Dataset - TypeError: only integer scalar arrays can be converted to a scalar index

analysiscenter / cardio

CardIO is a library for data science research of heart signals

Apache License 2.0

248 stars 78 forks source link

Hi, I'm new to Python but wanted to try ECG segmentation so I tried using cardio. I've installed below packages on Python 3.6.5 in addition to all the other packages that were needed in the process. I tried executing the example code of the ECG segmentation in the III. Models tutorial, and got an error message "TypeError: only integer scalar arrays can be converted to a scalar index". I've listed the codes that were executed followed by the error message.

pip3 install git+https://github.com/analysiscenter/cardio.git pip3 install git+https://github.com/analysiscenter/dataset.git pip install hmmlearn-0.2.1-cp36-cp36m-win_amd64.whl (after I downloaded the file from https://www.lfd.uci.edu/~gohlke/pythonlibs/#hmmlearn - installing hmmlearn from GitHub gave an error while installing)

Code:

import sys, os sys.path.append('..')

from cardio import EcgDataset

SIGNALS_PATH = "/notebooks/data/ECG/QT/" #set path to the QT database SIGNALS_MASK = os.path.join(SIGNALS_PATH, "*.hea")

dtst = EcgDataset(path=SIGNALS_MASK, no_ext=True, sort=True)

from cardio.pipelines import hmm_preprocessing_pipeline, hmm_train_pipeline import warnings warnings.filterwarnings('ignore')

pipeline = hmm_preprocessing_pipeline() ppl_inits = (dtst >> pipeline).run()

Error message: ppl_inits = (dtst >> pipeline).run()

Traceback (most recent call last):

File "", line 1, in ppl_inits = (dtst >> pipeline).run()

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\pipeline.py", line 1088, in run for _ in self.gen_batch(*args, **kwargs):

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\pipeline.py", line 1033, in gen_batch for batch in batch_generator:

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\base.py", line 162, in gen_batch for ix_batch in self.index.gen_batch(batch_size, shuffle, n_epochs, drop_last):

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\dsindex.py", line 276, in gen_batch batch = self.next_batch(batch_size, shuffle, n_epochs, drop_last, iter_params)

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\dsindex.py", line 250, in next_batch return self.create_batch(rest_items, pos=True)

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\dsindex.py", line 292, in create_batch batch = self.subset_by_pos(_batch_indices)

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\dsindex.py", line 80, in subset_by_pos return self.index[pos]

TypeError: only integer scalar arrays can be converted to a scalar index

I'm not sure what is the problem. I appreciate your help in advance.

I simply didn't specify the correct path with the data files. Once I downloaded the QT database and specified the correct path, it worked. But I have another problem now. After I built the model and saved it as a .dll file, I used it to predict, but it showed another error (the same error as before).

Code:

from cardio import EcgDataset from cardio.pipelines import hmm_predict_pipeline import warnings warnings.filterwarnings('ignore')

eds = EcgDataset(path="C:\PhysioNetQT_DataB\cardio\cardio\tests\data\A*.hea", no_ext=True, sort=True) batch = (eds >> hmm_predict_pipeline("C:\PhysioNetQT_DataB\model_dump.dll", annot="hmm_annotation")).next_batch()

batch.show_ecg("A00001", start=10, end=15, annot="hmm_annotation")

print("Heart rate: {0} bpm".format(int(.5 + batch["A00001"].meta["hr"])))

Error: batch = (eds >> hmm_predict_pipeline("C:\PhysioNetQT_DataB\model_dump.dll", annot="hmm_annotation")).next_batch()

Traceback (most recent call last):

File "", line 1, in batch = (eds >> hmm_predict_pipeline("C:\PhysioNetQT_DataB\model_dump.dll", annot="hmm_annotation")).next_batch()

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\pipeline.py", line 1057, in next_batch batch_res = self.next_batch(*self._lazy_run[0], **self._lazy_run[1])

File "C:\Anaconda3\lib\site-packages\cardio\dataset\dataset\pipeline.py", line 1062, in next_batch batch_res = next(self._batch_generator)