python计算IV值及使用
def CalcIV(Xvar, Yvar): N_0= np.sum(Yvar==0)N_1 = np.sum(Yvar==1)
N_0_group = np.zeros(np.unique(Xvar).shape)
N_1_group = np.zeros(np.unique(Xvar).shape)
for i in range(len(np.unique(Xvar))):
N_0_group = Yvar[(Xvar == np.unique(Xvar)) & (Yvar == 0)].count()
N_1_group = Yvar[(Xvar == np.unique(Xvar)) & (Yvar == 1)].count()
iv = np.sum((N_0_group/N_0 - N_1_group/N_1) * np.log((N_0_group/N_0)/(N_1_group/N_1)))
returniv
def caliv_batch(df, Kvar, Yvar):
df_Xvar = df.drop(, axis=1)
ivlist = []
for col in df_Xvar.columns:
iv = CalcIV(df, df)
ivlist.append(iv)
names = list(df_Xvar.columns)
iv_df = pd.DataFrame({'Var': names, 'Iv': ivlist}, columns=['Var', 'Iv'])
return iv_df
页:
[1]