是多少

def create_coefficient_csv_with_ratios(base_models, feature_cols, output_path,df):# 1. 配置与初始化n_decimal = 3  # 统一保留3位小数clean_features = [f.replace('Δ', '') for f in feature_cols]  # 清洗特征名data = {}# 2. 提取模型数据for baseid, model in base_models.items():# 提取并格式化系数相关数据coef = np.round(model.coef_.flatten(), n_decimal)coef[coef == -0.0] = 0.0  # 处理负零值coef_mean = np.round(model.coefs_mean.flatten(), n_decimal)coef_low = np.round(model.coefs_down.flatten(), n_decimal)  # 25% percentilecoef_high = np.round(model.coefs_up.flatten(), n_decimal)  # 75% percentile# 构建当前base的数据base_data = {}for i, feat in enumerate(clean_features):base_data[f"{feat}_coef"] = coef[i]base_data[f"{feat}_mean"] = coef_mean[i]base_data[f"{feat}_conf_low"] = coef_low[i]base_data[f"{feat}_conf_high"] = coef_high[i]data[baseid] = base_data# 3. 创建基础数据框coef_df = pd.DataFrame.from_dict(data, orient='index')coef_df.index.name = "base_id"# 4. 计算各特征系数列的零值比例（用于排序和统计）feature_stats = {}  # 存储每个特征的统计信息for feat in clean_features:coef_col = f"{feat}_coef"if coef_col in coef_df.columns:# 计算关键比例zero_ratio = (coef_df[coef_col] == 0).mean().round(n_decimal)positive_ratio = (coef_df[coef_col] > 0).mean().round(n_decimal)negative_ratio = (coef_df[coef_col] < 0).mean().round(n_decimal)non_zero_ratio = 1 - zero_ratio  # 非零比例feature_stats[feat] = {'zero_ratio': zero_ratio,'positive_ratio': positive_ratio,'negative_ratio': negative_ratio,'non_zero_ratio': non_zero_ratio}# 按非零比例降序排序特征（零值少的排前面）sorted_features = sorted(clean_features,key=lambda x: feature_stats[x]['non_zero_ratio'],reverse=True)# 5. 重新排列列（同一特征的指标连续）sorted_cols = []for feat in sorted_features:for suffix in ["coef", "mean", "conf_low", "conf_high"]:col = f"{feat}_{suffix}"if col in coef_df.columns:sorted_cols.append(col)coef_df = coef_df.reindex(columns=sorted_cols)# 6. 构建统计行（包含均值和比例）stats_row = {}for col in coef_df.columns:# 拆分特征名和指标类型feat = col.split('_')[0]metric = '_'.join(col.split('_')[1:])if metric == 'coef':# 系数列：统计比例stats_row[col] = f"z:{feature_stats[feat]['zero_ratio']}, " \f"p:{feature_stats[feat]['positive_ratio']}, " \f"n:{feature_stats[feat]['negative_ratio']}"else:# 其他列（均值/置信区间）：统计均值stats_row[col] = np.round(coef_df[col].mean(), n_decimal)# 添加统计行coef_df.loc["stats_summary"] = stats_row# 7. 写入CSV（带英文注释）with open(output_path, 'w', encoding='utf-8') as f:coef_df.to_csv(f, mode='a', header=True, encoding='utf-8')return coef_df