bert-toxic-comments-multilabel icon indicating copy to clipboard operation
bert-toxic-comments-multilabel copied to clipboard

FileNotFoundError: File val.csv does not exist

Open Pupinin opened this issue 5 years ago • 2 comments

While running the notebook I'm stuck at the above mentioned error. The code is:

Eval Fn

eval_examples = processor.get_dev_examples(args['data_dir'], size=args['val_size']) def eval(): ......

Error: FileNotFoundError Traceback (most recent call last) in 1 # Eval Fn ----> 2 eval_examples = processor.get_dev_examples(args['data_dir'], size=args['val_size']) 3 def eval(): 4 args['output_dir'].mkdir(exist_ok=True) 5

in get_dev_examples(self, data_dir, size) 22 filename = 'val.csv' 23 if size == -1: ---> 24 data_df = pd.read_csv(os.path.join(data_dir, filename)) 25 # data_df['comment_text'] = data_df['comment_text'].apply(cleanHtml) 26 return self._create_examples(data_df, "dev")

/anaconda/envs/py36/lib/python3.6/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, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, doublequote, delim_whitespace, low_memory, memory_map, float_precision) 676 skip_blank_lines=skip_blank_lines) 677 --> 678 return _read(filepath_or_buffer, kwds) 679 680 parser_f.name = name

/anaconda/envs/py36/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds) 438 439 # Create the parser. --> 440 parser = TextFileReader(filepath_or_buffer, **kwds) 441 442 if chunksize or iterator:

/anaconda/envs/py36/lib/python3.6/site-packages/pandas/io/parsers.py in init(self, f, engine, **kwds) 785 self.options['has_index_names'] = kwds['has_index_names'] 786 --> 787 self._make_engine(self.engine) 788 789 def close(self):

/anaconda/envs/py36/lib/python3.6/site-packages/pandas/io/parsers.py in _make_engine(self, engine) 1012 def _make_engine(self, engine='c'): 1013 if engine == 'c': -> 1014 self._engine = CParserWrapper(self.f, **self.options) 1015 else: 1016 if engine == 'python':

/anaconda/envs/py36/lib/python3.6/site-packages/pandas/io/parsers.py in init(self, src, **kwds) 1706 kwds['usecols'] = self.usecols 1707 -> 1708 self._reader = parsers.TextReader(src, **kwds) 1709 1710 passed_names = self.names is None

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

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

FileNotFoundError: File b'kaggle_data/toxic_comments/tmp/val.csv' does not exist

Pupinin avatar Mar 29 '19 10:03 Pupinin

You can create a val file yourself, just split the train.csv file

mridulnagpal avatar Mar 29 '19 12:03 mridulnagpal

You can create a val file yourself, just split the train.csv file

Have not thought of that. Thx!

Pupinin avatar Mar 29 '19 12:03 Pupinin