File size: 3,545 Bytes
6b93c3b | 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 | #!/usr/bin/env python3
"""Generate 1M rows (k=1..N) of secp256k1 features for the parity-prediction task.
Output: features.parquet (k held aside for traceability; not used as input)
"""
import os, sys, time, math
import numpy as np
import pandas as pd
# ---- curve params ------------------------------------------------------
p = 2**256 - 2**32 - 977
n = 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFEBAAEDCE6AF48A03BBFD25E8CD0364141
Gx = 55066263022277343669578718895168534326250603453777594175500187360389116729240
Gy = 32670510020758816978083085130507043184471273380659243275938904335757337482424
def inv(a): return pow(a, p-2, p)
def add(P, Q):
if P is None: return Q
if Q is None: return P
x1,y1=P; x2,y2=Q
if x1==x2 and (y1+y2)%p==0: return None
m=(3*x1*x1)*inv(2*y1)%p if P==Q else (y2-y1)*inv(x2-x1)%p
x3=(m*m-x1-x2)%p
return (x3,(m*(x1-x3)-y1)%p)
# ---- feature extraction on a single int v -----------------------------
def num_features(v, prefix):
s = str(v)
digs = [int(c) for c in s]
return {
f"{prefix}_num_digits": len(s),
f"{prefix}_first_digit": digs[0],
f"{prefix}_last_digit": digs[-1],
f"{prefix}_last2": v % 100,
f"{prefix}_last3": v % 1000,
f"{prefix}_digit_sum": sum(digs),
f"{prefix}_digit_sum_mod_9": sum(digs) % 9,
f"{prefix}_even_digit_count": sum(1 for d in digs if d%2==0),
f"{prefix}_odd_digit_count": sum(1 for d in digs if d%2==1),
f"{prefix}_zero_count": s.count("0"),
f"{prefix}_unique_digit_count": len(set(s)),
f"{prefix}_bit_length": v.bit_length(),
f"{prefix}_popcount": bin(v).count("1"),
f"{prefix}_state": v % 2,
f"{prefix}_mod_3": v % 3,
f"{prefix}_mod_5": v % 5,
f"{prefix}_mod_7": v % 7,
f"{prefix}_mod_11": v % 11,
f"{prefix}_mod_13": v % 13,
f"{prefix}_mod_17": v % 17,
f"{prefix}_mod_19": v % 19,
}
def main(N=1_000_000, out="features.parquet"):
G = (Gx, Gy)
P = None
rows = []
t0 = time.time()
LOG = max(1, N // 20)
for k in range(1, N+1):
P = add(P, G)
x, y = P
sxd = sum(int(c) for c in str(x))
syd = sum(int(c) for c in str(y))
row = {"k": k, "k_state": k & 1}
row.update(num_features(x, "x"))
row.update(num_features(y, "y"))
row["abs_x_minus_y"] = abs(x - y)
row["x_gt_y"] = int(x > y)
row["digit_sum_diff_xy"] = sxd - syd
rows.append(row)
if k % LOG == 0:
elapsed = time.time() - t0
rate = k / elapsed
eta = (N-k) / rate
print(f" k={k:>9}/{N} ({k/N*100:5.1f}%) rate={rate:>8.0f} k/s ETA={eta:5.0f}s", flush=True)
df = pd.DataFrame(rows)
# cast small ints to compact types
small_cols = [c for c in df.columns if c not in ("k","abs_x_minus_y")]
for c in small_cols:
if df[c].dtype != object and df[c].abs().max() < 2**15:
df[c] = df[c].astype("int16")
df["k"] = df["k"].astype("int64")
# abs_x_minus_y is huge; store as string (or float64 lossy). Use string to be exact.
df["abs_x_minus_y"] = df["abs_x_minus_y"].astype(str)
df.to_parquet(out, index=False, compression="snappy")
sz = os.path.getsize(out) / 1e6
print(f"\nwrote {out} 路 {len(df)} rows 路 {len(df.columns)} cols 路 {sz:.1f} MB 路 {time.time()-t0:.1f}s total")
if __name__ == "__main__":
N = int(sys.argv[1]) if len(sys.argv) > 1 else 1_000_000
main(N=N)
|