ML expanded and retrained #2276
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # This workflow runs benchmark | |
| # Separation of jobs helps to cache data even benchmark is fail | |
| name: Benchmark | |
| on: | |
| push: | |
| branches: [ main ] | |
| pull_request: | |
| branches: [ main ] | |
| jobs: | |
| # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # | |
| download_data: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout CredData | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: Samsung/CredData | |
| - name: Markup hashing | |
| run: | | |
| md5sum snapshot.yaml >checksums.md5 | |
| for f in $(find meta -type f|sort); do md5sum $f; done >>checksums.md5 | |
| for f in $(find . -maxdepth 1 -type f -name "*.py"|sort); do md5sum $f; done >>checksums.md5 | |
| cat checksums.md5 | |
| sha256sum checksums.md5 | |
| - name: Cache data | |
| id: cache-data | |
| uses: actions/cache@v4 | |
| with: | |
| path: data | |
| key: cred-data-${{ hashFiles('checksums.md5') }} | |
| - name: Set up Python 3.8 | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: "3.8" | |
| - name: Update PIP | |
| run: python -m pip install --upgrade pip | |
| - name: Install requirements of CredData | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| run: python -m pip install --requirement requirements.txt | |
| - name: Generate Data Asset | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| run: python download_data.py --data_dir data --jobs $(nproc) | |
| # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # | |
| run_benchmark: | |
| if: ${{ 'pull_request' == github.event_name }} | |
| needs: [ download_data ] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout CredData | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: Samsung/CredData | |
| - name: Markup hashing | |
| run: | | |
| md5sum snapshot.yaml >checksums.md5 | |
| for f in $(find meta -type f|sort); do md5sum $f; done >>checksums.md5 | |
| for f in $(find . -maxdepth 1 -type f -name "*.py"|sort); do md5sum $f; done >>checksums.md5 | |
| cat checksums.md5 | |
| sha256sum checksums.md5 | |
| - name: Cache data | |
| id: cache-data | |
| uses: actions/cache@v4 | |
| with: | |
| path: data | |
| key: cred-data-${{ hashFiles('checksums.md5') }} | |
| - name: Failure in case when cache missed | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| run: exit 1 | |
| - name: Check Data Asset - DEBUG | |
| if: steps.cache-data.outputs.cache-hit == 'true' | |
| run: ls -al . && ls -al data | |
| - name: Set up Python 3.8 | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: "3.8" | |
| - name: Update PIP | |
| run: python -m pip install --upgrade pip | |
| - name: Install requirements of CredData | |
| run: python -m pip install --requirement requirements.txt | |
| - name: Checkout CredSweeper | |
| uses: actions/checkout@v4 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| path: temp/CredSweeper | |
| - name: Patch benchmark for PR work | |
| run: | | |
| sed -i 's|CREDSWEEPER = "https://github.com/Samsung/CredSweeper.git"|CREDSWEEPER = "dummy://github.com/Samsung/CredSweeper.git"|' benchmark/common/constants.py | |
| grep --with-filename --line-number 'dummy://github.com/Samsung/CredSweeper.git' benchmark/common/constants.py | |
| - name: Install CredSweeper | |
| run: | | |
| python -m pip install temp/CredSweeper | |
| credsweeper_head= | |
| - name: Run CredSweeper tool | |
| run: | | |
| credsweeper --banner --jobs $(nproc) --path data --save-json report.${{ github.event.pull_request.head.sha }}.json | tee credsweeper.${{ github.event.pull_request.head.sha }}.log | |
| - name: Run Benchmark | |
| run: | | |
| python -m benchmark --scanner credsweeper --load report.${{ github.event.pull_request.head.sha }}.json | tee benchmark.${{ github.event.pull_request.head.sha }}.log | |
| - name: Upload CredSweeper log | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: credsweeper | |
| path: credsweeper.${{ github.event.pull_request.head.sha }}.log | |
| - name: Upload CredSweeper report | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: report | |
| path: report.${{ github.event.pull_request.head.sha }}.json | |
| - name: Upload benchmark output | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: benchmark | |
| path: benchmark.${{ github.event.pull_request.head.sha }}.log | |
| - name: Verify benchmark scores of the PR | |
| run: | | |
| diff --ignore-all-space --ignore-blank-lines temp/CredSweeper/cicd/benchmark.txt benchmark.${{ github.event.pull_request.head.sha }}.log | |
| # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # | |
| performance_benchmark: | |
| # put the benchmark in single job to keep constant environment during test | |
| needs: [ download_data ] | |
| runs-on: ubuntu-latest | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| python-version: [ "3.8", "3.9", "3.10", "3.11" ] | |
| steps: | |
| - name: Checkout CredData | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: Samsung/CredData | |
| - name: Markup hashing | |
| run: | | |
| md5sum snapshot.yaml >checksums.md5 | |
| for f in $(find meta -type f|sort); do md5sum $f; done >>checksums.md5 | |
| for f in $(find . -maxdepth 1 -type f -name "*.py"|sort); do md5sum $f; done >>checksums.md5 | |
| cat checksums.md5 | |
| sha256sum checksums.md5 | |
| - name: Cache data | |
| id: cache-data | |
| uses: actions/cache@v4 | |
| with: | |
| path: data | |
| key: cred-data-${{ hashFiles('checksums.md5') }} | |
| - name: Failure in case when cache missed | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| run: exit 1 | |
| - name: Exclude very huge data | |
| if: steps.cache-data.outputs.cache-hit == 'true' | |
| run: rm -rf data/0* data/2* data/7* data/8* data/a* data/b* data/d* data/e* data/f* | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Add synthetic huge data | |
| if: steps.cache-data.outputs.cache-hit == 'true' | |
| run: python -c "for n in range(7654321):print(f'{n:08x}')" >data/test.text | |
| - name: Update PIP | |
| run: python -m pip install --upgrade pip | |
| - name: Install released CredSweeper | |
| run: | | |
| python -m pip install credsweeper | |
| # check the banner | |
| credsweeper --banner | |
| - name: Run performance benchmark RELEASE | |
| run: | | |
| START_TIME=$(date +%s) | |
| /usr/bin/time --verbose credsweeper --log error --path data --save-json /dev/null | |
| FINISH_TIME=$(date +%s) | |
| RELEASE_TIME=$(( ${FINISH_TIME} - ${START_TIME} )) | |
| if [ 0 -lt ${RELEASE_TIME} ]; then | |
| echo Elapsed $(date -ud "@${RELEASE_TIME}" +"%H:%M:%S") | |
| else | |
| echo "Wrong result '${RELEASE_TIME}'" | |
| exit 1 | |
| fi | |
| echo "RELEASE_TIME=${RELEASE_TIME}" >> $GITHUB_ENV | |
| - name: Uninstall released CredSweeper | |
| run: | | |
| python -m pip uninstall -y credsweeper | |
| - name: Checkout base CredSweeper | |
| uses: actions/checkout@v4 | |
| with: | |
| ref: ${{ github.event.pull_request.base.sha }} | |
| path: temp/CredSweeper.base | |
| - name: Install base CredSweeper | |
| run: | | |
| python -m pip install temp/CredSweeper.base | |
| # check the banner | |
| credsweeper --banner | |
| - name: Run performance benchmark BASE | |
| run: | | |
| START_TIME=$(date +%s) | |
| /usr/bin/time --verbose credsweeper --log error --path data --save-json /dev/null | |
| FINISH_TIME=$(date +%s) | |
| BASE_TIME=$(( ${FINISH_TIME} - ${START_TIME} )) | |
| if [ 0 -lt ${BASE_TIME} ]; then | |
| echo Elapsed $(date -ud "@${BASE_TIME}" +"%H:%M:%S") | |
| else | |
| echo "Wrong result '${BASE_TIME}'" | |
| exit 1 | |
| fi | |
| echo "BASE_TIME=${BASE_TIME}" >> $GITHUB_ENV | |
| - name: Checkout current CredSweeper | |
| uses: actions/checkout@v4 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| path: temp/CredSweeper.head | |
| - name: Install current CredSweeper | |
| run: | | |
| python -m pip install temp/CredSweeper.head | |
| # check the banner | |
| credsweeper --banner | |
| - name: Run performance benchmark CURRENT | |
| run: | | |
| START_TIME=$(date +%s) | |
| /usr/bin/time --verbose credsweeper --log error --path data --save-json /dev/null | |
| FINISH_TIME=$(date +%s) | |
| HEAD_TIME=$(( ${FINISH_TIME} - ${START_TIME} )) | |
| if [ 0 -lt ${HEAD_TIME} ]; then | |
| echo Elapsed $(date -ud "@${HEAD_TIME}" +"%H:%M:%S") | |
| else | |
| echo "Wrong result '${HEAD_TIME}'" | |
| exit 1 | |
| fi | |
| echo "HEAD_TIME=${HEAD_TIME}" >> $GITHUB_ENV | |
| - name: Compare results | |
| run: | | |
| exit_code=0 | |
| LOW_DELTA=10 | |
| THRESHOLD=250 | |
| # RELEASE | |
| if [ ${RELEASE_TIME} -le ${HEAD_TIME} ]; then | |
| d=$(( 1000 * ( ${HEAD_TIME} - ${RELEASE_TIME} ) / ${RELEASE_TIME} )) | |
| echo "RELEASE_TIME (sec) = ${RELEASE_TIME}, current (sec) = ${HEAD_TIME}. Diff (% * 10): ${d}" | |
| if [ $LOW_DELTA -ge ${d} ]; then | |
| echo "Almost the same." | |
| elif [ $THRESHOLD -lt ${d} ]; then | |
| echo "Significantly Slowdown." | |
| exit_code=1 | |
| else | |
| echo "Slowdown." | |
| fi | |
| else | |
| d=$(( 1000 * ( ${RELEASE_TIME} - ${HEAD_TIME} ) / ${RELEASE_TIME} )) | |
| echo "RELEASE_TIME (sec) = ${RELEASE_TIME}, current (sec) = ${HEAD_TIME}. Diff (% * 10): ${d}" | |
| if [ $LOW_DELTA -ge ${d} ]; then | |
| echo "Almost the same." | |
| elif [ $THRESHOLD -lt ${d} ]; then | |
| echo "Significantly speed-up." | |
| else | |
| echo "Speed-up." | |
| fi | |
| fi | |
| # BASE | |
| if [ ${BASE_TIME} -le ${HEAD_TIME} ]; then | |
| d=$(( 1000 * ( ${HEAD_TIME} - ${BASE_TIME} ) / ${BASE_TIME} )) | |
| echo "BASE_TIME (sec) = ${BASE_TIME}, current (sec) = ${HEAD_TIME}. Diff (% * 10): ${d}" | |
| if [ $LOW_DELTA -ge ${d} ]; then | |
| echo "Almost the same." | |
| elif [ $THRESHOLD -lt ${d} ]; then | |
| echo "Significantly Slowdown." | |
| exit_code=1 | |
| else | |
| echo "Slowdown." | |
| fi | |
| else | |
| d=$(( 1000 * ( ${BASE_TIME} - ${HEAD_TIME} ) / ${BASE_TIME} )) | |
| echo "BASE_TIME (sec) = ${BASE_TIME}, current (sec) = ${HEAD_TIME}. Diff (% * 10): ${d}" | |
| if [ $LOW_DELTA -ge ${d} ]; then | |
| echo "Almost the same." | |
| elif [ $THRESHOLD -lt ${d} ]; then | |
| echo "Significantly speed-up." | |
| else | |
| echo "Speed-up." | |
| fi | |
| fi | |
| exit ${exit_code} | |
| # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # | |
| experiment: | |
| # the ml train test is placed here to use cached data set | |
| needs: [ download_data ] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout CredData | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: Samsung/CredData | |
| - name: Markup hashing | |
| run: | | |
| md5sum snapshot.yaml >checksums.md5 | |
| for f in $(find meta -type f|sort); do md5sum $f; done >>checksums.md5 | |
| for f in $(find . -maxdepth 1 -type f -name "*.py"|sort); do md5sum $f; done >>checksums.md5 | |
| cat checksums.md5 | |
| sha256sum checksums.md5 | |
| - name: Cache data | |
| id: cache-data | |
| uses: actions/cache@v4 | |
| with: | |
| path: data | |
| key: cred-data-${{ hashFiles('checksums.md5') }} | |
| - name: Failure in case when cache missed | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| run: exit 1 | |
| - name: Exclude some sets for speed-up | |
| run: | | |
| rm -rf data/2* data/8* data/b* | |
| rm -rf meta/2* meta/8* meta/b* | |
| mkdir -vp ${{ github.workspace }}/CredData | |
| mv data ${{ github.workspace }}/CredData/ | |
| mv meta ${{ github.workspace }}/CredData/ | |
| - name: Set up Python 3.8 | |
| if: steps.cache-data.outputs.cache-hit != 'true' | |
| uses: actions/setup-python@v3 | |
| with: | |
| python-version: "3.8" | |
| - name: Update PIP | |
| run: python -m pip install --upgrade pip | |
| - name: Checkout current CredSweeper | |
| uses: actions/checkout@v4 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| path: CredSweeper.head | |
| - name: Install development packages | |
| run: python -m pip install --requirement CredSweeper.head/requirements.txt | |
| - name: Install experimental packages | |
| # some versions will be changed for compatibility | |
| run: python -m pip install --requirement CredSweeper.head/experiment/requirements.txt | |
| - name: dbg | |
| run: echo ${{ github.workspace }} && ls -al ${{ github.workspace }} && tree ${{ github.workspace }} | |
| - name: Run the experiment | |
| run: | | |
| cd CredSweeper.head | |
| ls -al #dbg | |
| pwd #dbg | |
| export PYTHONPATH=$(pwd):${PYTHONPATH} | |
| cd experiment | |
| # check whether credsweeper is available as module | |
| python -m credsweeper --banner | |
| # use only 2 epochs for the test | |
| sed -i 's/epochs=42,/epochs=2,/' main.py | |
| python main.py --data ${{ github.workspace }}/CredData -j $(( 2 * $(nproc) )) | |
| ls -al results #dbg | |
| python -m tf2onnx.convert --saved-model $(find results -mindepth 1 -maxdepth 1 -type d) --output ../credsweeper/ml_model/ml_model.onnx --verbose | |
| # dbg | |
| git diff | |
| # crc32 should be changed | |
| python -m credsweeper --banner | |
| # run quick scan | |
| python -m credsweeper --log debug --path ../tests/samples --save-json | |
| NEW_MODEL_FOUND_SAMPLES=$(jq '.|length' output.json) | |
| if [ 100 -gt ${NEW_MODEL_FOUND_SAMPLES} ]; then | |
| echo "Failure: found ${NEW_MODEL_FOUND_SAMPLES} credentials" | |
| exit 1 | |
| fi | |
| # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # | |
| run_doc_benchmark: | |
| runs-on: ubuntu-latest | |
| if: ${{ 'Samsung/CredSweeper' == github.event.pull_request.head.repo.full_name }} | |
| steps: | |
| - name: Checkout CredSweeper | |
| if: ${{ 'pull_request' == github.event_name }} | |
| uses: actions/checkout@v4 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| - name: Send cURL request with the commit SHA | |
| if: ${{ 'pull_request' == github.event_name }} | |
| run: | | |
| COMMIT_SHA=$(git rev-parse HEAD) | |
| curl -X POST ${{ secrets.SLACK_URL }} \ | |
| --data-urlencode \ | |
| "payload={'text':'[BMT Request] ${{ github.event.repository.html_url }}/commit/${COMMIT_SHA}'}" | |
| # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # |