问问

import pandas as pd
import numpy as np
import re
from typing import Tupledef curve_score(value: float, spec_range: Tuple[float, float], weight: float,min_score: float = 0.0,base_curvature: float = 2.0,narrow_range_coeff: float = 5.0
) -> float:lower, upper = spec_rangeif lower <= value <= upper:return 1.0# 计算规格宽度和边界if lower == -np.inf and upper == np.inf:return 1.0elif lower == -np.inf:spec_width = abs(upper) * 2 if upper != 0 else 1bound = upperelif upper == np.inf:spec_width = abs(lower) * 2 if lower != 0 else 1bound = lowerelse:spec_width = upper - lowerbound = lower if value < lower else upper# 标准化距离distance = abs(value - bound)if spec_width == 0:distance_ratio = distance / (abs(bound) + 1e-6)else:distance_ratio = distance / spec_width# 动态曲率（基础曲率×权重×窄化系数）if spec_width > 0:narrow_coeff = 1 + narrow_range_coeff / (spec_width + 1)else:narrow_coeff = 1 + narrow_range_coeffdynamic_curvature = base_curvature * weight * narrow_coeff# 严重偏离额外惩罚if distance_ratio > 0.5:distance_ratio = distance_ratio ** 1.5return max(min_score, np.exp(-dynamic_curvature * distance_ratio))def dynamic_filter_sort(predictedDF, target_spec, weights):mask = pd.Series(True, index=predictedDF.index)filtered_df = predictedDF[mask].copy()score = pd.Series(0.0, index=filtered_df.index)for col, cond in target_spec.items():col_values = filtered_df[col].astype(float)weight = weights.get(col, 1.0)# 给窄范围spec加隐性权重（可选，根据需求开启）if '-' in cond:low, high = map(float, re.fullmatch(r'^(-?\d+\.?\d*)-(-?\d+\.?\d*)$', cond).groups())spec_width = high - lowif spec_width < 10:  # 范围宽度<10判定为窄范围weight *= 1.2  # 隐性权重系数# 条件处理if '-' in cond:spec = (low, high)normalized = col_values.apply(lambda x: curve_score(x, spec, weight=weight))score += normalized * weightelif cond.startswith('lt('):ceiling = float(cond[3:-1])spec = (-np.inf, ceiling)normalized = col_values.apply(lambda x: curve_score(x, spec, weight=weight))score += normalized * weightelif cond.startswith('gt('):floor = float(cond[3:-1])spec = (floor, np.inf)normalized = col_values.apply(lambda x: curve_score(x, spec, weight=weight))score += normalized * weightelse:try:target_val = float(cond)except ValueError:target_val = condspec = (target_val, target_val)normalized = col_values.apply(lambda x: curve_score(x, spec, weight=weight))score += normalized * weightfiltered_df['score#'] = round(score, 3)return filtered_df.sort_values('score#', ascending=False)# 业务代码（无需修改，直接使用）
data_df = pd.DataFrame(np.array(result['specMatrix'])[recipe_index,:].reshape(1,-1),columns=result['maxMatrix'].keys()
)
target_spec = {'Depth': '1100-1300', 'SOCremain': '0-500', 'SiNSWA': '86-89', 'TCD': '21-22','doubleslope': '0-1', 'maskremain': '2201.8-2833.7'
}
weights = {'Depth': 3, 'SOCremain': 1, 'SiNSWA': 1, 'TCD': 3,  # 可根据需要调整为3.5'doubleslope': 2, 'maskremain': 1
}data_df = (-dynamic_filter_sort(data_df, target_spec, weights)['score#'].values[:]).tolist()