feat(analysis): audit_market_snapshots — coverage, gap, fetch_ok, NULL rate

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
root
2026-05-13 09:33:28 +00:00
parent aeac8f2a95
commit d6af69f4cb
2 changed files with 187 additions and 0 deletions
+119
View File
@@ -2,13 +2,21 @@
from __future__ import annotations
import sqlite3
from datetime import UTC, datetime
from decimal import Decimal
from pathlib import Path
from cerbero_bite.analysis.data_audit import (
MarketAuditReport,
audit_market_snapshots,
)
from cerbero_bite.analysis.data_audit import ( # noqa: PLC2701
_detect_gaps,
_expected_ticks,
_max_zero_streak,
)
from cerbero_bite.state import connect, run_migrations, transaction
def test_expected_ticks_basic() -> None:
@@ -94,3 +102,114 @@ def test_max_zero_streak_single_zero_block() -> None:
def test_max_zero_streak_all_zeros() -> None:
assert _max_zero_streak([0, 0, 0]) == 3
def _make_conn(tmp_path: Path) -> sqlite3.Connection:
conn = connect(tmp_path / "state.sqlite")
run_migrations(conn)
return conn
def _seed_market(
conn: sqlite3.Connection,
*,
asset: str,
ts: datetime,
spot: Decimal | None = Decimal("3000"),
dvol: Decimal | None = Decimal("55"),
dealer_net_gamma: Decimal | None = Decimal("-50000000"),
fetch_ok: int = 1,
) -> None:
conn.execute(
"INSERT INTO market_snapshots(timestamp, asset, spot, dvol, "
"dealer_net_gamma, fetch_ok) VALUES (?,?,?,?,?,?)",
(
ts.isoformat(),
asset,
str(spot) if spot is not None else None,
str(dvol) if dvol is not None else None,
str(dealer_net_gamma) if dealer_net_gamma is not None else None,
fetch_ok,
),
)
def test_audit_market_full_coverage(tmp_path: Path) -> None:
conn = _make_conn(tmp_path)
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
until = datetime(2026, 5, 12, 13, 0, tzinfo=UTC)
try:
with transaction(conn):
for minute in (0, 15, 30, 45):
_seed_market(
conn,
asset="ETH",
ts=since.replace(minute=minute),
)
report = audit_market_snapshots(
conn, asset="ETH", since=since, until=until
)
finally:
conn.close()
assert report.asset == "ETH"
assert report.expected_ticks == 4
assert report.actual_ticks == 4
assert report.coverage_pct == Decimal("100")
assert report.gaps == ()
assert report.fetch_ok_zero_count == 0
assert report.max_fetch_ok_zero_streak == 0
def test_audit_market_detects_gap_and_streak(tmp_path: Path) -> None:
conn = _make_conn(tmp_path)
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
until = datetime(2026, 5, 12, 13, 30, tzinfo=UTC)
try:
with transaction(conn):
# 12:00 OK, 12:15 OK, gap (12:30, 12:45 missing), 13:00 fail,
# 13:15 fail, 13:30 outside window.
_seed_market(conn, asset="ETH", ts=since.replace(minute=0))
_seed_market(conn, asset="ETH", ts=since.replace(minute=15))
_seed_market(
conn, asset="ETH", ts=since.replace(hour=13, minute=0),
fetch_ok=0,
)
_seed_market(
conn, asset="ETH", ts=since.replace(hour=13, minute=15),
fetch_ok=0,
)
report = audit_market_snapshots(
conn, asset="ETH", since=since, until=until
)
finally:
conn.close()
assert report.expected_ticks == 6
assert report.actual_ticks == 4
# 12:15 → 13:00 is a 45-min gap → flagged
assert len(report.gaps) == 1
assert report.gaps[0].gap_minutes == 45
assert report.fetch_ok_zero_count == 2
assert report.max_fetch_ok_zero_streak == 2
def test_audit_market_null_rate_per_column(tmp_path: Path) -> None:
conn = _make_conn(tmp_path)
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
until = datetime(2026, 5, 12, 13, 0, tzinfo=UTC)
try:
with transaction(conn):
# 4 ticks, 1 with dealer_net_gamma=NULL → 25% null
for minute in (0, 15, 30, 45):
_seed_market(
conn,
asset="ETH",
ts=since.replace(minute=minute),
dealer_net_gamma=None if minute == 30 else Decimal("-50000000"),
)
report = audit_market_snapshots(
conn, asset="ETH", since=since, until=until
)
finally:
conn.close()
assert report.null_rate_by_column["dealer_net_gamma"] == Decimal("0.25")
assert report.null_rate_by_column["spot"] == Decimal("0")