braindecode 0.5__tar.gz → 0.5.1__tar.gz

{Braindecode-0.5 → Braindecode-0.5.1}/Braindecode.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.1
 Name: Braindecode
-Version: 0.5
+Version: 0.5.1
 Summary: A deep learning toolbox to decode raw time-domain EEG.
 Home-page: https://github.com/braindecode/braindecode
 Author: Robin Tibor Schirrmeister
@@ -13,8 +13,8 @@ Description: Braindecode
            :alt: Join the chat at https://gitter.im/braindecodechat/community
            :target: https://gitter.im/braindecodechat/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge
         
-        .. image:: https://travis-ci.org/braindecode/braindecode.svg?branch=master
-           :target: https://travis-ci.org/braindecode/braindecode
+        .. image:: https://github.com/braindecode/braindecode/workflows/tests-and-docs/badge.svg
+           :target: https://github.com/braindecode/braindecode/actions
         
         .. image:: https://circleci.com/gh/braindecode/braindecode.svg?style=svg
            :target: https://circleci.com/gh/braindecode/braindecode
@@ -36,7 +36,13 @@ Description: Braindecode
         
         1. Install pytorch from http://pytorch.org/ (you don't need to install torchvision).
         
-        2. Install latest release of braindecode via pip:
+        2. Install `MOABB <https://github.com/NeuroTechX/moabb>`_ via pip (needed if you want to use MOABB datasets utilities):
+        
+        .. code-block:: bash
+        
+          pip install moabb
+        
+        3. Install latest release of braindecode via pip:
         
         .. code-block:: bash
         
@@ -46,16 +52,11 @@ Description: Braindecode
         
         .. code-block:: bash
         
-        	curl -O https://raw.githubusercontent.com/braindecode/braindecode/master/environment.yml
-        	conda env create -f environment.yml
-        	conda activate braindecode
-        
-        .. note::
-          The latest development version of mne-python is currently required for
-          improvements to lazy loading performance. (commit 3989f998c5f974ed37e97fa3e6c8ead0f5a1cb2a).
+          curl -O https://raw.githubusercontent.com/braindecode/braindecode/master/environment.yml
+          conda env create -f environment.yml
+          conda activate braindecode
         
-        Install the latest version of braindecode via pip:
-        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+        alternatively, install the latest version of braindecode via pip:
         
         .. code-block:: bash
         

{Braindecode-0.5 → Braindecode-0.5.1}/Braindecode.egg-info/SOURCES.txt

@@ -17,18 +17,16 @@ braindecode/version.py
 braindecode/datasets/__init__.py
 braindecode/datasets/base.py
 braindecode/datasets/bbci.py
-braindecode/datasets/mne.py
 braindecode/datasets/moabb.py
+braindecode/datasets/sleep_physionet.py
 braindecode/datasets/tuh.py
-braindecode/datasets/xy.py
 braindecode/datautil/__init__.py
+braindecode/datautil/mne.py
 braindecode/datautil/preprocess.py
+braindecode/datautil/serialization.py
 braindecode/datautil/util.py
 braindecode/datautil/windowers.py
-braindecode/experiments/__init__.py
-braindecode/experiments/bcic_iv_2a/__init__.py
-braindecode/experiments/bcic_iv_2a/config.py
-braindecode/experiments/bcic_iv_2a/run.py
+braindecode/datautil/xy.py
 braindecode/models/__init__.py
 braindecode/models/deep4.py
 braindecode/models/eegnet.py
@@ -37,7 +35,12 @@ braindecode/models/functions.py
 braindecode/models/hybrid.py
 braindecode/models/modules.py
 braindecode/models/shallow_fbcsp.py
+braindecode/models/sleep_stager_chambon_2018.py
+braindecode/models/tcn.py
 braindecode/models/util.py
+braindecode/samplers/__init__.py
+braindecode/samplers/base.py
+braindecode/samplers/ssl.py
 braindecode/training/__init__.py
 braindecode/training/callbacks.py
 braindecode/training/losses.py
@@ -48,12 +51,18 @@ docs/Makefile
 docs/api.rst
 docs/conf.py
 docs/index.rst
+docs/whats_new.rst
 docs/_build/html/_downloads/1224801107d6c3b138edf8ee33de0561/plot_bcic_iv_2a_moabb_cropped.ipynb
 docs/_build/html/_downloads/176a7695926ccfe061692c4af12b673d/plot_dataset_example.ipynb
 docs/_build/html/_downloads/25408d8d92a873e370d4750ba414b84a/benchmark_lazy_eager_loading.ipynb
+docs/_build/html/_downloads/3e0455c88adcaa2571230abb981020db/plot_relative_positioning.ipynb
+docs/_build/html/_downloads/4855a497085ac8dc60a648bf4a72d647/plot_load_save_datasets.ipynb
 docs/_build/html/_downloads/49b1f19a86467aeaf762a1550583a845/plot_custom_dataset_example.ipynb
+docs/_build/html/_downloads/5bafba0488197e377d459780399abb29/plot_sleep_staging.ipynb
 docs/_build/html/_downloads/748680401b0360239d00624375dd9587/plot_bcic_iv_2a_moabb_trial.ipynb
+docs/_build/html/_downloads/8c06a965e21b52d199f98636388aaa21/tuh_eeg_corpus.ipynb
 docs/_build/html/_downloads/9c64c2c15907a661b1fe2d7dd209a434/plot_regression.ipynb
+docs/_build/html/_downloads/b38e40c9ee338673865922575e84fd7f/plot_split_dataset.ipynb
 docs/_build/html/_downloads/e42b5bd97033be02521040b0d5ee21c3/plot_mne_dataset_example.ipynb
 docs/_templates/autosummary/class.rst
 docs/_templates/autosummary/function.rst
@@ -68,23 +77,41 @@ docs/auto_examples/plot_custom_dataset_example.ipynb
 docs/auto_examples/plot_custom_dataset_example.rst
 docs/auto_examples/plot_dataset_example.ipynb
 docs/auto_examples/plot_dataset_example.rst
+docs/auto_examples/plot_load_save_datasets.ipynb
+docs/auto_examples/plot_load_save_datasets.rst
 docs/auto_examples/plot_mne_dataset_example.ipynb
 docs/auto_examples/plot_mne_dataset_example.rst
 docs/auto_examples/plot_regression.ipynb
 docs/auto_examples/plot_regression.rst
+docs/auto_examples/plot_relative_positioning.ipynb
+docs/auto_examples/plot_relative_positioning.rst
+docs/auto_examples/plot_sleep_staging.ipynb
+docs/auto_examples/plot_sleep_staging.rst
+docs/auto_examples/plot_split_dataset.ipynb
+docs/auto_examples/plot_split_dataset.rst
 docs/auto_examples/sg_execution_times.rst
+docs/auto_examples/tuh_eeg_corpus.ipynb
+docs/auto_examples/tuh_eeg_corpus.rst
 docs/generated/braindecode.classifier.EEGClassifier.rst
 docs/generated/braindecode.datasets.BaseConcatDataset.rst
 docs/generated/braindecode.datasets.BaseDataset.rst
 docs/generated/braindecode.datasets.MOABBDataset.rst
+docs/generated/braindecode.datasets.SleepPhysionet.rst
+docs/generated/braindecode.datasets.TUH.rst
+docs/generated/braindecode.datasets.TUHAbnormal.rst
 docs/generated/braindecode.datasets.WindowsDataset.rst
-docs/generated/braindecode.datasets.create_from_X_y.rst
-docs/generated/braindecode.datasets.create_from_mne_epochs.rst
-docs/generated/braindecode.datasets.create_from_mne_raw.rst
+docs/generated/braindecode.datautil.Preprocessor.rst
 docs/generated/braindecode.datautil.create_fixed_length_windows.rst
+docs/generated/braindecode.datautil.create_from_X_y.rst
+docs/generated/braindecode.datautil.create_from_mne_epochs.rst
+docs/generated/braindecode.datautil.create_from_mne_raw.rst
 docs/generated/braindecode.datautil.create_windows_from_events.rst
 docs/generated/braindecode.datautil.exponential_moving_demean.rst
 docs/generated/braindecode.datautil.exponential_moving_standardize.rst
+docs/generated/braindecode.datautil.filterbank.rst
+docs/generated/braindecode.datautil.load_concat_dataset.rst
+docs/generated/braindecode.datautil.preprocess.rst
+docs/generated/braindecode.datautil.save_concat_dataset.rst
 docs/generated/braindecode.datautil.scale.rst
 docs/generated/braindecode.datautil.zscore.rst
 docs/generated/braindecode.models.Deep4Net.rst
@@ -93,18 +120,41 @@ docs/generated/braindecode.models.EEGNetv4.rst
 docs/generated/braindecode.models.EEGResNet.rst
 docs/generated/braindecode.models.HybridNet.rst
 docs/generated/braindecode.models.ShallowFBCSPNet.rst
+docs/generated/braindecode.models.SleepStagerChambon2018.rst
+docs/generated/braindecode.models.TCN.rst
+docs/generated/braindecode.models.get_output_shape.rst
 docs/generated/braindecode.regressor.EEGRegressor.rst
+docs/generated/braindecode.samplers.RecordingSampler.rst
+docs/generated/braindecode.samplers.RelativePositioningSampler.rst
 docs/generated/braindecode.training.CroppedLoss.rst
 docs/generated/braindecode.training.CroppedTrialEpochScoring.rst
 docs/generated/braindecode.training.PostEpochTrainScoring.rst
 docs/generated/braindecode.training.trial_preds_from_window_preds.rst
 docs/generated/braindecode.util.set_random_seeds.rst
-docs/notebooks/Untitled.ipynb
-docs/source/braindecode.datasets.rst
-docs/source/braindecode.datautil.rst
-docs/source/braindecode.experiments.bcic_iv_2a.rst
-docs/source/braindecode.experiments.rst
-docs/source/braindecode.models.rst
-docs/source/braindecode.rst
-docs/source/braindecode.visualization.rst
-docs/source/modules.rst
+docs/generated/braindecode.visualization.compute_amplitude_gradients.rst
+test/__init__.py
+test/acceptance_tests/__init__.py
+test/acceptance_tests/test_cropped_decoding.py
+test/acceptance_tests/test_eeg_classifier.py
+test/acceptance_tests/test_model_architectures.py
+test/acceptance_tests/test_trialwise_decoding.py
+test/unit_tests/__init__.py
+test/unit_tests/test_eeg_classifier.py
+test/unit_tests/test_eeg_regressor.py
+test/unit_tests/test_scoring.py
+test/unit_tests/test_util.py
+test/unit_tests/datasets/__init__.py
+test/unit_tests/datasets/test_dataset.py
+test/unit_tests/datasets/test_mne.py
+test/unit_tests/datasets/test_sleep_physionet.py
+test/unit_tests/datasets/test_tuh.py
+test/unit_tests/datasets/test_xy.py
+test/unit_tests/datautil/__init__.py
+test/unit_tests/datautil/test_preprocess.py
+test/unit_tests/datautil/test_serialization.py
+test/unit_tests/datautil/test_windowers.py
+test/unit_tests/models/__init__.py
+test/unit_tests/models/test_models.py
+test/unit_tests/models/test_util.py
+test/unit_tests/visualization/__init__.py
+test/unit_tests/visualization/test_gradients.py

{Braindecode-0.5 → Braindecode-0.5.1}/Braindecode.egg-info/top_level.txt

@@ -1 +1,2 @@
 braindecode
+test

{Braindecode-0.5 → Braindecode-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.1
 Name: Braindecode
-Version: 0.5
+Version: 0.5.1
 Summary: A deep learning toolbox to decode raw time-domain EEG.
 Home-page: https://github.com/braindecode/braindecode
 Author: Robin Tibor Schirrmeister
@@ -13,8 +13,8 @@ Description: Braindecode
            :alt: Join the chat at https://gitter.im/braindecodechat/community
            :target: https://gitter.im/braindecodechat/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge
         
-        .. image:: https://travis-ci.org/braindecode/braindecode.svg?branch=master
-           :target: https://travis-ci.org/braindecode/braindecode
+        .. image:: https://github.com/braindecode/braindecode/workflows/tests-and-docs/badge.svg
+           :target: https://github.com/braindecode/braindecode/actions
         
         .. image:: https://circleci.com/gh/braindecode/braindecode.svg?style=svg
            :target: https://circleci.com/gh/braindecode/braindecode
@@ -36,7 +36,13 @@ Description: Braindecode
         
         1. Install pytorch from http://pytorch.org/ (you don't need to install torchvision).
         
-        2. Install latest release of braindecode via pip:
+        2. Install `MOABB <https://github.com/NeuroTechX/moabb>`_ via pip (needed if you want to use MOABB datasets utilities):
+        
+        .. code-block:: bash
+        
+          pip install moabb
+        
+        3. Install latest release of braindecode via pip:
         
         .. code-block:: bash
         
@@ -46,16 +52,11 @@ Description: Braindecode
         
         .. code-block:: bash
         
-        	curl -O https://raw.githubusercontent.com/braindecode/braindecode/master/environment.yml
-        	conda env create -f environment.yml
-        	conda activate braindecode
-        
-        .. note::
-          The latest development version of mne-python is currently required for
-          improvements to lazy loading performance. (commit 3989f998c5f974ed37e97fa3e6c8ead0f5a1cb2a).
+          curl -O https://raw.githubusercontent.com/braindecode/braindecode/master/environment.yml
+          conda env create -f environment.yml
+          conda activate braindecode
         
-        Install the latest version of braindecode via pip:
-        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+        alternatively, install the latest version of braindecode via pip:
         
         .. code-block:: bash
         

{Braindecode-0.5 → Braindecode-0.5.1}/README.rst

@@ -5,8 +5,8 @@ Braindecode
    :alt: Join the chat at https://gitter.im/braindecodechat/community
    :target: https://gitter.im/braindecodechat/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge
 
-.. image:: https://travis-ci.org/braindecode/braindecode.svg?branch=master
-   :target: https://travis-ci.org/braindecode/braindecode
+.. image:: https://github.com/braindecode/braindecode/workflows/tests-and-docs/badge.svg
+   :target: https://github.com/braindecode/braindecode/actions
 
 .. image:: https://circleci.com/gh/braindecode/braindecode.svg?style=svg
    :target: https://circleci.com/gh/braindecode/braindecode
@@ -28,7 +28,13 @@ Installation
 
 1. Install pytorch from http://pytorch.org/ (you don't need to install torchvision).
 
-2. Install latest release of braindecode via pip:
+2. Install `MOABB <https://github.com/NeuroTechX/moabb>`_ via pip (needed if you want to use MOABB datasets utilities):
+
+.. code-block:: bash
+
+  pip install moabb
+
+3. Install latest release of braindecode via pip:
 
 .. code-block:: bash
 
@@ -38,16 +44,11 @@ alternatively, if you use conda, you could create a dedicated environment with t
 
 .. code-block:: bash
 
-	curl -O https://raw.githubusercontent.com/braindecode/braindecode/master/environment.yml
-	conda env create -f environment.yml
-	conda activate braindecode
-
-.. note::
-  The latest development version of mne-python is currently required for
-  improvements to lazy loading performance. (commit 3989f998c5f974ed37e97fa3e6c8ead0f5a1cb2a).
+  curl -O https://raw.githubusercontent.com/braindecode/braindecode/master/environment.yml
+  conda env create -f environment.yml
+  conda activate braindecode
 
-Install the latest version of braindecode via pip:
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+alternatively, install the latest version of braindecode via pip:
 
 .. code-block:: bash
 

{Braindecode-0.5 → Braindecode-0.5.1}/braindecode/classifier.py

@@ -3,7 +3,7 @@ from sklearn.metrics import get_scorer
 from skorch.callbacks import EpochTimer, BatchScoring, PrintLog, EpochScoring
 from skorch.classifier import NeuralNet
 from skorch.classifier import NeuralNetClassifier
-from skorch.utils import train_loss_score, valid_loss_score, noop
+from skorch.utils import train_loss_score, valid_loss_score, noop, to_numpy
 
 from .training.scoring import PostEpochTrainScoring, CroppedTrialEpochScoring
 from .util import ThrowAwayIndexLoader, update_estimator_docstring
@@ -153,7 +153,7 @@ class EEGClassifier(NeuralNetClassifier):
         for X, y, i in self.get_iterator(dataset, drop_index=False):
             i_window_in_trials.append(i[0].cpu().numpy())
             i_window_stops.append(i[2].cpu().numpy())
-            preds.append(self.predict_proba(X))
+            preds.append(to_numpy(self.forward(X)))
             window_ys.append(y.cpu().numpy())
         preds = np.concatenate(preds)
         i_window_in_trials = np.concatenate(i_window_in_trials)
@@ -186,3 +186,73 @@ class EEGClassifier(NeuralNetClassifier):
             ),
             ("print_log", PrintLog()),
         ]
+
+    def predict_proba(self, X):
+        """Return the output of the module's forward method as a numpy
+        array. In case of cropped decoding returns averaged values for
+        each trial.
+
+        If the module's forward method returns multiple outputs as a
+        tuple, it is assumed that the first output contains the
+        relevant information and the other values are ignored.
+        If all values are relevant or module's output for each crop
+        is needed, consider using :func:`~skorch.NeuralNet.forward`
+        instead.
+
+        Parameters
+        ----------
+        X : input data, compatible with skorch.dataset.Dataset
+          By default, you should be able to pass:
+
+            * numpy arrays
+            * torch tensors
+            * pandas DataFrame or Series
+            * scipy sparse CSR matrices
+            * a dictionary of the former three
+            * a list/tuple of the former three
+            * a Dataset
+
+          If this doesn't work with your data, you have to pass a
+          ``Dataset`` that can deal with the data.
+
+        Returns
+        -------
+        y_proba : numpy ndarray
+
+        """
+        y_pred = super().predict_proba(X)
+        # Normally, we have to average the predictions across crops/timesteps
+        # to get one prediction per window/trial
+        # Predictions may be already averaged in CroppedTrialEpochScoring (y_pred.shape==2).
+        # However, when predictions are computed outside of CroppedTrialEpochScoring
+        # we have to average predictions, hence the check if len(y_pred.shape) == 3
+        if self.cropped and len(y_pred.shape) == 3:
+            return y_pred.mean(axis=-1)
+        else:
+            return y_pred
+
+    def predict(self, X):
+        """Return class labels for samples in X.
+
+        Parameters
+        ----------
+        X : input data, compatible with skorch.dataset.Dataset
+          By default, you should be able to pass:
+
+            * numpy arrays
+            * torch tensors
+            * pandas DataFrame or Series
+            * scipy sparse CSR matrices
+            * a dictionary of the former three
+            * a list/tuple of the former three
+            * a Dataset
+
+          If this doesn't work with your data, you have to pass a
+          ``Dataset`` that can deal with the data.
+
+        Returns
+        -------
+        y_pred : numpy ndarray
+
+        """
+        return self.predict_proba(X).argmax(1)

{Braindecode-0.5 → Braindecode-0.5.1}/braindecode/datasets/__init__.py

@@ -3,6 +3,5 @@ Loader code for some datasets.
 """
 from .base import WindowsDataset, BaseDataset, BaseConcatDataset
 from .moabb import MOABBDataset
-from .tuh import TUHAbnormal
-from .mne import create_from_mne_raw, create_from_mne_epochs
-from .xy import create_from_X_y
+from .tuh import TUH, TUHAbnormal
+from .sleep_physionet import SleepPhysionet