Files
AIclinicalresearch/extraction_service/operations/binning.py
HaHafeng f729699510 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
2025-12-08 17:38:08 +08:00

153 lines
5.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""
生成分类变量(分箱)操作
将连续数值变量转换为分类变量。
支持三种方法:自定义切点、等宽分箱、等频分箱。
"""
import pandas as pd
import numpy as np
from typing import List, Optional, Literal, Union
def apply_binning(
df: pd.DataFrame,
column: str,
method: Literal['custom', 'equal_width', 'equal_freq'],
new_column_name: str,
bins: Optional[List[Union[int, float]]] = None,
labels: Optional[List[Union[str, int]]] = None,
num_bins: int = 3
) -> pd.DataFrame:
"""
应用分箱操作
Args:
df: 输入数据框
column: 要分箱的列名
method: 分箱方法
- 'custom': 自定义切点
- 'equal_width': 等宽分箱
- 'equal_freq': 等频分箱
new_column_name: 新列名
bins: 自定义切点列表仅method='custom'时使用),如 [18, 60] → <18, 18-60, >60
labels: 标签列表(可选)
num_bins: 分组数量仅method='equal_width''equal_freq'时使用)
Returns:
分箱后的数据框
Examples:
>>> df = pd.DataFrame({'年龄': [15, 25, 35, 45, 55, 65, 75]})
>>> result = apply_binning(df, '年龄', 'custom', '年龄分组',
... bins=[18, 60], labels=['青少年', '成年', '老年'])
>>> result['年龄分组'].tolist()
['青少年', '成年', '成年', '成年', '成年', '老年', '老年']
"""
if df.empty:
return df
# 验证列是否存在
if column not in df.columns:
raise KeyError(f"'{column}' 不存在")
# 创建结果数据框
result = df.copy()
# 验证并转换数据类型
if not pd.api.types.is_numeric_dtype(result[column]):
# 尝试将字符串转换为数值
try:
result[column] = pd.to_numeric(result[column], errors='coerce')
print(f"警告: 列 '{column}' 已自动转换为数值类型")
except Exception as e:
raise TypeError(f"'{column}' 不是数值类型且无法转换,无法进行分箱")
# 检查是否有有效的数值
if result[column].isna().all():
raise ValueError(f"'{column}' 中没有有效的数值,无法进行分箱")
# 根据方法进行分箱
if method == 'custom':
# 自定义切点(用户输入的是中间切点,需要自动添加边界)
if not bins or len(bins) < 1:
raise ValueError('自定义切点至少需要1个值')
# 验证切点是否升序
if bins != sorted(bins):
raise ValueError('切点必须按升序排列')
# 自动添加左右边界
# 重要:始终添加边界,确保切点数+1=区间数
min_val = result[column].min()
max_val = result[column].max()
print(f'用户输入切点: {bins}')
print(f'数据范围: [{min_val:.2f}, {max_val:.2f}]')
# 构建完整的边界数组:始终添加左右边界
# 左边界取min(用户第一个切点, 数据最小值) - 0.001
# 右边界取max(用户最后一个切点, 数据最大值) + 0.001
left_bound = min(bins[0], min_val) - 0.001
right_bound = max(bins[-1], max_val) + 0.001
full_bins = [left_bound] + bins + [right_bound]
print(f'完整边界: {[f"{b:.1f}" for b in full_bins]}')
print(f'将生成 {len(full_bins) - 1} 个区间 = {len(bins) + 1} 个区间')
# 验证标签数量(区间数 = 边界数 - 1
expected_label_count = len(full_bins) - 1
if labels and len(labels) != expected_label_count:
raise ValueError(f'标签数量({len(labels)})必须等于区间数量({expected_label_count}')
result[new_column_name] = pd.cut(
result[column],
bins=full_bins,
labels=labels,
right=False,
include_lowest=True
)
elif method == 'equal_width':
# 等宽分箱
if num_bins < 2:
raise ValueError('分组数量至少为2')
result[new_column_name] = pd.cut(
result[column],
bins=num_bins,
labels=labels,
include_lowest=True
)
elif method == 'equal_freq':
# 等频分箱
if num_bins < 2:
raise ValueError('分组数量至少为2')
result[new_column_name] = pd.qcut(
result[column],
q=num_bins,
labels=labels,
duplicates='drop' # 处理重复边界值
)
else:
raise ValueError(f"不支持的分箱方法: {method}")
# 统计分布
print(f'分箱结果分布:')
value_counts = result[new_column_name].value_counts().sort_index()
for category, count in value_counts.items():
percentage = count / len(result) * 100
print(f' {category}: {count} 行 ({percentage:.1f}%)')
# 缺失值统计
missing_count = result[new_column_name].isna().sum()
if missing_count > 0:
print(f'警告: {missing_count} 个值无法分箱(可能是缺失值或边界问题)')
return result