#!/usr/bin/env python3 """Step 2 — fetch history for each candidate and compute metrics + patterns. python scripts/02_analyze_wallets.py Reads data/candidates.json Writes data/wallets.csv (one row per wallet: metrics + pattern features) data/ledgers/.parquet (cached raw ledgers for the backtester) """ import sys from pathlib import Path import pandas as pd sys.path.insert(0, str(Path(__file__).resolve().parents[1])) from pmct.client import PolymarketClient from pmct import ledger as ledger_mod from pmct import metrics as metrics_mod from pmct import patterns as patterns_mod from pmct import discover as discover_mod from pmct.util import load_config, cache_path, read_json def main(): cfg = load_config() acfg = cfg["analyze"] candidates = read_json(cache_path(cfg, "candidates.json")) or [] if not candidates: raise SystemExit("No candidates. Run 01_discover_wallets.py first.") client = PolymarketClient(sleep_sec=acfg["request_sleep_sec"]) # authoritative profit/volume from the leaderboard (one pass, reused for all) dcfg = cfg["discover"] lb_map = discover_mod.leaderboard_profit_map( client, dcfg["leaderboard_windows"], dcfg["leaderboard_top_n"]) print(f"authoritative leaderboard entries: {len(lb_map)}") # analyze leaderboard wallets first (authoritative profit = best copy targets), # then fill the budget with the rest, so max_wallets isn't wasted on low-hex # addresses that happen to sort first. candidates.sort(key=lambda w: (0 if w in lb_map else 1, w)) candidates = candidates[: acfg["max_wallets"]] rows = [] for i, w in enumerate(candidates, 1): try: raw = list(client.iter_activity( w, acfg["activity_page_limit"], acfg["max_pages_per_wallet"])) led = ledger_mod.normalize_activity(raw) if led.empty: continue open_df = ledger_mod.attach_open_positions(client.positions(w)) stats = metrics_mod.compute(w, led, open_df) feats = patterns_mod.extract(w, led) row = {**stats.to_dict(), **feats.to_dict()} row.pop("wallet", None) lb = lb_map.get(w, {}) lb_profit = lb.get("lb_profit") row["on_leaderboard"] = bool(lb) row["lb_profit"] = lb_profit row["lb_volume"] = lb.get("lb_volume") # authoritative profit: trust the leaderboard when ranked, else our recon row["profit_final"] = lb_profit if lb_profit is not None else row["total_pnl"] # recompute rebate share against the AUTHORITATIVE profit so truncated # (negative) reconstructions don't falsely flag profitable wallets pf = row["profit_final"] if pf and pf > 0: row["rebate_share"] = round(min(max(row["rebate_pnl"] / pf, 0.0), 1.0), 4) elif row["rebate_pnl"] > 0: row["rebate_share"] = 1.0 # no net directional profit, only rebates row = {"wallet": w, **row} rows.append(row) led.to_pickle(cache_path(cfg, "ledgers", f"{w}.pkl")) print(f"[{i}/{len(candidates)}] {w} pnl=${stats.total_pnl:>10} " f"wr={stats.win_rate:.2f} rep={feats.repeatability:.2f}") except Exception as e: # noqa: BLE001 - keep going through the batch print(f"[{i}/{len(candidates)}] {w} ERROR {e}") df = pd.DataFrame(rows) out = cache_path(cfg, "wallets.csv") df.to_csv(out, index=False) print(f"\nAnalyzed {len(df)} wallets -> {out}") if __name__ == "__main__": main()