statcompute

df1 <- read.table("credit_count.txt", header = T, sep = ",")
df2 <- df1[which(df1$CARDHLDR == 1), ]
Y <- df2$DEFAULT
X <- scale(df2[, 3:ncol(df2)])
i <- sample(seq(length(Y)), length(Y) / 2)

# WITHOUT BINNING
Y1 <- Y[i]
Y2 <- Y[-i]
X1 <- X[i, ]

statcompute

source("yager.R")
df <- read.table("lgd", header = T)[, 1:8]
Y <- 1 - df$rr
X <- scale(df[, 2:8])
pre.N <- 1000
trn.N <- 100
try.N <- 100
seeds <- floor(with(set.seed(2020), runif(try.N) * 1e8))

test_glm <- function(seed) {

statcompute

data(kyphosis, package = "gam")
y <- ifelse(kyphosis$Kyphosis == "present", 1, 0)
x <- scale(kyphosis[, -1])
### FIT A GRNN
net1 <- grnn.fit(x = x, y = y)
test <- grnn.search_auc(net1, sigmas = gen_sobol(min = 0.5, max = 1.5, n = 50), nfolds = 20)
net2 <- grnn.fit(x = x, y = y, sigma = min(test$best$sigma))
### FIT A GAM
library(gam)
gam1 <- gam(y~ Age + Number + Start, data = data.frame(y, x), family = binomial)

statcompute

### INITIATE A GRNN
net1 <- grnn.fit(x = X1, y = Y1)
### FIND THE OPTIMIZED PARAMETER
best <- grnn.optmiz_auc(net1, lower = 1, upper = 3)
### FIT A GRNN WITH THE OPTIMIZED PARAMETER
net2 <- grnn.fit(x = X1, y = Y1, sigma = best$sigma)
### CALCULATE PFI BY TRYING 1000 RANDOM PERMUTATIONS 
pfi_rank <- grnn.pfi(net2, ntry = 1000)
# idx               var        pfi
#   9  woe.bureau_score 0.06821683

statcompute

from numpy.random import seed
from pandas import read_csv, DataFrame
from sklearn.preprocessing import scale
from keras.layers.convolutional import Conv1D, MaxPooling1D
from keras.layers.merge import average
from keras.layers import Input, Dense, Flatten, Reshape, Dropout, SpatialDropout1D
from keras.models import Model
from keras.optimizers import SGD
from keras.utils import plot_model

statcompute

library(keras)
df <- read.csv("credit_count.txt")
Y <- matrix(df[df$CARDHLDR == 1, ]$DEFAULT)
X <- scale(df[df$CARDHLDR == 1, ][3:14])

inputs <- layer_input(shape = c(ncol(X)))

mlp <- inputs %>%
  layer_dense(units = 64, activation = 'relu', kernel_initializer = 'he_uniform') %>% 
  layer_dropout(rate = 0.2, seed = 1) %>% 

statcompute

Y <- df$bad
X <- scale(df_woe$df[, -1])
set.seed(2019)
i <- sample(seq(length(Y)), length(Y) / 4)
Y1 <- Y[i]
Y2 <- Y[-i]
X1 <- X[i, ]
X2 <- X[-i, ]
net1 <- grnn.fit(x = X1, y = Y1)
rst <- grnn.optmiz_auc(net1, lower = 1, upper = 3)

statcompute

df <- readRDS("df.rds") 
source("mob.R")
source("grnnet.R")
bin_out <- batch_bin(df, 3)
df_woe <- batch_woe(df, bin_out$BinLst)
Y <- df$bad
X <- scale(df_woe$df[, -1])
set.seed(2019)
i <- sample(seq(length(Y)), length(Y) / 4)
Y1 <- Y[i]

statcompute

Modeling Loss / Average Loss
  |
  |-- Loss without Zeroes
  |     |
  |     |-- Gamma
  |     |
  |     `-- Inverse Gaussian
  |
  |-- Loss with Some Zeros
  |     |

statcompute

Modeling Frequency
  |
  |-- Equi-Dispersion (Baseline)
  |     |
  |     `-- Standard Poisson
  |
  |-- Over-Dispersion
  |     |
  |     |-- Negative Binomial
  |     |