Gains Table
gains_table creates a data frame including distribution of total, negative, positive, positive rate and approval rate by score bins. It provides both equal width and equal frequency intervals on score binning.
gains_table(score, label, bin_num = 10, method = "freq", width_by = NULL, breaks_by = NULL, positive = "bad|1", ...)
score |
A list of credit score for actual and expected data samples. For example, score = list(actual = scoreA, expect = scoreE). |
label |
A list of label value for actual and expected data samples. For example, label = list(actual = labelA, expect = labelE). |
bin_num |
Integer, the number of score bins. Defaults to 10. If it is 'max', then individual scores are used as bins. |
method |
The score is binning by equal frequency or equal width. Accepted values are 'freq' and 'width'. Defaults to 'freq'. |
width_by |
Number, increment of the score breaks when method is set as 'width'. If it is provided the above parameter bin_num will not be used. Defaults to NULL. |
breaks_by |
The name of data set to create breakpoints. Defaults to the first data set. Or numeric values to set breakpoints manually. |
positive |
Value of positive class, Defaults to "bad|1". |
... |
Additional parameters. |
A data frame
# data preparing ------
# load germancredit data
data("germancredit")
# filter variable via missing rate, iv, identical value rate
dt_f = var_filter(germancredit, "creditability")
# breaking dt into train and test
dt_list = split_df(dt_f, "creditability")
label_list = lapply(dt_list, function(x) x$creditability)
# woe binning ------
bins = woebin(dt_list$train, "creditability")
# converting train and test into woe values
dt_woe_list = lapply(dt_list, function(x) woebin_ply(x, bins))
# glm ------
m1 = glm(creditability ~ ., family = binomial(), data = dt_woe_list$train)
# vif(m1, merge_coef = TRUE)
# Select a formula-based model by AIC
m_step = step(m1, direction="both", trace=FALSE)
m2 = eval(m_step$call)
# vif(m2, merge_coef = TRUE)
# predicted proability
pred_list = lapply(dt_woe_list, function(x) predict(m2, type = 'response', x))
# scorecard ------
card = scorecard(bins, m2)
# credit score, only_total_score = TRUE
score_list = lapply(dt_list, function(x) scorecard_ply(x, card))
# credit score, only_total_score = FALSE
score_list2 = lapply(dt_list, function(x) scorecard_ply(x, card, only_total_score=FALSE))
###### perf_eva examples ######
# Example I, one datset
## predicted p1
perf_eva(pred = pred_list$train, label=dt_list$train$creditability, title = 'train')
## predicted score
# perf_eva(pred = score_list$train, label=dt_list$train$creditability, title = 'train')
# Example II, multiple datsets
## predicted p1
perf_eva(pred = pred_list, label = label_list)
## predicted score
# perf_eva(score_list, label_list)
###### perf_psi examples ######
# Example I # only total psi
psi1 = perf_psi(score = score_list, label = label_list)
psi1$psi # psi data frame
psi1$pic # pic of score distribution
# Example II # both total and variable psi
psi2 = perf_psi(score = score_list, label = label_list)
# psi2$psi # psi data frame
# psi2$pic # pic of score distribution
###### gains_table examples ######
# Example I, input score and label can be a list or a vector
g1 = gains_table(score = score_list$train, label = label_list$train)
g2 = gains_table(score = score_list, label = label_list)
# Example II, specify the bins number and type
g3 = gains_table(score = score_list, label = label_list, bin_num = 20)
g4 = gains_table(score = score_list, label = label_list, method = 'width')Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.