Prediction on a raw test set of the best logistic regression model on discretized / grouped data.

This function discretizes a user-provided test dataset given a discretization scheme provided by an S4 glmdisc object. It then applies the learnt logistic regression model and outputs its prediction (see predict.glm).

This defines the method "discretize" which will discretize a new input dataset given a discretization scheme of S4 class glmdisc

discretize(object, data)

# S4 method for glmdisc
discretize(object, data)

Arguments

object	glmdisc object
data	the data to discretize according to the provided discretization scheme

Author

Adrien Ehrhardt.

Examples

# Simulation of a discretized logit model
set.seed(1)
x <- matrix(runif(300), nrow = 100, ncol = 3)
cuts <- seq(0, 1, length.out = 4)
xd <- apply(x, 2, function(col) as.numeric(cut(col, cuts)))
theta <- t(matrix(c(0, 0, 0, 2, 2, 2, -2, -2, -2), ncol = 3, nrow = 3))
log_odd <- rowSums(t(sapply(seq_along(xd[, 1]), function(row_id) {
  sapply(
    seq_along(xd[row_id, ]),
    function(element) theta[xd[row_id, element], element]
  )
})))
y <- rbinom(100, 1, 1 / (1 + exp(-log_odd)))

sem_disc <- glmdisc(x, y,
  iter = 50, m_start = 4, test = FALSE,
  validation = FALSE, criterion = "aic"
)
discretize(sem_disc, data.frame(x))
#>        [,1] [,2] [,3]
#>   [1,] "1"  "4"  "1" 
#>   [2,] "1"  "3"  "1" 
#>   [3,] "4"  "3"  "1" 
#>   [4,] "3"  "4"  "1" 
#>   [5,] "1"  "4"  "1" 
#>   [6,] "3"  "3"  "1" 
#>   [7,] "3"  "3"  "1" 
#>   [8,] "4"  "4"  "3" 
#>   [9,] "4"  "4"  "1" 
#>  [10,] "1"  "4"  "1" 
#>  [11,] "1"  "4"  "1" 
#>  [12,] "1"  "4"  "3" 
#>  [13,] "4"  "3"  "1" 
#>  [14,] "1"  "4"  "1" 
#>  [15,] "3"  "3"  "1" 
#>  [16,] "2"  "3"  "1" 
#>  [17,] "4"  "4"  "1" 
#>  [18,] "3"  "3"  "1" 
#>  [19,] "1"  "4"  "1" 
#>  [20,] "3"  "4"  "1" 
#>  [21,] "3"  "4"  "1" 
#>  [22,] "1"  "4"  "1" 
#>  [23,] "4"  "4"  "1" 
#>  [24,] "1"  "3"  "1" 
#>  [25,] "1"  "4"  "1" 
#>  [26,] "1"  "4"  "1" 
#>  [27,] "1"  "4"  "1" 
#>  [28,] "1"  "3"  "3" 
#>  [29,] "3"  "3"  "1" 
#>  [30,] "1"  "4"  "1" 
#>  [31,] "2"  "4"  "1" 
#>  [32,] "4"  "3"  "3" 
#>  [33,] "2"  "3"  "1" 
#>  [34,] "1"  "4"  "1" 
#>  [35,] "3"  "4"  "1" 
#>  [36,] "4"  "4"  "1" 
#>  [37,] "3"  "4"  "1" 
#>  [38,] "1"  "4"  "1" 
#>  [39,] "4"  "4"  "1" 
#>  [40,] "1"  "4"  "1" 
#>  [41,] "3"  "4"  "1" 
#>  [42,] "4"  "4"  "1" 
#>  [43,] "3"  "3"  "1" 
#>  [44,] "2"  "3"  "1" 
#>  [45,] "2"  "4"  "1" 
#>  [46,] "3"  "4"  "1" 
#>  [47,] "1"  "3"  "1" 
#>  [48,] "2"  "4"  "3" 
#>  [49,] "4"  "3"  "1" 
#>  [50,] "4"  "4"  "1" 
#>  [51,] "2"  "4"  "1" 
#>  [52,] "3"  "4"  "1" 
#>  [53,] "2"  "3"  "1" 
#>  [54,] "1"  "4"  "1" 
#>  [55,] "1"  "4"  "1" 
#>  [56,] "1"  "3"  "3" 
#>  [57,] "1"  "4"  "1" 
#>  [58,] "2"  "3"  "1" 
#>  [59,] "4"  "3"  "1" 
#>  [60,] "1"  "3"  "1" 
#>  [61,] "3"  "3"  "1" 
#>  [62,] "1"  "4"  "1" 
#>  [63,] "2"  "4"  "1" 
#>  [64,] "1"  "4"  "1" 
#>  [65,] "4"  "4"  "1" 
#>  [66,] "1"  "4"  "1" 
#>  [67,] "2"  "3"  "3" 
#>  [68,] "4"  "3"  "1" 
#>  [69,] "1"  "4"  "1" 
#>  [70,] "3"  "3"  "1" 
#>  [71,] "1"  "4"  "3" 
#>  [72,] "3"  "4"  "3" 
#>  [73,] "1"  "4"  "1" 
#>  [74,] "1"  "4"  "1" 
#>  [75,] "2"  "4"  "1" 
#>  [76,] "3"  "4"  "1" 
#>  [77,] "3"  "4"  "1" 
#>  [78,] "1"  "4"  "1" 
#>  [79,] "3"  "4"  "1" 
#>  [80,] "3"  "4"  "1" 
#>  [81,] "2"  "3"  "3" 
#>  [82,] "4"  "3"  "1" 
#>  [83,] "1"  "4"  "1" 
#>  [84,] "1"  "4"  "1" 
#>  [85,] "4"  "4"  "3" 
#>  [86,] "1"  "3"  "1" 
#>  [87,] "4"  "4"  "1" 
#>  [88,] "1"  "4"  "1" 
#>  [89,] "1"  "4"  "3" 
#>  [90,] "1"  "4"  "1" 
#>  [91,] "1"  "4"  "1" 
#>  [92,] "1"  "4"  "3" 
#>  [93,] "4"  "3"  "1" 
#>  [94,] "3"  "4"  "1" 
#>  [95,] "3"  "3"  "1" 
#>  [96,] "3"  "4"  "1" 
#>  [97,] "2"  "3"  "3" 
#>  [98,] "1"  "4"  "3" 
#>  [99,] "3"  "3"  "3" 
#> [100,] "4"  "4"  "1"