Spaces:
Running
Running
File size: 4,038 Bytes
d4c51f2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 | """Detect *repeatable* trading patterns in a wallet's ledger.
The user's second screen is "反覆出現、可複製的交易模式" — recurring, replicable
behavior. A wallet that made money once by luck is useless to copy; a wallet
that does the same identifiable thing over and over is copyable.
We reduce each wallet to a handful of style features, then collapse them into a
single `repeatability` score in [0, 1]. High score = tight entry-price band,
consistent bet sizing, topical concentration, and steady cadence over many
trades — i.e. a strategy, not noise.
"""
from __future__ import annotations
from dataclasses import dataclass, asdict
import numpy as np
import pandas as pd
# crude topic buckets from title keywords; used when Gamma tags are absent
_TOPICS = {
"sports": ["nba", "nfl", "mlb", "soccer", "ufc", "game", "vs ", "win the", "match"],
"crypto": ["btc", "bitcoin", "eth", "ethereum", "crypto", "solana", "coin"],
"politics": ["election", "president", "senate", "trump", "biden", "poll", "governor"],
"econ": ["fed", "rate", "cpi", "inflation", "gdp", "recession", "jobs"],
}
def _topic(title: str) -> str:
t = (title or "").lower()
for name, kws in _TOPICS.items():
if any(k in t for k in kws):
return name
return "other"
def _cv(x: np.ndarray) -> float:
"""Coefficient of variation, guarded against zero mean."""
x = x[x > 0]
if len(x) < 2 or x.mean() == 0:
return 1.0
return float(x.std() / x.mean())
def _hhi(counts: pd.Series) -> float:
"""Herfindahl concentration in [0,1]; 1 = all one bucket."""
if counts.sum() == 0:
return 0.0
p = counts / counts.sum()
return float((p ** 2).sum())
@dataclass
class PatternFeatures:
wallet: str
entry_band_tightness: float # 1 = all entries at same price
size_consistency: float # 1 = identical bet sizes
topic_concentration: float # 1 = single topic
cadence_regularity: float # 1 = evenly spaced over time
longshot_bias: float # mean(0.5 - entry_price), + = buys underdogs
dominant_topic: str
n_buys: int
repeatability: float # blended [0,1]
def to_dict(self) -> dict:
return asdict(self)
def extract(wallet: str, ledger: pd.DataFrame) -> PatternFeatures:
buys = ledger[ledger["side"].eq("BUY")].copy()
if len(buys) < 3:
return PatternFeatures(wallet, 0, 0, 0, 0, 0.0, "other", len(buys), 0.0)
# 1) entry-price band tightness: 1 - normalized std of entry prices
band_tightness = float(np.clip(1.0 - buys["price"].std() / 0.5, 0, 1))
# 2) sizing consistency: 1 - CV of trade notional (clipped)
size_consistency = float(np.clip(1.0 - _cv(buys["usdc"].values), 0, 1))
# 3) topic concentration via HHI
buys["topic"] = buys["title"].map(_topic)
topic_counts = buys["topic"].value_counts()
topic_conc = _hhi(topic_counts)
dominant_topic = str(topic_counts.index[0])
# 4) cadence regularity: 1 - CV of inter-trade gaps (regular => copyable)
gaps = buys["ts"].sort_values().diff().dropna().dt.total_seconds().values
cadence = float(np.clip(1.0 - _cv(gaps), 0, 1)) if len(gaps) >= 2 else 0.0
# 5) longshot bias (descriptive, not scored): + buys cheap underdogs
longshot = float((0.5 - buys["price"]).mean())
# volume confidence: patterns from few trades are unreliable; ramp 0->1 by ~50 buys
vol_conf = float(np.clip(np.log1p(len(buys)) / np.log1p(50), 0, 1))
repeatability = vol_conf * np.mean([
band_tightness, size_consistency, topic_conc, cadence
])
return PatternFeatures(
wallet=wallet,
entry_band_tightness=round(band_tightness, 3),
size_consistency=round(size_consistency, 3),
topic_concentration=round(topic_conc, 3),
cadence_regularity=round(cadence, 3),
longshot_bias=round(longshot, 4),
dominant_topic=dominant_topic,
n_buys=int(len(buys)),
repeatability=round(float(repeatability), 3),
)
|