Python pandas.compat.bytes_to_str() Examples

def get_dividends_yahoo(sid, start, end):
    # Taken from get_data_yahoo in Pandas library and adjust a single parameter to get dividends
    from pandas.compat import StringIO, bytes_to_str
    from pandas.io.common import urlopen

    start, end = pd.to_datetime(start), pd.to_datetime(end)
    url = ('http://ichart.finance.yahoo.com/table.csv?' + 's=%s' % sid +
           '&a=%s' % (start.month - 1) +
           '&b=%s' % start.day +
           '&c=%s' % start.year +
           '&d=%s' % (end.month - 1) +
           '&e=%s' % end.day +
           '&f=%s' % end.year +
           '&g=v' +  # THE CHANGE
           '&ignore=.csv')

    with urlopen(url) as resp:
        lines = resp.read()
    rs = pd.read_csv(StringIO(bytes_to_str(lines)), index_col=0,
                     parse_dates=True, na_values='-')[::-1]
    # Yahoo! Finance sometimes does this awesome thing where they
    # return 2 rows for the most recent business day
    if len(rs) > 2 and rs.index[-1] == rs.index[-2]:  # pragma: no cover
        rs = rs[:-1]
    return rs 

def __next__(self):
        newline = self.mmap.readline()

        # readline returns bytes, not str, in Python 3,
        # but Python's CSV reader expects str, so convert
        # the output to str before continuing
        if compat.PY3:
            newline = compat.bytes_to_str(newline)

        # mmap doesn't raise if reading past the allocated
        # data but instead returns an empty string, so raise
        # if that is returned
        if newline == '':
            raise StopIteration
        return newline 

def __next__(self):
        newline = self.mmap.readline()

        # readline returns bytes, not str, in Python 3,
        # but Python's CSV reader expects str, so convert
        # the output to str before continuing
        if compat.PY3:
            newline = compat.bytes_to_str(newline)

        # mmap doesn't raise if reading past the allocated
        # data but instead returns an empty string, so raise
        # if that is returned
        if newline == '':
            raise StopIteration
        return newline 

def read_clipboard(**kwargs):  # pragma: no cover
    """
    Read text from clipboard and pass to read_table. See read_table for the
    full argument list

    If unspecified, `sep` defaults to '\s+'

    Returns
    -------
    parsed : DataFrame
    """
    if kwargs.get('sep') is None and kwargs.get('delim_whitespace') is None:
        kwargs['sep'] = '\s+'
    from pandas.util.clipboard import clipboard_get
    from pandas.io.parsers import read_table
    text = clipboard_get()

    # try to decode (if needed on PY3)
    if compat.PY3:
        try:
            text = compat.bytes_to_str(
                text, encoding=(kwargs.get('encoding') or
                                get_option('display.encoding'))
            )
        except:
            pass
    return read_table(StringIO(text), **kwargs) 

def __next__(self):
        newline = self.mmap.readline()

        # readline returns bytes, not str, in Python 3,
        # but Python's CSV reader expects str, so convert
        # the output to str before continuing
        if compat.PY3:
            newline = compat.bytes_to_str(newline)

        # mmap doesn't raise if reading past the allocated
        # data but instead returns an empty string, so raise
        # if that is returned
        if newline == '':
            raise StopIteration
        return newline 

def __next__(self):
        newline = self.mmap.readline()

        # readline returns bytes, not str, in Python 3,
        # but Python's CSV reader expects str, so convert
        # the output to str before continuing
        if compat.PY3:
            newline = compat.bytes_to_str(newline)

        # mmap doesn't raise if reading past the allocated
        # data but instead returns an empty string, so raise
        # if that is returned
        if newline == '':
            raise StopIteration
        return newline 

def __next__(self):
        newline = self.mmap.readline()

        # readline returns bytes, not str, in Python 3,
        # but Python's CSV reader expects str, so convert
        # the output to str before continuing
        if compat.PY3:
            newline = compat.bytes_to_str(newline)

        # mmap doesn't raise if reading past the allocated
        # data but instead returns an empty string, so raise
        # if that is returned
        if newline == '':
            raise StopIteration
        return newline 

def read_clipboard(sep='\s+', **kwargs):  # pragma: no cover
    r"""
    Read text from clipboard and pass to read_table. See read_table for the
    full argument list

    Parameters
    ----------
    sep : str, default '\s+'.
        A string or regex delimiter. The default of '\s+' denotes
        one or more whitespace characters.

    Returns
    -------
    parsed : DataFrame
    """
    encoding = kwargs.pop('encoding', 'utf-8')

    # only utf-8 is valid for passed value because that's what clipboard
    # supports
    if encoding is not None and encoding.lower().replace('-', '') != 'utf8':
        raise NotImplementedError(
            'reading from clipboard only supports utf-8 encoding')

    from pandas.io.clipboard import clipboard_get
    from pandas.io.parsers import read_table
    text = clipboard_get()

    # try to decode (if needed on PY3)
    # Strange. linux py33 doesn't complain, win py33 does
    if compat.PY3:
        try:
            text = compat.bytes_to_str(
                text, encoding=(kwargs.get('encoding') or
                                get_option('display.encoding'))
            )
        except:
            pass

    # Excel copies into clipboard with \t separation
    # inspect no more then the 10 first lines, if they
    # all contain an equal number (>0) of tabs, infer
    # that this came from excel and set 'sep' accordingly
    lines = text[:10000].split('\n')[:-1][:10]

    # Need to remove leading white space, since read_table
    # accepts:
    #    a  b
    # 0  1  2
    # 1  3  4

    counts = set([x.lstrip().count('\t') for x in lines])
    if len(lines) > 1 and len(counts) == 1 and counts.pop() != 0:
        sep = '\t'

    if sep is None and kwargs.get('delim_whitespace') is None:
        sep = '\s+'

    return read_table(StringIO(text), sep=sep, **kwargs) 

def read_clipboard(sep='\s+', **kwargs):  # pragma: no cover
    r"""
    Read text from clipboard and pass to read_table. See read_table for the
    full argument list

    Parameters
    ----------
    sep : str, default '\s+'.
        A string or regex delimiter. The default of '\s+' denotes
        one or more whitespace characters.

    Returns
    -------
    parsed : DataFrame
    """
    encoding = kwargs.pop('encoding', 'utf-8')

    # only utf-8 is valid for passed value because that's what clipboard
    # supports
    if encoding is not None and encoding.lower().replace('-', '') != 'utf8':
        raise NotImplementedError(
            'reading from clipboard only supports utf-8 encoding')

    from pandas.io.clipboard import clipboard_get
    from pandas.io.parsers import read_table
    text = clipboard_get()

    # try to decode (if needed on PY3)
    # Strange. linux py33 doesn't complain, win py33 does
    if compat.PY3:
        try:
            text = compat.bytes_to_str(
                text, encoding=(kwargs.get('encoding') or
                                get_option('display.encoding'))
            )
        except:
            pass

    # Excel copies into clipboard with \t separation
    # inspect no more then the 10 first lines, if they
    # all contain an equal number (>0) of tabs, infer
    # that this came from excel and set 'sep' accordingly
    lines = text[:10000].split('\n')[:-1][:10]

    # Need to remove leading white space, since read_table
    # accepts:
    #    a  b
    # 0  1  2
    # 1  3  4

    counts = set([x.lstrip().count('\t') for x in lines])
    if len(lines) > 1 and len(counts) == 1 and counts.pop() != 0:
        sep = '\t'

    if sep is None and kwargs.get('delim_whitespace') is None:
        sep = '\s+'

    return read_table(StringIO(text), sep=sep, **kwargs)