def read_csv(
filepath_or_buffer,
sep=",",
header=0,
index_col=None,
names=None,
skiprows=None,
na_values=None,
parse_dates=False,
date_parser=None,
nrows=None,
iterator=False,
chunksize=None,
skip_footer=0,
converters=None,
verbose=False,
delimiter=None,
encoding=None,
):
if hasattr(filepath_or_buffer, "read"):
f = filepath_or_buffer
else:
try:
# universal newline mode
f = com._get_handle(filepath_or_buffer, "U", encoding=encoding)
except Exception: # pragma: no cover
f = com._get_handle(filepath_or_buffer, "r", encoding=encoding)
if delimiter is not None:
sep = delimiter
if date_parser is not None:
parse_dates = True
parser = TextParser(
f,
header=header,
index_col=index_col,
names=names,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
skiprows=skiprows,
delimiter=sep,
chunksize=chunksize,
skip_footer=skip_footer,
converters=converters,
verbose=verbose,
encoding=encoding,
)
if nrows is not None:
return parser.get_chunk(nrows)
elif chunksize or iterator:
return parser
return parser.get_chunk()
def read_csv(filepath_or_buffer,
sep=',',
header=0,
index_col=None,
names=None,
skiprows=None,
na_values=None,
parse_dates=False,
date_parser=None,
nrows=None,
iterator=False,
chunksize=None,
skip_footer=0,
converters=None,
verbose=False,
delimiter=None,
encoding=None):
if hasattr(filepath_or_buffer, 'read'):
f = filepath_or_buffer
else:
try:
# universal newline mode
f = com._get_handle(filepath_or_buffer, 'U', encoding=encoding)
except Exception: # pragma: no cover
f = com._get_handle(filepath_or_buffer, 'r', encoding=encoding)
if delimiter is not None:
sep = delimiter
if date_parser is not None:
parse_dates = True
parser = TextParser(f,
header=header,
index_col=index_col,
names=names,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
skiprows=skiprows,
delimiter=sep,
chunksize=chunksize,
skip_footer=skip_footer,
converters=converters,
verbose=verbose,
encoding=encoding)
if nrows is not None:
return parser.get_chunk(nrows)
elif chunksize or iterator:
return parser
return parser.get_chunk()
def _read(cls, filepath_or_buffer, kwds):
"Generic reader of line files."
encoding = kwds.get("encoding", None)
if isinstance(filepath_or_buffer, str) and _is_url(filepath_or_buffer):
from urllib2 import urlopen
filepath_or_buffer = urlopen(filepath_or_buffer)
if py3compat.PY3: # pragma: no cover
from io import TextIOWrapper
if encoding:
errors = "strict"
else:
errors = "replace"
encoding = "utf-8"
bytes = filepath_or_buffer.read()
filepath_or_buffer = StringIO(bytes.decode(encoding, errors))
if hasattr(filepath_or_buffer, "read"):
f = filepath_or_buffer
else:
try:
# universal newline mode
f = com._get_handle(filepath_or_buffer, "U", encoding=encoding)
except Exception: # pragma: no cover
f = com._get_handle(filepath_or_buffer, "r", encoding=encoding)
if kwds.get("date_parser", None) is not None:
if isinstance(kwds["parse_dates"], bool):
kwds["parse_dates"] = True
# Extract some of the arguments (pass chunksize on).
kwds.pop("filepath_or_buffer")
iterator = kwds.pop("iterator")
nrows = kwds.pop("nrows")
chunksize = kwds.get("chunksize", None)
# Create the parser.
parser = cls(f, **kwds)
if nrows is not None:
return parser.get_chunk(nrows)
elif chunksize or iterator:
return parser
return parser.get_chunk()
def _read(cls, filepath_or_buffer, kwds):
"Generic reader of line files."
encoding = kwds.get('encoding', None)
if isinstance(filepath_or_buffer, str) and _is_url(filepath_or_buffer):
from urllib2 import urlopen
filepath_or_buffer = urlopen(filepath_or_buffer)
if py3compat.PY3: # pragma: no cover
from io import TextIOWrapper
if encoding:
errors = 'strict'
else:
errors = 'replace'
encoding = 'utf-8'
bytes = filepath_or_buffer.read()
filepath_or_buffer = StringIO(bytes.decode(encoding, errors))
if hasattr(filepath_or_buffer, 'read'):
f = filepath_or_buffer
else:
try:
# universal newline mode
f = com._get_handle(filepath_or_buffer, 'U', encoding=encoding)
except Exception: # pragma: no cover
f = com._get_handle(filepath_or_buffer, 'r', encoding=encoding)
if kwds.get('date_parser', None) is not None:
if isinstance(kwds['parse_dates'], bool):
kwds['parse_dates'] = True
# Extract some of the arguments (pass chunksize on).
kwds.pop('filepath_or_buffer')
iterator = kwds.pop('iterator')
nrows = kwds.pop('nrows')
chunksize = kwds.get('chunksize', None)
# Create the parser.
parser = cls(f, **kwds)
if nrows is not None:
return parser.get_chunk(nrows)
elif chunksize or iterator:
return parser
return parser.get_chunk()
def _read(cls, filepath_or_buffer, kwds):
"Generic reader of line files."
encoding = kwds.get('encoding', None)
if isinstance(filepath_or_buffer, str) and _is_url(filepath_or_buffer):
from urllib2 import urlopen
filepath_or_buffer = urlopen(filepath_or_buffer)
if py3compat.PY3: # pragma: no cover
from io import TextIOWrapper
if encoding:
errors = 'strict'
else:
errors = 'replace'
encoding = 'utf-8'
bytes = filepath_or_buffer.read()
filepath_or_buffer = StringIO(bytes.decode(encoding, errors))
if hasattr(filepath_or_buffer, 'read'):
f = filepath_or_buffer
else:
try:
# universal newline mode
f = com._get_handle(filepath_or_buffer, 'U', encoding=encoding)
except Exception: # pragma: no cover
f = com._get_handle(filepath_or_buffer, 'r', encoding=encoding)
if kwds.get('date_parser', None) is not None:
if isinstance(kwds['parse_dates'], bool):
kwds['parse_dates'] = True
# Extract some of the arguments (pass chunksize on).
kwds.pop('filepath_or_buffer')
iterator = kwds.pop('iterator')
nrows = kwds.pop('nrows')
chunksize = kwds.get('chunksize', None)
# Create the parser.
parser = cls(f, **kwds)
if nrows is not None:
return parser.get_chunk(nrows)
elif chunksize or iterator:
return parser
return parser.get_chunk()
def my_to_csv(self, path_or_buf, sep=",", na_rep='', float_format=None,
cols=None, header=True, index=True, index_label=None,
mode='w', nanRep=None, encoding=None, quoting=None,
line_terminator='\n', write_dtypes=None):
"""
Write DataFrame to a comma-separated values (csv) file
Parameters
----------
path_or_buf : string or file handle / StringIO
File path
sep : character, default ","
Field delimiter for the output file.
na_rep : string, default ''
Missing data representation
float_format : string, default None
Format string for floating point numbers
cols : sequence, optional
Columns to write
header : boolean or list of string, default True
Write out column names. If a list of string is given it is
assumed to be aliases for the column names
index : boolean, default True
Write row names (index)
index_label : string or sequence, or False, default None
Column label for index column(s) if desired. If None is given, and
`header` and `index` are True, then the index names are used. A
sequence should be given if the DataFrame uses MultiIndex. If
False do not print fields for index names. Use index_label=False
for easier importing in R
nanRep : deprecated, use na_rep
mode : Python write mode, default 'w'
encoding : string, optional
a string representing the encoding to use if the contents are
non-ascii, for python versions prior to 3
line_terminator: string, default '\n'
The newline character or character sequence to use in the output
file
quoting : optional constant from csv module
defaults to csv.QUOTE_MINIMAL
"""
if nanRep is not None: # pragma: no cover
import warnings
warnings.warn("nanRep is deprecated, use na_rep",
FutureWarning)
na_rep = nanRep
if hasattr(path_or_buf, 'read'):
f = path_or_buf
close = False
else:
f = com._get_handle(path_or_buf, mode, encoding=encoding)
close = True
if quoting is None:
quoting = csv.QUOTE_MINIMAL
try:
if encoding is not None:
csvout = com.UnicodeWriter(f, lineterminator=line_terminator,
delimiter=sep, encoding=encoding,
quoting=quoting)
else:
csvout = csv.writer(f, lineterminator=line_terminator,
delimiter=sep, quoting=quoting)
self._helper_csv(csvout, na_rep=na_rep,
float_format=float_format, cols=cols,
header=header, index=index,
index_label=index_label, write_dtypes=write_dtypes)
finally:
if close:
f.close()
