing samples.
 
 In order to resample to work on indices that are non-datetimelike , the following procedure can be utilized.
 
-In the following examples, **df.index // 5** returns a binary array which is used to determine what get's selected for the groupby operation.
+In the following examples, **df.index // 5** returns a binary array which is used to determine what gets selected for the groupby operation.
 
 .. note:: The below example shows how we can downsample by consolidation of samples into fewer samples. Here by using **df.index // 5**, we are aggregating the samples in bins. By applying **std()** function, we aggregate the information contained in many samples into a small subset of values which is their standard deviation thereby reducing the number of samples.
 

doc/source/reshaping.rst

@@ -636,7 +636,7 @@ When a column contains only one level, it will be omitted in the result.
 
     pd.get_dummies(df, drop_first=True)
 
-
+.. _reshaping.factorize:
 
 Factorizing values
 ------------------

doc/source/whatsnew/v0.20.2.txt

@@ -23,6 +23,11 @@ Enhancements
 - ``Series`` provides a ``to_latex`` method (:issue:`16180`)
 - Added :attr:`Index.is_strictly_monotonic_increasing` and :attr:`Index.is_strictly_monotonic_decreasing` properties (:issue:`16515`)
 
+- A new groupby method :meth:`~pandas.core.groupby.GroupBy.ngroup`,
+  parallel to the existing :meth:`~pandas.core.groupby.GroupBy.cumcount`,
+  has been added to return the group order (:issue:`11642`); see
+  :ref:`here <groupby.ngroup>`.
+
 .. _whatsnew_0202.performance:
 
 Performance Improvements

pandas/core/groupby.py

@@ -150,7 +150,7 @@
     'last', 'first',
     'head', 'tail', 'median',
     'mean', 'sum', 'min', 'max',
-    'cumcount',
+    'cumcount', 'ngroup',
     'resample',
     'rank', 'quantile',
     'fillna',
@@ -1437,6 +1437,75 @@ def nth(self, n, dropna=None):
 
         return result
 
+    @Substitution(name='groupby')
+    @Appender(_doc_template)
+    def ngroup(self, ascending=True):
+        """
+        Number each group from 0 to the number of groups - 1.
+
+        This is the enumerative complement of cumcount.  Note that the
+        numbers given to the groups match the order in which the groups
+        would be seen when iterating over the groupby object, not the
+        order they are first observed.
+
+        .. versionadded:: 0.20.2
+
+        Parameters
+        ----------
+        ascending : bool, default True
+            If False, number in reverse, from number of group - 1 to 0.
+
+        Examples
+        --------
+
+        >>> df = pd.DataFrame({"A": list("aaabba")})
+        >>> df
+           A
+        0  a
+        1  a
+        2  a
+        3  b
+        4  b
+        5  a
+        >>> df.groupby('A').ngroup()
+        0    0
+        1    0
+        2    0
+        3    1
+        4    1
+        5    0
+        dtype: int64
+        >>> df.groupby('A').ngroup(ascending=False)
+        0    1
+        1    1
+        2    1
+        3    0
+        4    0
+        5    1
+        dtype: int64
+        >>> df.groupby(["A", [1,1,2,3,2,1]]).ngroup()
+        0    0
+        1    0
+        2    1
+        3    3
+        4    2
+        5    0
+        dtype: int64
+
+        See also
+        --------
+        .cumcount : Number the rows in each group.
+
+        """
+
+        self._set_group_selection()
+
+        index = self._selected_obj.index
+        result = Series(self.grouper.group_info[0], index)
+        if not ascending:
+            result = self.ngroups - 1 - result
+        return result
+
     @Substitution(name='groupby')
     @Appender(_doc_template)
     def cumcount(self, ascending=True):
@@ -1481,6 +1550,10 @@ def cumcount(self, ascending=True):
         4    0
         5    0
         dtype: int64
+
+        See also
+        --------
+        .ngroup : Number the groups themselves.
         """
 
         self._set_group_selection()