Issues accessing lexicon .json file #21
Description
Thanks so much for this project! I've encountered an issue on Jupyter Notebooks when trying to access the lexicon nrc_en.json. Here's the output of a sample that I tried to run:
from nrclex import NRCLex
text = "hateful"
emotion = NRCLex(text)
print("hateful", emotion.top_emotions)
FileNotFoundError Traceback (most recent call last)
Cell In[18], line 2
1 text = "hateful"
----> 2 emotion = NRCLex(text)
3 print("hateful", emotion.top_emotions)
File ~\Downloads\NRCLex-master\NRCLex-master\nrclex.py:60, in NRCLex.init(self, lexicon_file)
59 def init(self, lexicon_file='nrc_en.json'):
---> 60 with open(lexicon_file, 'r') as json_file:
61 self.lexicon = load(json_file)
FileNotFoundError: [Errno 2] No such file or directory: 'hateful'
I'm not quite sure what's causing the error, would you have any suggestions? I tried loading the nrc_en.json file to check what could be causing the issue, and I got the following:
ValueError Traceback (most recent call last)
Cell In[4], line 1
----> 1 df = pd.read_json('nrc_en.json')
File ~\Anaconda3\lib\site-packages\pandas\util_decorators.py:207, in deprecate_kwarg.._deprecate_kwarg..wrapper(*args, **kwargs)
205 else:
206 kwargs[new_arg_name] = new_arg_value
--> 207 return func(*args, **kwargs)
File ~\Anaconda3\lib\site-packages\pandas\util_decorators.py:311, in deprecate_nonkeyword_arguments..decorate..wrapper(*args, **kwargs)
305 if len(args) > num_allow_args:
306 warnings.warn(
307 msg.format(arguments=arguments),
308 FutureWarning,
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
File ~\Anaconda3\lib\site-packages\pandas\io\json_json.py:612, in read_json(path_or_buf, orient, typ, dtype, convert_axes, convert_dates, keep_default_dates, numpy, precise_float, date_unit, encoding, encoding_errors, lines, chunksize, compression, nrows, storage_options)
609 return json_reader
611 with json_reader:
--> 612 return json_reader.read()
File ~\Anaconda3\lib\site-packages\pandas\io\json_json.py:746, in JsonReader.read(self)
744 obj = self._get_object_parser(self._combine_lines(data_lines))
745 else:
--> 746 obj = self._get_object_parser(self.data)
747 self.close()
748 return obj
File ~\Anaconda3\lib\site-packages\pandas\io\json_json.py:768, in JsonReader._get_object_parser(self, json)
766 obj = None
767 if typ == "frame":
--> 768 obj = FrameParser(json, **kwargs).parse()
770 if typ == "series" or obj is None:
771 if not isinstance(dtype, bool):
File ~\Anaconda3\lib\site-packages\pandas\io\json_json.py:880, in Parser.parse(self)
878 self._parse_numpy()
879 else:
--> 880 self._parse_no_numpy()
882 if self.obj is None:
883 return None
File ~\Anaconda3\lib\site-packages\pandas\io\json_json.py:1132, in FrameParser._parse_no_numpy(self)
1129 orient = self.orient
1131 if orient == "columns":
-> 1132 self.obj = DataFrame(
1133 loads(json, precise_float=self.precise_float), dtype=None
1134 )
1135 elif orient == "split":
1136 decoded = {
1137 str(k): v
1138 for k, v in loads(json, precise_float=self.precise_float).items()
1139 }
File ~\Anaconda3\lib\site-packages\pandas\core\frame.py:636, in DataFrame.init(self, data, index, columns, dtype, copy)
630 mgr = self._init_mgr(
631 data, axes={"index": index, "columns": columns}, dtype=dtype, copy=copy
632 )
634 elif isinstance(data, dict):
635 # GH#38939 de facto copy defaults to False only in non-dict cases
--> 636 mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
637 elif isinstance(data, ma.MaskedArray):
638 import numpy.ma.mrecords as mrecords
File ~\Anaconda3\lib\site-packages\pandas\core\internals\construction.py:502, in dict_to_mgr(data, index, columns, dtype, typ, copy)
494 arrays = [
495 x
496 if not hasattr(x, "dtype") or not isinstance(x.dtype, ExtensionDtype)
497 else x.copy()
498 for x in arrays
499 ]
500 # TODO: can we get rid of the dt64tz special case above?
--> 502 return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)
File ~\Anaconda3\lib\site-packages\pandas\core\internals\construction.py:120, in arrays_to_mgr(arrays, columns, index, dtype, verify_integrity, typ, consolidate)
117 if verify_integrity:
118 # figure out the index, if necessary
119 if index is None:
--> 120 index = _extract_index(arrays)
121 else:
122 index = ensure_index(index)
File ~\Anaconda3\lib\site-packages\pandas\core\internals\construction.py:674, in _extract_index(data)
672 lengths = list(set(raw_lengths))
673 if len(lengths) > 1:
--> 674 raise ValueError("All arrays must be of the same length")
676 if have_dicts:
677 raise ValueError(
678 "Mixing dicts with non-Series may lead to ambiguous ordering."
679 )
ValueError: All arrays must be of the same length
Any help you could provide would be useful. Thank you!
Best,
Frankie