Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- ---------------------------------------------------------------------------
- ParserError Traceback (most recent call last)
- <ipython-input-6-14cf239fd04e> in <module>
- 3 import dask.dataframe as dd
- 4
- ----> 5 df= dd.read_csv("tweets_withheader.csv", quoting=csv.QUOTE_NONE)
- 6
- 7 df = df.compute()
- ~/anaconda3/lib/python3.7/site-packages/dask/dataframe/io/csv.py in read(urlpath, blocksize, collection, lineterminator, compression, sample, enforce, assume_missing, storage_options, include_path_column, **kwargs)
- 576 storage_options=storage_options,
- 577 include_path_column=include_path_column,
- --> 578 **kwargs
- 579 )
- 580
- ~/anaconda3/lib/python3.7/site-packages/dask/dataframe/io/csv.py in read_pandas(reader, urlpath, blocksize, collection, lineterminator, compression, sample, enforce, assume_missing, storage_options, include_path_column, **kwargs)
- 442
- 443 # Use sample to infer dtypes and check for presence of include_path_column
- --> 444 head = reader(BytesIO(b_sample), **kwargs)
- 445 if include_path_column and (include_path_column in head.columns):
- 446 raise ValueError(
- ~/anaconda3/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)
- 674 )
- 675
- --> 676 return _read(filepath_or_buffer, kwds)
- 677
- 678 parser_f.__name__ = name
- ~/anaconda3/lib/python3.7/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
- 452
- 453 try:
- --> 454 data = parser.read(nrows)
- 455 finally:
- 456 parser.close()
- ~/anaconda3/lib/python3.7/site-packages/pandas/io/parsers.py in read(self, nrows)
- 1131 def read(self, nrows=None):
- 1132 nrows = _validate_integer("nrows", nrows)
- -> 1133 ret = self._engine.read(nrows)
- 1134
- 1135 # May alter columns / col_dict
- ~/anaconda3/lib/python3.7/site-packages/pandas/io/parsers.py in read(self, nrows)
- 2035 def read(self, nrows=None):
- 2036 try:
- -> 2037 data = self._reader.read(nrows)
- 2038 except StopIteration:
- 2039 if self._first_chunk:
- pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.read()
- pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_low_memory()
- pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_rows()
- pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._tokenize_rows()
- pandas/_libs/parsers.pyx in pandas._libs.parsers.raise_parser_error()
- ParserError: Error tokenizing data. C error: Expected 25 fields in line 5, saw 26
Add Comment
Please, Sign In to add comment