diff options
| -rw-r--r-- | .github/workflows/analysis-notebook-test-binder.yml | 108 | ||||
| -rw-r--r-- | .gitignore | 4 | ||||
| -rw-r--r-- | README.md | 28 | ||||
| -rw-r--r-- | bin/run_notebooks.py | 67 | ||||
| -rw-r--r-- | environment.yml | 10 | ||||
| -rw-r--r-- | setup/environment.yml | 128 | ||||
| -rw-r--r-- | setup/setup.sh | 2 | ||||
| -rw-r--r-- | setup/setup_conda.sh | 2 | ||||
| -rw-r--r-- | setup/teardown.sh | 2 | ||||
| -rw-r--r-- | setup/teardown_conda.sh | 2 |
10 files changed, 218 insertions, 135 deletions
diff --git a/.github/workflows/analysis-notebook-test-binder.yml b/.github/workflows/analysis-notebook-test-binder.yml new file mode 100644 index 0000000..e0185c0 --- /dev/null +++ b/.github/workflows/analysis-notebook-test-binder.yml @@ -0,0 +1,108 @@ +# This is a basic workflow to help you get started with Actions + +name: analysis-notebook-test-binder + +# Controls when the action will run. Triggers the workflow on push or pull request +# events but only for the main branch +on: + push: + branches: [ main ] + pull_request: + branches: [ main ] + schedule: + # * is a special character in YAML so you have to quote this string + - cron: '5 4 * * 0' + +# A workflow run is made up of one or more jobs that can run sequentially or in parallel +jobs: + build: + # The type of runner that the job will run on + runs-on: ubuntu-latest + outputs: + IMAGE_SHA_NAME: ${{ steps.install-using-repo2docker.outputs.IMAGE_SHA_NAME }} + OUT_IMGNAME: ${{ steps.package-build.outputs.OUT_IMGNAME }} + strategy: + matrix: + # Two tests are sufficient because the other notebooks are already + # tested in the manual install and the timeline notebooks are almost + # identical + target: [ui_security_inventory_23_parsing.ipynb] + + # Steps represent a sequence of tasks that will be executed as part of the job + steps: + # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it + - name: Checkout + uses: actions/checkout@v2 + + - name: Create a docker image using repo2docker + id: install-using-repo2docker + uses: shankari/repo2docker-action@master + with: + IMAGE_NAME: "toriis" + + - name: Verify repo2docker environment + run: | + echo "image SHA was ${{ steps.install-using-repo2docker.outputs.IMAGE_SHA_NAME }}" + echo "Listing all images" + docker image list + + echo "Checking to see if toriis exists" + docker image list | grep toriis | wc -l + echo "Checking to see if repo2docker creation image exists" + docker image list | grep repo2docker | wc -l + + echo "Reading versions of related software" + echo "---- DOCKER ----" + docker --version + CURR_DOCKER_VER=`docker --version` + echo "---- CONDA ----" + docker run ${{ steps.install-using-repo2docker.outputs.IMAGE_SHA_NAME }} /srv/conda/bin/conda --version | cut -d " " -f 2 + CURR_CONDA_VER=`docker run ${{ steps.install-using-repo2docker.outputs.IMAGE_SHA_NAME }} /srv/conda/bin/conda --version | cut -d " " -f 2` + echo "---- repo2docker----" + docker run jupyter/repo2docker:master pip3 list | grep jupyter-repo2docker + CURR_R2D_VER=`docker run jupyter/repo2docker:master pip3 list | grep jupyter-repo2docker` + echo "On checking, docker ver is $CURR_DOCKER_VER" + echo " conda ver is $CURR_CONDA_VER and" + echo " repo2docker ver is $CURR_R2D_VER" + + - name: Start the recently built docker container + run: | + echo "image SHA was ${{ steps.install-using-repo2docker.outputs.IMAGE_SHA_NAME }}" + docker run --name toriis_test -d -p 8888:8888 ${{ steps.install-using-repo2docker.outputs.IMAGE_SHA_NAME }} jupyter notebook --ip 0.0.0.0 + + - name: Test the interactive timeline + run: | + echo "About to run notebooks" + docker exec toriis_test python bin/run_notebooks.py ${{ matrix.target }} + echo "After running the notebooks, checking container list" + docker container list + + - name: Copy the failure output + id: copy-failure-output + if: failure() + run: | + OUT_FILENAME=`echo ${{ matrix.target }} | sed "s/.ipynb/_out.ipynb/"` + echo "output filename = $OUT_FILENAME" + + echo "About to copy file from docker" + docker exec toriis_test ls + DOCKER_WD=`docker exec toriis_test pwd` + echo "DOCKER_WD=$DOCKER_WD" + docker exec toriis_test ls $DOCKER_WD + docker exec toriis_test ls $DOCKER_WD/$OUT_FILENAME + docker cp toriis_test:$DOCKER_WD/$OUT_FILENAME /tmp + ls -al /tmp/$OUT_FILENAME + echo "::set-output name=OUT_FILENAME::${OUT_FILENAME}" + + - name: Upload result for the interactive timeline + if: failure() + uses: actions/upload-artifact@v1 + with: + name: ${{ steps.copy-failure-output.outputs.OUT_FILENAME }} + path: /tmp/${{ steps.copy-failure-output.outputs.OUT_FILENAME }} + + - name: Shutdown the recently built docker container + run: | + echo "Running docker container list" + docker container list + docker stop toriis @@ -1,5 +1,9 @@ # Jupyter Notebook .ipynb_checkpoints +# Directory's to ignore +.conda +.idea + # Private Data data/FFIS-CU200-2021-Q4.xlsx @@ -1,19 +1,29 @@ +[](https://github.com/toriis-portal/toriis-analysis/actions/workflows/analysis-notebook-test-binder.yml) # toriis-analysis -Repository for scripts to evaluate public institutional investment data. +Repository for scripts to evaluate public institutional investment data. These scripts are designed to be launched with [binder](https://mybinder.org/) so that other community members can run their own analyses without any additional setup. + + + +[](https://mybinder.org/v2/gh/toriis-portal/toriis-analysis/HEAD) # Running existing notebook -1) - + Fork + clone repo - + Run `setup/setup.sh` to set up the local conda environment +1. **Interactive, UI-only:** Launch the repo in binder and clone one of the example notebooks +1. **Interactive, CLI only:** + 1. Fork + clone repo + 1. Run `setup/setup.sh` to set up the local conda environment - you may need to install the correct version of miniconda - + Start a local notebook suerver (`juypter notebook`) + 1. Start a local notebook suerver (`juypter notebook`) # Contributing You are welcome to contribute data and analysis results. Please make sure that you contribute **cleared notebooks** so version control capabilities work well. To clear a notebook, use `Kernel -> Researt & Clear Output)` -1) **CLI:** - + Create a new branch (`$ git checkout -b <branch_name>`) - + Commit the new notebook/data (`$ git add <new file>; git commit`) - + Push and generate a pull request +1. **UI-only:** + 1. Download the notebook (Download -> ipynb) + 1. Upload the notebook using the GitHub UI (Upload Files, next to Clone or Download) +1. **CLI only:** Follow the [instructions on github](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request) - i.e. + 1. Create a new branch (e.g. `$ git checkout -b`) + 1. Commit the new notebook (e.g. `$ git add` and `$ git commit`) + 1. Push and generate pull request + diff --git a/bin/run_notebooks.py b/bin/run_notebooks.py new file mode 100644 index 0000000..ea7e8ee --- /dev/null +++ b/bin/run_notebooks.py @@ -0,0 +1,67 @@ +# ! python +# coding: utf-8 +# From https://gist.github.com/tpogden/ec79f2ebe2baf45655445b575dc7f540 +# with some more context at https://ogden.eu/run-notebooks +# Thanks to @tpogden for his gist + +import os +import sys +import argparse +import glob + +import nbformat +from nbconvert.preprocessors import ExecutePreprocessor +from nbconvert.preprocessors.execute import CellExecutionError + +# Parse args +parser = argparse.ArgumentParser(description="Runs a set of Jupyter \ + notebooks.") +file_text = """ Notebook file(s) to be run, e.g. '*.ipynb' (default), +'my_nb1.ipynb', 'my_nb1.ipynb my_nb2.ipynb', 'my_dir/*.ipynb' +""" +parser.add_argument('file_list', metavar='F', type=str, nargs='*', + help=file_text) +parser.add_argument('-t', '--timeout', help='Length of time (in secs) a cell \ + can run before raising TimeoutError (default 600).', default=600, + required=False) +parser.add_argument('-p', '--run-path', help='The path the notebook will be \ + run from (default pwd).', default='.', required=False) +args = parser.parse_args() +print('Args:', args) +if not args.file_list: # Default file_list + args.file_list = glob.glob('*.ipynb') + +# Check list of notebooks +notebooks = [] +print('Notebooks to run:') +for f in args.file_list: + # Find notebooks but not notebooks previously output from this script + if f.endswith('.ipynb') and not f.endswith('_out.ipynb'): + print(f[:-6]) + notebooks.append(f[:-6]) # Want the filename without '.ipynb' + +# Execute notebooks and output +num_notebooks = len(notebooks) +print('*****') +for i, n in enumerate(notebooks): + n_out = n + '_out' + with open(n + '.ipynb') as f: + nb = nbformat.read(f, as_version=4) + ep = ExecutePreprocessor(timeout=int(args.timeout), kernel_name='python3') + try: + print('Running', n, ':', i, '/', num_notebooks) + out = ep.preprocess(nb, {'metadata': {'path': args.run_path}}) + except CellExecutionError: + out = None + msg = 'Error executing the notebook "%s".\n' % n + msg += 'See notebook "%s" for the traceback.' % n_out + print(msg) + sys.exit(1) + except TimeoutError: + msg = 'Timeout executing the notebook "%s".\n' % n + print(msg) + sys.exit(110) + finally: + # Write output file + with open(n_out + '.ipynb', mode='wt') as f: + nbformat.write(nb, f)
\ No newline at end of file diff --git a/environment.yml b/environment.yml new file mode 100644 index 0000000..9898f22 --- /dev/null +++ b/environment.yml @@ -0,0 +1,10 @@ +name: toriis +channels: + - conda-forge + - defaults +dependencies: + - numpy=1.23.5 + - pandas=1.5.3 + - requests=2.28.2 + - yfinance=0.2.12=pyhd8ed1ab_0 + - openpyxl=3.1.1
\ No newline at end of file diff --git a/setup/environment.yml b/setup/environment.yml index c72a998..9898f22 100644 --- a/setup/environment.yml +++ b/setup/environment.yml @@ -1,126 +1,10 @@ name: toriis channels: + - conda-forge - defaults dependencies: - - _libgcc_mutex=0.1=main - - _openmp_mutex=5.1=1_gnu - - anyio=3.5.0=py310h06a4308_0 - - argon2-cffi=21.3.0=pyhd3eb1b0_0 - - argon2-cffi-bindings=21.2.0=py310h7f8727e_0 - - asttokens=2.0.5=pyhd3eb1b0_0 - - attrs=22.1.0=py310h06a4308_0 - - babel=2.11.0=py310h06a4308_0 - - backcall=0.2.0=pyhd3eb1b0_0 - - beautifulsoup4=4.11.1=py310h06a4308_0 - - blas=1.0=mkl - - bleach=4.1.0=pyhd3eb1b0_0 - - bottleneck=1.3.5=py310ha9d4c09_0 - - brotlipy=0.7.0=py310h7f8727e_1002 - - bzip2=1.0.8=h7b6447c_0 - - ca-certificates=2023.01.10=h06a4308_0 - - certifi=2022.12.7=py310h06a4308_0 - - cffi=1.15.1=py310h5eee18b_3 - - charset-normalizer=2.0.4=pyhd3eb1b0_0 - - comm=0.1.2=py310h06a4308_0 - - cryptography=38.0.4=py310h9ce1e76_0 - - debugpy=1.5.1=py310h295c915_0 - - decorator=5.1.1=pyhd3eb1b0_0 - - defusedxml=0.7.1=pyhd3eb1b0_0 - - entrypoints=0.4=py310h06a4308_0 - - executing=0.8.3=pyhd3eb1b0_0 - - flit-core=3.6.0=pyhd3eb1b0_0 - - icu=58.2=he6710b0_3 - - idna=3.4=py310h06a4308_0 - - intel-openmp=2021.4.0=h06a4308_3561 - - ipykernel=6.19.2=py310h2f386ee_0 - - ipython=8.9.0=py310h06a4308_0 - - ipython_genutils=0.2.0=pyhd3eb1b0_1 - - jedi=0.18.1=py310h06a4308_1 - - jinja2=3.1.2=py310h06a4308_0 - - json5=0.9.6=pyhd3eb1b0_0 - - jsonschema=4.16.0=py310h06a4308_0 - - jupyter_client=7.4.9=py310h06a4308_0 - - jupyter_core=5.1.1=py310h06a4308_0 - - jupyter_server=1.23.4=py310h06a4308_0 - - jupyterlab=3.5.3=py310h06a4308_0 - - jupyterlab_pygments=0.1.2=py_0 - - jupyterlab_server=2.16.5=py310h06a4308_0 - - ld_impl_linux-64=2.38=h1181459_1 - - libffi=3.4.2=h6a678d5_6 - - libgcc-ng=11.2.0=h1234567_1 - - libgomp=11.2.0=h1234567_1 - - libsodium=1.0.18=h7b6447c_0 - - libstdcxx-ng=11.2.0=h1234567_1 - - libuuid=1.41.5=h5eee18b_0 - - libxml2=2.9.14=h74e7548_0 - - libxslt=1.1.35=h4e12654_0 - - lxml=4.9.1=py310h1edc446_0 - - markupsafe=2.1.1=py310h7f8727e_0 - - matplotlib-inline=0.1.6=py310h06a4308_0 - - mistune=0.8.4=py310h7f8727e_1000 - - mkl=2021.4.0=h06a4308_640 - - mkl-service=2.4.0=py310h7f8727e_0 - - mkl_fft=1.3.1=py310hd6ae3a3_0 - - mkl_random=1.2.2=py310h00e6091_0 - - nbclassic=0.4.8=py310h06a4308_0 - - nbclient=0.5.13=py310h06a4308_0 - - nbconvert=6.5.4=py310h06a4308_0 - - nbformat=5.7.0=py310h06a4308_0 - - ncurses=6.4=h6a678d5_0 - - nest-asyncio=1.5.6=py310h06a4308_0 - - notebook=6.5.2=py310h06a4308_0 - - notebook-shim=0.2.2=py310h06a4308_0 - - numexpr=2.8.4=py310h8879344_0 - - numpy=1.23.5=py310hd5efca6_0 - - numpy-base=1.23.5=py310h8e6c178_0 - - openssl=1.1.1t=h7f8727e_0 - - packaging=22.0=py310h06a4308_0 - - pandas=1.5.2=py310h1128e8f_0 - - pandocfilters=1.5.0=pyhd3eb1b0_0 - - parso=0.8.3=pyhd3eb1b0_0 - - pexpect=4.8.0=pyhd3eb1b0_3 - - pickleshare=0.7.5=pyhd3eb1b0_1003 - - pip=22.3.1=py310h06a4308_0 - - platformdirs=2.5.2=py310h06a4308_0 - - prometheus_client=0.14.1=py310h06a4308_0 - - prompt-toolkit=3.0.36=py310h06a4308_0 - - psutil=5.9.0=py310h5eee18b_0 - - ptyprocess=0.7.0=pyhd3eb1b0_2 - - pure_eval=0.2.2=pyhd3eb1b0_0 - - pycparser=2.21=pyhd3eb1b0_0 - - pygments=2.11.2=pyhd3eb1b0_0 - - pyopenssl=22.0.0=pyhd3eb1b0_0 - - pyrsistent=0.18.0=py310h7f8727e_0 - - pysocks=1.7.1=py310h06a4308_0 - - python=3.10.9=h7a1cb2a_0 - - python-dateutil=2.8.2=pyhd3eb1b0_0 - - python-fastjsonschema=2.16.2=py310h06a4308_0 - - pytz=2022.7=py310h06a4308_0 - - pyzmq=23.2.0=py310h6a678d5_0 - - readline=8.2=h5eee18b_0 - - requests=2.28.1=py310h06a4308_0 - - send2trash=1.8.0=pyhd3eb1b0_1 - - setuptools=65.6.3=py310h06a4308_0 - - six=1.16.0=pyhd3eb1b0_1 - - sniffio=1.2.0=py310h06a4308_1 - - soupsieve=2.3.2.post1=py310h06a4308_0 - - sqlite=3.40.1=h5082296_0 - - stack_data=0.2.0=pyhd3eb1b0_0 - - terminado=0.17.1=py310h06a4308_0 - - tinycss2=1.2.1=py310h06a4308_0 - - tk=8.6.12=h1ccaba5_0 - - tomli=2.0.1=py310h06a4308_0 - - tornado=6.2=py310h5eee18b_0 - - traitlets=5.7.1=py310h06a4308_0 - - typing-extensions=4.4.0=py310h06a4308_0 - - typing_extensions=4.4.0=py310h06a4308_0 - - tzdata=2022g=h04d1e81_0 - - urllib3=1.26.14=py310h06a4308_0 - - wcwidth=0.2.5=pyhd3eb1b0_0 - - webencodings=0.5.1=py310h06a4308_1 - - websocket-client=0.58.0=py310h06a4308_4 - - wheel=0.37.1=pyhd3eb1b0_0 - - xz=5.2.10=h5eee18b_1 - - zeromq=4.3.4=h2531618_0 - - zlib=1.2.13=h5eee18b_0 -prefix: /home/gabrielkosmacher/miniconda3/envs/toriis + - numpy=1.23.5 + - pandas=1.5.3 + - requests=2.28.2 + - yfinance=0.2.12=pyhd8ed1ab_0 + - openpyxl=3.1.1
\ No newline at end of file diff --git a/setup/setup.sh b/setup/setup.sh index d2631f9..6730a4f 100644 --- a/setup/setup.sh +++ b/setup/setup.sh @@ -11,4 +11,4 @@ set -e source setup/checks/check_for_conda.sh conda env update --name toriis --file setup/environment.yml -conda activate toriis +conda activate toriis
\ No newline at end of file diff --git a/setup/setup_conda.sh b/setup/setup_conda.sh index e7d4e3e..ee4d57f 100644 --- a/setup/setup_conda.sh +++ b/setup/setup_conda.sh @@ -19,4 +19,4 @@ else # Useful for debugging any issues with conda conda info -a echo "Successfully installed at $INSTALL_PREFIX. Please run 'source $SOURCE_SCRIPT' in every terminal where you want to use conda" -fi +fi
\ No newline at end of file diff --git a/setup/teardown.sh b/setup/teardown.sh index 308fde8..f8ad631 100644 --- a/setup/teardown.sh +++ b/setup/teardown.sh @@ -1,3 +1,3 @@ # taken from mobilitynet-analysis-scripts/setup/teardown.sh conda activate base -conda env remove --name toriis +conda env remove --name toriis
\ No newline at end of file diff --git a/setup/teardown_conda.sh b/setup/teardown_conda.sh index 2fde7a5..a61f834 100644 --- a/setup/teardown_conda.sh +++ b/setup/teardown_conda.sh @@ -6,4 +6,4 @@ if [ -z $EXP_CONDA_VER ]; then else INSTALL_PREFIX=$HOME/miniconda-$EXP_CONDA_VER rm -rf $INSTALL_PREFIX -fi +fi
\ No newline at end of file |