Skip to content

Create caches for gin ecephys data and virtual env #1827

Create caches for gin ecephys data and virtual env

Create caches for gin ecephys data and virtual env #1827

name: Create caches for gin ecephys data and virtual env
on:
workflow_dispatch:
push: # When something is pushed into main this checks if caches need to be re-created
branches:
- main
schedule:
- cron: "0 12 * * *" # Daily at noon UTC
jobs:
create-gin-data-cache-if-missing:
name: Caching data env
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-latest]
steps:
- uses: actions/setup-python@v5
with:
python-version: '3.11'
- name: Create the directory to store the data
run: |
mkdir -p ~/spikeinterface_datasets/ephy_testing_data/
ls -l ~/spikeinterface_datasets
shell: bash
- name: Get current hash (SHA) of the ephy_testing_data repo
id: repo_hash
run: |
echo "dataset_hash=$(git ls-remote https://gin.g-node.org/NeuralEnsemble/ephy_testing_data.git HEAD | cut -f1)"
echo "dataset_hash=$(git ls-remote https://gin.g-node.org/NeuralEnsemble/ephy_testing_data.git HEAD | cut -f1)" >> $GITHUB_OUTPUT
shell: bash
- uses: actions/cache@v4
id: cache-datasets
with:
path: ~/spikeinterface_datasets
key: ${{ runner.os }}-datasets-${{ steps.repo_hash.outputs.dataset_hash }}
lookup-only: 'true' # Avoids downloading the data, saving behavior is not affected.
- name: Cache found?
run: echo "Cache-hit == ${{steps.cache-datasets.outputs.cache-hit == 'true'}}"
shell: bash
- name: Installing datalad and git-annex
if: steps.cache-datasets.outputs.cache-hit != 'true'
run: |
git config --global user.email "[email protected]"
git config --global user.name "CI Almighty"
python -m pip install -U pip # Official recommended way
pip install datalad-installer
if [ ${{ runner.os }} == 'Linux' ]; then
datalad-installer --sudo ok git-annex --method datalad/packages
elif [ ${{ runner.os }} == 'macOS' ]; then
datalad-installer --sudo ok git-annex --method brew
elif [ ${{ runner.os }} == 'Windows' ]; then
datalad-installer --sudo ok git-annex --method datalad/git-annex:release
fi
pip install datalad
git config --global filter.annex.process "git-annex filter-process" # recommended for efficiency
shell: bash
- name: Download dataset
if: steps.cache-datasets.outputs.cache-hit != 'true'
run: |
datalad install --recursive --get-data https://gin.g-node.org/NeuralEnsemble/ephy_testing_data
shell: bash
- name: Move the downloaded data to the right directory
if: steps.cache-datasets.outputs.cache-hit != 'true'
run: |
mv ./ephy_testing_data ~/spikeinterface_datasets/
shell: bash
- name: Show size of the cache to assert data is downloaded
run: |
cd ~
pwd
du -hs spikeinterface_datasets # Should show the size of ephy_testing_data
cd spikeinterface_datasets
pwd
ls -lh # Should show ephy_testing_data
cd ephy_testing_data
ls -lh
shell: bash