Added repr string for Grouper and TimeGrouper

Author: tp

pandas/core/groupby.py

@@ -233,6 +233,10 @@ class Grouper(object):
 
     >>> df.groupby(Grouper(level='date', freq='60s', axis=1))
     """
+    _attributes = collections.OrderedDict((('key', None), ('level', None),
+                                           ('freq', None), ('axis', 0),
+                                           ('sort', False)
+                                           ))
 
     def __new__(cls, *args, **kwargs):
         if kwargs.get('freq') is not None:
@@ -333,6 +337,15 @@ def _set_grouper(self, obj, sort=False):
     def groups(self):
         return self.grouper.groups
 
+    def __repr__(self):
+        defaults = self._attributes
+        sd = self.__dict__
+        attrs = collections.OrderedDict((k, sd[k]) for k, v in defaults.items()
+                                        if k in sd and sd[k] != v)
+        attrs = ", ".join("{}={!r}".format(k, v) for k, v in attrs.items())
+        cls_name = self.__class__.__name__
+        return "{}({})".format(cls_name, attrs)
+
 
 class GroupByPlot(PandasObject):
     """

pandas/core/resample.py

@@ -1,4 +1,5 @@
 from datetime import timedelta
+import collections
 import numpy as np
 import warnings
 import copy
@@ -1021,14 +1022,24 @@ class TimeGrouper(Grouper):
     Use begin, end, nperiods to generate intervals that cannot be derived
     directly from the associated object
     """
+    # _attributes is used in __repr__below
+    _attributes = Grouper._attributes.copy()
+    _attributes.update((('freq', 'Min'), ('closed', None), ('label', None),
+                        ('how', 'mean'), ('nperiods', None), ('axis', 0),
+                        ('fill_method', None), ('limit', None),
+                        ('loffset', None), ('kind', None),
+                        ('convention', None), ('base', 0),
+                        ('convention', 'e'), ('sort', True),
+                        ))
+    _end_types = {'M', 'A', 'Q', 'BM', 'BA', 'BQ', 'W'}
 
     def __init__(self, freq='Min', closed=None, label=None, how='mean',
                  nperiods=None, axis=0,
                  fill_method=None, limit=None, loffset=None, kind=None,
                  convention=None, base=0, **kwargs):
         freq = to_offset(freq)
 
-        end_types = set(['M', 'A', 'Q', 'BM', 'BA', 'BQ', 'W'])
+        end_types = self._end_types
         rule = freq.rule_code
         if (rule in end_types or
                 ('-' in rule and rule[:rule.find('-')] in end_types)):
@@ -1043,6 +1054,7 @@ def __init__(self, freq='Min', closed=None, label=None, how='mean',
                 label = 'left'
 
         self.closed = closed
+        self.freq = freq
         self.label = label
         self.nperiods = nperiods
         self.kind = kind
@@ -1286,6 +1298,25 @@ def _get_period_bins(self, ax):
 
         return binner, bins, labels
 
+    def __repr__(self):
+        defaults = self._attributes.copy()
+        end_types = self._end_types
+        rule = self.freq.rule_code
+        if (rule in end_types or
+                ('-' in rule and rule[:rule.find('-')] in end_types)):
+            defaults.update(closed='right', label='right')
+        else:
+            defaults.update(closed='left', label='left')
+
+        sd = self.__dict__
+        attrs = collections.OrderedDict((k, sd[k]) for k, v in defaults.items()
+                                        if k in sd and sd[k] != v)
+        if 'freq' in attrs:
+            attrs['freq'] = attrs['freq'].freqstr
+        attrs = ", ".join("{}={!r}".format(k, v) for k, v in attrs.items())
+        cls_name = self.__class__.__name__
+        return "{}({})".format(cls_name, attrs)
+
 
 def _take_new_index(obj, indexer, new_index, axis=0):
     from pandas.core.api import Series, DataFrame

pandas/tests/groupby/test_groupby.py

@@ -130,6 +130,17 @@ def test_grouper_index_types(self):
             df.index = list(reversed(df.index.tolist()))
             df.groupby(list('abcde')).apply(lambda x: x)
 
+    def test_grouper_repr(self):
+        # Added in GH17727
+        result = repr(pd.Grouper(key='A'))
+        assert result == "Grouper(key='A')"
+
+        result = repr(pd.Grouper(key='key', freq='50Min', label='right'))
+        cls_name_result, attrib_result = result.split('(')
+        attrib_result = set(attrib_result.rstrip(')').split(', '))
+        assert cls_name_result == 'TimeGrouper'
+        assert attrib_result == {"key='key'", "label='right'", "freq='50T'"}
+
     def test_grouper_multilevel_freq(self):
 
         # GH 7885

pandas/tests/test_resample.py

@@ -3157,6 +3157,14 @@ def setup_method(self, method):
         self.ts = Series(np.random.randn(1000),
                          index=date_range('1/1/2000', periods=1000))
 
+    def test_timegrouper_repr(self):
+        # Added in GH17727
+        result = repr(TimeGrouper(key='key', freq='50Min', label='right'))
+        cls_name_result, attrib_result = result.split('(')
+        attrib_result = set(attrib_result.rstrip(')').split(', '))
+        assert cls_name_result == 'TimeGrouper'
+        assert attrib_result == {"key='key'", "label='right'", "freq='50T'"}
+
     def test_apply(self):
         with tm.assert_produces_warning(FutureWarning,
                                         check_stacklevel=False):