pandas.read_csv from string or package data

Viewed 60226

I have some csv text data in a package which I want to read using read_csv. I was doing this by

from pkgutil import get_data
from StringIO import StringIO

data = read_csv(StringIO(get_data('package.subpackage', 'path/to/data.csv')))

However, StringIO.StringIO disappears in Python 3, and io.StringIO only accepts Unicode. Is there a simple way to do this?

Edit: the following does not appear to work

import pandas as pd

import pkgutil
from io import StringIO

def get_data_file(pkg, path):
    f = StringIO()
    contents = unicode(pkgutil.get_data('pymc.examples', 'data/wells.dat'))
    f.write(contents)
    return f

wells = get_data_file('pymc.examples', 'data/wells.dat')

data = pd.read_csv(wells, delimiter=' ', index_col='id',
                   dtype={'switch': np.int8})

failing with

  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 401, in parser_f
    return _read(filepath_or_buffer, kwds)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 209, in _read
    parser = TextFileReader(filepath_or_buffer, **kwds)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 509, in __init__
    self._make_engine(self.engine)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 611, in _make_engine
    self._engine = CParserWrapper(self.f, **self.options)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 893, in __init__
    self._reader = _parser.TextReader(src, **kwds)
  File "parser.pyx", line 441, in pandas._parser.TextReader.__cinit__ (pandas/src/parser.c:3940)
  File "parser.pyx", line 551, in pandas._parser.TextReader._get_header (pandas/src/parser.c:5096)
pandas._parser.CParserError: Passed header=0 but only 0 lines in file
2 Answers
Related