import pandas as pd
import numpy as np
from statsmodels.stats.outliers_influence import variance_inflation_factor

# 实际数据
df = pd.read_csv("paper_data.csv")

df = df.drop(columns=["before_last_NO2", "before_last_O3", "last_year_pm10",
                        "before_last_pm1",	"before_last_pm2.5","last_year_pm1","last_year_OM","last_year_BC",
                    	'before_last_pm10',	'last_year_NO3',	'last_year_NH4',	'before_last_SO4',
                    	'before_last_NO3',	'before_last_NH4',	'before_last_OM',	'before_last_BC',	'before_last_nl'])
# 计算每个变量的 VIF方差膨胀因子
def calculate_vif(df):
    vif_data = pd.DataFrame()
    vif_data["Variable"] = df.columns
    vif_data["VIF"] = [
        variance_inflation_factor(df.values, i) for i in range(df.shape[1])
    ]
    return vif_data

# 调用函数计算 VIF
vif_result = calculate_vif(df)

# 输出 VIF 结果
print(vif_result)