synthetic data generator for smoke tests

synth_gen.py

@@ -0,0 +1,41 @@
+"""Generate synthetic 1h bars + 8h funding for harness smoke tests.
+
+Layout matches crypto_eval.data.load_local exactly:
+  <out>/bars_BTCUSDT_1h.parquet  (UTC DatetimeIndex, OHLCV)
+  <out>/funding_BTCUSDT.parquet  (UTC DatetimeIndex, funding_rate)
+  <out>/manifest.json            ({"outputs": {...}} placeholder)
+"""
+import json
+import sys
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+
+out = Path(sys.argv[1] if len(sys.argv) > 1 else "/tmp/synthdata")
+out.mkdir(parents=True, exist_ok=True)
+
+rng = np.random.default_rng(7)
+n = 20_000
+idx = pd.date_range("2022-01-01", periods=n, freq="1h", tz="UTC")
+ret = rng.normal(0.0, 0.01, n)
+close = 30_000.0 * np.exp(np.cumsum(ret))
+open_ = np.r_[close[0], close[:-1]]
+high = np.maximum(open_, close) * (1 + rng.uniform(0, 0.002, n))
+low = np.minimum(open_, close) * (1 - rng.uniform(0, 0.002, n))
+vol = rng.lognormal(8, 0.5, n)
+
+bars = pd.DataFrame(
+    {"open": open_, "high": high, "low": low, "close": close, "volume": vol},
+    index=idx,
+)
+bars.to_parquet(out / "bars_BTCUSDT_1h.parquet")
+
+fidx = idx[::8]
+funding = pd.DataFrame(
+    {"funding_rate": rng.normal(1e-4, 2e-4, len(fidx))}, index=fidx
+)
+funding.to_parquet(out / "funding_BTCUSDT.parquet")
+
+(out / "manifest.json").write_text(json.dumps({"outputs": {}}, indent=2))
+print(f"synthetic data written to {out}: {n} bars, {len(fidx)} funding ticks")