outlier-detection

Step 1 加载数据并配置环境

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns

# 设置中英文字体以支持可视化显示 (SimHei 或 WenQuanYi)
plt.rcParams['font.sans-serif'] = ['SimHei', 'WenQuanYi Zen Hei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False

# 加载数据
file_path = 'data.xlsx'  # 替换为实际文件路径
df = pd.read_excel(file_path)

# 基础信息检查
print(f"数据形状: {df.shape}")
print(f"数据类型:\n{df.dtypes}")
print(df.head())

Step 2 基于 IQR 方法识别异常值

# 自动筛选数值型列进行分析
target_cols = df.select_dtypes(include=[np.number]).columns.tolist()
outlier_summary = []

for col in target_cols:
    data = df[col].dropna()
    if data.empty:
        continue
        
    # 四分位距计算 (IQR)
    Q1 = data.quantile(0.25)
    Q3 = data.quantile(0.75)
    IQR = Q3 - Q1
    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR
    
    # 识别异常值
    outliers = data[(data < lower_bound) | (data > upper_bound)]
    
    outlier_summary.append({
        'target_col': col,
        'outlier_count': len(outliers),
        'outlier_ratio': f"{(len(outliers)/len(data)*100):.2f}%",
        'lower_limit': lower_bound,
        'upper_limit': upper_bound,