eegdash 0.0.8__tar.gz → 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of eegdash might be problematic. Click here for more details.

Files changed (34) hide show
  1. {eegdash-0.0.8/src/eegdash.egg-info → eegdash-0.1.0}/PKG-INFO +26 -56
  2. {eegdash-0.0.8 → eegdash-0.1.0}/README.md +13 -46
  3. eegdash-0.1.0/eegdash/__init__.py +4 -0
  4. eegdash-0.1.0/eegdash/data_config.py +28 -0
  5. {eegdash-0.0.8/src → eegdash-0.1.0}/eegdash/data_utils.py +193 -148
  6. eegdash-0.1.0/eegdash/features/__init__.py +25 -0
  7. eegdash-0.1.0/eegdash/features/datasets.py +456 -0
  8. eegdash-0.1.0/eegdash/features/decorators.py +43 -0
  9. eegdash-0.1.0/eegdash/features/extractors.py +210 -0
  10. eegdash-0.1.0/eegdash/features/feature_bank/__init__.py +6 -0
  11. eegdash-0.1.0/eegdash/features/feature_bank/complexity.py +96 -0
  12. eegdash-0.1.0/eegdash/features/feature_bank/connectivity.py +59 -0
  13. eegdash-0.1.0/eegdash/features/feature_bank/csp.py +101 -0
  14. eegdash-0.1.0/eegdash/features/feature_bank/dimensionality.py +107 -0
  15. eegdash-0.1.0/eegdash/features/feature_bank/signal.py +103 -0
  16. eegdash-0.1.0/eegdash/features/feature_bank/spectral.py +116 -0
  17. eegdash-0.1.0/eegdash/features/feature_bank/utils.py +48 -0
  18. eegdash-0.1.0/eegdash/features/serialization.py +87 -0
  19. eegdash-0.1.0/eegdash/features/utils.py +116 -0
  20. eegdash-0.1.0/eegdash/main.py +416 -0
  21. {eegdash-0.0.8 → eegdash-0.1.0/eegdash.egg-info}/PKG-INFO +26 -56
  22. eegdash-0.1.0/eegdash.egg-info/SOURCES.txt +26 -0
  23. eegdash-0.1.0/eegdash.egg-info/requires.txt +13 -0
  24. eegdash-0.1.0/eegdash.egg-info/top_level.txt +1 -0
  25. eegdash-0.1.0/pyproject.toml +68 -0
  26. eegdash-0.0.8/pyproject.toml +0 -36
  27. eegdash-0.0.8/src/eegdash/__init__.py +0 -1
  28. eegdash-0.0.8/src/eegdash/main.py +0 -311
  29. eegdash-0.0.8/src/eegdash.egg-info/SOURCES.txt +0 -11
  30. eegdash-0.0.8/src/eegdash.egg-info/requires.txt +0 -10
  31. eegdash-0.0.8/src/eegdash.egg-info/top_level.txt +0 -2
  32. {eegdash-0.0.8 → eegdash-0.1.0}/LICENSE +0 -0
  33. {eegdash-0.0.8/src → eegdash-0.1.0}/eegdash.egg-info/dependency_links.txt +0 -0
  34. {eegdash-0.0.8 → eegdash-0.1.0}/setup.cfg +0 -0
{eegdash-0.0.8/src/eegdash.egg-info → eegdash-0.1.0}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: eegdash
3
- Version: 0.0.8
3
+ Version: 0.1.0
4
4
  Summary: EEG data for machine learning
5
5
  Author-email: Young Truong <dt.young112@gmail.com>, Arnaud Delorme <adelorme@gmail.com>
6
6
  License: GNU General Public License
@@ -29,19 +29,22 @@ Project-URL: Issues, https://github.com/sccn/EEG-Dash-Data/issues
29
29
  Classifier: Programming Language :: Python :: 3
30
30
  Classifier: License :: OSI Approved :: MIT License
31
31
  Classifier: Operating System :: OS Independent
32
- Requires-Python: >=3.8
32
+ Requires-Python: >3.10
33
33
  Description-Content-Type: text/markdown
34
34
  License-File: LICENSE
35
- Requires-Dist: xarray
35
+ Requires-Dist: braindecode
36
+ Requires-Dist: mne_bids
37
+ Requires-Dist: numba
38
+ Requires-Dist: numpy
39
+ Requires-Dist: pandas
40
+ Requires-Dist: pybids
41
+ Requires-Dist: pymongo
36
42
  Requires-Dist: python-dotenv
37
43
  Requires-Dist: s3fs
38
- Requires-Dist: mne
39
- Requires-Dist: pynwb
40
- Requires-Dist: h5py
41
- Requires-Dist: pymongo
42
- Requires-Dist: joblib
43
- Requires-Dist: braindecode
44
- Requires-Dist: mne-bids
44
+ Requires-Dist: scipy
45
+ Requires-Dist: tqdm
46
+ Requires-Dist: xarray
47
+ Requires-Dist: pre-commit
45
48
  Dynamic: license-file
46
49
 
47
50
  # EEG-Dash
@@ -50,60 +53,21 @@ To leverage recent and ongoing advancements in large-scale computational methods
50
53
  ## Data source
51
54
  The data in EEG-DaSh originates from a collaboration involving 25 laboratories, encompassing 27,053 participants. This extensive collection includes MEEG data, which is a combination of EEG and MEG signals. The data is sourced from various studies conducted by these labs, involving both healthy subjects and clinical populations with conditions such as ADHD, depression, schizophrenia, dementia, autism, and psychosis. Additionally, data spans different mental states like sleep, meditation, and cognitive tasks. In addition, EEG-DaSh will incorporate a subset of the data converted from NEMAR, which includes 330 MEEG BIDS-formatted datasets, further expanding the archive with well-curated, standardized neuroelectromagnetic data.
52
55
 
53
- ## Available data
56
+ ## Featured data
54
57
 
55
- The following datasets are currently available on EEGDash.
58
+ The following HBN datasets are currently featured on EEGDash. Documentation about these datasets is available [here](https://neuromechanist.github.io/data/hbn/).
56
59
 
57
60
  | DatasetID | Participants | Files | Sessions | Population | Channels | Is 10-20? | Modality | Size |
58
61
  |---|---|---|---|---|---|---|---|---|
59
- | [ds002181](https://nemar.org/dataexplorer/detail?dataset_id=ds002181) | 20 | 949 | 1 | Healthy | 63 | 10-20 | Visual | 0.163 GB |
60
- | [ds002578](https://nemar.org/dataexplorer/detail?dataset_id=ds002578) | 2 | 22 | 1 | Healthy | 256 | 10-20 | Visual | 0.001 TB |
61
- | [ds002680](https://nemar.org/dataexplorer/detail?dataset_id=ds002680) | 14 | 4977 | 2 | Healthy | 0 | 10-20 | Visual | 0.01 TB |
62
- | [ds002691](https://nemar.org/dataexplorer/detail?dataset_id=ds002691) | 20 | 146 | 1 | Healthy | 32 | other | Visual | 0.001 TB |
63
- | [ds002718](https://nemar.org/dataexplorer/detail?dataset_id=ds002718) | 18 | 582 | 1 | Healthy | 70 | other | Visual | 0.005 TB |
64
- | [ds003061](https://nemar.org/dataexplorer/detail?dataset_id=ds003061) | 13 | 282 | 1 | Not specified | 64 | 10-20 | Auditory | 0.002 TB |
65
- | [ds003690](https://nemar.org/dataexplorer/detail?dataset_id=ds003690) | 75 | 2630 | 1 | Healthy | 61 | 10-20 | Auditory | 0.023 TB |
66
- | [ds003805](https://nemar.org/dataexplorer/detail?dataset_id=ds003805) | 1 | 10 | 1 | Healthy | 19 | 10-20 | Multisensory | 0 TB |
67
- | [ds003838](https://nemar.org/dataexplorer/detail?dataset_id=ds003838) | 65 | 947 | 1 | Healthy | 63 | 10-20 | Auditory | 100.2 GB |
68
- | [ds004010](https://nemar.org/dataexplorer/detail?dataset_id=ds004010) | 24 | 102 | 1 | Healthy | 64 | other | Multisensory | 0.025 TB |
69
- | [ds004040](https://nemar.org/dataexplorer/detail?dataset_id=ds004040) | 13 | 160 | 2 | Healthy | 64 | 10-20 | Auditory | 0.012 TB |
70
- | [ds004350](https://nemar.org/dataexplorer/detail?dataset_id=ds004350) | 24 | 960 | 2 | Healthy | 64 | other | Visual | 0.023 TB |
71
- | [ds004362](https://nemar.org/dataexplorer/detail?dataset_id=ds004362) | 109 | 9162 | 1 | Healthy | 64 | 10-20 | Visual | 0.008 TB |
72
- | [ds004504](https://nemar.org/dataexplorer/detail?dataset_id=ds004504) | 88 | 269 | 1 | Dementia | 19 | 10-20 | Resting State | 2.6 GB |
73
- | [ds004554](https://nemar.org/dataexplorer/detail?dataset_id=ds004554) | 16 | 101 | 1 | Healthy | 99 | 10-20 | Visual | 0.009 TB |
74
- | [ds004635](https://nemar.org/dataexplorer/detail?dataset_id=ds004635) | 48 | 292 | 1 | Healthy | 129 | other | Multisensory | 26.1 GB |
75
- | [ds004657](https://nemar.org/dataexplorer/detail?dataset_id=ds004657) | 24 | 838 | 6 | Not specified | 64 | 10-20 | Motor | 43.1 GB |
76
- | [ds004660](https://nemar.org/dataexplorer/detail?dataset_id=ds004660) | 21 | 299 | 1 | Healthy | 32 | 10-20 | Multisensory | 7.2 GB |
77
- | [ds004661](https://nemar.org/dataexplorer/detail?dataset_id=ds004661) | 17 | 90 | 1 | Not specified | 64 | 10-20 | Multisensory | 1.4 GB |
78
- | [ds004745](https://nemar.org/dataexplorer/detail?dataset_id=ds004745) | 52 | 762 | 1 | Healthy | 64 | ? | Auditory | 0 TB |
79
- | [ds004785](https://nemar.org/dataexplorer/detail?dataset_id=ds004785) | 17 | 74 | 1 | Healthy | 32 | ? | Motor | 0 TB |
80
- | [ds004841](https://nemar.org/dataexplorer/detail?dataset_id=ds004841) | 20 | 1034 | 2 | Not specified | 64 | 10-20 | Multisensory | 7.3 GB |
81
- | [ds004842](https://nemar.org/dataexplorer/detail?dataset_id=ds004842) | 14 | 719 | 2 | Not specified | 64 | ? | Multisensory | 5.2 GB |
82
- | [ds004843](https://nemar.org/dataexplorer/detail?dataset_id=ds004843) | 14 | 649 | 1 | Not specified | 64 | ? | Visual | 7.7 GB |
83
- | [ds004844](https://nemar.org/dataexplorer/detail?dataset_id=ds004844) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 22.3 GB |
84
- | [ds004849](https://nemar.org/dataexplorer/detail?dataset_id=ds004849) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
85
- | [ds004850](https://nemar.org/dataexplorer/detail?dataset_id=ds004850) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
86
- | [ds004851](https://nemar.org/dataexplorer/detail?dataset_id=ds004851) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
87
- | [ds004852](https://nemar.org/dataexplorer/detail?dataset_id=ds004852) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
88
- | [ds004853](https://nemar.org/dataexplorer/detail?dataset_id=ds004853) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
89
- | [ds004854](https://nemar.org/dataexplorer/detail?dataset_id=ds004854) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
90
- | [ds004855](https://nemar.org/dataexplorer/detail?dataset_id=ds004855) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
91
- | [ds005034](https://nemar.org/dataexplorer/detail?dataset_id=ds005034) | 25 | 406 | 2 | Healthy | 129 | ? | Visual | 61.4 GB |
92
- | [ds005079](https://nemar.org/dataexplorer/detail?dataset_id=ds005079) | 1 | 210 | 12 | Healthy | 64 | ? | Multisensory | 1.7 GB |
93
- | [ds005342](https://nemar.org/dataexplorer/detail?dataset_id=ds005342) | 32 | 134 | 1 | Healthy | 17 | ? | Visual | 2 GB |
94
- | [ds005410](https://nemar.org/dataexplorer/detail?dataset_id=ds005410) | 81 | 492 | 1 | Healthy | 63 | ? | ? | 19.8 GB |
95
62
  | [ds005505](https://nemar.org/dataexplorer/detail?dataset_id=ds005505) | 136 | 5393 | 1 | Healthy | 129 | other | Visual | 103 GB |
96
63
  | [ds005506](https://nemar.org/dataexplorer/detail?dataset_id=ds005506) | 150 | 5645 | 1 | Healthy | 129 | other | Visual | 112 GB |
97
64
  | [ds005507](https://nemar.org/dataexplorer/detail?dataset_id=ds005507) | 184 | 7273 | 1 | Healthy | 129 | other | Visual | 140 GB |
98
65
  | [ds005508](https://nemar.org/dataexplorer/detail?dataset_id=ds005508) | 324 | 13393 | 1 | Healthy | 129 | other | Visual | 230 GB |
99
- | [ds005509](https://nemar.org/dataexplorer/detail?dataset_id=ds005509) | 330 | 19980 | 1 | Healthy | 129 | other | Visual | 224 GB |
100
66
  | [ds005510](https://nemar.org/dataexplorer/detail?dataset_id=ds005510) | 135 | 4933 | 1 | Healthy | 129 | other | Visual | 91 GB |
101
- | [ds005511](https://nemar.org/dataexplorer/detail?dataset_id=ds005511) | 381 | 18604 | 1 | Healthy | 129 | other | Visual | 245 GB |
102
67
  | [ds005512](https://nemar.org/dataexplorer/detail?dataset_id=ds005512) | 257 | 9305 | 1 | Healthy | 129 | other | Visual | 157 GB |
103
68
  | [ds005514](https://nemar.org/dataexplorer/detail?dataset_id=ds005514) | 295 | 11565 | 1 | Healthy | 129 | other | Visual | 185 GB |
104
- | [ds005672](https://nemar.org/dataexplorer/detail?dataset_id=ds005672) | 3 | 18 | 1 | Healthy | 64 | 10-20 | Visual | 4.2 GB |
105
- | [ds005697](https://nemar.org/dataexplorer/detail?dataset_id=ds005697) | 52 | 210 | 1 | Healthy | 64 | 10-20 | Visual | 67 GB |
106
- | [ds005787](https://nemar.org/dataexplorer/detail?dataset_id=ds005787) | 30 | ? | 4 | Healthy | 64 | 10-20 | Visual | 185 GB |
69
+
70
+ A total of [246 other datasets](datasets.md) are also available through EEGDash.
107
71
 
108
72
  ## Data format
109
73
  EEGDash queries return a **Pytorch Dataset** formatted to facilitate machine learning (ML) and deep learning (DL) applications. PyTorch Datasets are the best format for EEGDash queries because they provide an efficient, scalable, and flexible structure for machine learning (ML) and deep learning (DL) applications. They allow seamless integration with PyTorch’s DataLoader, enabling efficient batching, shuffling, and parallel data loading, which is essential for training deep learning models on large EEG datasets.
@@ -115,7 +79,7 @@ EEGDash datasets are processed using the popular [BrainDecode](https://braindeco
115
79
 
116
80
  ### Install
117
81
  Use your preferred Python environment manager with Python > 3.9 to install the package.
118
- * To install the eegdash package, use the following temporary command (a direct pip install eegdash option will be available soon): `pip install -i https://test.pypi.org/simple/eegdash`
82
+ * To install the eegdash package, use the following command: `pip install eegdash`
119
83
  * To verify the installation, start a Python session and type: `from eegdash import EEGDash`
120
84
 
121
85
  ### Data access
@@ -124,7 +88,10 @@ To use the data from a single subject, enter:
124
88
 
125
89
  ```python
126
90
  from eegdash import EEGDashDataset
127
- ds_NDARDB033FW5 = EEGDashDataset({'dataset': 'ds005514', 'task': 'RestingState', 'subject': 'NDARDB033FW5'})
91
+
92
+ ds_NDARDB033FW5 = EEGDashDataset(
93
+ {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
94
+ )
128
95
  ```
129
96
 
130
97
  This will search and download the metadata for the task **RestingState** for subject **NDARDB033FW5** in BIDS dataset **ds005514**. The actual data will not be downloaded at this stage. Following standard practice, data is only downloaded once it is processed. The **ds_NDARDB033FW5** object is a fully functional BrainDecode dataset, which is itself a PyTorch dataset. This [tutorial](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_eoec.ipynb) shows how to preprocess the EEG data, extracting portions of the data containing eyes-open and eyes-closed segments, then perform eyes-open vs. eyes-closed classification using a (shallow) deep-learning model.
@@ -133,7 +100,10 @@ To use the data from multiple subjects, enter:
133
100
 
134
101
  ```python
135
102
  from eegdash import EEGDashDataset
136
- ds_ds005505rest = EEGDashDataset({'dataset': 'ds005505', 'task': 'RestingState'}, target_name='sex')
103
+
104
+ ds_ds005505rest = EEGDashDataset(
105
+ {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
106
+ )
137
107
  ```
138
108
 
139
109
  This will search and download the metadata for the task 'RestingState' for all subjects in BIDS dataset 'ds005505' (a total of 136). As above, the actual data will not be downloaded at this stage so this command is quick to execute. Also, the target class for each subject is assigned using the target_name parameter. This means that this object is ready to be directly fed to a deep learning model, although the [tutorial script](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_sex_classification.ipynb) performs minimal processing on it, prior to training a deep-learning model. Because 14 gigabytes of data are downloaded, this tutorial takes about 10 minutes to execute.
{eegdash-0.0.8 → eegdash-0.1.0}/README.md RENAMED
@@ -4,60 +4,21 @@ To leverage recent and ongoing advancements in large-scale computational methods
4
4
  ## Data source
5
5
  The data in EEG-DaSh originates from a collaboration involving 25 laboratories, encompassing 27,053 participants. This extensive collection includes MEEG data, which is a combination of EEG and MEG signals. The data is sourced from various studies conducted by these labs, involving both healthy subjects and clinical populations with conditions such as ADHD, depression, schizophrenia, dementia, autism, and psychosis. Additionally, data spans different mental states like sleep, meditation, and cognitive tasks. In addition, EEG-DaSh will incorporate a subset of the data converted from NEMAR, which includes 330 MEEG BIDS-formatted datasets, further expanding the archive with well-curated, standardized neuroelectromagnetic data.
6
6
 
7
- ## Available data
7
+ ## Featured data
8
8
 
9
- The following datasets are currently available on EEGDash.
9
+ The following HBN datasets are currently featured on EEGDash. Documentation about these datasets is available [here](https://neuromechanist.github.io/data/hbn/).
10
10
 
11
11
  | DatasetID | Participants | Files | Sessions | Population | Channels | Is 10-20? | Modality | Size |
12
12
  |---|---|---|---|---|---|---|---|---|
13
- | [ds002181](https://nemar.org/dataexplorer/detail?dataset_id=ds002181) | 20 | 949 | 1 | Healthy | 63 | 10-20 | Visual | 0.163 GB |
14
- | [ds002578](https://nemar.org/dataexplorer/detail?dataset_id=ds002578) | 2 | 22 | 1 | Healthy | 256 | 10-20 | Visual | 0.001 TB |
15
- | [ds002680](https://nemar.org/dataexplorer/detail?dataset_id=ds002680) | 14 | 4977 | 2 | Healthy | 0 | 10-20 | Visual | 0.01 TB |
16
- | [ds002691](https://nemar.org/dataexplorer/detail?dataset_id=ds002691) | 20 | 146 | 1 | Healthy | 32 | other | Visual | 0.001 TB |
17
- | [ds002718](https://nemar.org/dataexplorer/detail?dataset_id=ds002718) | 18 | 582 | 1 | Healthy | 70 | other | Visual | 0.005 TB |
18
- | [ds003061](https://nemar.org/dataexplorer/detail?dataset_id=ds003061) | 13 | 282 | 1 | Not specified | 64 | 10-20 | Auditory | 0.002 TB |
19
- | [ds003690](https://nemar.org/dataexplorer/detail?dataset_id=ds003690) | 75 | 2630 | 1 | Healthy | 61 | 10-20 | Auditory | 0.023 TB |
20
- | [ds003805](https://nemar.org/dataexplorer/detail?dataset_id=ds003805) | 1 | 10 | 1 | Healthy | 19 | 10-20 | Multisensory | 0 TB |
21
- | [ds003838](https://nemar.org/dataexplorer/detail?dataset_id=ds003838) | 65 | 947 | 1 | Healthy | 63 | 10-20 | Auditory | 100.2 GB |
22
- | [ds004010](https://nemar.org/dataexplorer/detail?dataset_id=ds004010) | 24 | 102 | 1 | Healthy | 64 | other | Multisensory | 0.025 TB |
23
- | [ds004040](https://nemar.org/dataexplorer/detail?dataset_id=ds004040) | 13 | 160 | 2 | Healthy | 64 | 10-20 | Auditory | 0.012 TB |
24
- | [ds004350](https://nemar.org/dataexplorer/detail?dataset_id=ds004350) | 24 | 960 | 2 | Healthy | 64 | other | Visual | 0.023 TB |
25
- | [ds004362](https://nemar.org/dataexplorer/detail?dataset_id=ds004362) | 109 | 9162 | 1 | Healthy | 64 | 10-20 | Visual | 0.008 TB |
26
- | [ds004504](https://nemar.org/dataexplorer/detail?dataset_id=ds004504) | 88 | 269 | 1 | Dementia | 19 | 10-20 | Resting State | 2.6 GB |
27
- | [ds004554](https://nemar.org/dataexplorer/detail?dataset_id=ds004554) | 16 | 101 | 1 | Healthy | 99 | 10-20 | Visual | 0.009 TB |
28
- | [ds004635](https://nemar.org/dataexplorer/detail?dataset_id=ds004635) | 48 | 292 | 1 | Healthy | 129 | other | Multisensory | 26.1 GB |
29
- | [ds004657](https://nemar.org/dataexplorer/detail?dataset_id=ds004657) | 24 | 838 | 6 | Not specified | 64 | 10-20 | Motor | 43.1 GB |
30
- | [ds004660](https://nemar.org/dataexplorer/detail?dataset_id=ds004660) | 21 | 299 | 1 | Healthy | 32 | 10-20 | Multisensory | 7.2 GB |
31
- | [ds004661](https://nemar.org/dataexplorer/detail?dataset_id=ds004661) | 17 | 90 | 1 | Not specified | 64 | 10-20 | Multisensory | 1.4 GB |
32
- | [ds004745](https://nemar.org/dataexplorer/detail?dataset_id=ds004745) | 52 | 762 | 1 | Healthy | 64 | ? | Auditory | 0 TB |
33
- | [ds004785](https://nemar.org/dataexplorer/detail?dataset_id=ds004785) | 17 | 74 | 1 | Healthy | 32 | ? | Motor | 0 TB |
34
- | [ds004841](https://nemar.org/dataexplorer/detail?dataset_id=ds004841) | 20 | 1034 | 2 | Not specified | 64 | 10-20 | Multisensory | 7.3 GB |
35
- | [ds004842](https://nemar.org/dataexplorer/detail?dataset_id=ds004842) | 14 | 719 | 2 | Not specified | 64 | ? | Multisensory | 5.2 GB |
36
- | [ds004843](https://nemar.org/dataexplorer/detail?dataset_id=ds004843) | 14 | 649 | 1 | Not specified | 64 | ? | Visual | 7.7 GB |
37
- | [ds004844](https://nemar.org/dataexplorer/detail?dataset_id=ds004844) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 22.3 GB |
38
- | [ds004849](https://nemar.org/dataexplorer/detail?dataset_id=ds004849) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
39
- | [ds004850](https://nemar.org/dataexplorer/detail?dataset_id=ds004850) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
40
- | [ds004851](https://nemar.org/dataexplorer/detail?dataset_id=ds004851) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
41
- | [ds004852](https://nemar.org/dataexplorer/detail?dataset_id=ds004852) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
42
- | [ds004853](https://nemar.org/dataexplorer/detail?dataset_id=ds004853) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
43
- | [ds004854](https://nemar.org/dataexplorer/detail?dataset_id=ds004854) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
44
- | [ds004855](https://nemar.org/dataexplorer/detail?dataset_id=ds004855) | 17 | 481 | 4 | Not specified | 64 | ? | Multisensory | 0.077 GB |
45
- | [ds005034](https://nemar.org/dataexplorer/detail?dataset_id=ds005034) | 25 | 406 | 2 | Healthy | 129 | ? | Visual | 61.4 GB |
46
- | [ds005079](https://nemar.org/dataexplorer/detail?dataset_id=ds005079) | 1 | 210 | 12 | Healthy | 64 | ? | Multisensory | 1.7 GB |
47
- | [ds005342](https://nemar.org/dataexplorer/detail?dataset_id=ds005342) | 32 | 134 | 1 | Healthy | 17 | ? | Visual | 2 GB |
48
- | [ds005410](https://nemar.org/dataexplorer/detail?dataset_id=ds005410) | 81 | 492 | 1 | Healthy | 63 | ? | ? | 19.8 GB |
49
13
  | [ds005505](https://nemar.org/dataexplorer/detail?dataset_id=ds005505) | 136 | 5393 | 1 | Healthy | 129 | other | Visual | 103 GB |
50
14
  | [ds005506](https://nemar.org/dataexplorer/detail?dataset_id=ds005506) | 150 | 5645 | 1 | Healthy | 129 | other | Visual | 112 GB |
51
15
  | [ds005507](https://nemar.org/dataexplorer/detail?dataset_id=ds005507) | 184 | 7273 | 1 | Healthy | 129 | other | Visual | 140 GB |
52
16
  | [ds005508](https://nemar.org/dataexplorer/detail?dataset_id=ds005508) | 324 | 13393 | 1 | Healthy | 129 | other | Visual | 230 GB |
53
- | [ds005509](https://nemar.org/dataexplorer/detail?dataset_id=ds005509) | 330 | 19980 | 1 | Healthy | 129 | other | Visual | 224 GB |
54
17
  | [ds005510](https://nemar.org/dataexplorer/detail?dataset_id=ds005510) | 135 | 4933 | 1 | Healthy | 129 | other | Visual | 91 GB |
55
- | [ds005511](https://nemar.org/dataexplorer/detail?dataset_id=ds005511) | 381 | 18604 | 1 | Healthy | 129 | other | Visual | 245 GB |
56
18
  | [ds005512](https://nemar.org/dataexplorer/detail?dataset_id=ds005512) | 257 | 9305 | 1 | Healthy | 129 | other | Visual | 157 GB |
57
19
  | [ds005514](https://nemar.org/dataexplorer/detail?dataset_id=ds005514) | 295 | 11565 | 1 | Healthy | 129 | other | Visual | 185 GB |
58
- | [ds005672](https://nemar.org/dataexplorer/detail?dataset_id=ds005672) | 3 | 18 | 1 | Healthy | 64 | 10-20 | Visual | 4.2 GB |
59
- | [ds005697](https://nemar.org/dataexplorer/detail?dataset_id=ds005697) | 52 | 210 | 1 | Healthy | 64 | 10-20 | Visual | 67 GB |
60
- | [ds005787](https://nemar.org/dataexplorer/detail?dataset_id=ds005787) | 30 | ? | 4 | Healthy | 64 | 10-20 | Visual | 185 GB |
20
+
21
+ A total of [246 other datasets](datasets.md) are also available through EEGDash.
61
22
 
62
23
  ## Data format
63
24
  EEGDash queries return a **Pytorch Dataset** formatted to facilitate machine learning (ML) and deep learning (DL) applications. PyTorch Datasets are the best format for EEGDash queries because they provide an efficient, scalable, and flexible structure for machine learning (ML) and deep learning (DL) applications. They allow seamless integration with PyTorch’s DataLoader, enabling efficient batching, shuffling, and parallel data loading, which is essential for training deep learning models on large EEG datasets.
@@ -69,7 +30,7 @@ EEGDash datasets are processed using the popular [BrainDecode](https://braindeco
69
30
 
70
31
  ### Install
71
32
  Use your preferred Python environment manager with Python > 3.9 to install the package.
72
- * To install the eegdash package, use the following temporary command (a direct pip install eegdash option will be available soon): `pip install -i https://test.pypi.org/simple/eegdash`
33
+ * To install the eegdash package, use the following command: `pip install eegdash`
73
34
  * To verify the installation, start a Python session and type: `from eegdash import EEGDash`
74
35
 
75
36
  ### Data access
@@ -78,7 +39,10 @@ To use the data from a single subject, enter:
78
39
 
79
40
  ```python
80
41
  from eegdash import EEGDashDataset
81
- ds_NDARDB033FW5 = EEGDashDataset({'dataset': 'ds005514', 'task': 'RestingState', 'subject': 'NDARDB033FW5'})
42
+
43
+ ds_NDARDB033FW5 = EEGDashDataset(
44
+ {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
45
+ )
82
46
  ```
83
47
 
84
48
  This will search and download the metadata for the task **RestingState** for subject **NDARDB033FW5** in BIDS dataset **ds005514**. The actual data will not be downloaded at this stage. Following standard practice, data is only downloaded once it is processed. The **ds_NDARDB033FW5** object is a fully functional BrainDecode dataset, which is itself a PyTorch dataset. This [tutorial](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_eoec.ipynb) shows how to preprocess the EEG data, extracting portions of the data containing eyes-open and eyes-closed segments, then perform eyes-open vs. eyes-closed classification using a (shallow) deep-learning model.
@@ -87,7 +51,10 @@ To use the data from multiple subjects, enter:
87
51
 
88
52
  ```python
89
53
  from eegdash import EEGDashDataset
90
- ds_ds005505rest = EEGDashDataset({'dataset': 'ds005505', 'task': 'RestingState'}, target_name='sex')
54
+
55
+ ds_ds005505rest = EEGDashDataset(
56
+ {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
57
+ )
91
58
  ```
92
59
 
93
60
  This will search and download the metadata for the task 'RestingState' for all subjects in BIDS dataset 'ds005505' (a total of 136). As above, the actual data will not be downloaded at this stage so this command is quick to execute. Also, the target class for each subject is assigned using the target_name parameter. This means that this object is ready to be directly fed to a deep learning model, although the [tutorial script](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_sex_classification.ipynb) performs minimal processing on it, prior to training a deep-learning model. Because 14 gigabytes of data are downloaded, this tutorial takes about 10 minutes to execute.
eegdash-0.1.0/eegdash/__init__.py ADDED
@@ -0,0 +1,4 @@
1
+ from .main import EEGDash, EEGDashDataset
2
+
3
+ __all__ = ["EEGDash", "EEGDashDataset"]
4
+ __version__ = "0.1.0"
eegdash-0.1.0/eegdash/data_config.py ADDED
@@ -0,0 +1,28 @@
1
+ config = {
2
+ "required_fields": ["data_name"],
3
+ "attributes": {
4
+ "data_name": "str",
5
+ "dataset": "str",
6
+ "bidspath": "str",
7
+ "subject": "str",
8
+ "task": "str",
9
+ "session": "str",
10
+ "run": "str",
11
+ "sampling_frequency": "float",
12
+ "modality": "str",
13
+ "nchans": "int",
14
+ "ntimes": "int",
15
+ },
16
+ "description_fields": ["subject", "session", "run", "task", "age", "gender", "sex"],
17
+ "bids_dependencies_files": [
18
+ "dataset_description.json",
19
+ "participants.tsv",
20
+ "events.tsv",
21
+ "events.json",
22
+ "eeg.json",
23
+ "electrodes.tsv",
24
+ "channels.tsv",
25
+ "coordsystem.json",
26
+ ],
27
+ "accepted_query_fields": ["data_name", "dataset"],
28
+ }