brainscore standardizes the interface between neuroscience metrics and the data they operate on. Brain recordings (termed "assemblies", e.g. neural or behavioral) are packaged in a standard format. This allows metrics (e.g. neural predictivity, RDMs) to operate on many assemblies without having to be re-written. Together with http://github.com/brain-score/candidate_models, brainscore allows scoring candidate models of the brain on a range of assemblies and metrics.

Recommended for most users. Use Brain-Score as a library. You will need Python >= 3.6 and pip >= 18.1.

pip install git+https://github.com/brain-score/brain-score

To contribute to Brain-Score, please send in a pull request.

import brainscore
data = brainscore.get_assembly("dicarlo.MajajHong2015")
data
> <xarray.NeuronRecordingAssembly 'dicarlo.MajajHong2015' (neuroid: 296, presentation: 268800, time_bin: 1)>
> array([[[ 0.060929],
>         [-0.686162],
>         ...,
> Coordinates:
>   * neuroid          (neuroid) MultiIndex
>   - neuroid_id       (neuroid) object 'Chabo_L_M_5_9' 'Chabo_L_M_6_9' ...
>   ...

from brainscore.metrics.rdm import RDM
metric = RDM()
score = metric(assembly1=data, assembly2=data)
> Score(aggregation: 2)>
> array([1., 0.])
> Coordinates:
>   * aggregation    'center' 'error'

Some steps may take minutes because data has to be downloaded during first-time use.

For more details, see the documentation.

MIT license

##CI environment Add CI related build commands to test_setup.sh. The script is executed in CI environment for unittests.