COMMAND:
import pickle
from wikidatasets.processFunctions import (
    get_subclasses,
    query_wikidata_dump,
    build_dataset,
)

path = "power_tools/"  # this will contain the files output through the process
dump_path = "latest-all.json.bz2"  # path to the bz2 dump file
n_lines = 56208653  # this can be an upper bound
test_entities = get_subclasses("Q1327701")
# Q1327701 refers to power tool : tool that is actuated by an additional power source and mechanism other than by hand alone

query_wikidata_dump(
    dump_path, path, n_lines, test_entities=test_entities, collect_labels=True
)

labels = pickle.load(open(path + "labels.pkl", "rb"))
build_dataset(path, labels)


ERROR:
---------------------------------------------------------------------------
UnicodeEncodeError                        Traceback (most recent call last)
<ipython-input-1-0a38d065a0ef> in <module>
     17 
     18 labels = pickle.load(open(path + "labels.pkl", "rb"))
---> 19 build_dataset(path, labels)

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\site-packages\wikidatasets\processFunctions.py in build_dataset(path, labels, return_, dump_date)
    169     write_csv(edges, path + 'edges.txt')
    170     write_csv(attributes, path + 'attributes.txt')
--> 171     write_ent_dict(nodes, path + 'nodes.txt')
    172     write_ent_dict(entities, path + 'entities.txt')
    173     write_rel_dict(relations, path + 'relations.txt')

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\site-packages\wikidatasets\utils.py in write_ent_dict(df, name)
    195         f.write('# Entities: {}\n'.format(len(df)))
    196         f.write('entityID\twikidataID\tlabel\n')
--> 197         df.to_csv(f, sep='\t', header=False, index=False)
    198 
    199 

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\site-packages\pandas\core\generic.py in to_csv(self, path_or_buf, sep, na_rep, float_format, columns, header, index, index_label, mode, encoding, compression, quoting, quotechar, line_terminator, chunksize, tupleize_cols, date_format, doublequote, escapechar, decimal)
   3018                                  doublequote=doublequote,
   3019                                  escapechar=escapechar, decimal=decimal)
-> 3020         formatter.save()
   3021 
   3022         if path_or_buf is None:

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\site-packages\pandas\io\formats\csvs.py in save(self)
    170                 self.writer = UnicodeWriter(f, **writer_kwargs)
    171 
--> 172             self._save()
    173 
    174         finally:

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\site-packages\pandas\io\formats\csvs.py in _save(self)
    286                 break
    287 
--> 288             self._save_chunk(start_i, end_i)
    289 
    290     def _save_chunk(self, start_i, end_i):

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\site-packages\pandas\io\formats\csvs.py in _save_chunk(self, start_i, end_i)
    312                                         quoting=self.quoting)
    313 
--> 314         libwriters.write_csv_rows(self.data, ix, self.nlevels,
    315                                   self.cols, self.writer)

pandas/_libs/writers.pyx in pandas._libs.writers.write_csv_rows()

~\AppData\Local\Continuum\miniconda3\envs\prd_knw_gph\lib\encodings\cp1252.py in encode(self, input, final)
     17 class IncrementalEncoder(codecs.IncrementalEncoder):
     18     def encode(self, input, final=False):
---> 19         return codecs.charmap_encode(input,self.errors,encoding_table)[0]
     20 
     21 class IncrementalDecoder(codecs.IncrementalDecoder):

UnicodeEncodeError: 'charmap' codec can't encode character '\u0142' in position 14: character maps to <undefined>