refactor: restructure repo into core/app modules with per-study folders

Reorganize Palladium codebase into a modular architecture with `core/`
shared logic and `app/` Streamlit UI, separating per-study assets into
`studies/YYYYMM_<Vendor>/` folders containing notebooks, seed data, and
configuration. Update README to reflect new structure, add `.gitignore`
entries for `.env` and study exports, and refresh component documentation.
This commit is contained in:
2026-05-20 22:28:12 -04:00
parent a6f3ee3676
commit a2420ed692
52 changed files with 35300 additions and 105 deletions

View File

@@ -0,0 +1,195 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "15a4163e",
"metadata": {},
"source": [
"# 04 — Export for the report pipeline\n",
"\n",
"Build the structured JSON envelope consumed by the html2docx report\n",
"generation pipeline (Peitho). Output goes to `exports/export.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "18f02ef8",
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"from pathlib import Path\n",
"\n",
"ROOT = Path.cwd().resolve()\n",
"while ROOT != ROOT.parent and not (ROOT / 'core').is_dir():\n",
" ROOT = ROOT.parent\n",
"if str(ROOT) not in sys.path:\n",
" sys.path.insert(0, str(ROOT))\n",
"STUDY = ROOT / 'studies' / '202602_AmazonConnect'\n",
"if str(STUDY) not in sys.path:\n",
" sys.path.insert(0, str(STUDY))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7d91c01d",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"from datetime import datetime, timezone\n",
"\n",
"import config\n",
"import seed_data\n",
"from core import __version__\n",
"from core.calculations import apply_scenario\n",
"from core.export.report_data import _compute_summary\n",
"from core.notebook_helpers import display"
]
},
{
"cell_type": "markdown",
"id": "cff0b35b",
"metadata": {},
"source": [
"## Build the envelope\n",
"\n",
"Two paths:\n",
"\n",
"* **Live** — `core.export.build_report_data(client, public_id)` pulls\n",
" authoritative values + summary from Athena and stamps it.\n",
"* **Local** — when no `TOOL_PUBLIC_ID` is configured, build the envelope\n",
" directly from `seed_data` so this notebook is always runnable."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "19416ff3",
"metadata": {},
"outputs": [],
"source": [
"if config.TOOL_PUBLIC_ID:\n",
" from core.export import build_report_data\n",
" from core.tei_client import TEIClient\n",
"\n",
" client = TEIClient()\n",
" envelope = build_report_data(\n",
" client,\n",
" config.TOOL_PUBLIC_ID,\n",
" include_scenarios=True,\n",
" study_slug=config.STUDY_SLUG,\n",
" )\n",
" source = 'live (Athena)'\n",
"else:\n",
" summary = _compute_summary(\n",
" seed_data.BENEFITS, seed_data.COSTS, config.DISCOUNT_RATE, config.ANALYSIS_YEARS\n",
" )\n",
" summary['roi'] = summary.get('roi_pct')\n",
" scenarios = {}\n",
" for name in ('conservative', 'moderate', 'aggressive'):\n",
" sb = apply_scenario(seed_data.BENEFITS, name, table='benefits')\n",
" sc = apply_scenario(seed_data.COSTS, name, table='costs')\n",
" scenarios[name] = _compute_summary(sb, sc, config.DISCOUNT_RATE, config.ANALYSIS_YEARS)\n",
" envelope = {\n",
" 'metadata': {\n",
" 'study_slug': config.STUDY_SLUG,\n",
" 'tool_public_id': '',\n",
" 'tool_name': 'Amazon Connect TEI (local seed)',\n",
" 'report_name': 'Total Economic Impact™ Of Amazon Connect',\n",
" 'report_vendor': 'AWS',\n",
" 'report_version': '1.0',\n",
" 'generated_at': datetime.now(timezone.utc).isoformat(),\n",
" 'generator': f'palladium core {__version__} (offline)',\n",
" },\n",
" 'report': {\n",
" 'name': 'Total Economic Impact™ Of Amazon Connect',\n",
" 'vendor': 'AWS',\n",
" 'version': '1.0',\n",
" 'discount_rate': config.DISCOUNT_RATE,\n",
" 'analysis_period_years': config.ANALYSIS_YEARS,\n",
" },\n",
" 'values': {'benefits': seed_data.BENEFITS, 'costs': seed_data.COSTS},\n",
" 'summary': summary,\n",
" 'scenarios': scenarios,\n",
" 'assumptions': seed_data.ASSUMPTIONS,\n",
" }\n",
" source = 'offline seed data'\n",
"\n",
"display.alert(f'Envelope built from <b>{source}</b>.', 'info')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "98e94d07",
"metadata": {},
"outputs": [],
"source": [
"out_path = STUDY / 'exports' / 'export.json'\n",
"out_path.parent.mkdir(parents=True, exist_ok=True)\n",
"out_path.write_text(json.dumps(envelope, indent=2, default=str))\n",
"size_kb = out_path.stat().st_size / 1024\n",
"display.alert(f'Wrote <code>{out_path.relative_to(ROOT)}</code> ({size_kb:.1f} KB).', 'success')"
]
},
{
"cell_type": "markdown",
"id": "d09cad64",
"metadata": {},
"source": [
"## Envelope shape\n",
"\n",
"Top-level keys consumed by the report pipeline:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "841f12a1",
"metadata": {},
"outputs": [],
"source": [
"for key in envelope:\n",
" sub = envelope[key]\n",
" if isinstance(sub, dict):\n",
" print(f' {key}: dict with keys {list(sub.keys())}')\n",
" elif isinstance(sub, list):\n",
" print(f' {key}: list[{len(sub)}]')\n",
" else:\n",
" print(f' {key}: {type(sub).__name__}')"
]
},
{
"cell_type": "markdown",
"id": "17d6d0ce",
"metadata": {},
"source": [
"Done. Hand off `exports/export.json` to **Peitho** / **html2docx** to produce the final Word report."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}