You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
pyEEG is a library for processing EEG data built mostly on top of MNE-py and scikit-learn. It is framed to work with data collected with naturalistic stimuli, therefore with continuous recordings rather than trial-based designs. It allows analysis of continuous m/eeg and generation of temporal response functions with continuous signals as stimuli or real-valued events (e.g. word-level or phoneme-level features).
8
+
`natMEEG` is a library for processing M/EEG data built mostly on top of MNE-py and scikit-learn. It is framed to work with data collected with naturalistic stimuli, therefore with continuous recordings rather than trial-based designs. It allows analysis of continuous m/eeg and generation of temporal response functions with continuous signals as stimuli or real-valued events (e.g. word-level or phoneme-level features).
8
9
9
10
You can find the [documentation here](https://hugo-w.github.io/pyEEG-docs/index.html).
10
11
11
-
> Note that this code repository is relatively old and **unmaintained**. Most useful code about computing TRF is contained in `pyeeg/models.py`, especially in the class `TRFEstimator` and the function `_svd_regress`: the latter implements TRF estimation with memory efficient and accelerated computation for handling multiple epochs or multiple subjects.
12
+
> ⚠️**Caution**:
13
+
> - Note that this code repository is relatively old and **unmaintained**. Most useful code about computing TRF is contained in `pyeeg/models.py`, especially in the class `TRFEstimator` and the function `_svd_regress`: the latter implements TRF estimation with memory efficient and accelerated computation for handling multiple epochs or multiple subjects.
14
+
> - It is recommended to use the code as a reference for your own implementation rather than relying on it for production use.
15
+
> - Finaly note that the repository went through a name change from `pyEEG` to `natMEEG`, so you might find references to `pyEEG` in the code and documentation.
12
16
13
17
------
14
18
15
19
## Installation
16
20
17
21
### Dependencies
18
22
19
-
pyEEG requires:
23
+
natMEEG requires:
20
24
21
25
- Python (>= 3.10)
22
26
- psutil
@@ -35,7 +39,7 @@ Install requirements:
35
39
pip install -r requirements.txt
36
40
```
37
41
38
-
To generate the doc, Python package `sphinx` (>= 1.1.0), `sphinx_rtd_theme` and `nbsphinx` are required (`sphinx` can be installed from `conda` and the others from `pip`).
42
+
To generate the doc, Python package `sphinx` (>= 1.1.0), `sphinx_rtd_theme` and `nbsphinx` are required.
39
43
40
44
### User Installation
41
45
@@ -44,12 +48,24 @@ To generate the doc, Python package `sphinx` (>= 1.1.0), `sphinx_rtd_theme` and
44
48
You can install the package from PyPI using `pip`:
45
49
46
50
```bash
47
-
pip install pyEEG
51
+
pip install natMEEG
52
+
```
53
+
54
+
If you want to install docs building dependencies, you can do:
55
+
56
+
```bash
57
+
pip install natMEEG[docs]
58
+
```
59
+
60
+
If you want to install the package with all dependencies (including MNE), you can do:
61
+
62
+
```bash
63
+
pip install natMEEG[full]
48
64
```
49
65
50
66
### From Source
51
67
52
-
From terminal (or `conda` shell in Windows), `cd` in root directory of the library (directory containing `setup.py` file) and type:
68
+
From terminal, `cd` in root directory of the library after cloning this repository (directory containing `pyproject.toml` file).
53
69
54
70
To get the package installed only through symbolic links, namely so that you can modify the source code and use modified versions at will when importing the package in your python scripts do:
0 commit comments