Skip to content

UnicodeEncodeError: 'charmap' codec can't encode character '\u2264' in position 30: character maps to <undefined> #50

Open
@lordegeology

Description

@lordegeology

from timeshap.explainer import global_report
sequence_id_feat = 'id'
time_feat = 'Date'
#pos_dataset = d_test_normalized[d_test_normalized['label'] == 1]
schema = schema = list(trial.columns)
pruning_dict = {'tol': [ 0.025, 0.05],'path': 'prun_all_tf.csv'}
event_dict = {'path': 'event_all_tf.csv', 'rs': 42, 'nsamples': 32000}
feature_dict = {'path': 'feature_all_tf.csv','rs': 42, 'nsamples': 32000, 'feature_names': model_features, 'plot_features': plot_feats}
prun_stats, global_plot = global_report(f, trial, pruning_dict, event_dict, feature_dict, average_event, model_features, schema, sequence_id_feat, time_feat, )
prun_stats

While running the above code, I am getting the following error related to encoding:

UnicodeEncodeError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_14916\4246322402.py in
7 event_dict = {'path': 'event_all_tf.csv', 'rs': 42, 'nsamples': 32000}
8 feature_dict = {'path': 'feature_all_tf.csv','rs': 42, 'nsamples': 32000, 'feature_names': model_features, 'plot_features': plot_feats}
----> 9 prun_stats, global_plot = global_report(f, trial, pruning_dict, event_dict, feature_dict, average_event, model_features, schema, sequence_id_feat, time_feat, )
10 prun_stats

c:\programdata\anaconda3\lib\site-packages\timeshap\explainer\global_methods.py in global_report(f, data, pruning_dict, event_dict, feature_dict, baseline, model_features, schema, entity_col, time_col, append_to_files, max_instances, verbose)
294 """
295 prun_indexes, event_data, feat_data =
--> 296 calc_global_explanations(f, data, pruning_dict, event_dict,
297 feature_dict, baseline, model_features,
298 schema, entity_col, time_col, append_to_files,

c:\programdata\anaconda3\lib\site-packages\timeshap\explainer\global_methods.py in calc_global_explanations(f, data, pruning_dict, event_dict, feature_dict, baseline, model_features, schema, entity_col, time_col, append_to_files, max_instances, verbose)
209 else:
210 print("Calculating pruning algorithm")
--> 211 prun_indexes = prune_all(f, data, pruning_dict, baseline,
212 model_features_index, schema, entity_col_index,
213 time_col_index, append_to_files, verbose)

c:\programdata\anaconda3\lib\site-packages\timeshap\explainer\pruning.py in prune_all(f, data, pruning_dict, baseline, model_features, schema, entity_col, time_col, append_to_files, verbose)
414 with open(file_path, 'a', newline='') as file:
415 writer = csv.writer(file, delimiter=',')
--> 416 writer.writerows(local_pruning_data.values)
417
418 prun_data = pd.DataFrame(np.concatenate(ret_prun_data), columns=names)

c:\programdata\anaconda3\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 '\u2264' in position 30: character maps to

Is the issue while writing to the csv or vice versa? I am pretty lost here.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions