ZeroDivisionError when apply pipeline in my data

[pjgao]

pipeline = Pipeline([('augmenter', RelevantFeatureAugmenter(column_id='serial_number', column_sort='date')),
            ('classifier', XGBClassifier())])


X_disk = pd.DataFrame(index=y_disk.index)
xtrain,xtest,ytrain,ytest = train_test_split(X_disk,y_disk,test_size=0.4)
pipeline.set_params(augmenter__timeseries_container=ts_disk)
pipeline.fit(xtrain, ytrain)
confusion_matrix(ytest,pipeline.predict(xtest))

Here is the error info:

ZeroDivisionError Traceback (most recent call last)
in ()
6 xtrain,xtest,ytrain,ytest = train_test_split(X_disk,y_disk,test_size=0.4)
7 pipeline.set_params(augmenter__timeseries_container=ts_disk)
----> 8 pipeline.fit(xtrain, ytrain)
9 confusion_matrix(ytest,pipeline.predict(xtest))

/anaconda3/lib/python3.6/site-packages/tsfresh/transformers/feature_augmenter.py in transform(self, X)
189 profile=self.profile,
190 profiling_filename=self.profiling_filename,
--> 191 profiling_sorting=self.profiling_sorting)
192
193 X = pd.merge(X, extracted_features, left_index=True, right_index=True, how="left")

~/anaconda3/lib/python3.6/site-packages/tsfresh/feature_extraction/extraction.py in extract_features(timeseries_container, default_fc_parameters, kind_to_fc_parameters, column_id, column_sort, column_kind, column_value, chunksize, n_jobs, show_warnings, disable_progressbar, impute_function, profile, profiling_filename, profiling_sorting, distributor)
150 default_fc_parameters=default_fc_parameters,
151 kind_to_fc_parameters=kind_to_fc_parameters,
--> 152 distributor=distributor)
153
154 # Impute the result if requested

~/anaconda3/lib/python3.6/site-packages/tsfresh/feature_extraction/extraction.py in _do_extraction(df, column_id, column_value, column_kind, default_fc_parameters, kind_to_fc_parameters, n_jobs, chunk_size, disable_progressbar, distributor)
231 kwargs = dict(default_fc_parameters=default_fc_parameters, kind_to_fc_parameters=kind_to_fc_parameters)
232 result = distributor.map_reduce(_do_extraction_on_chunk, data=data_in_chunks, chunk_size=chunk_size,
--> 233 function_kwargs=kwargs)
234 distributor.close()
235

~/anaconda3/lib/python3.6/site-packages/tsfresh/utilities/distribution.py in map_reduce(self, map_function, data, function_kwargs, chunk_size, data_length)
140
141 if hasattr(self, "progressbar_title"):
--> 142 total_number_of_expected_results = math.ceil(data_length / chunk_size)
143 result = tqdm(self.distribute(_function_with_partly_reduce, chunk_generator, map_kwargs),
144 total=total_number_of_expected_results,

ZeroDivisionError: division by zero

[MaxBenChrist]

This looks like your data has a lenght of 0, is the time series container empty?