analysiscenter / cardio

CardIO is a library for data science research of heart signals
https://analysiscenter.github.io/cardio/
Apache License 2.0
248 stars 78 forks source link

what is difference A00001~A08528 microsoft Access Table Shortcut and sel30~selxx #30

Closed gsm2055 closed 5 years ago

gsm2055 commented 5 years ago

there is item in " ..\cardio\cardio\tests\data " A0001~A00013 .hea and Microsoft Access Table Shortcut.

but there isn't in qt-database-1.0.0 Microsoft Access Table Shortcut.

what's the difference. and how can i read in qt-database-1.0.0?

using qt-database-1.0.0 i can train HMM algorithm. but i can't find the midium result..

gsm2055 commented 5 years ago

i get this error

File "", line 4, in batch_with_data.show_ecg('A00008', start=30, end=35)

File "D:\anaconda3\lib\site-packages\cardio-0.3.0-py3.7.egg\cardio\core\ecg_batch.py", line 390, in show_ecg i = 0 if index is None else self.get_pos(None, "signal", index)

File "D:\anaconda3\lib\site-packages\cardio-0.3.0-py3.7.egg\cardio\batchflow\batch.py", line 334, in get_pos pos = self.index.get_pos(index)

File "D:\anaconda3\lib\site-packages\cardio-0.3.0-py3.7.egg\cardio\batchflow\dsindex.py", line 148, in get_pos pos = self._pos[index]

`import os import sys sys.path.append("..")

import cardio.batchflow as bf from cardio import EcgBatch from cardio.models.metrics import classification_report

import tensorflow as tf

index = bf.FilesIndex(path="C:/Users/gsm20/Downloads/TestData/A*.hea", no_ext=True, sort=True)

print(index.indices)

%%

eds = bf.Dataset(index, batch_class=EcgBatch) batch = eds.next_batch(batch_size=2) batch_with_data = batch.load(fmt="wfdb", components=["signal", "meta"]) batch_with_data.show_ecg('A00008', start=30, end=35)`

dpodvyaznikov commented 5 years ago

Hi, @gsm2055!

Those files are not Microsoft Access Table files. In wfdb format data files can have different extensions: mat, dat, etc. So you should read those files as usual with load(fmt='wfdb', ...) method. Please, refer to WFDB Guide for more information.

Regarding your second message: it is most likely that there is no element with index A00008 in batch. Try printing batch.indices, and use one of those indices in show_ecg.

gsm2055 commented 5 years ago

really thx to your reply.

i don't know exactly how use .dat file. i know .mat file can use in matlab.

but i want to know how can i use .dat file to show using python..

can you tell me how can i use .dat file to look signal??

best regard

Endrew

-----Original Message----- From: "Dmitry Podvyaznikov"notifications@github.com To: "analysiscenter/cardio"cardio@noreply.github.com; Cc: "gsm2055"gsm2055@naver.com; "Mention"mention@noreply.github.com; Sent: 2019-08-30 (금) 19:01:02 (GMT+09:00) Subject: Re: [analysiscenter/cardio] what is difference A00001~A08528 microsoft Access Table Shortcut and sel30~selxx (#30)

Hi, @gsm2055! Those files are not Microsoft Access Table files. In wfdb format data files can have different extensions: mat, dat, etc. So you should read those files as usual with load(fmt='wfdb', ...) method. Please, refer to WFDB Guide for more information. Regarding your second message: it is most likely that there is no element with index A00008 in batch. Try printing batch.indices, and use one of those indices in show_ecg. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

dpodvyaznikov commented 5 years ago

CardIO uses wfdb library to read data in wfdb format. You can use this library independently from CardIO. Please, read the documentation and go through demo notebook. wfdb has a built-in function to display signals.

Also, to display signal with CardIO, you can refer to tutorials/III. Models.ipynb, section CardIO segmentation models. First code chunk shows how to create EcgDataset object with QT data. Then you can generate new batch and use load and show_ecg methods as usual.