perslab / CELLEX

CELLEX (CELL-type EXpression-specificity)
GNU General Public License v3.0
36 stars 9 forks source link

mapping crashes due to FileNotFoundError #9

Closed tstannius closed 4 years ago

tstannius commented 4 years ago

code entered

cellex.utils.mapping.ens_mouse_to_ens_human(eso.results["esmu"], drop_unmapped=True, verbose=True)

expected behavior

Map gene names

actual behavior

Mapping: mouse ensembl gene id's --> human ensembl gene id's ...

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-11-75787d394ce1> in <module>
----> 1 cellex.utils.mapping.ens_mouse_to_ens_human(eso.results["esmu"], drop_unmapped=True, verbose=True)

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/site-packages/cellex/utils/mapping/ens_mouse_to_ens_human.py in ens_mouse_to_ens_human(df_unmapped, drop_unmapped, verbose)
     35     fp_mapping_file = "CELLEX/cellex/utils/mapping/maps/hsapiens_mmusculus_unique_orthologs.GRCh37.ens_v91.txt.gz"
     36 
---> 37     df_map = pd.read_csv(fp_mapping_file, delim_whitespace=True)
     38 
     39     # create dictionary for mapping mouse ensemble gene id's to human ensembl gene id's

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/site-packages/pandas/io/parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, dialect, error_bad_lines, warn_bad_lines, delim_whitespace, low_memory, memory_map, float_precision)
    683         )
    684 
--> 685         return _read(filepath_or_buffer, kwds)
    686 
    687     parser_f.__name__ = name

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
    455 
    456     # Create the parser.
--> 457     parser = TextFileReader(fp_or_buf, **kwds)
    458 
    459     if chunksize or iterator:

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/site-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
    893             self.options["has_index_names"] = kwds["has_index_names"]
    894 
--> 895         self._make_engine(self.engine)
    896 
    897     def close(self):

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/site-packages/pandas/io/parsers.py in _make_engine(self, engine)
   1133     def _make_engine(self, engine="c"):
   1134         if engine == "c":
-> 1135             self._engine = CParserWrapper(self.f, **self.options)
   1136         else:
   1137             if engine == "python":

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/site-packages/pandas/io/parsers.py in __init__(self, src, **kwds)
   1904         kwds["usecols"] = self.usecols
   1905 
-> 1906         self._reader = parsers.TextReader(src, **kwds)
   1907         self.unnamed_cols = self._reader.unnamed_cols
   1908 

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.__cinit__()

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._setup_parser_source()

/tools/anaconda/envs/djw472/py3_PT/lib/python3.7/gzip.py in __init__(self, filename, mode, compresslevel, fileobj, mtime)
    161             mode += 'b'
    162         if fileobj is None:
--> 163             fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')
    164         if filename is None:
    165             filename = getattr(fileobj, 'name', '')

FileNotFoundError: [Errno 2] No such file or directory: 'CELLEX/cellex/utils/mapping/maps/hsapiens_mmusculus_unique_orthologs.GRCh37.ens_v91.txt.gz'
tstannius commented 4 years ago

Fixed by @pvtodorov in #6