BUG: let formatters be list in DataFrame.to_string, too. close #2520

Author: wesm

RELEASE.rst

@@ -230,6 +230,7 @@ pandas 0.10.0
   - Union of empty DataFrames now return empty with concatenated index (GH2307_)
   - DataFrame.sort_index raises more helpful exception if sorting by column
     with duplicates (GH2488_)
+  - DataFrame.to_string formatters can be list, too (GH2520_)
 
 .. _GH407: https://github.com/pydata/pandas/issues/407
 .. _GH821: https://github.com/pydata/pandas/issues/821
@@ -343,6 +344,7 @@ pandas 0.10.0
 .. _GH2133: https://github.com/pydata/pandas/issues/2133
 .. _GH2307: https://github.com/pydata/pandas/issues/2307
 .. _GH2488: https://github.com/pydata/pandas/issues/2488
+.. _GH2520: https://github.com/pydata/pandas/issues/2520
 
 
 pandas 0.9.1

pandas/core/format.py

@@ -40,7 +40,8 @@
         string representation of NAN to use, default 'NaN'
     formatters : list or dict of one-parameter functions, optional
         formatter functions to apply to columns' elements by position or name,
-        default None, if the result is a string , it must be a unicode string.
+        default None, if the result is a string , it must be a unicode
+        string. List must be of length equal to the number of columns.
     float_format : one-parameter function, optional
         formatter function to apply to columns' elements if they are floats
         default None
@@ -170,8 +171,22 @@ def _strlen(x):
 
     return _strlen
 
+class TableFormatter(object):
 
-class DataFrameFormatter(object):
+
+    def _get_formatter(self, i):
+        if isinstance(self.formatters, (list, tuple)):
+            if com.is_integer(i):
+                return self.formatters[i]
+            else:
+                return None
+        else:
+            if com.is_integer(i) and i not in self.columns:
+                i = self.columns[i]
+            return self.formatters.get(i, None)
+
+
+class DataFrameFormatter(TableFormatter):
     """
     Render a DataFrame
 
@@ -361,8 +376,7 @@ def to_latex(self, force_unicode=None, column_format=None):
         self.buf.write('\\end{tabular}\n')
 
     def _format_col(self, i):
-        col = self.columns[i]
-        formatter = self.formatters.get(col)
+        formatter = self._get_formatter(i)
         return format_array(self.frame.icol(i).values, formatter,
                             float_format=self.float_format,
                             na_rep=self.na_rep,
@@ -399,9 +413,10 @@ def is_numeric_dtype(dtype):
             dtypes = self.frame.dtypes
             need_leadsp = dict(zip(fmt_columns, map(is_numeric_dtype, dtypes)))
             str_columns = [[' ' + x
-                            if col not in self.formatters and need_leadsp[x]
+                            if not self._get_formatter(i) and need_leadsp[x]
                             else x]
-                           for col, x in zip(self.columns, fmt_columns)]
+                           for i, (col, x) in
+                           enumerate(zip(self.columns, fmt_columns))]
 
         if self.show_index_names and self.has_index_names:
             for x in str_columns:
@@ -425,7 +440,8 @@ def _get_formatted_index(self):
         show_index_names = self.show_index_names and self.has_index_names
         show_col_names = (self.show_index_names and self.has_column_names)
 
-        fmt = self.formatters.get('__index__', None)
+        fmt = self._get_formatter('__index__')
+
         if isinstance(index, MultiIndex):
             fmt_index = index.format(sparsify=self.sparsify, adjoin=False,
                                      names=show_index_names,
@@ -457,7 +473,7 @@ def _get_column_name_list(self):
         return names
 
 
-class HTMLFormatter(object):
+class HTMLFormatter(TableFormatter):
 
     indent_delta = 2
 
@@ -656,9 +672,9 @@ def _write_body(self, indent):
     def _write_regular_rows(self, fmt_values, indent):
         ncols = len(self.columns)
 
-        if '__index__' in self.fmt.formatters:
-            f = self.fmt.formatters['__index__']
-            index_values = self.frame.index.map(f)
+        fmt = self.fmt._get_formatter('__index__')
+        if fmt is not None:
+            index_values = self.frame.index.map(fmt)
         else:
             index_values = self.frame.index.format()
 

pandas/tests/test_format.py

@@ -174,13 +174,16 @@ def test_to_string_with_formatters(self):
                         'object': [(1,2), True, False]},
                         columns=['int', 'float', 'object'])
 
-        result = df.to_string(formatters={'int': lambda x: '0x%x' % x,
-                                          'float': lambda x: '[% 4.1f]' % x,
-                                          'object': lambda x: '-%s-' % str(x)})
+        formatters = [('int', lambda x: '0x%x' % x),
+                      ('float', lambda x: '[% 4.1f]' % x),
+                      ('object', lambda x: '-%s-' % str(x))]
+        result = df.to_string(formatters=dict(formatters))
+        result2 = df.to_string(formatters=zip(*formatters)[1])
         self.assertEqual(result, ('  int  float    object\n'
                                   '0 0x1 [ 1.0]  -(1, 2)-\n'
                                   '1 0x2 [ 2.0]    -True-\n'
                                   '2 0x3 [ 3.0]   -False-'))
+        self.assertEqual(result, result2)
 
     def test_to_string_with_formatters_unicode(self):
         df = DataFrame({u'c/\u03c3':[1,2,3]})