feat: add fundamentals parity reporting

This commit is contained in:
2026-07-23 21:17:58 +02:00
parent 361cfd7883
commit ce8c60d957
26 changed files with 1331 additions and 8 deletions
+4
View File
@@ -61,6 +61,10 @@ class Settings(BaseSettings):
sec_max_retries: int = 4
sec_request_timeout_seconds: float = 30.0
# A5 read-only comparison artifacts. Production must keep this outside the
# rsync deployment tree so the 5-7 day review window survives deploys.
fundamentals_parity_report_dir: str = "reports/fundamentals-parity"
# Regime Monitor — FRED (VIX level + HY credit spreads). Optional: without it
# the volatility (P5) and credit-spread (F2) signals are reported as n/a.
fred_api_key: str = ""
+30
View File
@@ -453,6 +453,36 @@ async def toggle_job(
)
@router.get("/admin/fundamentals-parity", response_model=APIEnvelope)
async def get_fundamentals_parity_report(
_admin: User = Depends(require_admin),
):
"""Latest read-only A5 source/score comparison, or null before first run."""
return APIEnvelope(
status="success", data=admin_service.get_fundamentals_parity_report()
)
@router.get("/admin/fundamentals-parity/csv", response_model=APIEnvelope)
async def get_fundamentals_parity_csv(
_admin: User = Depends(require_admin),
):
"""Latest flattened A5 report for an authenticated browser download."""
artifact = admin_service.get_fundamentals_parity_csv()
data = None if artifact is None else {"filename": artifact[0], "content": artifact[1]}
return APIEnvelope(status="success", data=data)
@router.get("/admin/fundamentals-parity/json", response_model=APIEnvelope)
async def get_fundamentals_parity_json(
_admin: User = Depends(require_admin),
):
"""Canonical A5 JSON artifact for an authenticated browser download."""
artifact = admin_service.get_fundamentals_parity_json()
data = None if artifact is None else {"filename": artifact[0], "content": artifact[1]}
return APIEnvelope(status="success", data=data)
# ---------------------------------------------------------------------------
# System events (operational warnings / errors)
# ---------------------------------------------------------------------------
+61
View File
@@ -40,6 +40,7 @@ from app.services import (
sentiment_service,
settings_store,
shadow_book_service,
fundamentals_parity_service,
)
from app.services.data_import import STATUS_FAILED, SourceImporter, run_import
from app.services.dolt_earnings_importer import DoltEarningsImporter
@@ -98,6 +99,7 @@ _JOB_NAMES = [
"fundamental_collector",
"dolt_earnings_import",
"sec_fundamentals_import",
"fundamentals_parity_report",
"rr_scanner",
"ticker_universe_sync",
"alerts",
@@ -981,6 +983,49 @@ async def run_sec_fundamentals_import() -> None:
await _run_shadow_import("sec_fundamentals_import", SecFundamentalsImporter())
async def run_fundamentals_parity_report() -> None:
"""Generate the A5 comparison bundle without mutating live fundamentals/scores."""
job_name = "fundamentals_parity_report"
_log_event(logging.INFO, "job_start", job=job_name)
_runtime_start(job_name, total=1)
try:
async with async_session_factory() as db:
if not await _is_job_enabled(db, job_name):
_runtime_finish(
job_name, "skipped", processed=0, total=1, message="Disabled"
)
return
report, artifacts = await fundamentals_parity_service.generate_and_store(
db, settings.fundamentals_parity_report_dir
)
summary = report["summary"]
message = (
f"{summary['universe_count']} tickers · "
f"{summary['fundamental_score_material_changes']} material score changes"
)
_runtime_finish(job_name, "completed", processed=1, total=1, message=message)
_log_event(
logging.INFO,
"job_complete",
job=job_name,
generated_at=report["generated_at"],
json_path=artifacts["json"],
csv_path=artifacts["csv"],
)
except asyncio.CancelledError:
_runtime_finish(job_name, "error", processed=0, total=1, message="Cancelled")
raise
except Exception as exc:
_runtime_finish(job_name, "error", processed=0, total=1, message=str(exc))
_log_event(
logging.ERROR,
"job_error",
job=job_name,
error_type=type(exc).__name__,
message=str(exc),
)
# ---------------------------------------------------------------------------
# Job: R:R Scanner
# ---------------------------------------------------------------------------
@@ -1524,6 +1569,7 @@ SCHEDULE_DEFAULTS: dict[str, str] = {
# Shadow source imports. They never write legacy fundamental_data before A5.
"schedule_dolt_earnings_cron": "30 2 * * *",
"schedule_sec_fundamentals_cron": "0 4 * * *",
"schedule_fundamentals_parity_cron": "30 5 * * *",
# Fetch in-progress bars → scan → Telegram (manual MOC window).
"schedule_near_close_pipeline_cron": "30 15 * * mon-fri",
# Fetch final bars → outcome eval (must not run on the partial near-close bar).
@@ -1539,6 +1585,7 @@ _CRON_JOBS: dict[str, str] = {
"daily_pipeline": "schedule_daily_pipeline_cron",
"dolt_earnings_import": "schedule_dolt_earnings_cron",
"sec_fundamentals_import": "schedule_sec_fundamentals_cron",
"fundamentals_parity_report": "schedule_fundamentals_parity_cron",
"near_close_pipeline": "schedule_near_close_pipeline_cron",
"after_close_pipeline": "schedule_after_close_pipeline_cron",
"intraday_pipeline": "schedule_intraday_pipeline_cron",
@@ -1645,6 +1692,17 @@ def configure_scheduler(schedule_config: dict[str, str] | None = None) -> None:
name="SEC Fundamentals Import (shadow)",
replace_existing=True,
)
scheduler.add_job(
run_fundamentals_parity_report,
_cron_trigger(
cfg["schedule_fundamentals_parity_cron"],
tz,
"schedule_fundamentals_parity_cron",
),
id="fundamentals_parity_report",
name="Fundamentals Parity Report (read-only)",
replace_existing=True,
)
scheduler.add_job(
run_near_close_pipeline,
_cron_trigger(
@@ -1720,6 +1778,9 @@ def configure_scheduler(schedule_config: dict[str, str] | None = None) -> None:
},
dolt_earnings_import={"cron": cfg["schedule_dolt_earnings_cron"]},
sec_fundamentals_import={"cron": cfg["schedule_sec_fundamentals_cron"]},
fundamentals_parity_report={
"cron": cfg["schedule_fundamentals_parity_cron"]
},
near_close_pipeline={
"cron": cfg["schedule_near_close_pipeline_cron"],
"steps": [name for name, _ in _NEAR_CLOSE_PIPELINE_STEPS],
+3
View File
@@ -78,6 +78,9 @@ class ScheduleConfigUpdate(BaseModel):
(min hour dom month dow); timezone is an IANA name (e.g. America/New_York)."""
schedule_timezone: str | None = Field(default=None, max_length=64)
schedule_daily_pipeline_cron: str | None = Field(default=None, max_length=120)
schedule_dolt_earnings_cron: str | None = Field(default=None, max_length=120)
schedule_sec_fundamentals_cron: str | None = Field(default=None, max_length=120)
schedule_fundamentals_parity_cron: str | None = Field(default=None, max_length=120)
schedule_near_close_pipeline_cron: str | None = Field(default=None, max_length=120)
schedule_after_close_pipeline_cron: str | None = Field(default=None, max_length=120)
schedule_intraday_pipeline_cron: str | None = Field(default=None, max_length=120)
+1
View File
@@ -26,6 +26,7 @@ class MetricItem(BaseModel):
industry: MetricIndustry | None = None
period_end: str | None = None
filed_date: str | None = None
caveat: str | None = None
source: str = "sec"
+29
View File
@@ -614,6 +614,7 @@ VALID_JOB_NAMES = {
"fundamental_collector",
"dolt_earnings_import",
"sec_fundamentals_import",
"fundamentals_parity_report",
"rr_scanner",
"ticker_universe_sync",
"outcome_evaluator",
@@ -637,6 +638,7 @@ JOB_LABELS = {
"fundamental_collector": "Fundamental Collector",
"dolt_earnings_import": "Dolt Earnings Import (shadow)",
"sec_fundamentals_import": "SEC Fundamentals Import (shadow)",
"fundamentals_parity_report": "Fundamentals Parity Report (read-only)",
"rr_scanner": "R:R Scanner",
"ticker_universe_sync": "Ticker Universe Sync",
"outcome_evaluator": "Outcome Evaluator",
@@ -775,3 +777,30 @@ async def toggle_job(db: AsyncSession, job_name: str, enabled: bool) -> SystemSe
key = f"job_{job_name}_enabled"
return await update_setting(db, key, str(enabled).lower())
def get_fundamentals_parity_report() -> dict | None:
"""Return the latest compact A5 summary, if the job has run."""
from app.config import settings
from app.services.fundamentals_parity_service import load_latest
report = load_latest(settings.fundamentals_parity_report_dir)
if report is not None:
report.pop("rows", None) # full per-ticker data is download-only
return report
def get_fundamentals_parity_csv() -> tuple[str, str] | None:
"""Return the latest A5 CSV filename and content for authenticated download."""
from app.config import settings
from app.services.fundamentals_parity_service import load_latest_csv
return load_latest_csv(settings.fundamentals_parity_report_dir)
def get_fundamentals_parity_json() -> tuple[str, str] | None:
"""Return the canonical A5 JSON artifact for authenticated download."""
from app.config import settings
from app.services.fundamentals_parity_service import load_latest_json
return load_latest_json(settings.fundamentals_parity_report_dir)
+3 -1
View File
@@ -121,6 +121,7 @@ def _build_metrics(derived, peer_derived, two: str | None) -> list[dict[str, Any
"industry": industry,
"period_end": _iso(series.period_end) if series else None,
"filed_date": _iso(series.filed_date) if series else None,
"caveat": series.caveat if series else None,
"source": "sec",
})
return out
@@ -303,7 +304,8 @@ async def _latest_close(db, ticker_id: int) -> tuple[float, date] | None:
def _empty_metrics() -> list[dict[str, Any]]:
return [{"key": k, "value": None, "history": [], "industry": None,
"period_end": None, "filed_date": None, "source": "sec"} for k in METRIC_KEYS]
"period_end": None, "filed_date": None, "caveat": None,
"source": "sec"} for k in METRIC_KEYS]
def _empty_earnings() -> dict[str, Any]:
+41
View File
@@ -27,6 +27,11 @@ _FP_TO_Q = {"Q1": 1, "Q2": 2, "Q3": 3, "FY": 4}
_Q_TO_FP = {1: "Q1", 2: "Q2", 3: "Q3", 4: "FY"}
_PREV_FP = {"Q2": "Q1", "Q3": "Q2", "FY": "Q3"}
TAPE_LEN = 4 # quarter-tape length
SPLIT_SUSPECT_SHARE_CHANGE_PCT = 25.0
SPLIT_SENSITIVE_CAVEAT = (
"Not comparable: share count changed at least 25%; possible split or "
"corporate action."
)
# Duration (flow) fields differenced from YTD into discrete quarters + summed to TTM.
_FLOW_FIELDS = (
@@ -47,6 +52,7 @@ class MetricSeries:
history: list[MetricPoint] = field(default_factory=list) # oldest -> newest, <= TAPE_LEN
period_end: date | None = None
filed_date: date | None = None
caveat: str | None = None
@dataclass
@@ -96,6 +102,7 @@ def derive(snapshots: Iterable[Any]) -> DerivedFundamentals:
"net_debt_to_ebitda": _leverage_series(selected, discrete, tape),
"share_count_change_yoy": _share_change_series(selected, tape),
}
_guard_split_sensitive_metrics(result.metrics)
for series in result.metrics.values():
series.period_end = latest_row.period_end
series.filed_date = latest_row.filed_date
@@ -248,6 +255,40 @@ def _share_change_series(selected, tape) -> MetricSeries:
return _series(pts)
def _guard_split_sensitive_metrics(metrics: dict[str, MetricSeries]) -> None:
"""Suppress historical comparisons likely distorted by a corporate action.
Company Facts has no point-in-time split factors. A large YoY share-count
move can therefore make both the point-in-time share comparison and
per-share EPS growth non-comparable. Keep the raw facts in snapshots, but
expose nulls plus an explicit caveat in the user-facing derived series.
"""
shares = metrics.get("share_count_change_yoy")
eps = metrics.get("eps_growth_yoy")
if shares is None or eps is None:
return
suspect_periods = {
point.period_end
for point in shares.history
if point.value is not None
and abs(point.value) >= SPLIT_SUSPECT_SHARE_CHANGE_PCT
}
if not suspect_periods:
return
for series in (shares, eps):
latest_guarded = bool(
series.history and series.history[-1].period_end in suspect_periods
)
for point in series.history:
if point.period_end in suspect_periods:
point.value = None
series.value = series.history[-1].value if series.history else None
if latest_guarded:
series.caveat = SPLIT_SENSITIVE_CAVEAT
def _net_debt(row: Any) -> float | None:
if row is None:
return None
+598
View File
@@ -0,0 +1,598 @@
"""Read-only A5 comparison of legacy and SEC/Dolt fundamental inputs.
The report deliberately does not write ``fundamental_data`` or score tables.
It reconstructs the current legacy and candidate fundamental scores, projects
their composite-score/rank effect with the active weights, and archives a
timestamped JSON + CSV bundle for explicit human approval.
"""
from __future__ import annotations
import csv
import io
import json
import math
import os
import statistics
from collections import defaultdict
from datetime import date, datetime, timezone
from pathlib import Path
from typing import Any, Iterable
from zoneinfo import ZoneInfo
from sqlalchemy import func, select, text
from sqlalchemy.ext.asyncio import AsyncSession
from app.models.data_import_run import DataImportRun
from app.models.earnings_event import EarningsEvent
from app.models.fundamental import FundamentalData
from app.models.fundamental_snapshot import FundamentalSnapshot
from app.models.ohlcv import OHLCVRecord
from app.models.ticker import Ticker
from app.services import fundamentals_derivation as deriv
REPORT_VERSION = 1
APPROVAL_STATUS = "pending_explicit_approval"
FIELD_KEYS = ("pe_ratio", "revenue_growth", "earnings_surprise")
MIN_SCORE_METRICS = 2
# Materiality is a review aid, never an automatic cutover verdict. Definition
# changes remain visible even when a delta falls inside these bands.
FIELD_TOLERANCES = {
"pe_ratio": {"absolute": 1.0, "relative_pct": 10.0},
"revenue_growth": {"absolute": 2.0, "relative_pct": None},
"earnings_surprise": {"absolute": 2.0, "relative_pct": None},
}
DEFINITION_NOTES = {
"pe_ratio": (
"Legacy provider P/E convention versus latest close divided by "
"SEC-derived TTM diluted EPS."
),
"revenue_growth": (
"Legacy provider growth convention versus SEC-derived TTM revenue YoY."
),
"earnings_surprise": (
"Legacy provider latest surprise versus latest completed Dolt earnings "
"event with actual and estimate."
),
}
def fundamental_score(
pe_ratio: float | None,
revenue_growth: float | None,
earnings_surprise: float | None,
) -> float | None:
"""Match the production fundamental-dimension formula without persistence."""
scores: list[float] = []
if _finite(pe_ratio) and pe_ratio > 0:
scores.append(max(0.0, min(100.0, 100.0 - (pe_ratio - 15.0) * (100.0 / 30.0))))
if _finite(revenue_growth):
scores.append(max(0.0, min(100.0, 50.0 + revenue_growth * 2.5)))
if _finite(earnings_surprise):
scores.append(max(0.0, min(100.0, 50.0 + earnings_surprise * 5.0)))
return sum(scores) / len(scores) if len(scores) >= MIN_SCORE_METRICS else None
async def build_report(
db: AsyncSession,
*,
generated_at: datetime | None = None,
today: date | None = None,
) -> dict[str, Any]:
"""Build a point-in-time parity report from one database session."""
generated_at = generated_at or datetime.now(timezone.utc)
today = today or datetime.now(ZoneInfo("America/New_York")).date()
# A report must not mix rows from before and after a concurrent import
# promotion. The scheduled job provides a fresh session, so establish the
# production snapshot before its first query and have Postgres enforce the
# no-write contract as well. SQLite tests retain their normal transaction.
if db.get_bind().dialect.name == "postgresql":
connection = await db.connection(
execution_options={"isolation_level": "REPEATABLE READ"}
)
await connection.execute(text("SET TRANSACTION READ ONLY"))
tickers = list((await db.execute(select(Ticker).order_by(Ticker.symbol))).scalars())
ticker_ids = [ticker.id for ticker in tickers]
ciks = sorted({ticker.cik for ticker in tickers if ticker.cik})
legacy_by_ticker = await _legacy_values(db, ticker_ids)
derived_by_cik = await _derived_by_cik(db, ciks)
closes_by_ticker = await _latest_closes(db, ticker_ids)
surprise_by_ticker = await _latest_surprises(db, ticker_ids, today)
source_runs = await _source_runs(db)
rows: list[dict[str, Any]] = []
for ticker in tickers:
legacy = legacy_by_ticker.get(ticker.id)
derived = derived_by_cik.get(ticker.cik) if ticker.cik else None
close = closes_by_ticker.get(ticker.id)
candidate_pe = (
_pe(close[0], derived.ttm_diluted_eps)
if close is not None and derived is not None
else None
)
growth_series = (
derived.metrics.get("revenue_growth_yoy") if derived is not None else None
)
candidate = {
"pe_ratio": candidate_pe,
"revenue_growth": growth_series.value if growth_series else None,
"earnings_surprise": surprise_by_ticker.get(ticker.id),
}
legacy_values = {
"pe_ratio": legacy.pe_ratio if legacy else None,
"revenue_growth": legacy.revenue_growth if legacy else None,
"earnings_surprise": legacy.earnings_surprise if legacy else None,
}
fields = {
key: _field_comparison(key, legacy_values[key], candidate[key])
for key in FIELD_KEYS
}
legacy_score = fundamental_score(**legacy_values)
candidate_score = fundamental_score(**candidate)
rows.append(
{
"symbol": ticker.symbol,
"cik": ticker.cik,
"legacy_fetched_at": _iso(legacy.fetched_at) if legacy else None,
"price_date": _iso(close[1]) if close else None,
"fields": fields,
"scores": {
"legacy_fundamental": _round(legacy_score),
"candidate_fundamental": _round(candidate_score),
"fundamental_delta": _delta(legacy_score, candidate_score),
"legacy_fundamental_rank": None,
"candidate_fundamental_rank": None,
"fundamental_rank_change": None,
},
}
)
_attach_ranks(rows, "legacy_fundamental", "legacy_fundamental_rank")
_attach_ranks(rows, "candidate_fundamental", "candidate_fundamental_rank")
for row in rows:
scores = row["scores"]
scores["fundamental_rank_change"] = _rank_change(
scores["legacy_fundamental_rank"], scores["candidate_fundamental_rank"]
)
return {
"report_version": REPORT_VERSION,
"generated_at": generated_at.isoformat(),
"as_of_date": today.isoformat(),
"approval_status": APPROVAL_STATUS,
"read_only": True,
"fundamental_score_formula": (
"Equal-weighted mean of 2+ available sub-scores: P/E = "
"clamp(100-(pe-15)*(100/30)); revenue growth = "
"clamp(50+growth*2.5); earnings surprise = "
"clamp(50+surprise*5)."
),
"source_runs": source_runs,
"definition_notes": DEFINITION_NOTES,
"materiality_notes": {
"fields": FIELD_TOLERANCES,
"fundamental_score_absolute": 5.0,
"automatic_cutover": False,
},
"summary": _summary(rows),
"rows": rows,
}
def store_report(report: dict[str, Any], report_dir: str | Path) -> dict[str, str]:
"""Atomically archive JSON/CSV artifacts and update the latest manifest."""
directory = Path(report_dir).expanduser().resolve()
directory.mkdir(parents=True, exist_ok=True)
stamp = _artifact_stamp(report["generated_at"])
json_name = f"fundamentals-parity-{stamp}.json"
csv_name = f"fundamentals-parity-{stamp}.csv"
json_path = directory / json_name
csv_path = directory / csv_name
_atomic_write(json_path, json.dumps(report, indent=2, sort_keys=True) + "\n")
_atomic_write(csv_path, report_csv(report))
manifest = {
"generated_at": report["generated_at"],
"json_file": json_name,
"csv_file": csv_name,
}
_atomic_write(
directory / "latest.json",
json.dumps(manifest, indent=2, sort_keys=True) + "\n",
)
return {
"json": str(json_path),
"csv": str(csv_path),
"manifest": str(directory / "latest.json"),
}
async def generate_and_store(
db: AsyncSession,
report_dir: str | Path,
*,
generated_at: datetime | None = None,
today: date | None = None,
) -> tuple[dict[str, Any], dict[str, str]]:
report = await build_report(db, generated_at=generated_at, today=today)
return report, store_report(report, report_dir)
def load_latest(report_dir: str | Path) -> dict[str, Any] | None:
manifest = _load_manifest(report_dir)
if manifest is None:
return None
try:
path = _manifest_artifact(report_dir, manifest, "json_file")
loaded = json.loads(path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError, TypeError, ValueError):
return None
return loaded if isinstance(loaded, dict) else None
def load_latest_csv(report_dir: str | Path) -> tuple[str, str] | None:
return _load_latest_text_artifact(report_dir, "csv_file")
def load_latest_json(report_dir: str | Path) -> tuple[str, str] | None:
return _load_latest_text_artifact(report_dir, "json_file")
def _load_latest_text_artifact(
report_dir: str | Path, manifest_key: str
) -> tuple[str, str] | None:
manifest = _load_manifest(report_dir)
if manifest is None:
return None
try:
path = _manifest_artifact(report_dir, manifest, manifest_key)
return path.name, path.read_text(encoding="utf-8")
except (OSError, TypeError, ValueError):
return None
def report_csv(report: dict[str, Any]) -> str:
output = io.StringIO(newline="")
columns = [
"symbol",
"cik",
"legacy_fetched_at",
"price_date",
*(
f"{field}_{suffix}"
for field in FIELD_KEYS
for suffix in ("legacy", "candidate", "absolute_delta", "relative_delta_pct", "material")
),
"legacy_fundamental",
"candidate_fundamental",
"fundamental_delta",
"legacy_fundamental_rank",
"candidate_fundamental_rank",
"fundamental_rank_change",
]
writer = csv.DictWriter(output, fieldnames=columns)
writer.writeheader()
for row in report.get("rows", []):
flat = {
"symbol": row["symbol"],
"cik": row.get("cik"),
"legacy_fetched_at": row.get("legacy_fetched_at"),
"price_date": row.get("price_date"),
**row["scores"],
}
for field in FIELD_KEYS:
comparison = row["fields"][field]
for suffix in (
"legacy",
"candidate",
"absolute_delta",
"relative_delta_pct",
"material",
):
flat[f"{field}_{suffix}"] = comparison.get(suffix)
writer.writerow(flat)
return output.getvalue()
async def _legacy_values(
db: AsyncSession, ticker_ids: list[int]
) -> dict[int, FundamentalData]:
if not ticker_ids:
return {}
rows = (
await db.execute(
select(FundamentalData).where(FundamentalData.ticker_id.in_(ticker_ids))
)
).scalars()
return {row.ticker_id: row for row in rows}
async def _derived_by_cik(
db: AsyncSession, ciks: list[str]
) -> dict[str, deriv.DerivedFundamentals]:
if not ciks:
return {}
grouped: dict[str, list[FundamentalSnapshot]] = defaultdict(list)
rows = (
await db.execute(
select(FundamentalSnapshot).where(FundamentalSnapshot.cik.in_(ciks))
)
).scalars()
for row in rows:
grouped[row.cik].append(row)
return {cik: deriv.derive(grouped.get(cik, [])) for cik in ciks}
async def _latest_closes(
db: AsyncSession, ticker_ids: list[int]
) -> dict[int, tuple[float, date]]:
if not ticker_ids:
return {}
latest = (
select(OHLCVRecord.ticker_id, func.max(OHLCVRecord.date).label("max_date"))
.where(OHLCVRecord.ticker_id.in_(ticker_ids))
.group_by(OHLCVRecord.ticker_id)
.subquery()
)
rows = (
await db.execute(
select(OHLCVRecord.ticker_id, OHLCVRecord.close, OHLCVRecord.date).join(
latest,
(OHLCVRecord.ticker_id == latest.c.ticker_id)
& (OHLCVRecord.date == latest.c.max_date),
)
)
).all()
return {
ticker_id: (float(close), close_date)
for ticker_id, close, close_date in rows
if _finite(close)
}
async def _latest_surprises(
db: AsyncSession, ticker_ids: list[int], today: date
) -> dict[int, float]:
if not ticker_ids:
return {}
rows = (
await db.execute(
select(EarningsEvent)
.where(
EarningsEvent.ticker_id.in_(ticker_ids),
EarningsEvent.announce_date < today,
)
.order_by(EarningsEvent.ticker_id, EarningsEvent.announce_date.desc())
)
).scalars()
out: dict[int, float] = {}
for row in rows:
if row.ticker_id in out:
continue
surprise = _surprise(row.eps_estimate, row.eps_actual)
if surprise is not None:
out[row.ticker_id] = surprise
return out
async def _source_runs(db: AsyncSession) -> dict[str, dict[str, Any] | None]:
sources = ("sec_facts", "dolt_earnings")
rows = (
await db.execute(
select(DataImportRun)
.where(
DataImportRun.source.in_(sources),
DataImportRun.status.in_(("promoted", "no_op")),
)
.order_by(DataImportRun.id.desc())
)
).scalars()
latest: dict[str, dict[str, Any] | None] = {source: None for source in sources}
for row in rows:
if latest[row.source] is None:
latest[row.source] = {
"run_id": row.id,
"status": row.status,
"revision": row.revision,
"source_max_date": _iso(row.source_max_date),
"completed_at": _iso(row.completed_at),
}
return latest
def _field_comparison(
key: str, legacy: float | None, candidate: float | None
) -> dict[str, Any]:
legacy = float(legacy) if _finite(legacy) else None
candidate = float(candidate) if _finite(candidate) else None
absolute = _delta(legacy, candidate)
relative = (
None
if absolute is None or legacy in (None, 0)
else round(absolute / abs(legacy) * 100.0, 4)
)
tolerance = FIELD_TOLERANCES[key]
material = False
if absolute is not None:
material = abs(absolute) > tolerance["absolute"]
relative_limit = tolerance["relative_pct"]
if relative_limit is not None:
material = material and relative is not None and abs(relative) > relative_limit
return {
"legacy": _round(legacy),
"candidate": _round(candidate),
"absolute_delta": absolute,
"relative_delta_pct": relative,
"material": material,
"definition_changed": True,
}
def _attach_ranks(rows: list[dict[str, Any]], value_key: str, rank_key: str) -> None:
values = [
row["scores"][value_key]
for row in rows
if _finite(row["scores"][value_key])
]
for row in rows:
value = row["scores"][value_key]
row["scores"][rank_key] = (
1 + sum(other > value for other in values) if _finite(value) else None
)
def _summary(rows: list[dict[str, Any]]) -> dict[str, Any]:
field_stats = {}
for key in FIELD_KEYS:
comparisons = [row["fields"][key] for row in rows]
deltas = [
abs(item["absolute_delta"])
for item in comparisons
if item["absolute_delta"] is not None
]
field_stats[key] = {
"legacy_available": sum(item["legacy"] is not None for item in comparisons),
"candidate_available": sum(
item["candidate"] is not None for item in comparisons
),
"both_available": len(deltas),
"material_differences": sum(item["material"] for item in comparisons),
"median_absolute_delta": _round(statistics.median(deltas) if deltas else None),
"p95_absolute_delta": _round(_percentile(deltas, 0.95)),
"max_absolute_delta": _round(max(deltas) if deltas else None),
}
fundamental_deltas = _score_deltas(rows, "fundamental_delta")
changed_rows = sorted(
(
{
"symbol": row["symbol"],
"fundamental_delta": row["scores"]["fundamental_delta"],
"fundamental_rank_change": row["scores"]["fundamental_rank_change"],
}
for row in rows
if row["scores"]["fundamental_delta"] is not None
),
key=lambda item: (
abs(item["fundamental_delta"] or 0),
),
reverse=True,
)[:20]
return {
"universe_count": len(rows),
"legacy_fundamental_score_available": _count_score(
rows, "legacy_fundamental"
),
"candidate_fundamental_score_available": _count_score(
rows, "candidate_fundamental"
),
"fundamental_scores_compared": len(fundamental_deltas),
"fundamental_score_material_changes": sum(
abs(delta) > 5.0 for delta in fundamental_deltas
),
"fundamental_rank_changes": _rank_change_count(
rows, "fundamental_rank_change"
),
"field_stats": field_stats,
"largest_changes": changed_rows,
}
def _score_deltas(rows: Iterable[dict[str, Any]], key: str) -> list[float]:
return [
row["scores"][key]
for row in rows
if row["scores"][key] is not None
]
def _count_score(rows: Iterable[dict[str, Any]], key: str) -> int:
return sum(row["scores"][key] is not None for row in rows)
def _rank_change_count(rows: Iterable[dict[str, Any]], key: str) -> int:
return sum(
row["scores"][key] not in (None, 0)
for row in rows
)
def _rank_change(legacy: int | None, candidate: int | None) -> int | None:
# Positive means the candidate improved its rank.
return legacy - candidate if legacy is not None and candidate is not None else None
def _surprise(estimate: float | None, actual: float | None) -> float | None:
if not _finite(estimate) or not _finite(actual) or estimate == 0:
return None
return (actual - estimate) / abs(estimate) * 100.0
def _pe(price: float | None, ttm_eps: float | None) -> float | None:
if not _finite(price) or price <= 0 or not _finite(ttm_eps) or ttm_eps <= 0:
return None
return price / ttm_eps
def _delta(legacy: float | None, candidate: float | None) -> float | None:
if not _finite(legacy) or not _finite(candidate):
return None
return round(candidate - legacy, 4)
def _round(value: float | None, digits: int = 4) -> float | None:
return round(float(value), digits) if _finite(value) else None
def _percentile(values: list[float], quantile: float) -> float | None:
if not values:
return None
ordered = sorted(values)
index = max(0, math.ceil(quantile * len(ordered)) - 1)
return ordered[index]
def _finite(value: Any) -> bool:
return (
isinstance(value, (int, float))
and not isinstance(value, bool)
and math.isfinite(value)
)
def _iso(value: Any) -> str | None:
return value.isoformat() if value is not None else None
def _artifact_stamp(raw: str) -> str:
parsed = datetime.fromisoformat(raw.replace("Z", "+00:00"))
return parsed.astimezone(timezone.utc).strftime("%Y%m%dT%H%M%S%fZ")
def _atomic_write(path: Path, content: str) -> None:
temp = path.with_name(f".{path.name}.{os.getpid()}.tmp")
temp.write_text(content, encoding="utf-8", newline="")
os.replace(temp, path)
def _load_manifest(report_dir: str | Path) -> dict[str, Any] | None:
path = Path(report_dir).expanduser().resolve() / "latest.json"
try:
loaded = json.loads(path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError, TypeError, ValueError):
return None
return loaded if isinstance(loaded, dict) else None
def _manifest_artifact(
report_dir: str | Path, manifest: dict[str, Any], key: str
) -> Path:
directory = Path(report_dir).expanduser().resolve()
name = Path(str(manifest.get(key, ""))).name
if not name:
raise ValueError(f"Latest parity manifest has no {key}")
return directory / name