Merge pull request #7974 from dsm054/allow_nameless_callables

BUG: Allow __name__less callables as groupby hows (GH7929)

Author: jreback

doc/source/v0.15.0.txt

@@ -389,9 +389,8 @@ Bug Fixes
 - Bug in ``GroupBy.transform()`` where int groups with a transform that
   didn't preserve the index were incorrectly truncated (:issue:`7972`).
 
-
-
-
+- Bug in ``groupby`` where callable objects without name attributes would take the wrong path,
+  and produce a ``DataFrame`` instead of a ``Series`` (:issue:`7929`)
 
 
 - Bug in ``read_html`` where the ``infer_types`` argument forced coercion of

pandas/core/common.py

@@ -9,6 +9,7 @@
 import csv
 import types
 from datetime import datetime, timedelta
+from functools import partial
 
 from numpy.lib.format import read_array, write_array
 import numpy as np
@@ -2432,7 +2433,22 @@ def _is_sequence(x):
     except (TypeError, AttributeError):
         return False
 
-
+def _get_callable_name(obj):
+    # typical case has name
+    if hasattr(obj, '__name__'):
+        return getattr(obj, '__name__')
+    # some objects don't; could recurse
+    if isinstance(obj, partial):
+        return _get_callable_name(obj.func)
+    # fall back to class name
+    if hasattr(obj, '__call__'):
+        return obj.__class__.__name__
+    # everything failed (probably because the argument
+    # wasn't actually callable); we return None
+    # instead of the empty string in this case to allow
+    # distinguishing between no name and a name of ''
+    return None
+    
 _string_dtypes = frozenset(map(_get_dtype_from_object, (compat.binary_type,
                                                         compat.text_type)))
 

pandas/core/groupby.py

@@ -1221,7 +1221,8 @@ def apply(self, f, data, axis=0):
         group_keys = self._get_group_keys()
 
         # oh boy
-        if (f.__name__ not in _plotting_methods and
+        f_name = com._get_callable_name(f)
+        if (f_name not in _plotting_methods and
                 hasattr(splitter, 'fast_apply') and axis == 0):
             try:
                 values, mutated = splitter.fast_apply(f, group_keys)
@@ -2185,11 +2186,11 @@ def _aggregate_multiple_funcs(self, arg):
                 if isinstance(f, compat.string_types):
                     columns.append(f)
                 else:
-                    columns.append(f.__name__)
+                    # protect against callables without names
+                    columns.append(com._get_callable_name(f))
             arg = lzip(columns, arg)
 
         results = {}
-
         for name, func in arg:
             if name in results:
                 raise SpecificationError('Function names must be unique, '

pandas/tests/test_common.py

@@ -38,6 +38,26 @@ def __getitem__(self):
 
     assert(not is_seq(A()))
 
+def test_get_callable_name():
+    from functools import partial
+    getname = com._get_callable_name
+
+    def fn(x): 
+        return x
+    lambda_ = lambda x: x
+    part1 = partial(fn)
+    part2 = partial(part1)
+    class somecall(object):
+        def __call__(self):
+            return x
+
+    assert getname(fn) == 'fn'
+    assert getname(lambda_)
+    assert getname(part1) == 'fn'
+    assert getname(part2) == 'fn'
+    assert getname(somecall()) == 'somecall'
+    assert getname(1) is None
+
 
 def test_notnull():
     assert notnull(1.)

pandas/tests/test_groupby.py

@@ -25,6 +25,7 @@
 from pandas.core.panel import Panel
 from pandas.tools.merge import concat
 from collections import defaultdict
+from functools import partial
 import pandas.core.common as com
 import numpy as np
 
@@ -2910,6 +2911,24 @@ def test_multi_function_flexible_mix(self):
         assert_frame_equal(result, expected)
         assert_frame_equal(result2, expected)
 
+    def test_agg_callables(self):
+        # GH 7929
+        df = DataFrame({'foo' : [1,2], 'bar' :[3,4]}).astype(np.int64)
+
+        class fn_class(object):
+            def __call__(self, x):
+                return sum(x)
+
+        equiv_callables = [sum, np.sum,
+                           lambda x: sum(x),
+                           lambda x: x.sum(),
+                           partial(sum), fn_class()]
+        
+        expected = df.groupby("foo").agg(sum)
+        for ecall in equiv_callables:
+            result = df.groupby('foo').agg(ecall)
+            assert_frame_equal(result, expected)
+
     def test_set_group_name(self):
         def f(group):
             assert group.name is not None
@@ -4530,6 +4549,8 @@ def test_transform_doesnt_clobber_ints(self):
         tm.assert_frame_equal(result, expected)
 
 
+
+
 def assert_fp_equal(a, b):
     assert (np.abs(a - b) < 1e-12).all()
 

pandas/tseries/tests/test_resample.py

@@ -1,6 +1,7 @@
 # pylint: disable=E1101
 
 from datetime import datetime, timedelta
+from functools import partial
 
 from pandas.compat import range, lrange, zip, product
 import numpy as np
@@ -140,6 +141,30 @@ def _ohlc(group):
                 exc.args += ('how=%s' % arg,)
                 raise
 
+    def test_resample_how_callables(self):
+        # GH 7929
+        data = np.arange(5, dtype=np.int64)
+        ind = pd.DatetimeIndex(start='2014-01-01', periods=len(data), freq='d')
+        df = pd.DataFrame({"A": data, "B": data}, index=ind)
+        
+        def fn(x, a=1):
+            return str(type(x))
+
+        class fn_class:
+            def __call__(self, x):
+                return str(type(x))
+
+        df_standard = df.resample("M", how=fn)
+        df_lambda = df.resample("M", how=lambda x: str(type(x)))
+        df_partial = df.resample("M", how=partial(fn))
+        df_partial2 = df.resample("M", how=partial(fn, a=2))
+        df_class = df.resample("M", how=fn_class())
+
+        assert_frame_equal(df_standard, df_lambda)
+        assert_frame_equal(df_standard, df_partial)
+        assert_frame_equal(df_standard, df_partial2)
+        assert_frame_equal(df_standard, df_class)
+        
     def test_resample_basic_from_daily(self):
         # from daily
         dti = DatetimeIndex(
@@ -765,6 +790,7 @@ def test_resample_timegrouper(self):
             assert_frame_equal(result, expected)
 
 
+
 def _simple_ts(start, end, freq='D'):
     rng = date_range(start, end, freq=freq)
     return Series(np.random.randn(len(rng)), index=rng)