Michael
6df726e69e
Replaces the Shopify / RevOps / Bookkeeper demo trio with three accounting personas that share one buyer, each entering through a workflow where a messy export costs money — all running the same saved 4-step pipeline: - bank_reconciliation.csv (Bookkeeper): 26 -> 20 rows, 6 double-posted transactions caught after date+amount standardization. - vendor_1099.csv (AP / 1099): 24 records -> 8 vendors, 7 missing EINs recovered via dedup merge — the 1099-complete story. - ar_open_invoices.csv (AR): 26 -> 21 rows, 5 double-entered invoices removed, blank status backfilled from the twin row. Every number is validated against the live engine and pinned by tests/test_demo_pipelines.py (read path mirrors app_demo._load_demo: dtype=str, keep_default_na=False). Rewires src/gui/app_demo.py PERSONAS (keys bookkeeper / ap-1099 / ar-aging, accounting H1/sub/CTA) and rewrites docs/DEMO-PLAN.md sections 3/4/7 with the validated outcomes. (Repo hygiene forced by a partial-clone gap: finalizes the already-deleted, unreferenced samples/messy_text.csv whose blob was unrecoverable.) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
72 lines
3.1 KiB
Python
72 lines
3.1 KiB
Python
"""Demo pipelines must keep showing value (accounting personas).
|
|
|
|
Each persona's preloaded dataset + saved pipeline is the marketing surface
|
|
driven by ``src/gui/app_demo.py``. These tests pin that every demo loads,
|
|
runs clean, and produces its headline value (duplicate rows removed, clean
|
|
parse, disguised nulls caught) — so a stale dataset or an engine change can't
|
|
silently gut the sales demo. The read path mirrors ``app_demo._load_demo``
|
|
exactly (``dtype=str, keep_default_na=False`` so every disguised null survives
|
|
to the pipeline).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pandas as pd
|
|
import pytest
|
|
|
|
from src.core.pipeline import Pipeline, run_pipeline
|
|
|
|
_REPO = Path(__file__).resolve().parent.parent
|
|
_DEMO = _REPO / "samples" / "demo"
|
|
|
|
# (data_file, pipeline_file, min_duplicates_removed) — one per accounting
|
|
# persona in app_demo.PERSONAS. The dup floors are the validated demo numbers.
|
|
_DEMOS = [
|
|
("bank_reconciliation.csv", "bank_reconciliation_pipeline.json", 6),
|
|
("vendor_1099.csv", "vendor_1099_pipeline.json", 8),
|
|
("ar_open_invoices.csv", "ar_open_invoices_pipeline.json", 5),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("data_file,pipeline_file,min_dupes", _DEMOS)
|
|
def test_demo_runs_clean_and_shows_value(data_file, pipeline_file, min_dupes):
|
|
df = pd.read_csv(_DEMO / data_file, dtype=str, keep_default_na=False)
|
|
pipe = Pipeline.from_file(_DEMO / pipeline_file)
|
|
res = run_pipeline(df, pipe, stop_on_error=True)
|
|
|
|
# 1. Nothing errored — the demo never shows a visitor a red banner.
|
|
assert all(sr.error is None for sr in res.step_results), [
|
|
(sr.step.tool, sr.error) for sr in res.step_results
|
|
]
|
|
|
|
# 2. Dedup removed the designed duplicate rows (the headline value).
|
|
assert res.final_rows < res.initial_rows
|
|
dedup = next(sr for sr in res.step_results if sr.step.tool == "dedup")
|
|
assert dedup.summary["duplicates_removed"] >= min_dupes
|
|
|
|
# 3. Standardization parsed every typed cell — a demo with unparseable
|
|
# cells reads as "the tool choked," which kills the pitch.
|
|
fmt = next(sr for sr in res.step_results if sr.step.tool == "format_standardize")
|
|
assert fmt.summary["cells_unparseable"] == 0
|
|
assert fmt.summary["cells_changed"] > 0
|
|
|
|
# 4. The disguised nulls (—, (blank), TBD, …) were caught.
|
|
miss = next(sr for sr in res.step_results if sr.step.tool == "missing")
|
|
assert miss.summary["sentinels_standardized"] > 0
|
|
|
|
|
|
def test_app_demo_references_each_demo_file():
|
|
"""Every data/pipeline file the demo app names must exist on disk.
|
|
|
|
Guards against a rename in app_demo.py drifting away from samples/demo/
|
|
(or vice versa) without a test catching it.
|
|
"""
|
|
src = (_REPO / "src" / "gui" / "app_demo.py").read_text(encoding="utf-8")
|
|
for data_file, pipeline_file, _ in _DEMOS:
|
|
assert data_file in src, f"{data_file} not referenced in app_demo.py"
|
|
assert pipeline_file in src, f"{pipeline_file} not referenced in app_demo.py"
|
|
assert (_DEMO / data_file).exists(), f"missing {data_file}"
|
|
assert (_DEMO / pipeline_file).exists(), f"missing {pipeline_file}"
|