Python pandas.io.common._stringify_path() Examples

def to_hdf(path_or_buf, key, value, mode=None, complevel=None, complib=None,
           append=None, **kwargs):
    """ store this object, close it if we opened it """

    if append:
        f = lambda store: store.append(key, value, **kwargs)
    else:
        f = lambda store: store.put(key, value, **kwargs)

    path_or_buf = _stringify_path(path_or_buf)
    if isinstance(path_or_buf, string_types):
        with HDFStore(path_or_buf, mode=mode, complevel=complevel,
                      complib=complib) as store:
            f(store)
    else:
        f(path_or_buf) 

def to_hdf(path_or_buf, key, value, mode=None, complevel=None, complib=None,
           append=None, **kwargs):
    """ store this object, close it if we opened it """

    if append:
        f = lambda store: store.append(key, value, **kwargs)
    else:
        f = lambda store: store.put(key, value, **kwargs)

    path_or_buf = _stringify_path(path_or_buf)
    if isinstance(path_or_buf, string_types):
        with HDFStore(path_or_buf, mode=mode, complevel=complevel,
                      complib=complib) as store:
            f(store)
    else:
        f(path_or_buf) 

def to_hdf(path_or_buf, key, value, mode=None, complevel=None, complib=None,
           append=None, **kwargs):
    """ store this object, close it if we opened it """

    if append:
        f = lambda store: store.append(key, value, **kwargs)
    else:
        f = lambda store: store.put(key, value, **kwargs)

    path_or_buf = _stringify_path(path_or_buf)
    if isinstance(path_or_buf, string_types):
        with HDFStore(path_or_buf, mode=mode, complevel=complevel,
                      complib=complib) as store:
            f(store)
    else:
        f(path_or_buf) 

def __init__(self, path, mode=None, complevel=None, complib=None,
                 fletcher32=False, **kwargs):
        try:
            import tables  # noqa
        except ImportError as ex:  # pragma: no cover
            raise ImportError('HDFStore requires PyTables, "{ex}" problem '
                              'importing'.format(ex=str(ex)))

        if complib is not None and complib not in tables.filters.all_complibs:
            raise ValueError(
                "complib only supports {libs} compression.".format(
                    libs=tables.filters.all_complibs))

        if complib is None and complevel is not None:
            complib = tables.filters.default_complib

        self._path = _stringify_path(path)
        if mode is None:
            mode = 'a'
        self._mode = mode
        self._handle = None
        self._complevel = complevel if complevel else 0
        self._complib = complib
        self._fletcher32 = fletcher32
        self._filters = None
        self.open(mode=mode, **kwargs) 

def test_stringify_path_localpath(self):
        path = os.path.join('foo', 'bar')
        abs_path = os.path.abspath(path)
        lpath = LocalPath(path)
        assert icom._stringify_path(lpath) == abs_path 

def test_stringify_path_fspath(self):
        p = CustomFSPath('foo/bar.csv')
        result = icom._stringify_path(p)
        assert result == 'foo/bar.csv' 

def write(self, writer, sheet_name='Sheet1', startrow=0,
              startcol=0, freeze_panes=None, engine=None):
        """
        writer : string or ExcelWriter object
            File path or existing ExcelWriter
        sheet_name : string, default 'Sheet1'
            Name of sheet which will contain DataFrame
        startrow :
            upper left cell row to dump data frame
        startcol :
            upper left cell column to dump data frame
        freeze_panes : tuple of integer (length 2), default None
            Specifies the one-based bottommost row and rightmost column that
            is to be frozen
        engine : string, default None
            write engine to use if writer is a path - you can also set this
            via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``,
            and ``io.excel.xlsm.writer``.
        """
        from pandas.io.excel import ExcelWriter
        from pandas.io.common import _stringify_path

        if isinstance(writer, ExcelWriter):
            need_save = False
        else:
            writer = ExcelWriter(_stringify_path(writer), engine=engine)
            need_save = True

        formatted_cells = self.get_formatted_cells()
        writer.write_cells(formatted_cells, sheet_name,
                           startrow=startrow, startcol=startcol,
                           freeze_panes=freeze_panes)
        if need_save:
            writer.save() 

def __init__(self, path, mode=None, complevel=None, complib=None,
                 fletcher32=False, **kwargs):

        if 'format' in kwargs:
            raise ValueError('format is not a defined argument for HDFStore')

        try:
            import tables  # noqa
        except ImportError as ex:  # pragma: no cover
            raise ImportError('HDFStore requires PyTables, "{ex!s}" problem '
                              'importing'.format(ex=ex))

        if complib is not None and complib not in tables.filters.all_complibs:
            raise ValueError(
                "complib only supports {libs} compression.".format(
                    libs=tables.filters.all_complibs))

        if complib is None and complevel is not None:
            complib = tables.filters.default_complib

        self._path = _stringify_path(path)
        if mode is None:
            mode = 'a'
        self._mode = mode
        self._handle = None
        self._complevel = complevel if complevel else 0
        self._complib = complib
        self._fletcher32 = fletcher32
        self._filters = None
        self.open(mode=mode, **kwargs) 

def read_feather(path, columns=None, use_threads=True):
    """
    Load a feather-format object from the file path

    .. versionadded 0.20.0

    Parameters
    ----------
    path : string file path, or file-like object
    columns : sequence, default None
        If not provided, all columns are read

        .. versionadded 0.24.0
    nthreads : int, default 1
        Number of CPU threads to use when reading to pandas.DataFrame

       .. versionadded 0.21.0
       .. deprecated 0.24.0
    use_threads : bool, default True
        Whether to parallelize reading using multiple threads

       .. versionadded 0.24.0

    Returns
    -------
    type of object stored in file

    """

    feather, pyarrow = _try_import()
    path = _stringify_path(path)

    if LooseVersion(pyarrow.__version__) < LooseVersion('0.11.0'):
        int_use_threads = int(use_threads)
        if int_use_threads < 1:
            int_use_threads = 1
        return feather.read_feather(path, columns=columns,
                                    nthreads=int_use_threads)

    return feather.read_feather(path, columns=columns,
                                use_threads=bool(use_threads)) 

def write(self, writer, sheet_name='Sheet1', startrow=0,
              startcol=0, freeze_panes=None, engine=None):
        """
        writer : string or ExcelWriter object
            File path or existing ExcelWriter
        sheet_name : string, default 'Sheet1'
            Name of sheet which will contain DataFrame
        startrow :
            upper left cell row to dump data frame
        startcol :
            upper left cell column to dump data frame
        freeze_panes : tuple of integer (length 2), default None
            Specifies the one-based bottommost row and rightmost column that
            is to be frozen
        engine : string, default None
            write engine to use if writer is a path - you can also set this
            via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``,
            and ``io.excel.xlsm.writer``.
        """
        from pandas.io.excel import ExcelWriter
        from pandas.io.common import _stringify_path

        if isinstance(writer, ExcelWriter):
            need_save = False
        else:
            writer = ExcelWriter(_stringify_path(writer), engine=engine)
            need_save = True

        formatted_cells = self.get_formatted_cells()
        writer.write_cells(formatted_cells, sheet_name,
                           startrow=startrow, startcol=startcol,
                           freeze_panes=freeze_panes)
        if need_save:
            writer.save() 

def test_stringify_path_localpath(self):
        path = os.path.join('foo', 'bar')
        abs_path = os.path.abspath(path)
        lpath = LocalPath(path)
        assert icom._stringify_path(lpath) == abs_path 

def read_feather(path, nthreads=1):
    """
    Load a feather-format object from the file path

    .. versionadded 0.20.0

    Parameters
    ----------
    path : string file path, or file-like object
    nthreads : int, default 1
        Number of CPU threads to use when reading to pandas.DataFrame

       .. versionadded 0.21.0

    Returns
    -------
    type of object stored in file

    """

    feather = _try_import()
    path = _stringify_path(path)

    if feather.__version__ < LooseVersion('0.4.0'):
        return feather.read_dataframe(path)

    return feather.read_dataframe(path, nthreads=nthreads) 

def test_stringify_path_pathlib(self):
        tm._skip_if_no_pathlib()

        rel_path = common._stringify_path(Path('.'))
        assert rel_path == '.'
        redundant_path = common._stringify_path(Path('foo//bar'))
        assert redundant_path == os.path.join('foo', 'bar') 

def test_stringify_path_localpath(self):
        tm._skip_if_no_localpath()

        path = os.path.join('foo', 'bar')
        abs_path = os.path.abspath(path)
        lpath = LocalPath(path)
        assert common._stringify_path(lpath) == abs_path 

def test_stringify_path_fspath(self):
        p = CustomFSPath('foo/bar.csv')
        result = common._stringify_path(p)
        assert result == 'foo/bar.csv' 

def write(self, writer, sheet_name='Sheet1', startrow=0,
              startcol=0, freeze_panes=None, engine=None):
        """
        writer : string or ExcelWriter object
            File path or existing ExcelWriter
        sheet_name : string, default 'Sheet1'
            Name of sheet which will contain DataFrame
        startrow :
            upper left cell row to dump data frame
        startcol :
            upper left cell column to dump data frame
        freeze_panes : tuple of integer (length 2), default None
            Specifies the one-based bottommost row and rightmost column that
            is to be frozen
        engine : string, default None
            write engine to use if writer is a path - you can also set this
            via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``,
            and ``io.excel.xlsm.writer``.
        """
        from pandas.io.excel import ExcelWriter
        from pandas.io.common import _stringify_path

        if isinstance(writer, ExcelWriter):
            need_save = False
        else:
            writer = ExcelWriter(_stringify_path(writer), engine=engine)
            need_save = True

        formatted_cells = self.get_formatted_cells()
        writer.write_cells(formatted_cells, sheet_name,
                           startrow=startrow, startcol=startcol,
                           freeze_panes=freeze_panes)
        if need_save:
            writer.save() 

def read_feather(path, nthreads=1):
    """
    Load a feather-format object from the file path

    .. versionadded 0.20.0

    Parameters
    ----------
    path : string file path, or file-like object
    nthreads : int, default 1
        Number of CPU threads to use when reading to pandas.DataFrame

       .. versionadded 0.21.0

    Returns
    -------
    type of object stored in file

    """

    feather = _try_import()
    path = _stringify_path(path)

    if feather.__version__ < LooseVersion('0.4.0'):
        return feather.read_dataframe(path)

    return feather.read_dataframe(path, nthreads=nthreads) 

def to_pickle(obj, path, compression='infer', protocol=pkl.HIGHEST_PROTOCOL):
    """
    Pickle (serialize) object to input file path

    Parameters
    ----------
    obj : any object
    path : string
        File path
    compression : {'infer', 'gzip', 'bz2', 'xz', None}, default 'infer'
        a string representing the compression to use in the output file

        .. versionadded:: 0.20.0
    protocol : int
        Int which indicates which protocol should be used by the pickler,
        default HIGHEST_PROTOCOL (see [1], paragraph 12.1.2). The possible
        values for this parameter depend on the version of Python. For Python
        2.x, possible values are 0, 1, 2. For Python>=3.0, 3 is a valid value.
        For Python >= 3.4, 4 is a valid value. A negative value for the
        protocol parameter is equivalent to setting its value to
        HIGHEST_PROTOCOL.

        .. [1] https://docs.python.org/3/library/pickle.html
        .. versionadded:: 0.21.0


    """
    path = _stringify_path(path)
    inferred_compression = _infer_compression(path, compression)
    f, fh = _get_handle(path, 'wb',
                        compression=inferred_compression,
                        is_text=False)
    if protocol < 0:
        protocol = pkl.HIGHEST_PROTOCOL
    try:
        pkl.dump(obj, f, protocol=protocol)
    finally:
        for _f in fh:
            _f.close() 

def read_feather(path, nthreads=1):
    """
    Load a feather-format object from the file path

    .. versionadded 0.20.0

    Parameters
    ----------
    path : string file path, or file-like object
    nthreads : int, default 1
        Number of CPU threads to use when reading to pandas.DataFrame

       .. versionadded 0.21.0

    Returns
    -------
    type of object stored in file

    """

    feather = _try_import()
    path = _stringify_path(path)

    if LooseVersion(feather.__version__) < LooseVersion('0.4.0'):
        return feather.read_dataframe(path)

    return feather.read_dataframe(path, nthreads=nthreads) 

def test_stringify_path_pathlib(self):
        rel_path = icom._stringify_path(Path('.'))
        assert rel_path == '.'
        redundant_path = icom._stringify_path(Path('foo//bar'))
        assert redundant_path == os.path.join('foo', 'bar') 

def test_stringify_path_fspath(self):
        p = CustomFSPath('foo/bar.csv')
        result = icom._stringify_path(p)
        assert result == 'foo/bar.csv' 

def write(self, writer, sheet_name='Sheet1', startrow=0,
              startcol=0, freeze_panes=None, engine=None):
        """
        writer : string or ExcelWriter object
            File path or existing ExcelWriter
        sheet_name : string, default 'Sheet1'
            Name of sheet which will contain DataFrame
        startrow :
            upper left cell row to dump data frame
        startcol :
            upper left cell column to dump data frame
        freeze_panes : tuple of integer (length 2), default None
            Specifies the one-based bottommost row and rightmost column that
            is to be frozen
        engine : string, default None
            write engine to use if writer is a path - you can also set this
            via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``,
            and ``io.excel.xlsm.writer``.
        """
        from pandas.io.excel import ExcelWriter
        from pandas.io.common import _stringify_path

        if isinstance(writer, ExcelWriter):
            need_save = False
        else:
            writer = ExcelWriter(_stringify_path(writer), engine=engine)
            need_save = True

        formatted_cells = self.get_formatted_cells()
        writer.write_cells(formatted_cells, sheet_name,
                           startrow=startrow, startcol=startcol,
                           freeze_panes=freeze_panes)
        if need_save:
            writer.save() 

def test_stringify_path_fspath(self):
        p = CustomFSPath('foo/bar.csv')
        result = common._stringify_path(p)
        assert result == 'foo/bar.csv' 

def write(self, writer, sheet_name='Sheet1', startrow=0,
              startcol=0, freeze_panes=None, engine=None):
        """
        writer : string or ExcelWriter object
            File path or existing ExcelWriter
        sheet_name : string, default 'Sheet1'
            Name of sheet which will contain DataFrame
        startrow :
            upper left cell row to dump data frame
        startcol :
            upper left cell column to dump data frame
        freeze_panes : tuple of integer (length 2), default None
            Specifies the one-based bottommost row and rightmost column that
            is to be frozen
        engine : string, default None
            write engine to use if writer is a path - you can also set this
            via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``,
            and ``io.excel.xlsm.writer``.
        """
        from pandas.io.excel import ExcelWriter
        from pandas.io.common import _stringify_path

        if isinstance(writer, ExcelWriter):
            need_save = False
        else:
            writer = ExcelWriter(_stringify_path(writer), engine=engine)
            need_save = True

        formatted_cells = self.get_formatted_cells()
        writer.write_cells(formatted_cells, sheet_name,
                           startrow=startrow, startcol=startcol,
                           freeze_panes=freeze_panes)
        if need_save:
            writer.save() 

def test_stringify_path_localpath(self):
        path = os.path.join('foo', 'bar')
        abs_path = os.path.abspath(path)
        lpath = LocalPath(path)
        assert common._stringify_path(lpath) == abs_path 

def test_stringify_path_pathlib(self):
        rel_path = common._stringify_path(Path('.'))
        assert rel_path == '.'
        redundant_path = common._stringify_path(Path('foo//bar'))
        assert redundant_path == os.path.join('foo', 'bar') 

def test_stringify_path_pathlib(self):
        rel_path = icom._stringify_path(Path('.'))
        assert rel_path == '.'
        redundant_path = icom._stringify_path(Path('foo//bar'))
        assert redundant_path == os.path.join('foo', 'bar') 

def __init__(self, path, mode=None, complevel=None, complib=None,
                 fletcher32=False, **kwargs):

        if 'format' in kwargs:
            raise ValueError('format is not a defined argument for HDFStore')

        try:
            import tables  # noqa
        except ImportError as ex:  # pragma: no cover
            raise ImportError('HDFStore requires PyTables, "{ex!s}" problem '
                              'importing'.format(ex=ex))

        if complib is not None and complib not in tables.filters.all_complibs:
            raise ValueError(
                "complib only supports {libs} compression.".format(
                    libs=tables.filters.all_complibs))

        if complib is None and complevel is not None:
            complib = tables.filters.default_complib

        self._path = _stringify_path(path)
        if mode is None:
            mode = 'a'
        self._mode = mode
        self._handle = None
        self._complevel = complevel if complevel else 0
        self._complib = complib
        self._fletcher32 = fletcher32
        self._filters = None
        self.open(mode=mode, **kwargs) 

def read_feather(path, columns=None, use_threads=True):
    """
    Load a feather-format object from the file path

    .. versionadded 0.20.0

    Parameters
    ----------
    path : string file path, or file-like object
    columns : sequence, default None
        If not provided, all columns are read

        .. versionadded 0.24.0
    nthreads : int, default 1
        Number of CPU threads to use when reading to pandas.DataFrame

       .. versionadded 0.21.0
       .. deprecated 0.24.0
    use_threads : bool, default True
        Whether to parallelize reading using multiple threads

       .. versionadded 0.24.0

    Returns
    -------
    type of object stored in file

    """

    feather, pyarrow = _try_import()
    path = _stringify_path(path)

    if LooseVersion(pyarrow.__version__) < LooseVersion('0.11.0'):
        int_use_threads = int(use_threads)
        if int_use_threads < 1:
            int_use_threads = 1
        return feather.read_feather(path, columns=columns,
                                    nthreads=int_use_threads)

    return feather.read_feather(path, columns=columns,
                                use_threads=bool(use_threads)) 

def read_sas(filepath_or_buffer, format=None, index=None, encoding=None,
             chunksize=None, iterator=False):
    """
    Read SAS files stored as either XPORT or SAS7BDAT format files.

    Parameters
    ----------
    filepath_or_buffer : string or file-like object
        Path to the SAS file.
    format : string {'xport', 'sas7bdat'} or None
        If None, file format is inferred from file extension. If 'xport' or
        'sas7bdat', uses the corresponding format.
    index : identifier of index column, defaults to None
        Identifier of column that should be used as index of the DataFrame.
    encoding : string, default is None
        Encoding for text data.  If None, text data are stored as raw bytes.
    chunksize : int
        Read file `chunksize` lines at a time, returns iterator.
    iterator : bool, defaults to False
        If True, returns an iterator for reading the file incrementally.

    Returns
    -------
    DataFrame if iterator=False and chunksize=None, else SAS7BDATReader
    or XportReader
    """
    if format is None:
        buffer_error_msg = ("If this is a buffer object rather "
                            "than a string name, you must specify "
                            "a format string")
        filepath_or_buffer = _stringify_path(filepath_or_buffer)
        if not isinstance(filepath_or_buffer, compat.string_types):
            raise ValueError(buffer_error_msg)
        fname = filepath_or_buffer.lower()
        if fname.endswith(".xpt"):
            format = "xport"
        elif fname.endswith(".sas7bdat"):
            format = "sas7bdat"
        else:
            raise ValueError("unable to infer format of SAS file")

    if format.lower() == 'xport':
        from pandas.io.sas.sas_xport import XportReader
        reader = XportReader(filepath_or_buffer, index=index,
                             encoding=encoding,
                             chunksize=chunksize)
    elif format.lower() == 'sas7bdat':
        from pandas.io.sas.sas7bdat import SAS7BDATReader
        reader = SAS7BDATReader(filepath_or_buffer, index=index,
                                encoding=encoding,
                                chunksize=chunksize)
    else:
        raise ValueError('unknown SAS format')

    if iterator or chunksize:
        return reader

    data = reader.read()
    reader.close()
    return data