adding unit test framework, cleaning reqs, readme, gitignore

Author: korymath

.gitignore

@@ -1,4 +1,6 @@
 *.DS_Store
+eeg-notebooks/
+deepeeg/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

README.md

@@ -6,27 +6,34 @@ MNE/Keras/Tensorflow library for classification of EEG data
 * [Kory W. Mathewson](https://github.com/korymath)
 
 ![DeepEEG Image](DeepEEGImage2.png)
- 
-Keras/Tensorflow deep learning stacks that processes EEG trials or raw files from the MNE toolbox as input and predicts binary trial category as output (could scale to multiclass?). This is all made to run on Google Colab notebooks using cloud GPU capabilities, so the git repo's get loaded at the start of the code into the workspace. Minor mods may be needed to use local Jupyter notebook. Long term goal of command line interface and mne toolbox plugin.
+
+DeepEEG is a Keras/Tensorflow deep learning library that processes EEG trials or raw files from the MNE toolbox as input and predicts binary trial category as output (could scale to multiclass?). This is all made to run on Google Colab notebooks using cloud GPU capabilities, so the git repo's get loaded at the start of the code into the workspace. Minor modifications may be needed to use local Jupyter notebook. Long term goal of command line interface and MNE toolbox plugin.
 
 Colab Notebook Example:
 https://colab.research.google.com/github/kylemath/DeepEEG/blob/master/notebooks/DeepEEG.ipynb
 
-Getting Started Locally:
+## Getting Started Locally:
 
+DeepEEG is tested on macOS 10.14 with Python3.
+Prepare your environment the first time:
 
-To prepare your environment the first time:
-```python
+```sh
+# using conda
 conda create -n deepeeg
 source activate deepeeg
+# using virtualenv
+# python3 -m venv deepeeg
+# source deepeeg/bin/activate
+```
+
+```sh
 git clone https://github.com/kylemath/DeepEEG/
 cd DeepEEG
-chmod +x install.sh
-bash install.sh
+./install.sh
 git clone https://github.com/kylemath/eeg-notebooks
-python
 ```
 
+You are now ready to run DeepEEG.
 
 This loads in some example data from eeg-notebooks
 
@@ -64,16 +71,23 @@ model,_ = CreateModel(feats)
 TrainTestVal(model,feats)
 ```
 
+## Tests
+
+You can run the unittests with the following command:
+```
+python -m unittest
+```
+
 Strategy:
-* Load in Brain Products or Interaxon Muse files with mne as mne.raw, 
+* Load in Brain Products or Interaxon Muse files with mne as mne.raw,
 * PreProcess(mne.raw) - normal ERP preprocessing to get trials by time by electrode mne.epochs
 * FeatureEngineer(mne.epochs) - Either time domain or frequency domain feature extraction in DeepEEG.Feats class
 * CreateModel(DeepEEG.Feats) - Customizes DeepEEG.Model for input data, pick from NN, CNN, LSTM, or AutoEncoders, splits data
 * TrainTestVal(DeepEEG.Feats,DeepEEG.Model) - Train the model, validate it during training, and test it once complete, Plot loss during learning and at test
-                                             
+
 Dataset example:
 * Interaxon Muse - eeg-notebooks -  https://github.com/kylemath/eeg-notebooks
-* Brain Recorder Data 
+* Brain Recorder Data
 
 API:
 * Input the data directory and subject numbers of any eeg-notebook experiment (https://github.com/kylemath/eeg-notebooks)
@@ -88,19 +102,19 @@ LearningModels:
 * Can also try using (AUTO) or (AUTODeep) to clean eeg data, or create features for other models
 
 DataModels:
-* Try subject specific models 
+* Try subject specific models
 * Then pool data over all subjects
 * Then try multilevel models (in the works)
 
-Using: 
+Using:
 * https://github.com/kylemath/eeg-notebooks
 * https://github.com/mne-tools/mne-python
 * https://github.com/keras-team/keras/blob/master/examples/imdb_cnn_lstm.py
 * https://github.com/ml4a/ml4a-guides/blob/master/notebooks/keras_classification.ipynb
 * https://github.com/tevisgehr/EEG-Classification
 
 Resources:
-* https://arxiv.org/pdf/1901.05498.pdf 
+* https://arxiv.org/pdf/1901.05498.pdf
 * http://proceedings.mlr.press/v56/Thodoroff16.pdf
 * https://arxiv.org/abs/1511.06448
 * https://github.com/ml4a

install.sh

@@ -1 +1,2 @@
+pip install --upgrade pip
 pip install -r requirements.txt

requirements.txt

@@ -4,6 +4,6 @@ Keras-Applications==1.0.7
 Keras-Preprocessing==1.0.9
 mne==0.17.0
 numpy==1.16.1
-PyYAML==4.2b1s
+PyYAML==4.2b1
 scipy==1.2.0
 six==1.12.0

tests.py

@@ -0,0 +1,56 @@
+import unittest
+from utils import Feats
+from utils import PreProcess
+from utils import CreateModel
+from utils import TrainTestVal
+from utils import LoadMuseData
+from utils import FeatureEngineer
+
+
+class ExampleTest(unittest.TestCase):
+    """
+    Our basic test class
+    """
+
+    def test_addition(self):
+        """
+        The actual test.
+        Any method which starts with ``test_`` will considered as a test case.
+        """
+        res = 2 + 2
+        self.assertEqual(res, 4)
+
+    def test_feats(self):
+        """
+        Testing utils import.
+        """
+        feats = Feats()
+        self.assertEqual(feats.num_classes, 2)
+
+    def test_example_muse(self):
+        """
+        Testing example Muse code.
+        """
+
+        # Load Data
+        raw = LoadMuseData(subs=[101, 102], nsesh=2, data_dir='visual/cueing')
+
+        # Pre-Process EEG Data
+        epochs = PreProcess(raw=raw, event_id={'LeftCue': 1, 'RightCue': 2})
+
+        # Engineer Features for Model
+        feats = FeatureEngineer(epochs=epochs)
+
+        # Create Model
+        model, _ = CreateModel(feats=feats)
+
+        # Train with validation, then Test
+        model, data = TrainTestVal(model=model,
+                                   feats=feats,
+                                   train_epochs=1,
+                                   show_plots=False)
+
+        self.assertLess(data['acc'], 1)
+
+if __name__ == '__main__':
+    unittest.main()