总览 · ← 返回运行 20261002-034201-search-t1-abc-r1-C-native

节点 n60

改了什么

方法说明?节点程序自带的 METHOD.md：这个程序做了什么、为什么。

来自 programs.git 60aa67bb35:solution/METHOD.md

调研员的计划

代码改动?这个节点的程序和父节点程序的逐行差别：绿色是新增，红色是删除。

对比：父节点版本 3ed9cbb827。改动的文件：solution/METHOD.md +2 −2、solution/run.py +91 −3

diff --git a/solution/METHOD.md b/solution/METHOD.mdindex 601de6d..ea99743 100644--- a/solution/METHOD.md+++ b/solution/METHOD.md@@ -1,4 +1,4 @@ ## 改了什么-将 with-replace 加权抽样改为按类型分层的 without-replace 抽样：先按家族权重计算每型目标细胞数，再在每型内无放回抽样（不足时取全部），剩余名额从未选细胞中补齐。不加任何表达位移。理由：Program 1 用同样的分层无放回抽样在 de_recovery 上得到 51.33（vs 本节点 with-replace 的 49.35），且无放回避免了重复细胞导致的经验分布失真，应同时有利于 covariation。+1) 加入按类型分层的距离分箱抽样（N_BINS=20, MIN_CELLS_FOR_BINNING=30）：在每个细胞类型内按到质心的距离分箱，按箱比例无放回抽样，保留型内表达分布结构，改善 covariation。2) 家族权重从 1.6/0.15/0.9 调为 1.5/0.2/0.95（Program 1 验证的更优值）。3) 当有两个官方输入阶段时（final 视图），加极小 EB 收缩位移 α=0.015；单阶段（proxy）退化为纯抽样。理由：父节点分析建议"在无放回条件下重新尝试小幅 EB 位移"；Program 2 证明 ALPHA=0 时 binning 已有效，极小 alpha 试探方向分是否受益而不破坏 covariation。 ## 用到的知识与出处-Program 1 实验结果（de_recovery 51.33、direction 54.01，分层无放回 + EB 位移）；父节点 9 配置（权重 1.6/0.15/0.9）；第 0 轮反馈证明 EB 位移在 with-replace 下破坏 covariation，故本轮只用无放回抽样、不加位移。+Program 1（score 52.65，binning + 权重 1.5/0.2/0.95）；Program 2（score 52.64，binning + ALPHA=0）；父节点 30 ANALYSIS 的 next_suggestions（"在分层无放回基础上重新尝试小幅 EB 位移"）；方法卡 T1-02（收缩系数 α 为超参，不能默认 α=1）。diff --git a/solution/run.py b/solution/run.pyindex 05ac101..45c2609 100644--- a/solution/run.py+++ b/solution/run.py@@ -15,7 +15,9 @@ import argparse import re  import numpy as np+from scipy import sparse as sp +from src.task1_temporal.baselines import shift_rows from src.task1_temporal.view_io import (     inputs_by_time,     labels_of,@@ -26,6 +28,10 @@ from src.task1_temporal.view_io import (     write_prediction, ) +ALPHA = 0.015+N_BINS = 20+MIN_CELLS_FOR_BINNING = 30+ _HEART_PAT = re.compile(     r"cm\b|cardi|heart|shf|endocard|oft\b|avc|ift\b|sv[- ]cm|v[- ]cm|"     r"proepicard|pericard|epicard|blood",@@ -43,14 +49,62 @@ _GUT_PAT = re.compile(  def family_weight(name: str) -> float:     if _HEART_PAT.search(name):-        return 1.6+        return 1.5     if _REDUCED_PAT.search(name):-        return 0.15+        return 0.2     if _GUT_PAT.search(name):-        return 0.9+        return 0.95     return 1.0  +def _submatrix(X, mask):+    sub = X[mask]+    if sp.issparse(sub):+        return np.asarray(sub.todense())+    return np.asarray(sub)+++def eb_shrunk_deltas(prev_X, prev_labels, last_X, last_labels, alpha):+    prev_types = set(np.unique(prev_labels))+    last_types = np.unique(last_labels)+    deltas = {}+    for t in last_types:+        last_mask = last_labels == t+        n_last = int(last_mask.sum())+        if n_last == 0:+            continue+        last_sub = last_X[last_mask]+        if sp.issparse(last_sub):+            mean_last = np.asarray(last_sub.mean(axis=0)).ravel()+            var_last = np.asarray(last_sub.multiply(last_sub).mean(axis=0)).ravel() - mean_last**2+        else:+            arr = np.asarray(last_sub)+            mean_last = arr.mean(axis=0).ravel()+            var_last = arr.var(axis=0).ravel()+        var_last = np.maximum(var_last, 0.0)+        if t in prev_types:+            prev_mask = prev_labels == t+            n_prev = int(prev_mask.sum())+            prev_sub = prev_X[prev_mask]+            if sp.issparse(prev_sub):+                mean_prev = np.asarray(prev_sub.mean(axis=0)).ravel()+                var_prev = np.asarray(prev_sub.multiply(prev_sub).mean(axis=0)).ravel() - mean_prev**2+            else:+                arr_p = np.asarray(prev_sub)+                mean_prev = arr_p.mean(axis=0).ravel()+                var_prev = arr_p.var(axis=0).ravel()+            var_prev = np.maximum(var_prev, 0.0)+            delta = mean_last - mean_prev+            se2 = var_prev / max(n_prev, 1) + var_last / max(n_last, 1)+            n_eff = min(n_prev, n_last)+            size_factor = n_eff / (n_eff + 50.0)+            shrink = float(np.mean(delta**2 / (delta**2 + se2 + 1e-10)))+            deltas[t] = alpha * size_factor * shrink * delta+        else:+            deltas[t] = np.zeros(last_X.shape[1])+    return deltas++ def main() -> None:     parser = argparse.ArgumentParser()     parser.add_argument("--data", required=True)@@ -88,6 +142,35 @@ def main() -> None:         type_idx = np.where(labels == u)[0]         if n_take >= len(type_idx):             indices.append(type_idx)+            continue+        if len(type_idx) > MIN_CELLS_FOR_BINNING and n_take >= 5:+            sub = _submatrix(last.X, type_idx)+            centroid = sub.mean(axis=0)+            dists = np.linalg.norm(sub - centroid, axis=1)+            bin_edges = np.quantile(dists, np.linspace(0, 1, N_BINS + 1)[1:-1])+            bin_ids = np.searchsorted(bin_edges, dists)+            bin_props = np.bincount(bin_ids, minlength=N_BINS) / len(type_idx)+            per_bin = np.floor(bin_props * n_take).astype(int)+            rem = n_take - per_bin.sum()+            fr = (bin_props * n_take) - per_bin+            for i in np.argsort(-fr)[:rem]:+                per_bin[i] += 1+            per_bin = np.minimum(per_bin, np.bincount(bin_ids, minlength=N_BINS))+            chosen = []+            for b in range(N_BINS):+                b_idx = type_idx[bin_ids == b]+                nb = min(per_bin[b], len(b_idx))+                if nb > 0:+                    chosen.append(rng.choice(b_idx, size=nb, replace=False))+            if chosen:+                sel = np.concatenate(chosen)+            else:+                sel = rng.choice(type_idx, size=n_take, replace=False)+            if len(sel) < n_take:+                leftover = np.setdiff1d(type_idx, sel)+                extra = rng.choice(leftover, size=n_take - len(sel), replace=False)+                sel = np.concatenate([sel, extra])+            indices.append(sel)         else:             indices.append(rng.choice(type_idx, size=n_take, replace=False))     rows = np.concatenate(indices)@@ -96,6 +179,11 @@ def main() -> None:         extra = rng.choice(remaining, size=n_target - len(rows), replace=False)         rows = np.concatenate([rows, extra])     X = last.X[rows]+    if len(stages) >= 2:+        prev = read_stage(args.data, stages[-2], genes)+        deltas = eb_shrunk_deltas(prev.X, labels_of(prev), last.X, labels, ALPHA)+        del prev+        X = shift_rows(X, labels[rows], deltas)     write_prediction(X, genes, args.out, seed=args.seed)  

调研来源?调研员查到并用到的知识条目和文献检索结果（只列标题和编号）。

没有记录调研来源。

分析结果?分析员写的 ANALYSIS.json：改了什么、各组分数怎么变、假设是否成立、经验和下一步建议。

对话摘要?每个角色和大模型对话的统计：轮数、工具调用、用时、token 数和最后的回答摘录；原始记录只给路径。

只给统计和最后回答的摘录；完整对话请到原始记录位置里列出的文件看。

分析员

ANALYSIS.json written

native

stream

SEARCH
```python
#!/usr/bin/env python3
"""Stratified without-replace sampling with tuned family weights and small EB shift.

Improves cell_state by adjusting family weights (heart 1.6, reduced 0.25, gut 0.95)
and adds distance-based binning to preserve within-type radial structure.
Applies very small EB-shrunk pseudobulk delta (alpha=0.1) to nudge direction
without damaging covariation (safe with without-replace sampling).
"""

from __future__ import annotations

import argparse
import re

import numpy as np
from scipy import sparse as sp

from src.task1_temporal.view_io import (
    inputs_by_time,
    labels_of,
    load_manifest,
    panel_genes,
    read_stage,
    target_n_cells,
    write_prediction,
)

N_BINS = 20
MIN_CELLS_FOR_BINNING = 30
ALPHA = 0.1

_HEART_PAT = re.compile(
    r"cm\b|cardi|heart|shf|endocard|oft\b|avc|ift\b|sv[- ]cm|v[- ]cm|"
    r"proepicard|pericard|epicard|blood",
    re.IGNORECASE,
)
_REDUCED_PAT = re.compile(
    r"surface\s*ectoderm|exem|paraxial|neural\s*tube|neural|notochord",