pandatools.py 文件源码

def superReadFile(filepath,**kwargs):
    """ 
    Uses pandas.read_excel (on excel files) and returns a dataframe of the first sheet (unless sheet is specified in kwargs)
    Uses superReadText (on .txt,.tsv, or .csv files) and returns a dataframe of the data.
    One function to read almost all types of data files.    
    """
    if isinstance(filepath, pd.DataFrame):
        return filepath

    ext = os.path.splitext(filepath)[1].lower()

    if ext in ['.xlsx', '.xls']:
        kwargs.pop('dtype', None)
        return pd.read_excel(filepath,**kwargs)

    elif ext in ['.txt','.tsv','.csv']:
        return superReadText(filepath, **kwargs)

    elif ext in ['.gz', '.bz2', '.zip', 'xz']:
        return superReadCSV(filepath, **kwargs)

    elif ext in ['.h5']:
        return pd.read_hdf(filepath)

    else:
        raise NotImplementedError("Unable to read '{}' files".format(ext))