# convert discontinuous data to continuous

**URL:** https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652
**Category:** Support & Discussions
**Tags:** visualization, eeg, preprocessing, epochs
**Created:** [September 5, 2021, 2:52am UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652 "2021-09-05T02:52:40Z")
**Posts on this page:** 6
**Page:** 1

<div class="post-metadata">

### Author: ![Mostafa](https://avatars.discourse-cdn.com/v4/letter/m/f0a364/32.png) [@Mostafa](https://mne.discourse.group/u/Mostafa)
#### Post date: [September 5, 2021, 2:52am UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652/1 "2021-09-05T02:52:40Z")

</div>

Hi MNE users,

I’ve epoched my data to remove artifacts using make\_fixed\_length\_epochs() function. Is there any way to convert the 3D epoched data (Epochs_channels_Samples) back to the initial type and format (2D data (Channels\*Samples))?

Thank you,

---

<div class="post-metadata">

### Author: ![richard](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/richard/32/15_2.png) [@richard](https://mne.discourse.group/u/richard)
#### Post date: [September 8, 2021, 8:26pm UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652/2 "2021-09-08T20:26:30Z")

</div>

Hello @Mostafa,

are you sure you really want to do that? The reconstructed continuous data will most likely have discontinuities if you removed any epochs, and this can cause problems down the road…

---

<div class="post-metadata">

### Author: ![drammock](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/drammock/32/4_2.png) [@drammock](https://mne.discourse.group/u/drammock)
#### Post date: [September 9, 2021, 2:25pm UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652/3 "2021-09-09T14:25:54Z")

</div>

setting aside whether it is a good idea, there is some code in [this answer](https://mne.discourse.group/t/epoching-on-epoched-data/3638/5) that will get you there.

---

<div class="post-metadata">

### Author: ![Mostafa](https://avatars.discourse-cdn.com/v4/letter/m/f0a364/32.png) [@Mostafa](https://mne.discourse.group/u/Mostafa)
#### Post date: [September 15, 2021, 12:12am UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652/4 "2021-09-15T00:12:17Z")

</div>

Thank you @richard and @drammock . You are right. it doesn’t look a good idea. I found another way around to solve my problem.

---

<div class="post-metadata">

### Author: ![eyamu](https://avatars.discourse-cdn.com/v4/letter/e/bbce88/32.png) [@eyamu](https://mne.discourse.group/u/eyamu)
#### Post date: [March 3, 2022, 3:21pm UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652/5 "2022-03-03T15:21:31Z")

</div>

Hello @Mostafa , how did you go by this? I am faced with same issue.  
Is working with the averaged or evoked object the correct thing here?

---

<div class="post-metadata">

### Author: ![Mostafa](https://avatars.discourse-cdn.com/v4/letter/m/f0a364/32.png) [@Mostafa](https://mne.discourse.group/u/Mostafa)
#### Post date: [June 10, 2022, 12:16am UTC](https://mne.discourse.group/t/convert-discontinuous-data-to-continuous/3652/6 "2022-06-10T00:16:58Z")

</div>

Hi @eyamu ,  
As Richard mentioned above, it’s not a good idea as the removed epochs would create discontinuities in your data. However, if you still want to do that, you can use the following code.

```python
data = epochs.get_data()
pseudo_raw_data = np.hstack(data)
pseudo_raw = mne.io.RawArray(pseudo_raw_data, epochs.info)

```