From 6f5013e8ab45946d738eab3ca6e4a7ff1aedde21 Mon Sep 17 00:00:00 2001 From: HaHafeng Date: Sun, 21 Dec 2025 18:09:58 +0800 Subject: [PATCH] fix(dc): Fix pivot column name tuple issue for single value column Problem: - When selecting only 1 value column in Pivot (long-to-wide), column names were incorrectly formatted as 'FMA___('FMA', 'baseline')' instead of 'FMA___baseline' - This occurred because pandas pivot_table() sometimes returns tuple column names even for single value columns, but the code didn't handle this case Root Cause: - Line 112-127 in pivot.py assumed single value columns always have simple string column names, without checking for tuples - Multi-value column logic (line 129-145) correctly handled tuples with isinstance() Solution: - Add isinstance(col, tuple) check in single value column mode - Extract pivot_value from tuple[1] if column name is a tuple - Maintain backward compatibility for non-tuple column names Testing: - Single value column: FMA___ + tuple -> 'FMA___baseline' (fixed) - Multiple value columns: Already working correctly (no change) Impact: Fixes historical bug in Tool C Pivot feature --- extraction_service/operations/pivot.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/extraction_service/operations/pivot.py b/extraction_service/operations/pivot.py index c5220a28..55b2a6f8 100644 --- a/extraction_service/operations/pivot.py +++ b/extraction_service/operations/pivot.py @@ -110,7 +110,7 @@ def pivot_long_to_wide( # ✨ 修复：更健壮的列名展平逻辑 if len(value_columns) == 1: - # 单个值列：列名是单层的 (pivot_value1, pivot_value2, ...) + # 单个值列：列名可能是单层的，也可能是元组 print(f'📝 单值列模式：展平列名', flush=True) # 获取原始值列名（用于生成新列名） @@ -119,8 +119,15 @@ def pivot_long_to_wide( # 生成新列名：值列名___透视值 new_columns = [] for col in df_pivot.columns: - # col 是透视列的某个值（如 0, 1, 2） - new_col_name = f'{value_col_name}___{col}' + # ✅ 修复：检查col是否是元组（pandas在某些情况下会返回元组） + if isinstance(col, tuple): + # 如果是元组 (值列名, 透视值)，取第二个元素 + pivot_value = col[1] + new_col_name = f'{value_col_name}___{pivot_value}' + else: + # 如果不是元组，直接使用（兼容旧行为） + new_col_name = f'{value_col_name}___{col}' + new_columns.append(new_col_name) print(f' 生成列: {new_col_name}', flush=True)