feat(dc): Complete Tool C quick action buttons Phase 1-2 - 7 functions

Summary:
- Implement 7 quick action functions (filter, recode, binning, conditional, dropna, compute, pivot)
- Refactor to pre-written Python functions architecture (stable and secure)
- Add 7 Python operations modules with full type hints
- Add 7 frontend Dialog components with user-friendly UI
- Fix NaN serialization issues and auto type conversion
- Update all related documentation

Technical Details:
- Python: operations/ module (filter.py, recode.py, binning.py, conditional.py, dropna.py, compute.py, pivot.py)
- Backend: QuickActionService.ts with 7 execute methods
- Frontend: 7 Dialog components with complete validation
- Toolbar: Enable 7 quick action buttons

Status: Phase 1-2 completed, basic testing passed, ready for further testing
This commit is contained in:
2025-12-08 17:38:08 +08:00
parent af325348b8
commit f729699510
158 changed files with 13814 additions and 273 deletions

View File

@@ -0,0 +1,109 @@
"""
高级筛选操作
提供多条件筛选功能支持AND/OR逻辑组合。
"""
import pandas as pd
from typing import List, Dict, Any, Literal
def apply_filter(
df: pd.DataFrame,
conditions: List[Dict[str, Any]],
logic: Literal['and', 'or'] = 'and'
) -> pd.DataFrame:
"""
应用筛选条件
Args:
df: 输入数据框
conditions: 筛选条件列表,每个条件包含:
- column: 列名
- operator: 运算符 (=, !=, >, <, >=, <=, contains, not_contains,
starts_with, ends_with, is_null, not_null)
- value: 值is_null和not_null不需要
logic: 逻辑组合方式 ('and''or')
Returns:
筛选后的数据框
Examples:
>>> df = pd.DataFrame({'年龄': [25, 35, 45], '性别': ['', '', '']})
>>> conditions = [
... {'column': '年龄', 'operator': '>', 'value': 30},
... {'column': '性别', 'operator': '=', 'value': ''}
... ]
>>> result = apply_filter(df, conditions, logic='and')
>>> len(result)
1
"""
if not conditions:
raise ValueError('筛选条件不能为空')
if df.empty:
return df
# 生成各个条件的mask
masks = []
for cond in conditions:
column = cond['column']
operator = cond['operator']
value = cond.get('value')
# 验证列是否存在
if column not in df.columns:
raise KeyError(f"'{column}' 不存在")
# 根据运算符生成mask
if operator == '=':
mask = df[column] == value
elif operator == '!=':
mask = df[column] != value
elif operator == '>':
mask = df[column] > value
elif operator == '<':
mask = df[column] < value
elif operator == '>=':
mask = df[column] >= value
elif operator == '<=':
mask = df[column] <= value
elif operator == 'contains':
mask = df[column].astype(str).str.contains(str(value), na=False)
elif operator == 'not_contains':
mask = ~df[column].astype(str).str.contains(str(value), na=False)
elif operator == 'starts_with':
mask = df[column].astype(str).str.startswith(str(value), na=False)
elif operator == 'ends_with':
mask = df[column].astype(str).str.endswith(str(value), na=False)
elif operator == 'is_null':
mask = df[column].isna()
elif operator == 'not_null':
mask = df[column].notna()
else:
raise ValueError(f"不支持的运算符: {operator}")
masks.append(mask)
# 组合所有条件
if logic == 'and':
final_mask = pd.concat(masks, axis=1).all(axis=1)
elif logic == 'or':
final_mask = pd.concat(masks, axis=1).any(axis=1)
else:
raise ValueError(f"不支持的逻辑运算: {logic}")
# 应用筛选
result = df[final_mask].copy()
# 打印统计信息
original_rows = len(df)
filtered_rows = len(result)
removed_rows = original_rows - filtered_rows
print(f'原始数据: {original_rows}')
print(f'筛选后: {filtered_rows}')
print(f'删除: {removed_rows} 行 ({removed_rows/original_rows*100:.1f}%)')
return result