HaHafeng
75ceeb0653
Critical fixes: 1. Compute column: Add Chinese comma support in formula validation - Problem: Formula with Chinese comma failed validation - Fix: Add Chinese comma character to allowed_chars regex - Example: Support formulas like 'col1（kg）+ col2，col3' 2. Binning operation: Fix NaN serialization error - Problem: 'Out of range float values are not JSON compliant: nan' - Fix: Enhanced NaN/inf handling in binning endpoint - Added np.inf/-np.inf replacement before JSON serialization - Added manual JSON serialization with NaN->null conversion 3. Enhanced all operation endpoints for consistency - Updated conditional, dropna endpoints with same NaN/inf handling - Ensures all operations return JSON-compliant data Modified files: - extraction_service/operations/compute.py: Add Chinese comma to regex - extraction_service/main.py: Enhanced NaN handling in binning/conditional/dropna Status: Hotfix complete, ready for testing
82 lines
2.3 KiB
Python
82 lines
2.3 KiB
Python
"""
|
||
数值映射（重编码）操作
|
||
|
||
将分类变量的原始值映射为新值（如：男→1，女→2）。
|
||
"""
|
||
|
||
import pandas as pd
|
||
from typing import Dict, Any, Optional
|
||
|
||
|
||
def apply_recode(
|
||
df: pd.DataFrame,
|
||
column: str,
|
||
mapping: Dict[Any, Any],
|
||
create_new_column: bool = True,
|
||
new_column_name: Optional[str] = None
|
||
) -> pd.DataFrame:
|
||
"""
|
||
应用数值映射
|
||
|
||
Args:
|
||
df: 输入数据框
|
||
column: 要重编码的列名
|
||
mapping: 映射字典，如 {'男': 1, '女': 2}
|
||
create_new_column: 是否创建新列（True）或覆盖原列（False）
|
||
new_column_name: 新列名（create_new_column=True时使用）
|
||
|
||
Returns:
|
||
重编码后的数据框
|
||
|
||
Examples:
|
||
>>> df = pd.DataFrame({'性别': ['男', '女', '男', '女']})
|
||
>>> mapping = {'男': 1, '女': 2}
|
||
>>> result = apply_recode(df, '性别', mapping, True, '性别_编码')
|
||
>>> result['性别_编码'].tolist()
|
||
[1, 2, 1, 2]
|
||
"""
|
||
if df.empty:
|
||
return df
|
||
|
||
# 验证列是否存在
|
||
if column not in df.columns:
|
||
raise KeyError(f"列 '{column}' 不存在")
|
||
|
||
if not mapping:
|
||
raise ValueError('映射字典不能为空')
|
||
|
||
# 确定目标列名
|
||
if create_new_column:
|
||
target_column = new_column_name or f'{column}_编码'
|
||
else:
|
||
target_column = column
|
||
|
||
# 创建结果数据框（避免修改原数据）
|
||
result = df.copy()
|
||
|
||
# 应用映射
|
||
result[target_column] = result[column].map(mapping)
|
||
|
||
# 统计结果
|
||
mapped_count = result[target_column].notna().sum()
|
||
unmapped_count = result[target_column].isna().sum()
|
||
total_count = len(result)
|
||
|
||
print(f'映射完成: {mapped_count} 个值成功映射')
|
||
|
||
if unmapped_count > 0:
|
||
print(f'警告: {unmapped_count} 个值未找到对应映射')
|
||
# 找出未映射的唯一值
|
||
unmapped_mask = result[target_column].isna()
|
||
unmapped_values = result.loc[unmapped_mask, column].unique()
|
||
print(f'未映射的值: {list(unmapped_values)[:10]}') # 最多显示10个
|
||
|
||
# 映射成功率
|
||
success_rate = (mapped_count / total_count * 100) if total_count > 0 else 0
|
||
print(f'映射成功率: {success_rate:.1f}%')
|
||
|
||
return result
|
||
|
||
|
||
|