name: excel-smart-analysis-and-cleaning description: "对多 Sheet Excel 进行智能清洗、跨表核对与可视化分析。。"
Step1 对数据进行深度清洗,包括合并单元格填充(ffill)、正则化文本处理、RGB 颜色分量转换以及异常值识别。
import re
def clean_data(df, target_col):
# 1. 处理合并单元格:向下填充
df[target_col] = df[target_col].ffill()
# 2. 正则清洗:去除数字前缀、特殊字符及首尾空格
def regex_clean(text):
if not isinstance(text, str): return text
text = re.sub(r'^\d+[\.\s\-]+', '', text) # 去除如 "1. " 的前缀
text = re.sub(r'[^\u4e00-\u9fa5a-zA-Z0-9]', '', text) # 仅保留中英数
return text.strip()
df[target_col] = df[target_col].apply(regex_clean)
# 3. 数值转换与 RGB 逻辑筛选(示例:筛选黑色/无色值)
# 假设列名为 'Red', 'Green', 'Blue'
rgb_cols = ['Red', 'Green', 'Blue']
for col in rgb_cols:
if col in df.columns:
df[col] = pd.to_numeric(df[col], errors='coerce').fillna(0)
if all(c in df.columns for c in rgb_cols):
black_mask = (df['Red'] == 0) & (df['Green'] == 0) & (df['Blue'] == 0)
df = df[black_mask]
return df
# 遍历所有 sheet 进行清洗
cleaned_dfs = {name: clean_data(df, 'group_col') for name, df in df_dict.items()}