adding ddof parameter back into std and var

Author: Chang She

pandas/core/frame.py

@@ -3585,21 +3585,21 @@ def mad(self, axis=0, skipna=True, level=None):
     @Substitution(name='unbiased variance', shortname='var',
                   na_action=_doc_exclude_na, extras='')
     @Appender(_stat_doc)
-    def var(self, axis=0, skipna=True, level=None):
+    def var(self, axis=0, skipna=True, level=None, ddof=1):
         if level is not None:
             return self._agg_by_level('var', axis=axis, level=level,
                                       skipna=skipna)
         return self._reduce(nanops.nanvar, axis=axis, skipna=skipna,
-                            numeric_only=None)
+                            numeric_only=None, ddof=ddof)
 
     @Substitution(name='unbiased standard deviation', shortname='std',
                   na_action=_doc_exclude_na, extras='')
     @Appender(_stat_doc)
-    def std(self, axis=0, skipna=True, level=None):
+    def std(self, axis=0, skipna=True, level=None, ddof=1):
         if level is not None:
             return self._agg_by_level('std', axis=axis, level=level,
                                       skipna=skipna)
-        return np.sqrt(self.var(axis=axis, skipna=skipna))
+        return np.sqrt(self.var(axis=axis, skipna=skipna, ddof=ddof))
 
     @Substitution(name='unbiased skewness', shortname='skew',
                   na_action=_doc_exclude_na, extras='')
@@ -3619,8 +3619,8 @@ def _agg_by_level(self, name, axis=0, level=0, skipna=True):
         applyf = lambda x: method(x, axis=axis, skipna=skipna)
         return grouped.aggregate(applyf)
 
-    def _reduce(self, op, axis=0, skipna=True, numeric_only=None):
-        f = lambda x: op(x, axis=axis, skipna=skipna)
+    def _reduce(self, op, axis=0, skipna=True, numeric_only=None, **kwds):
+        f = lambda x: op(x, axis=axis, skipna=skipna, **kwds)
         labels = self._get_agg_axis(axis)
         if numeric_only is None:
             try:

pandas/core/nanops.py

@@ -17,7 +17,10 @@ def _bottleneck_switch(bn_name, alt, zero_value=None, **kwargs):
         bn_func = getattr(bn, bn_name)
     except (AttributeError, NameError):  # pragma: no cover
         bn_func = None
-    def f(values, axis=None, skipna=True):
+    def f(values, axis=None, skipna=True, **kwds):
+        if len(kwargs) > 0:
+            for k, v in kwargs.iteritems():
+                kwds[k] = v
         try:
             if zero_value is not None and values.size == 0:
                 if values.ndim == 1:
@@ -29,14 +32,14 @@ def f(values, axis=None, skipna=True):
                     return result
 
             if _USE_BOTTLENECK and skipna and values.dtype != np.object_:
-                result = bn_func(values, axis=axis, **kwargs)
+                result = bn_func(values, axis=axis, **kwds)
                 # prefer to treat inf/-inf as NA
                 if _has_infs(result):
-                    result = alt(values, axis=axis, skipna=skipna, **kwargs)
+                    result = alt(values, axis=axis, skipna=skipna, **kwds)
             else:
-                result = alt(values, axis=axis, skipna=skipna, **kwargs)
+                result = alt(values, axis=axis, skipna=skipna, **kwds)
         except Exception:
-            result = alt(values, axis=axis, skipna=skipna, **kwargs)
+            result = alt(values, axis=axis, skipna=skipna, **kwds)
 
         return result
 
@@ -180,7 +183,7 @@ def nanargmin(values, axis=None, skipna=True):
 nansum = _bottleneck_switch('nansum', _nansum, zero_value=0)
 nanmean = _bottleneck_switch('nanmean', _nanmean)
 nanmedian = _bottleneck_switch('nanmedian', _nanmedian)
-nanvar = _bottleneck_switch('nanvar', _nanvar, ddof=1)
+nanvar = _bottleneck_switch('nanvar', _nanvar)
 nanmin = _bottleneck_switch('nanmin', _nanmin)
 nanmax = _bottleneck_switch('nanmax', _nanmax)
 

pandas/core/series.py

@@ -1012,7 +1012,7 @@ def std(self, axis=None, dtype=None, out=None, ddof=1, skipna=True,
             level=None):
         if level is not None:
             return self._agg_by_level('std', level=level, skipna=skipna)
-        return np.sqrt(nanops.nanvar(self.values, skipna=skipna))
+        return np.sqrt(nanops.nanvar(self.values, skipna=skipna, ddof=ddof))
 
     @Substitution(name='unbiased variance', shortname='var',
                   na_action=_doc_exclude_na, extras='')
@@ -1021,7 +1021,7 @@ def var(self, axis=None, dtype=None, out=None, ddof=1, skipna=True,
             level=None):
         if level is not None:
             return self._agg_by_level('var', level=level, skipna=skipna)
-        return nanops.nanvar(self.values, skipna=skipna)
+        return nanops.nanvar(self.values, skipna=skipna, ddof=ddof)
 
     @Substitution(name='unbiased skewness', shortname='skew',
                   na_action=_doc_exclude_na, extras='')