from __future__ import annotations from collections import defaultdict from .excel_parse import class_sort_key from .kalman import ( fit_qr, hamilton, holdout_hits, kalman_filter, monte_carlo, ranks_desc, zscores, ) TRACK_DEFAULTS = { "物理": [{"id": "t88", "name": "特控线上", "k": 88}], "历史": [ {"id": "top5", "name": "尖子生", "k": 5}, {"id": "top12", "name": "600分以上", "k": 12}, {"id": "top52", "name": "特控线上", "k": 52}, ], } def infer_track_group(track: str) -> str: t = track or "" if "历史" in t: return "历史" if "物理" in t: return "物理" return t or "未分方向" def default_targets(groups: list[str]) -> dict[str, list[dict]]: out = {} for g in groups: if g in TRACK_DEFAULTS: out[g] = [dict(x) for x in TRACK_DEFAULTS[g]] else: out[g] = [{"id": "top20", "name": "年级前20%", "k": 20}] return out def select_students(parsed: dict, settings: dict) -> list[dict]: include_art = settings.get("include_art", False) include_leave = settings.get("include_leave", False) include_mingyuan = settings.get("include_mingyuan", True) include_other = settings.get("include_other", True) exams = settings.get("exams") or parsed["exams"] selected = [] for s in parsed["students"]: if s["art"] and not include_art: continue if s["leave"] and not include_leave: continue st = s["status"] or "在籍" if st == "明远" and not include_mingyuan: continue if st not in ("在籍", "明远", "") and not include_other: continue scores = {e: s["scores"].get(e) for e in exams} if all(v is None for v in scores.values()): continue row = dict(s) row["scores"] = scores row["group"] = infer_track_group(s["track"]) selected.append(row) return selected def _forecast_horizon(q: float, p: float, horizon: int) -> float: return p + max(1, horizon) * q def analyze(parsed: dict, settings: dict) -> dict: exams = settings.get("exams") or parsed["exams"] if not exams: raise ValueError("没有可用的考试列") horizon = int(settings.get("horizon", 1)) n_sim = int(settings.get("n_sim", 600)) selected = select_students(parsed, settings) groups = sorted({s["group"] for s in selected}) targets = settings.get("targets") or default_targets(groups) # fit Q,R per group on z-scores group_models = {} for g in groups: members = [s for s in selected if s["group"] == g] z_by_exam = {} for e in exams: z_by_exam[e] = zscores([s["scores"].get(e) for s in members]) for i, s in enumerate(members): s["z"] = [z_by_exam[e][i] for e in exams] s["ranks"] = [] for e in exams: rk = ranks_desc([s["scores"].get(e) for s in members]) for i, s in enumerate(members): s["ranks"].append(rk[i]) series = [s["z"] for s in members] q, r, rmse = fit_qr(series) group_models[g] = {"q": q, "r": r, "rmse": rmse, "n": len(members)} for s in members: fr = kalman_filter(s["z"], q, r) s["kf_x"] = fr.x s["kf_p"] = fr.p s["kf_xs"] = fr.xs s["kf_ps"] = fr.ps if fr.x is None: s["pred_mean"] = None s["pred_var"] = None else: s["pred_mean"] = fr.x s["pred_var"] = _forecast_horizon(q, fr.p if fr.p is not None else r, horizon) results = [] for g in groups: members = [s for s in selected if s["group"] == g] g_targets = targets.get(g) or default_targets([g])[g] model = group_models[g] eligible = [s for s in members if s["pred_mean"] is not None] last_ranks = [s["ranks"][-1] if s["ranks"] else None for s in members] holdouts = [] if len(exams) >= 3: series = [s["z"] for s in members] true_ranks = [s["ranks"][-1] if s["ranks"] else None for s in members] last_train_ranks = [s["ranks"][-2] if len(s["ranks"]) >= 2 else None for s in members] for t in g_targets: k = min(int(t["k"]), max(1, sum(1 for r in true_ranks if r is not None))) h = holdout_hits( series, last_train_ranks, true_ranks, model["q"], model["r"], k, ) h["target_id"] = t["id"] h["target_name"] = t["name"] h["k"] = k holdouts.append(h) target_blocks = [] for t in g_targets: k = int(t["k"]) k = max(1, min(k, len(eligible))) means = [s["pred_mean"] for s in eligible] variances = [s["pred_var"] for s in eligible] class_ids = [s["class_name"] for s in eligible] probs, class_q = monte_carlo(means, variances, class_ids, k, n_sim=n_sim) for s, p in zip(eligible, probs): s.setdefault("probs", {})[t["id"]] = p # current on-line: last exam rank <= k class_now = defaultdict(int) class_n = defaultdict(int) class_exp = defaultdict(float) class_mingyuan_exp = defaultdict(float) for s in members: class_n[s["class_name"]] += 1 for s in eligible: class_exp[s["class_name"]] += s["probs"][t["id"]] if s.get("status") == "明远": class_mingyuan_exp[s["class_name"]] += s["probs"][t["id"]] if s["ranks"] and s["ranks"][-1] is not None and s["ranks"][-1] <= k: class_now[s["class_name"]] += 1 class_names = sorted(class_n.keys(), key=class_sort_key) expected = [class_exp[c] for c in class_names] assigned = hamilton(expected, k) rows = [] for c, a in zip(class_names, assigned): qtl = class_q.get(c, {"p20": 0, "p50": 0, "p80": 0, "mean": 0}) rows.append( { "class_name": c, "n": class_n[c], "current": class_now[c], "expected": round(class_exp[c], 2), "assigned": a, "floor": int(qtl["p20"]), "median": int(qtl["p50"]), "stretch": int(qtl["p80"]), "delta": a - class_now[c], "mingyuan_expected": round(class_mingyuan_exp[c], 2), } ) critical = [] for s in eligible: p = s["probs"][t["id"]] if 0.2 <= p <= 0.8: critical.append( { "sid": s["sid"], "name": s["name"], "class_name": s["class_name"], "p": round(p, 3), "last_rank": s["ranks"][-1] if s["ranks"] else None, "status": s.get("status") or "", } ) critical.sort(key=lambda x: -x["p"]) target_blocks.append( { "id": t["id"], "name": t["name"], "k": k, "classes": rows, "critical_n": len(critical), "critical": critical[:80], "sum_expected": round(sum(expected), 2), } ) results.append( { "group": g, "n": len(members), "model": { "q": model["q"], "r": model["r"], "rmse": round(model["rmse"], 3) if model["rmse"] is not None else None, "horizon": horizon, "n_sim": n_sim, }, "holdout": holdouts, "targets": target_blocks, } ) student_views = [] for s in selected: student_views.append( { "sid": s["sid"], "name": s["name"], "class_name": s["class_name"], "group": s["group"], "track": s["track"], "subjects": s["subjects"], "status": s.get("status") or "", "move": s.get("move") or "", "art": s["art"], "leave": s["leave"], "scores": s["scores"], "z": s.get("z"), "ranks": s.get("ranks"), "kf_xs": s.get("kf_xs"), "kf_ps": s.get("kf_ps"), "pred_mean": s.get("pred_mean"), "pred_var": s.get("pred_var"), "probs": {k: round(v, 4) for k, v in (s.get("probs") or {}).items()}, } ) return { "exams": exams, "horizon": horizon, "n_selected": len(selected), "n_total": len(parsed["students"]), "groups": results, "students": student_views, } def class_comment(row: dict, target_name: str) -> str: assigned = row["assigned"] current = row["current"] expected = row["expected"] floor = row["floor"] stretch = row["stretch"] name = row["class_name"] bits = [ f"{name}班{target_name}下达 {assigned} 人（滤波期望 {expected:.1f}）。" ] if assigned > current: bits.append(f"比最近一次在线人数多 {assigned - current} 人，班级里有上升轨迹的临界生，需要把潜力兑现。") elif assigned < current: bits.append(f"比最近一次在线人数少 {current - assigned} 人，说明部分当前在线学生轨迹不稳，重点是保住临界生。") else: bits.append("与最近一次在线人数持平，按现有轨迹属于维持性目标。") bits.append(f"模拟分布大约在 {floor}–{stretch} 人之间，超越下达人数才算跑赢预估。") return "".join(bits)