Merge pull request #9209 from mortada/numeric_only

added mising numeric_only option for DataFrame.std/var/sem

Author: jreback

doc/source/whatsnew/v0.16.0.txt

@@ -620,3 +620,5 @@ Bug Fixes
 - Fixed bug with reading CSV files from Amazon S3 on python 3 raising a TypeError (:issue:`9452`)
 - Bug in the Google BigQuery reader where the 'jobComplete' key may be present but False in the query results (:issue:`8728`)
 - Bug in ``Series.values_counts`` with excluding ``NaN`` for categorical type ``Series`` with ``dropna=True`` (:issue:`9443`)
+
+- Fixed mising numeric_only option for ``DataFrame.std/var/sem`` (:issue:`9201`)

pandas/core/generic.py

@@ -4093,7 +4093,7 @@ def _make_stat_function_ddof(name, desc, f):
             @Substitution(outname=name, desc=desc)
             @Appender(_num_doc)
             def stat_func(self, axis=None, skipna=None, level=None, ddof=1,
-                          **kwargs):
+                          numeric_only=None, **kwargs):
                 if skipna is None:
                     skipna = True
                 if axis is None:
@@ -4102,6 +4102,7 @@ def stat_func(self, axis=None, skipna=None, level=None, ddof=1,
                     return self._agg_by_level(name, axis=axis, level=level,
                                               skipna=skipna, ddof=ddof)
                 return self._reduce(f, name, axis=axis,
+                                    numeric_only=numeric_only,
                                     skipna=skipna, ddof=ddof)
             stat_func.__name__ = name
             return stat_func

pandas/core/nanops.py

@@ -332,7 +332,7 @@ def _get_counts_nanvar(mask, axis, ddof):
 def _nanvar(values, axis=None, skipna=True, ddof=1):
     # private nanvar calculator
     mask = isnull(values)
-    if not is_floating_dtype(values):
+    if is_any_int_dtype(values):
         values = values.astype('f8')
 
     count, d = _get_counts_nanvar(mask, axis, ddof)

pandas/tests/test_frame.py

@@ -11503,6 +11503,32 @@ def test_var_std(self):
             self.assertFalse((result < 0).any())
             nanops._USE_BOTTLENECK = True
 
+    def test_numeric_only_flag(self):
+        # GH #9201
+        methods = ['sem', 'var', 'std']
+        df1 = DataFrame(np.random.randn(5, 3), columns=['foo', 'bar', 'baz'])
+        # set one entry to a number in str format
+        df1.ix[0, 'foo'] = '100'
+
+        df2 = DataFrame(np.random.randn(5, 3), columns=['foo', 'bar', 'baz'])
+        # set one entry to a non-number str
+        df2.ix[0, 'foo'] = 'a'
+
+        for meth in methods:
+            result = getattr(df1, meth)(axis=1, numeric_only=True)
+            expected = getattr(df1[['bar', 'baz']], meth)(axis=1)
+            assert_series_equal(expected, result)
+
+            result = getattr(df2, meth)(axis=1, numeric_only=True)
+            expected = getattr(df2[['bar', 'baz']], meth)(axis=1)
+            assert_series_equal(expected, result)
+
+            assertRaisesRegexp(TypeError, 'float',
+                               getattr(df1, meth), axis=1, numeric_only=False)
+
+            assertRaisesRegexp(TypeError, 'float',
+                               getattr(df2, meth), axis=1, numeric_only=False)
+
     def test_sem(self):
         alt = lambda x: np.std(x, ddof=1)/np.sqrt(len(x))
         self._check_stat_op('sem', alt)