Skip to content

For the cronjob, avoid re-downloading the cache dataset if present (#… #143

For the cronjob, avoid re-downloading the cache dataset if present (#…

For the cronjob, avoid re-downloading the cache dataset if present (#… #143

name: Create caches for gin ecephys data and virtual env
on:
workflow_dispatch:
push: # When someting is pushed into main this checks if caches need to re-created
branches:
- main
schedule:
- cron: "0 12 * * *" # Daily at noon UTC
jobs:
create-virtual-env-cache-if-missing:
name: Caching virtual env
runs-on: "ubuntu-latest"
steps:
- uses: actions/checkout@v3
- uses: actions/setup-python@v4
with:
python-version: '3.10'
- name: Get current year-month
id: date
run: |
echo "date=$(date +'%Y-%m')" >> $GITHUB_OUTPUT
- name: Get current dependencies hash
id: dependencies
run: |
echo "hash=${{hashFiles('**/pyproject.toml')}}" >> $GITHUB_OUTPUT
- uses: actions/cache@v3
id: cache-venv
with:
path: ${{ github.workspace }}/test_env
key: ${{ runner.os }}-venv-${{ steps.dependencies.outputs.hash }}-${{ steps.date.outputs.date }}
lookup-only: 'true' # Avoids downloading the data, saving behavior is not affected.
- name: Cache found?
run: echo "Cache-hit == ${{steps.cache-venv.outputs.cache-hit == 'true'}}"
- name: Create the virtual environment to be cached
if: steps.cache-venv.outputs.cache-hit != 'true'
uses: ./.github/actions/build-test-environment
create-gin-data-cache-if-missing:
name: Caching data env
runs-on: "ubuntu-latest"
steps:
- uses: actions/setup-python@v4
with:
python-version: '3.10'
- name: Create the directory to store the data
run: |
mkdir --parents --verbose $HOME/spikeinterface_datasets/ephy_testing_data/
chmod -R 777 $HOME/spikeinterface_datasets
ls -l $HOME/spikeinterface_datasets
- name: Get current hash (SHA) of the ephy_testing_data repo
id: repo_hash
run: |
echo "dataset_hash=$(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
- uses: actions/cache@v3
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'}}"
- name: Installing datalad and git-annex
if: steps.cache-datasets.outputs.cache-hit != 'true'
run: |
git config --global user.email "CI@example.com"
git config --global user.name "CI Almighty"
python -m pip install -U pip # Official recommended way
pip install datalad-installer
datalad-installer --sudo ok git-annex --method datalad/packages
pip install datalad
git config --global filter.annex.process "git-annex filter-process" # recommended for efficiency
- 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
- name: Move the downloaded data to the right directory
if: steps.cache-datasets.outputs.cache-hit != 'true'
run: |
mv --force ./ephy_testing_data $HOME/spikeinterface_datasets/
- name: Show size of the cache to assert data is downloaded
run: |
cd $HOME
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