b1e06b1b9e
OEWS: the BLS API serves only the latest OEWS year, so history comes
from the annual oesm{yy}nat.zip files (2013–2024), which bls.gov only
serves to a full browser header set; each zip's national_M{year}_dl
sheet (xls through 2013, xlsx after; OCC_GROUP through 2018, O_GROUP
plus area/industry columns from 2019) is normalised to one row per SOC
occupation with employment and the hourly/annual wage distribution,
suppressed cells (* # **) as NULL, and the BLS series-id prefix kept
per row. One bib Source per release (module:bls, table:bls.oews,
source:bls-website, year:N) and a cms.ingest_log row with the zip's
sha256.
CES: a closed registry of employment (01) and average hourly earnings
(03) series for health care, ambulatory care, offices of physicians,
home health, hospitals and nursing/residential care (CES65<industry>
<type>), pulled through the public API in 10-year × 25-series chunks
(20 × 50 with BLS_API_KEY), monthly rows with the series id on every
row, one bib Source per series.
stack bls oews [--year]... [--write [--offline]] [--occ]...;
stack bls ces [--write] [--series]... [--annual]. Notebook 7f overlays
clinical-staff wages (31-9092, 29-2061, 29-1141, 29-1171) and
physician-office / ambulatory employment on the family's exposure
dates. CLI docs regenerated.
79 lines
2.5 KiB
Python
79 lines
2.5 KiB
Python
"""CLI entry point for the stack platform.
|
|
|
|
Usage::
|
|
|
|
uv run stack --help
|
|
uv run stack run readmissions
|
|
uv run stack load cclf --path data/cclf/
|
|
uv run stack bib sync
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import typer
|
|
|
|
from cli.api import app as api_app
|
|
from cli.bib import app as bib_app
|
|
from cli.bls import app as bls_app
|
|
from cli.comments import app as comments_app
|
|
from cli.db import app as db_app
|
|
from cli.docs import app as docs_app
|
|
from cli.generate import app as generate_app
|
|
from cli.health import health
|
|
from cli.lake import app as lake_app
|
|
from cli.llm import app as llm_app
|
|
from cli.load import app as load_app
|
|
from cli.mail import app as mail_app
|
|
from cli.perf import app as perf_app
|
|
from cli.pfs import app as pfs_app
|
|
from cli.prisma import app as prisma_app
|
|
from cli.rec import app as rec_app
|
|
from cli.run import run
|
|
from cli.validate import validate
|
|
from cli.zot import app as zot_app
|
|
|
|
app = typer.Typer(
|
|
name="stack",
|
|
help="Healthcare data platform CLI.",
|
|
no_args_is_help=True,
|
|
)
|
|
|
|
app.command()(run)
|
|
app.command()(validate)
|
|
app.command()(health)
|
|
app.add_typer(load_app, name="load", help="Ingest data (CCLF, BCDA, seeds).")
|
|
app.add_typer(generate_app, name="generate", help="Regenerate code artefacts.")
|
|
app.add_typer(bib_app, name="bib", help="Bibliography operations.")
|
|
app.add_typer(
|
|
bls_app,
|
|
name="bls",
|
|
help="BLS occupation wages (OEWS) and health-care employment (CES).",
|
|
)
|
|
app.add_typer(
|
|
comments_app,
|
|
name="comments",
|
|
help="CMS rulemaking comment text extraction & analysis.",
|
|
)
|
|
app.add_typer(lake_app, name="lake", help="Lakehouse schema and data.")
|
|
app.add_typer(llm_app, name="llm", help="Local RAG — index, search, tag.")
|
|
app.add_typer(db_app, name="db", help="DuckDB utilities.")
|
|
app.add_typer(docs_app, name="docs", help="Documentation generation.")
|
|
app.add_typer(api_app, name="api", help="API server.")
|
|
app.add_typer(perf_app, name="perf", help="Pipeline telemetry utilities.")
|
|
app.add_typer(
|
|
rec_app,
|
|
name="rec",
|
|
help="Reconcile calculated payments against CMS ground-truth files.",
|
|
)
|
|
app.add_typer(
|
|
pfs_app, name="pfs", help="Code elements, lineage events and derived families."
|
|
)
|
|
app.add_typer(zot_app, name="zot", help="Zotero database maintenance.")
|
|
app.add_typer(prisma_app, name="prisma", help="LLM-driven PRISMA screening workflow.")
|
|
app.add_typer(mail_app, name="mail", help="Maddy mail server (DO + Resend smarthost).")
|
|
|
|
|
|
def main() -> None:
|
|
"""Entry point for ``uv run stack``."""
|
|
app()
|