Load files in plugin - Githubissues

sfritzs commented 5 months ago

Hi @josenimo and @melonora ,

I am trying to load some files in the plugin and face an issue. I pasted the error below. Thanks for your help.

All the best, Sonja

INFO: Loaded 36 regionprops csvs.

UnicodeDecodeError Traceback (most recent call last) File ~\Documents\Image_Processing\napari-cell-gater\src\cell_gater\widgets\sample_widget.py:135, in SampleWidget._open_sample_dialog(self=) 132 folder = self._dir_dialog() 134 if folder not in {"", None}: --> 135 self._assign_regionprops_to_model(folder) folder = 'Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv' self = <cell_gater.widgets.sample_widget.SampleWidget object at 0x00000225B7906D40> 136 update_open_history(folder)

File ~\Documents\Image_Processing\napari-cell-gater\src\cell_gater\widgets\sample_widget.py:171, in SampleWidget._assign_regionprops_to_model(self=, folder='Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv') 169 def _assign_regionprops_to_model(self, folder: str) -> None: 170 """Read the csv files in the directory and assign the resulting concatenated DataFrame in the DataModel.""" --> 171 self.model.regionprops_df = stack_csv_files(Path(folder)) self = <cell_gater.widgets.sample_widget.SampleWidget object at 0x00000225B7906D40> folder = 'Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv'

File ~\Documents\Image_Processing\napari-cell-gater\src\cell_gater\utils\csv_df.py:30, in stack_csv_files(csv_dir=WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv')) 28 df = pd.DataFrame() 29 for file in csv_files: ---> 30 df_file = pd.read_csv(file) file = WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv') pd = <module 'pandas' from 'C:\Users\sfritzs\AppData\Roaming\Python\Python310\site-packages\pandas\init.py'> 31 df_file["sample_id"] = file.stem 32 df = pd.concat([df, df_file], ignore_index=True)

File ~\AppData\Roaming\Python\Python310\site-packages\pandas\io\parsers\readers.py:948, in read_csv(filepath_or_buffer=WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv'), sep=, delimiter=None, header='infer', names=, index_col=None, usecols=None, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=None, infer_datetime_format=, keep_date_col=False, date_parser=, date_format=None, dayfirst=False, cache_dates=True, iterator=False, chunksize=None, compression='infer', thousands=None, decimal='.', lineterminator=None, quotechar='"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, encoding_errors='strict', dialect=None, on_bad_lines='error', delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None, storage_options=None, dtype_backend=) 935 kwds_defaults = _refine_defaults_read( 936 dialect, 937 delimiter, (...) 944 dtype_backend=dtype_backend, 945 ) 946 kwds.update(kwds_defaults) --> 948 return _read(filepath_or_buffer, kwds) kwds = {'delimiter': ',', 'header': 'infer', 'names': None, 'index_col': None, 'usecols': None, 'dtype': None, 'engine': 'c', 'converters': None, 'true_values': None, 'false_values': None, 'skipinitialspace': False, 'skiprows': None, 'skipfooter': 0, 'nrows': None, 'na_values': None, 'keep_default_na': True, 'na_filter': True, 'verbose': False, 'skip_blank_lines': True, 'parse_dates': False, 'infer_datetime_format': , 'keep_date_col': False, 'date_parser': , 'date_format': None, 'dayfirst': False, 'cache_dates': True, 'iterator': False, 'chunksize': None, 'compression': 'infer', 'thousands': None, 'decimal': '.', 'lineterminator': None, 'quotechar': '"', 'quoting': 0, 'doublequote': True, 'escapechar': None, 'comment': None, 'encoding': None, 'encoding_errors': 'strict', 'dialect': None, 'on_bad_lines': <BadLineHandleMethod.ERROR: 0>, 'delim_whitespace': False, 'low_memory': True, 'memory_map': False, 'float_precision': None, 'storage_options': None, 'dtype_backend': , 'engine_specified': False} filepath_or_buffer = WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv')

File ~\AppData\Roaming\Python\Python310\site-packages\pandas\io\parsers\readers.py:611, in _read(filepath_or_buffer=WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv'), kwds={'cache_dates': True, 'chunksize': None, 'comment': None, 'compression': 'infer', 'converters': None, 'date_format': None, 'date_parser': , 'dayfirst': False, 'decimal': '.', 'delim_whitespace': False, ...}) 608 _validate_names(kwds.get("names", None)) 610 # Create the parser. --> 611 parser = TextFileReader(filepath_or_buffer, **kwds) TextFileReader = <class 'pandas.io.parsers.readers.TextFileReader'> filepath_or_buffer = WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv') kwds = {'delimiter': ',', 'header': 'infer', 'names': None, 'index_col': None, 'usecols': None, 'dtype': None, 'engine': 'c', 'converters': None, 'true_values': None, 'false_values': None, 'skipinitialspace': False, 'skiprows': None, 'skipfooter': 0, 'nrows': None, 'na_values': None, 'keep_default_na': True, 'na_filter': True, 'verbose': False, 'skip_blank_lines': True, 'parse_dates': False, 'infer_datetime_format': , 'keep_date_col': False, 'date_parser': , 'date_format': None, 'dayfirst': False, 'cache_dates': True, 'iterator': False, 'chunksize': None, 'compression': 'infer', 'thousands': None, 'decimal': '.', 'lineterminator': None, 'quotechar': '"', 'quoting': 0, 'doublequote': True, 'escapechar': None, 'comment': None, 'encoding': None, 'encoding_errors': 'strict', 'dialect': None, 'on_bad_lines': <BadLineHandleMethod.ERROR: 0>, 'delim_whitespace': False, 'low_memory': True, 'memory_map': False, 'float_precision': None, 'storage_options': None, 'dtype_backend': , 'engine_specified': False} 613 if chunksize or iterator: 614 return parser

File ~\AppData\Roaming\Python\Python310\site-packages\pandas\io\parsers\readers.py:1448, in TextFileReader.init(self=, f=WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv'), engine='c', **kwds={'cache_dates': True, 'chunksize': None, 'comment': None, 'compression': 'infer', 'converters': None, 'date_format': None, 'date_parser': , 'dayfirst': False, 'decimal': '.', 'delim_whitespace': False, ...}) 1445 self.options["has_index_names"] = kwds["has_index_names"] 1447 self.handles: IOHandles | None = None -> 1448 self._engine = self._make_engine(f, self.engine) self.engine = 'c' self = <pandas.io.parsers.readers.TextFileReader object at 0x00000225B9BA4F10> f = WindowsPath('Y:/Sonjas_Head_and_Neck/P21E05_HN26/cylinter/csv/._1.csv')

File ~\AppData\Roaming\Python\Python310\site-packages\pandas\io\parsers\readers.py:1723, in TextFileReader._make_engine(self=, f=<_io.TextIOWrapper name='Y:\\Sonjas_Head_and_Nec...ylinter\\csv\\._1.csv' mode='r' encoding='utf-8'>, engine='c') 1720 raise ValueError(msg) 1722 try: -> 1723 return mapping[engine](f, **self.options) mapping = {'c': <class 'pandas.io.parsers.c_parser_wrapper.CParserWrapper'>, 'python': <class 'pandas.io.parsers.python_parser.PythonParser'>, 'pyarrow': <class 'pandas.io.parsers.arrow_parser_wrapper.ArrowParserWrapper'>, 'python-fwf': <class 'pandas.io.parsers.python_parser.FixedWidthFieldParser'>} engine = 'c' f = <_io.TextIOWrapper name='Y:\\Sonjas_Head_and_Neck\\P21E05_HN26\\cylinter\\csv\\._1.csv' mode='r' encoding='utf-8'> self = <pandas.io.parsers.readers.TextFileReader object at 0x00000225B9BA4F10> mapping[engine] = <class 'pandas.io.parsers.c_parser_wrapper.CParserWrapper'> self.options = {'delimiter': ',', 'escapechar': None, 'quotechar': '"', 'quoting': 0, 'doublequote': True, 'skipinitialspace': False, 'lineterminator': None, 'header': 0, 'index_col': None, 'names': None, 'skiprows': set(), 'na_values': {'', 'N/A', 'NA', 'None', 'n/a', '-nan', 'NULL', '-NaN', '-1.#IND', '', 'NaN', '-1.#QNAN', '1.#IND', '1.#QNAN', 'nan', '#NA', '#N/A N/A', '#N/A', 'null'}, 'keep_default_na': True, 'true_values': None, 'false_values': None, 'converters': {}, 'dtype': None, 'cache_dates': True, 'thousands': None, 'comment': None, 'decimal': '.', 'parse_dates': False, 'keep_date_col': False, 'dayfirst': False, 'date_parser': , 'date_format': None, 'usecols': None, 'verbose': False, 'encoding': None, 'compression': 'infer', 'skip_blank_lines': True, 'encoding_errors': 'strict', 'on_bad_lines': <BadLineHandleMethod.ERROR: 0>, 'dtype_backend': , 'delim_whitespace': False, 'na_filter': True, 'low_memory': True, 'memory_map': False, 'float_precision': None, 'storage_options': None, 'na_fvalues': set()} 1724 except Exception: 1725 if self.handles is not None:

File ~\AppData\Roaming\Python\Python310\site-packages\pandas\io\parsers\c_parser_wrapper.py:93, in CParserWrapper.init(self=, src=<_io.TextIOWrapper name='Y:\\Sonjas_Head_and_Nec...ylinter\\csv\\._1.csv' mode='r' encoding='utf-8'>, kwds={'allow_leading_cols': True, 'comment': None, 'converters': {}, 'decimal': '.', 'delim_whitespace': False, 'delimiter': ',', 'doublequote': True, 'dtype': None, 'dtype_backend': 'numpy', 'encoding_errors': 'strict', ...}) 90 if kwds["dtype_backend"] == "pyarrow": 91 # Fail here loudly instead of in cython after reading 92 import_optional_dependency("pyarrow") ---> 93 self._reader = parsers.TextReader(src, kwds) kwds = {'delimiter': ',', 'escapechar': None, 'quotechar': '"', 'quoting': 0, 'doublequote': True, 'skipinitialspace': False, 'lineterminator': None, 'header': 0, 'index_col': None, 'names': None, 'skiprows': set(), 'na_values': {'', 'N/A', 'NA', 'None', 'n/a', '-nan', 'NULL', '-NaN', '-1.#IND', '', 'NaN', '-1.#QNAN', '1.#IND', '1.#QNAN', 'nan', '#NA', '#N/A N/A', '#N/A', 'null'}, 'keep_default_na': True, 'true_values': None, 'false_values': None, 'converters': {}, 'dtype': None, 'thousands': None, 'comment': None, 'decimal': '.', 'usecols': None, 'verbose': False, 'skip_blank_lines': True, 'encoding_errors': 'strict', 'on_bad_lines': 0, 'dtype_backend': 'numpy', 'delim_whitespace': False, 'na_filter': True, 'float_precision': None, 'na_fvalues': set(), 'allow_leading_cols': True} self = <pandas.io.parsers.c_parser_wrapper.CParserWrapper object at 0x00000225B9BA4EE0> src = <_io.TextIOWrapper name='Y:\\Sonjas_Head_and_Neck\\P21E05_HN26\\cylinter\\csv\\._1.csv' mode='r' encoding='utf-8'> parsers = <module 'pandas._libs.parsers' from 'C:\Users\sfritzs\AppData\Roaming\Python\Python310\site-packages\pandas\_libs\parsers.cp310-win_amd64.pyd'> 95 self.unnamed_cols = self._reader.unnamed_cols 97 # error: Cannot determine type of 'names'

File parsers.pyx:579, in pandas._libs.parsers.TextReader.cinit()

File parsers.pyx:668, in pandas._libs.parsers.TextReader._get_header()

File parsers.pyx:879, in pandas._libs.parsers.TextReader._tokenize_rows()

File parsers.pyx:890, in pandas._libs.parsers.TextReader._check_tokenize_status()

File parsers.pyx:2050, in pandas._libs.parsers.raise_parser_error()

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb0 in position 37: invalid start byte