ENH: add decimal support in to_csv (GH8448)

remove numpy directory

Reformating internals.py

Test for to_csv decimal separator option

Joris' comments

issue number as comment

Author: bertrandhaut

doc/source/whatsnew/v0.16.0.txt

@@ -62,6 +62,7 @@ New features
 - ``StringMethods.pad()`` and ``center()`` now accept ``fillchar`` option to specify filling character (:issue:`9352`)
 - Added ``StringMethods.zfill()`` which behave as the same as standard ``str`` (:issue:`9387`)
 - Added ``days_in_month`` (compatibility alias ``daysinmonth``) property to ``Timestamp``, ``DatetimeIndex``, ``Period``, ``PeriodIndex``, and ``Series.dt`` (:issue:`9572`)
+- Added ``decimal`` option in ``to_csv`` to provide formatting for non-'.' decimal separators (:issue:`781`)
 
 DataFrame Assign
 ~~~~~~~~~~~~~~~~

pandas/core/format.py

@@ -1173,7 +1173,7 @@ def __init__(self, obj, path_or_buf=None, sep=",", na_rep='', float_format=None,
                  mode='w', nanRep=None, encoding=None, quoting=None,
                  line_terminator='\n', chunksize=None, engine=None,
                  tupleize_cols=False, quotechar='"', date_format=None,
-                 doublequote=True, escapechar=None):
+                 doublequote=True, escapechar=None, decimal='.'):
 
         self.engine = engine  # remove for 0.13
         self.obj = obj
@@ -1185,6 +1185,7 @@ def __init__(self, obj, path_or_buf=None, sep=",", na_rep='', float_format=None,
         self.sep = sep
         self.na_rep = na_rep
         self.float_format = float_format
+        self.decimal = decimal
 
         self.header = header
         self.index = index
@@ -1513,6 +1514,7 @@ def _save_chunk(self, start_i, end_i):
             b = self.blocks[i]
             d = b.to_native_types(slicer=slicer, na_rep=self.na_rep,
                                   float_format=self.float_format,
+                                  decimal=self.decimal,
                                   date_format=self.date_format)
 
             for col_loc, col in zip(b.mgr_locs, d):

pandas/core/frame.py

@@ -1112,7 +1112,7 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
                mode='w', encoding=None, quoting=None,
                quotechar='"', line_terminator='\n', chunksize=None,
                tupleize_cols=False, date_format=None, doublequote=True,
-               escapechar=None, **kwds):
+               escapechar=None, decimal='.', **kwds):
         r"""Write DataFrame to a comma-separated values (csv) file
 
         Parameters
@@ -1164,6 +1164,8 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
             or new (expanded format) if False)
         date_format : string, default None
             Format string for datetime objects
+        decimal: string, default '.'
+            Character recognized as decimal separator. E.g. use ',' for European data
         """
 
         formatter = fmt.CSVFormatter(self, path_or_buf,
@@ -1178,7 +1180,8 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
                                      tupleize_cols=tupleize_cols,
                                      date_format=date_format,
                                      doublequote=doublequote,
-                                     escapechar=escapechar)
+                                     escapechar=escapechar,
+                                     decimal=decimal)
         formatter.save()
 
         if path_or_buf is None:

pandas/core/internals.py

@@ -1219,7 +1219,7 @@ def _try_cast(self, element):
         except:  # pragma: no cover
             return element
 
-    def to_native_types(self, slicer=None, na_rep='', float_format=None,
+    def to_native_types(self, slicer=None, na_rep='', float_format=None, decimal='.',
                         **kwargs):
         """ convert to our native types format, slicing if desired """
 
@@ -1229,10 +1229,22 @@ def to_native_types(self, slicer=None, na_rep='', float_format=None,
         values = np.array(values, dtype=object)
         mask = isnull(values)
         values[mask] = na_rep
-        if float_format:
+        
+        
+        if float_format and decimal != '.':
+            formatter = lambda v : (float_format % v).replace('.',decimal,1)
+        elif decimal != '.':
+            formatter = lambda v : ('%g' % v).replace('.',decimal,1)
+        elif float_format:
+            formatter = lambda v : float_format % v
+        else:
+            formatter = None
+            
+        if formatter:
             imask = (~mask).ravel()
             values.flat[imask] = np.array(
-                [float_format % val for val in values.ravel()[imask]])
+                [formatter(val) for val in values.ravel()[imask]])
+        
         return values.tolist()
 
     def should_store(self, value):

pandas/core/series.py

@@ -2325,7 +2325,7 @@ def from_csv(cls, path, sep=',', parse_dates=True, header=None,
     def to_csv(self, path, index=True, sep=",", na_rep='',
                float_format=None, header=False,
                index_label=None, mode='w', nanRep=None, encoding=None,
-               date_format=None):
+               date_format=None, decimal='.'):
         """
         Write Series to a comma-separated values (csv) file
 
@@ -2353,14 +2353,16 @@ def to_csv(self, path, index=True, sep=",", na_rep='',
             non-ascii, for python versions prior to 3
         date_format: string, default None
             Format string for datetime objects.
+        decimal: string, default '.'
+            Character recognized as decimal separator. E.g. use ',' for European data
         """
         from pandas.core.frame import DataFrame
         df = DataFrame(self)
         # result is only a string if no path provided, otherwise None
         result = df.to_csv(path, index=index, sep=sep, na_rep=na_rep,
                   float_format=float_format, header=header,
                   index_label=index_label, mode=mode, nanRep=nanRep,
-                  encoding=encoding, date_format=date_format)
+                  encoding=encoding, date_format=date_format, decimal=decimal)
         if path is None:
             return result
 

pandas/tests/test_format.py

@@ -1738,7 +1738,7 @@ def test_to_html_columns_arg(self):
         self.assertNotIn('<th>B</th>', result)
 
     def test_to_html_multiindex(self):
-        columns = MultiIndex.from_tuples(list(zip(np.arange(2).repeat(2), 
+        columns = MultiIndex.from_tuples(list(zip(np.arange(2).repeat(2),
                                                      np.mod(lrange(4), 2))),
                                             names=['CL0', 'CL1'])
         df = DataFrame([list('abcd'), list('efgh')], columns=columns)
@@ -2396,6 +2396,21 @@ def test_csv_to_string(self):
         expected = ',col\n0,1\n1,2\n'
         self.assertEqual(df.to_csv(), expected)
 
+    def test_to_csv_decimal(self):
+        # GH 781
+        df = DataFrame({'col1' : [1], 'col2' : ['a'], 'col3' : [10.1] })
+
+        expected_default = ',col1,col2,col3\n0,1,a,10.1\n'
+        self.assertEqual(df.to_csv(), expected_default)
+
+        expected_european_excel = ';col1;col2;col3\n0;1;a;10,1\n'
+        self.assertEqual(df.to_csv(decimal=',',sep=';'), expected_european_excel)
+
+        expected_float_format_default = ',col1,col2,col3\n0,1,a,10.10\n'
+        self.assertEqual(df.to_csv(float_format = '%.2f'), expected_float_format_default)
+
+        expected_float_format = ';col1;col2;col3\n0;1;a;10,10\n'
+        self.assertEqual(df.to_csv(decimal=',',sep=';', float_format = '%.2f'), expected_float_format)
 
 class TestSeriesFormatting(tm.TestCase):
     _multiprocess_can_split_ = True