KangchengHou/dask-pgen

dapgen score (README Example) on tests/test-data/plink2.merged.pgen with a generated 3-column random weight file; output written to .coldpass/probe_score.tsv and read back

cd <host-path> && ls -la && cat README* 2>/dev/null | head -300
cd <host-path> && ls -la .github/workflows 2>/dev/null; git log --oneline -1 2>/dev/null; which python3 pip3 node npm uv 2>&1; python3 --version
cd <host-path> && cat .github/workflows/workflow.yml setup.py pyproject.toml; ls -R bin dapgen tests | head -60; cat bin/* | head -40
cd <host-path> && export NODE_USE_ENV_PROXY=1 && (sudo apt-get install -y python3-venv >/tmp/apt.log 2>&1 || (sudo apt-get update >/dev/null 2>&1 && sudo apt-get install -y python3-venv >/tmp/apt.log 2>&1)); python3 -m venv <host-path> && <host-path> install -q -U cython numpy pandas_plink pytest 2>&1 | tail -5; <host-path> install -e . 2>&1 | tail -5; echo EXIT=$?
cd <host-path> && cat tests/test_cli.py; cat tests/test-data/make-test-data.sh | head -30; ls <host-path> | grep dapgen; ls -la .gitignore && cat .gitignore
cd <host-path> && mkdir -p .coldpass && export PATH=<host-path> && python -c "
import dapgen, numpy as np, os
p=dapgen.get_test_data('plink2.merged.pgen'); print(p)
df=dapgen.read_pvar(p.replace('.pgen','.pvar'))
np.random.seed(1234)
for c in ['WEIGHT1','WEIGHT2','WEIGHT3']: df[c]=np.random.normal(size=len(df))
df.to_csv('<host-path>\t'); print(df.columns.tolist(), len(df))
" && dapgen score --plink $(python -c "import dapgen;print(dapgen.get_test_data('plink2.merged.pgen'))") --weights .coldpass/weight.tsv --weight-col-prefix WEIGHT --chrom-col CHROM --pos-col POS --alt-col ALT --ref-col REF --out .coldpass/score.tsv --center True --threads 4 --memory 2000 2>&1 | tail -15; echo EXIT=$?; head -3 .coldpass/score.tsv
mkdir -p <host-path> && cd /tmp && mkdir -p plink2dl && cd plink2dl && curl -sSL -o plink2.zip "https://s3.amazonaws.com/plink2-assets/alpha7/plink2_linux_x86_64_20261015.zip"; echo CURL=$?; ls -la; (unzip -o plink2.zip && mv plink2 <host-path> && <host-path> --version) 2>&1 | tail -5
cd /tmp/plink2dl && python3 -I -c "import zipfile;zipfile.ZipFile('plink2.zip').extractall('.')" && mv plink2 <host-path> && chmod +x <host-path> && <host-path> --version 2>&1 | head -3
cd <host-path> && export PATH=<host-path> && PG=$(python -c "import dapgen;print(dapgen.get_test_data('plink2.merged.pgen'))") && dapgen score --plink $PG --weights .coldpass/weight.tsv --weight-col-prefix WEIGHT --chrom-col CHROM --pos-col POS --alt-col ALT --ref-col REF --out .coldpass/score.tsv --center True --threads 4 --memory 2000 > .coldpass/run.log 2>&1; echo EXIT=$?; tail -5 .coldpass/run.log; head -3 .coldpass/score.tsv; ls -la .coldpass
cd <host-path> && rm -f .coldpass/score.tsv .coldpass/run.log && cat > .coldpass/probe.json <<'EOF'
{"kind":"cli","argv":["<host-path>","NODE_USE_ENV_PROXY":"1"},"expected_text":"Results written to"}
EOF
cat > .coldpass/report.json <<'EOF'
{"outcome":"working","operation":"dapgen score (README Example) on tests/test-data/plink2.merged.pgen with a generated 3-column random weight file; output written to .coldpass/probe_score.tsv and read back","operation_scope":"Runs the CLI score path end to end including plink2 allele frequency calculation. Requires plink2 binary on PATH (downloaded from the CI URL in .github/workflows/workflow.yml). Not exercised: pip install from PyPI, the README's example weights (user-supplied), full pytest/flake8 suites (intentionally skipped).","steps":["sudo apt-get install python3-venv","python3 -m venv <host-path> install -U cython numpy pandas_plink pytest","<host-path> install -e . (README 'git clone ... pip install -e .' path) ","curl plink2 zip from CI URL, extracted with python zipfile, placed at <host-path>","dapgen score --plink <test pgen> --weights .coldpass/weight.tsv ... --center True --out .coldpass/score.tsv (exit 0, 522 variants, 99 individuals scored)"],"deviations":["README 'pip install -e .' needs a venv on this Ubuntu (PEP 668); created <host-path>","unzip not installed; used python3 zipfile to extract plink2 from the CI zip.","plink2 is not an install dependency of the package; installed it manually from the CI URL to <host-path> since dapgen raises 'plink2 not found in PATH' otherwise.","Weights file generated with dapgen.read_pvar + numpy random (the repo's test_cli approach) because README weights path is user-supplied."],"stuck_step":null,"main_blocker":null,"suggested_fix":null}
EOF
<env-var>=<host-path> python3 -I <host-path> --validate; echo EXIT=$?