35 lines
1.6 KiB
Python
 | # SPDX-License-Identifier: LicenseRef-PolyForm-Noncommercial-1.0.0 (see LICENSE)
| ||
"""Count completed patterns per 1,000 closed bars from the OHLC columns of dump CSVs (aggregate numbers only).
| |||
| |||
python3 tests/frequency.py <dump dir> M15 H1 H4 > docs/data/pattern-frequency.json
| |||
Reads <dump dir>/dump/hm_default_<SYMBOL>_<TF>.csv; every closed bar is scanned with tests/reference.py (default inputs)."""
| |||
import json
| |||
import sys
| |||
from pathlib import Path
| |||
| |||
import pandas as pd
| |||
| |||
sys.path.insert(0, str(Path(__file__).parent))
| |||
from reference import NAMES, Params, run # noqa: E402
| |||
| |||
root = Path(sys.argv[1])
| |||
result = {}
| |||
for tf in sys.argv[2:]:
| |||
bars = 0
| |||
cnt = {n: [0, 0] for n in NAMES} # bullish, bearish
| |||
per_symbol = {}
| |||
for f in sorted(root.glob(f"dump/hm_default_*_{tf}.csv")):
| |||
d = pd.read_csv(f)
| |||
h, l, c = (d[k].to_numpy(float)[:-1] for k in ("high", "low", "close"))
| |||
ev = run(h, l, c, Params())
| |||
for e in ev:
| |||
cnt[e["name"]][0 if e["dir"] > 0 else 1] += 1
| |||
sym = f.stem.split("_")[2]
| |||
per_symbol[sym] = dict(bars=len(c), patterns=len(ev))
| |||
bars += len(c)
| |||
total = sum(sum(v) for v in cnt.values())
| |||
result[tf] = dict(closed_bars=bars, per_symbol=per_symbol,
| |||
per_1000_bars={n: dict(bullish=round(1000 * v[0] / bars, 2), bearish=round(1000 * v[1] / bars, 2))
| |||
for n, v in cnt.items()},
| |||
per_1000_bars_total=round(1000 * total / bars, 2), bars_per_pattern=round(bars / max(1, total)))
| |||
print(json.dumps(result, indent=1))
|