library(scorecard)
data("germancredit")
print(dim(germancredit))
print(names(germancredit))
print(head(germancredit[,20:21]))

# 变量选择
dt_s <- var_filter(germancredit, y="creditability")
print(dim(dt_s))

# 数据集划分为训练集和测试集
dt_list <- split_df(dt_s)
train <- dt_list$train
test <- dt_list$test

# woe 分箱 自动分箱
bins <- woebin(dt_s, y="creditability")

# 绘制分箱后的坏账率可视化，对应14张图，这里只展示最后一张
woebin_plot(bins)

train_woe <-  woebin_ply(train, bins)
test_woe <-  woebin_ply(test, bins)
print(dim(train_woe))
print(dim(test_woe))

m1 <- glm( creditability ~ ., family = binomial(), data = train_woe)
summary(m1)

# 逐步回归选择变量
m_step <- step(m1, direction="both", trace = FALSE)
m2 <- eval(m_step$call)
summary(m2)

# 模型性能验证 ks和roc
# 预测的概率
train_pred <- predict(m2, train_woe, type = 'response')
test_pred <- predict(m2, test_woe, type = 'response')

# 性能
train_perf <- perf_eva(train$creditability, train_pred, title = 'train')

test_perf <- perf_eva(test$creditability, test_pred, title = 'test')

# 生成评分卡
card <- scorecard(bins, m2)
card

train_score <- scorecard_ply(train, card, print_step = 0)
# 验证集评分
test_score <- scorecard_ply(test, card, print_step = 0)

print(train_score)

print(test_score)

# 模型的稳定性度量
# psi
psi_result <- perf_psi(
  score = list(train = train_score, test = test_score),
  label = list(train = train$creditability, test = test$creditability)
)