COMPAT: Expand compatibility with fromnumeric.py

Expands compatibility with fromnumeric.py in tslib.pyx and
puts checks in window.py, groupby.py, and resample.py to
ensure that pandas functions such as 'mean' are not called
via the numpy library.

Closes gh-12811.

doc/source/whatsnew/v0.18.2.txt

@@ -46,7 +46,8 @@ API changes
 
 
 - Non-convertible dates in an excel date column will be returned without conversion and the column will be ``object`` dtype, rather than raising an exception  (:issue:`10001`)
-
+- Compatibility with NumPy array methods has been expanded to timestamps (:issue: `12811`)
+- An ``UnsupportedFunctionCall`` error is now raised if groupby or resample functions like ``mean`` are called via NumPy (:issue: `12811`)
 
 .. _whatsnew_0182.api.tolist:
 

pandas/compat/numpy/function.py

@@ -21,7 +21,7 @@
 from numpy import ndarray
 from pandas.util.validators import (validate_args, validate_kwargs,
                                     validate_args_and_kwargs)
-from pandas.core.common import is_integer
+from pandas.core.common import is_integer, UnsupportedFunctionCall
 from pandas.compat import OrderedDict
 
 
@@ -245,3 +245,77 @@ def validate_transpose_for_generic(inst, kwargs):
             msg += " for {klass} instances".format(klass=klass)
 
         raise ValueError(msg)
+
+
+def validate_window_func(name, args, kwargs):
+    numpy_args = ('axis', 'dtype', 'out')
+    msg = ("numpy operations are not "
+           "valid with window objects. "
+           "Use .{func}() directly instead ".format(func=name))
+
+    if len(args) > 0:
+        raise UnsupportedFunctionCall(msg)
+
+    for arg in numpy_args:
+        if arg in kwargs:
+            raise UnsupportedFunctionCall(msg)
+
+
+def validate_rolling_func(name, args, kwargs):
+    numpy_args = ('axis', 'dtype', 'out')
+    msg = ("numpy operations are not "
+           "valid with window objects. "
+           "Use .rolling(...).{func}() instead ".format(func=name))
+
+    if len(args) > 0:
+        raise UnsupportedFunctionCall(msg)
+
+    for arg in numpy_args:
+        if arg in kwargs:
+            raise UnsupportedFunctionCall(msg)
+
+
+def validate_expanding_func(name, args, kwargs):
+    numpy_args = ('axis', 'dtype', 'out')
+    msg = ("numpy operations are not "
+           "valid with window objects. "
+           "Use .expanding(...).{func}() instead ".format(func=name))
+
+    if len(args) > 0:
+        raise UnsupportedFunctionCall(msg)
+
+    for arg in numpy_args:
+        if arg in kwargs:
+            raise UnsupportedFunctionCall(msg)
+
+
+def validate_groupby_func(name, args, kwargs):
+    """
+    'args' and 'kwargs' should be empty because all of
+    their necessary parameters are explicitly listed in
+    the function signature
+    """
+    if len(args) + len(kwargs) > 0:
+        raise UnsupportedFunctionCall((
+            "numpy operations are not valid "
+            "with groupby. Use .groupby(...)."
+            "{func}() instead".format(func=name)))
+
+RESAMPLER_NUMPY_OPS = ('min', 'max', 'sum', 'prod',
+                       'mean', 'std', 'var')
+
+
+def validate_resampler_func(method, args, kwargs):
+    """
+    'args' and 'kwargs' should be empty because all of
+    their necessary parameters are explicitly listed in
+    the function signature
+    """
+    if len(args) + len(kwargs) > 0:
+        if method in RESAMPLER_NUMPY_OPS:
+            raise UnsupportedFunctionCall((
+                "numpy operations are not valid "
+                "with resample. Use .resample(...)."
+                "{func}() instead".format(func=method)))
+        else:
+            raise TypeError("too many arguments passed in")

pandas/core/common.py

@@ -41,6 +41,10 @@ class AmbiguousIndexError(PandasError, KeyError):
     pass
 
 
+class UnsupportedFunctionCall(ValueError):
+    pass
+
+
 class AbstractMethodError(NotImplementedError):
     """Raise this error instead of NotImplementedError for abstract methods
     while keeping compatibility with Python 2 and Python 3.

pandas/core/generic.py

@@ -5299,7 +5299,7 @@ def _make_stat_function(cls, name, name1, name2, axis_descr, desc, f):
     @Appender(_num_doc)
     def stat_func(self, axis=None, skipna=None, level=None, numeric_only=None,
                   **kwargs):
-        nv.validate_stat_func(tuple(), kwargs)
+        nv.validate_stat_func(tuple(), kwargs, fname=name)
         if skipna is None:
             skipna = True
         if axis is None:
@@ -5319,7 +5319,7 @@ def _make_stat_function_ddof(cls, name, name1, name2, axis_descr, desc, f):
     @Appender(_num_ddof_doc)
     def stat_func(self, axis=None, skipna=None, level=None, ddof=1,
                   numeric_only=None, **kwargs):
-        nv.validate_stat_ddof_func(tuple(), kwargs)
+        nv.validate_stat_ddof_func(tuple(), kwargs, fname=name)
         if skipna is None:
             skipna = True
         if axis is None:
@@ -5340,7 +5340,7 @@ def _make_cum_function(cls, name, name1, name2, axis_descr, desc, accum_func,
     @Appender("Return cumulative {0} over requested axis.".format(name) +
               _cnum_doc)
     def cum_func(self, axis=None, dtype=None, out=None, skipna=True, **kwargs):
-        nv.validate_cum_func(tuple(), kwargs)
+        nv.validate_cum_func(tuple(), kwargs, fname=name)
         if axis is None:
             axis = self._stat_axis_number
         else:
@@ -5374,7 +5374,7 @@ def _make_logical_function(cls, name, name1, name2, axis_descr, desc, f):
     @Appender(_bool_doc)
     def logical_func(self, axis=None, bool_only=None, skipna=None, level=None,
                      **kwargs):
-        nv.validate_logical_func(tuple(), kwargs)
+        nv.validate_logical_func(tuple(), kwargs, fname=name)
         if skipna is None:
             skipna = True
         if axis is None:

pandas/core/groupby.py

@@ -11,6 +11,7 @@
     callable, map
 )
 from pandas import compat
+from pandas.compat.numpy import function as nv
 from pandas.compat.numpy import _np_version_under1p8
 from pandas.core.base import (PandasObject, SelectionMixin, GroupByError,
                               DataError, SpecificationError)
@@ -954,12 +955,13 @@ def count(self):
 
     @Substitution(name='groupby')
     @Appender(_doc_template)
-    def mean(self):
+    def mean(self, *args, **kwargs):
         """
         Compute mean of groups, excluding missing values
 
         For multiple groupings, the result index will be a MultiIndex
         """
+        nv.validate_groupby_func('mean', args, kwargs)
         try:
             return self._cython_agg_general('mean')
         except GroupByError:
@@ -993,7 +995,7 @@ def f(x):
 
     @Substitution(name='groupby')
     @Appender(_doc_template)
-    def std(self, ddof=1):
+    def std(self, ddof=1, *args, **kwargs):
         """
         Compute standard deviation of groups, excluding missing values
 
@@ -1005,12 +1007,13 @@ def std(self, ddof=1):
             degrees of freedom
         """
 
-        # todo, implement at cython level?
+        # TODO: implement at Cython level?
+        nv.validate_groupby_func('std', args, kwargs)
         return np.sqrt(self.var(ddof=ddof))
 
     @Substitution(name='groupby')
     @Appender(_doc_template)
-    def var(self, ddof=1):
+    def var(self, ddof=1, *args, **kwargs):
         """
         Compute variance of groups, excluding missing values
 
@@ -1021,7 +1024,7 @@ def var(self, ddof=1):
         ddof : integer, default 1
             degrees of freedom
         """
-
+        nv.validate_groupby_func('var', args, kwargs)
         if ddof == 1:
             return self._cython_agg_general('var')
         else:
@@ -1317,17 +1320,19 @@ def cumcount(self, ascending=True):
 
     @Substitution(name='groupby')
     @Appender(_doc_template)
-    def cumprod(self, axis=0):
+    def cumprod(self, axis=0, *args, **kwargs):
         """Cumulative product for each group"""
+        nv.validate_groupby_func('cumprod', args, kwargs)
         if axis != 0:
             return self.apply(lambda x: x.cumprod(axis=axis))
 
         return self._cython_transform('cumprod')
 
     @Substitution(name='groupby')
     @Appender(_doc_template)
-    def cumsum(self, axis=0):
+    def cumsum(self, axis=0, *args, **kwargs):
         """Cumulative sum for each group"""
+        nv.validate_groupby_func('cumsum', args, kwargs)
         if axis != 0:
             return self.apply(lambda x: x.cumprod(axis=axis))