Fix To Numeric on Decimal Fields

Author: Roger Thomas

doc/source/whatsnew/v0.20.0.txt

@@ -109,3 +109,5 @@ Performance Improvements
 
 Bug Fixes
 ~~~~~~~~~
+
+- Bug in ``DataFrame(..).apply(to_numeric)`` when values are of type decimal.Decimal. (:issue:`14827`)

pandas/src/inference.pyx

@@ -1,3 +1,4 @@
+from decimal import Decimal
 import sys
 cimport util
 from tslib import NaT, get_timezone
@@ -673,6 +674,9 @@ def maybe_convert_numeric(object[:] values, set na_values,
         elif util.is_complex_object(val):
             complexes[i] = val
             seen_complex = True
+        elif isinstance(val, Decimal):
+            floats[i] = complexes[i] = val
+            seen_float = True
         else:
             try:
                 status = floatify(val, &fval, &maybe_int)

pandas/tools/tests/test_util.py

@@ -2,6 +2,7 @@
 import locale
 import codecs
 import nose
+import decimal
 
 import numpy as np
 from numpy import iinfo
@@ -208,6 +209,26 @@ def test_numeric(self):
         res = to_numeric(s)
         tm.assert_series_equal(res, expected)
 
+        # GH 14827
+        df = pd.DataFrame(dict(
+            a=[1.2, decimal.Decimal(3.14), decimal.Decimal("infinity"), '0.1'],
+            b=[1.0, 2.0, 3.0, 4.0],
+        ))
+        expected = pd.DataFrame(dict(
+            a=[1.2, 3.14, np.inf, 0.1],
+            b=[1.0, 2.0, 3.0, 4.0],
+        ))
+
+        # Test to_numeric over one column
+        df_copy = df.copy()
+        df_copy['a'] = df_copy['a'].apply(to_numeric)
+        tm.assert_frame_equal(df_copy, expected)
+
+        # Test to_numeric over multiple columns
+        df_copy = df.copy()
+        df_copy[['a', 'b']] = df_copy[['a', 'b']].apply(to_numeric)
+        tm.assert_frame_equal(df_copy, expected)
+
     def test_all_nan(self):
         s = pd.Series(['a', 'b', 'c'])
         res = to_numeric(s, errors='coerce')

pandas/tools/util.py

@@ -1,3 +1,4 @@
+from decimal import Decimal
 import numpy as np
 import pandas.lib as lib
 
@@ -173,6 +174,8 @@ def to_numeric(arg, errors='raise', downcast=None):
             values = arg.values
     elif isinstance(arg, (list, tuple)):
         values = np.array(arg, dtype='O')
+    elif isinstance(arg, Decimal):
+        return float(arg)
     elif np.isscalar(arg):
         if is_number(arg):
             return arg