Adriano Dal Pastro
16d73c309a
Nuovo campo ChainAuditReport.ask_zero_count. La logica del loop parsifica prima l'ask: se ask<=0 è "missing ask side" (su Deribit significa nessun ordine in vendita), conta in ask_zero_count e non applica il check bid>ask. Solo con ask>0 si confronta con bid. Sul DB prod gli "bid>ask" del primo audit (27 ETH + 10 BTC negli ultimi 7d) erano tutti falsi positivi con ask=0 — concentrati sulla weekly 2026-05-29, OI alti ma volume basso. Dopo il fix: bid>ask=0, ask<=0=83 ETH + 13 BTC. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
449 lines
14 KiB
Python
449 lines
14 KiB
Python
"""Unit tests for analysis.data_audit."""
|
|
|
|
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 (
|
|
ChainAuditReport,
|
|
MarketAuditReport,
|
|
audit_market_snapshots,
|
|
audit_option_chain,
|
|
)
|
|
from cerbero_bite.analysis.data_audit import ( # noqa: PLC2701
|
|
_detect_gaps,
|
|
_expected_ticks,
|
|
_max_zero_streak,
|
|
_pct,
|
|
)
|
|
from cerbero_bite.state import connect, run_migrations, transaction
|
|
|
|
|
|
def test_expected_ticks_basic() -> None:
|
|
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 13, 0, tzinfo=UTC)
|
|
# 12:00, 12:15, 12:30, 12:45 → 4 ticks before 13:00
|
|
assert _expected_ticks(since, until) == 4
|
|
|
|
|
|
def test_expected_ticks_inclusive_left_exclusive_right() -> None:
|
|
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 12, 15, tzinfo=UTC)
|
|
# Only 12:00
|
|
assert _expected_ticks(since, until) == 1
|
|
|
|
|
|
def test_expected_ticks_unaligned_since_rounds_up() -> None:
|
|
since = datetime(2026, 5, 12, 12, 7, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 12, 30, tzinfo=UTC)
|
|
# First aligned tick after 12:07 is 12:15, then 12:30 is excluded
|
|
assert _expected_ticks(since, until) == 1
|
|
|
|
|
|
def test_expected_ticks_non_multiple_span_uses_ceiling() -> None:
|
|
# Span = 16 min (12:00 → 12:16): ticks 12:00 AND 12:15 are < 12:16.
|
|
# floor(16/15) = 1 would under-count; the correct answer is 2.
|
|
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 12, 16, tzinfo=UTC)
|
|
assert _expected_ticks(since, until) == 2
|
|
|
|
|
|
def test_expected_ticks_exact_quarter_boundary_is_excluded() -> None:
|
|
# Until landing exactly on a */15 tick: that tick is NOT counted
|
|
# because the window is half-open on the right.
|
|
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 12, 45, tzinfo=UTC)
|
|
# Ticks at 12:00, 12:15, 12:30 → 3 (12:45 excluded)
|
|
assert _expected_ticks(since, until) == 3
|
|
|
|
|
|
def test_detect_gaps_returns_empty_when_no_gap() -> None:
|
|
ts = [
|
|
datetime(2026, 5, 12, 12, 0, tzinfo=UTC),
|
|
datetime(2026, 5, 12, 12, 15, tzinfo=UTC),
|
|
datetime(2026, 5, 12, 12, 30, tzinfo=UTC),
|
|
]
|
|
assert _detect_gaps(ts) == ()
|
|
|
|
|
|
def test_detect_gaps_flags_above_threshold() -> None:
|
|
ts = [
|
|
datetime(2026, 5, 12, 12, 0, tzinfo=UTC),
|
|
datetime(2026, 5, 12, 12, 45, tzinfo=UTC), # 45-min gap
|
|
datetime(2026, 5, 12, 13, 0, tzinfo=UTC),
|
|
]
|
|
gaps = _detect_gaps(ts)
|
|
assert len(gaps) == 1
|
|
assert gaps[0].gap_minutes == 45
|
|
assert gaps[0].prev_timestamp == ts[0]
|
|
assert gaps[0].next_timestamp == ts[1]
|
|
|
|
|
|
def test_detect_gaps_ignores_threshold_boundary() -> None:
|
|
# 20-min gap is exactly the threshold → NOT flagged (strict >)
|
|
ts = [
|
|
datetime(2026, 5, 12, 12, 0, tzinfo=UTC),
|
|
datetime(2026, 5, 12, 12, 20, tzinfo=UTC),
|
|
]
|
|
assert _detect_gaps(ts) == ()
|
|
|
|
|
|
def test_max_zero_streak_empty() -> None:
|
|
assert _max_zero_streak([]) == 0
|
|
|
|
|
|
def test_max_zero_streak_no_zeros() -> None:
|
|
assert _max_zero_streak([1, 1, 1, 1]) == 0
|
|
|
|
|
|
def test_max_zero_streak_single_zero_block() -> None:
|
|
assert _max_zero_streak([1, 0, 0, 0, 1, 0, 1]) == 3
|
|
|
|
|
|
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")
|
|
|
|
|
|
def test_pct_empty_returns_zero() -> None:
|
|
assert _pct([], 50) == 0
|
|
|
|
|
|
def test_pct_single_value_returns_that_value() -> None:
|
|
assert _pct([42], 50) == 42
|
|
assert _pct([42], 10) == 42
|
|
assert _pct([42], 90) == 42
|
|
|
|
|
|
def test_pct_median_odd_count() -> None:
|
|
assert _pct([10, 20, 30, 40, 50], 50) == 30
|
|
|
|
|
|
def test_pct_p10_p90_on_100_values() -> None:
|
|
# inclusive method on [1..100]:
|
|
# p10 interpolates to 10.9 → 11; p90 interpolates to 90.1 → 90.
|
|
values = list(range(1, 101))
|
|
assert _pct(values, 10) == 11
|
|
assert _pct(values, 90) == 90
|
|
|
|
|
|
def _seed_chain_row(
|
|
conn: sqlite3.Connection,
|
|
*,
|
|
asset: str,
|
|
ts: datetime,
|
|
instrument: str,
|
|
strike: str = "3000",
|
|
expiry: datetime | None = None,
|
|
option_type: str = "C",
|
|
bid: str | None = "0.01",
|
|
ask: str | None = "0.02",
|
|
iv: str | None = "0.7",
|
|
) -> None:
|
|
if expiry is None:
|
|
expiry = datetime(2026, 6, 12, 8, 0, tzinfo=UTC)
|
|
conn.execute(
|
|
"INSERT INTO option_chain_snapshots(timestamp, asset, instrument_name, "
|
|
"strike, expiry, option_type, bid, ask, iv) "
|
|
"VALUES (?,?,?,?,?,?,?,?,?)",
|
|
(
|
|
ts.isoformat(),
|
|
asset,
|
|
instrument,
|
|
strike,
|
|
expiry.isoformat(),
|
|
option_type,
|
|
bid,
|
|
ask,
|
|
iv,
|
|
),
|
|
)
|
|
|
|
|
|
def test_audit_chain_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):
|
|
ts = since.replace(minute=minute)
|
|
for i in range(10):
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument=f"ETH-EXP-{i}-C",
|
|
strike=str(3000 + i * 50),
|
|
)
|
|
report = audit_option_chain(
|
|
conn, asset="ETH", since=since, until=until
|
|
)
|
|
finally:
|
|
conn.close()
|
|
assert isinstance(report, ChainAuditReport)
|
|
assert report.asset == "ETH"
|
|
assert report.expected_snapshots == 4
|
|
assert report.actual_snapshots == 4
|
|
assert report.coverage_pct == Decimal("100")
|
|
assert report.quotes_per_snap_median == 10
|
|
assert report.quotes_per_snap_p10 == 10
|
|
assert report.quotes_per_snap_p90 == 10
|
|
assert report.bid_gt_ask_count == 0
|
|
assert report.ask_zero_count == 0
|
|
assert report.iv_null_count == 0
|
|
assert report.iv_null_pct == Decimal("0")
|
|
|
|
|
|
def test_audit_chain_detects_bid_gt_ask_and_iv_null(tmp_path: Path) -> None:
|
|
conn = _make_conn(tmp_path)
|
|
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 12, 30, tzinfo=UTC)
|
|
try:
|
|
with transaction(conn):
|
|
ts = since.replace(minute=0)
|
|
# Crossed BBO: bid > ask
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-A",
|
|
bid="0.10",
|
|
ask="0.05",
|
|
)
|
|
# Missing IV
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-B",
|
|
strike="3050",
|
|
iv=None,
|
|
)
|
|
# Normal row (control)
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-C",
|
|
strike="3100",
|
|
)
|
|
report = audit_option_chain(
|
|
conn, asset="ETH", since=since, until=until
|
|
)
|
|
finally:
|
|
conn.close()
|
|
assert report.bid_gt_ask_count == 1
|
|
assert report.ask_zero_count == 0
|
|
assert report.iv_null_count == 1
|
|
# 1 of 3 quotes → 33.33%
|
|
assert report.iv_null_pct == Decimal("33.33")
|
|
|
|
|
|
def test_audit_chain_ask_zero_counted_separately(tmp_path: Path) -> None:
|
|
conn = _make_conn(tmp_path)
|
|
since = datetime(2026, 5, 12, 12, 0, tzinfo=UTC)
|
|
until = datetime(2026, 5, 12, 12, 30, tzinfo=UTC)
|
|
try:
|
|
with transaction(conn):
|
|
ts = since.replace(minute=0)
|
|
# ask=0 → conta in ask_zero, NON in bid_gt_ask
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-A",
|
|
bid="0.05",
|
|
ask="0",
|
|
)
|
|
# ask negativo (impossibile economicamente) → ask_zero
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-B",
|
|
strike="3050",
|
|
bid="0.05",
|
|
ask="-0.01",
|
|
)
|
|
# Crossed BBO reale (ask>0) → bid_gt_ask
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-C",
|
|
strike="3100",
|
|
bid="0.10",
|
|
ask="0.05",
|
|
)
|
|
# Normal control
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=ts,
|
|
instrument="ETH-D",
|
|
strike="3150",
|
|
)
|
|
report = audit_option_chain(
|
|
conn, asset="ETH", since=since, until=until
|
|
)
|
|
finally:
|
|
conn.close()
|
|
assert report.ask_zero_count == 2
|
|
assert report.bid_gt_ask_count == 1
|
|
|
|
|
|
def test_audit_chain_missing_snapshots(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):
|
|
# Only 2 of the expected 4 ticks have data
|
|
for minute in (0, 15):
|
|
_seed_chain_row(
|
|
conn,
|
|
asset="ETH",
|
|
ts=since.replace(minute=minute),
|
|
instrument=f"ETH-{minute}",
|
|
)
|
|
report = audit_option_chain(
|
|
conn, asset="ETH", since=since, until=until
|
|
)
|
|
finally:
|
|
conn.close()
|
|
assert report.expected_snapshots == 4
|
|
assert report.actual_snapshots == 2
|
|
assert report.coverage_pct == Decimal("50")
|
|
|
|
|
|
def test_audit_chain_empty_window_returns_zero_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:
|
|
report = audit_option_chain(
|
|
conn, asset="ETH", since=since, until=until
|
|
)
|
|
finally:
|
|
conn.close()
|
|
assert report.expected_snapshots == 4
|
|
assert report.actual_snapshots == 0
|
|
assert report.coverage_pct == Decimal("0")
|
|
assert report.quotes_per_snap_median == 0
|
|
assert report.bid_gt_ask_count == 0
|
|
assert report.iv_null_count == 0
|