Description
Please see http://nbviewer.ipython.org/6443825 . Below is an unformatted version.
pandas' read_csv is supposed to handle short rows by filling them with NaN. It does so most of the time. However, if the first row is short and you specify header=None, then you get an error. This happens whether or not you specify column names.
In [20]:
from pandas import DataFrame, read_csv
This works:
In [21]:
mydata='1,2,3\n1,2\n1,2\n'
read_csv(StringIO.StringIO(mydata),header=None,names=['one','two','three'])
Out[21]:
one two three
0 1 2 3
1 1 2 NaN
2 1 2 NaN
But this doesn't:
In [22]:
mydata='1,2\n1,2,3\n4,5,6\n'
read_csv(StringIO.StringIO(mydata),header=None,names=['one','two','three'])
CParserError Traceback (most recent call last)
in ()
1 mydata='1,2\n1,2,3\n4,5,6\n'
----> 2 read_csv(StringIO.StringIO(mydata),header=None,names=['one','two','three'])
/usr/lib/python2.7/dist-packages/pandas/io/parsers.pyc in parser_f(filepath_or_buffer, sep, dialect, compression, doublequote, escapechar, quotechar, quoting, skipinitialspace, lineterminator, header, index_col, names, prefix, skiprows, skipfooter, skip_footer, na_values, true_values, false_values, delimiter, converters, dtype, usecols, engine, delim_whitespace, as_recarray, na_filter, compact_ints, use_unsigned, low_memory, buffer_lines, warn_bad_lines, error_bad_lines, keep_default_na, thousands, comment, decimal, parse_dates, keep_date_col, dayfirst, date_parser, memory_map, nrows, iterator, chunksize, verbose, encoding, squeeze)
397 buffer_lines=buffer_lines)
398
--> 399 return _read(filepath_or_buffer, kwds)
400
401 parser_f.name = name
/usr/lib/python2.7/dist-packages/pandas/io/parsers.pyc in _read(filepath_or_buffer, kwds)
206
207 # Create the parser.
--> 208 parser = TextFileReader(filepath_or_buffer, **kwds)
209
210 if nrows is not None:
/usr/lib/python2.7/dist-packages/pandas/io/parsers.pyc in init(self, f, engine, **kwds)
505 self.options['has_index_names'] = kwds['has_index_names']
506
--> 507 self._make_engine(self.engine)
508
509 def _get_options_with_defaults(self, engine):
/usr/lib/python2.7/dist-packages/pandas/io/parsers.pyc in _make_engine(self, engine)
607 def _make_engine(self, engine='c'):
608 if engine == 'c':
--> 609 self._engine = CParserWrapper(self.f, **self.options)
610 else:
611 if engine == 'python':
/usr/lib/python2.7/dist-packages/pandas/io/parsers.pyc in init(self, src, *_kwds)
888 # #2442
889 kwds['allow_leading_cols'] = self.index_col is not False
--> 890 self._reader = _parser.TextReader(src, *_kwds)
891
892 # XXX
/usr/lib/python2.7/dist-packages/pandas/_parser.so in pandas._parser.TextReader.cinit (pandas/src/parser.c:3946)()
/usr/lib/python2.7/dist-packages/pandas/_parser.so in pandas._parser.TextReader._get_header (pandas/src/parser.c:5628)()
CParserError: Column names have 3 fields, data has 2 fields