#liberaries

#detach("package:remhmm", unload = TRUE)
#devtools::install_github("Mbehbahani/DigiPy/remhmm")
library(remhmm)
library(REHdynamics)
library(remstats)
## Warning: package 'remstats' was built under R version 4.3.2
library(remstimate)
## Warning: package 'remstimate' was built under R version 4.3.2
library("nloptr")
## Warning: package 'nloptr' was built under R version 4.3.2

Parameter settings for Scenario1

m=2 #Number States
q=1 #Number of variables (In REM it means the Number of statistics)
num_obs <- 100
N_relations<-200 #number of relational events in each state 

# Hidden State
transition_probs <- matrix(c(0.2,0.8,0.8,0.2), nrow = 2,byrow=TRUE)
initial_probs <- c(0.1, 0.9)

# Initial Values for Optimization
gamma0=matrix(c(0.2,0.8,0.8,0.2), nrow = 2,byrow=TRUE)
mean0=c(0.1,0.5) 
sd0=c(0.3,0.4)
delta0=c(0.3, 0.7)


vc= matrices_to_vector(gamma0, mean0, sd0, delta0)

Lgamma <- matrix(c(0,0,0,0), nrow = 2,byrow=TRUE)
Lmean0 <- c(-Inf,-Inf)
Lsd0 <- c(0,0)
Ldelta0 <- c(0, 0)
Lvc <- matrices_to_vector(Lgamma, Lmean0, Lsd0, Ldelta0)

Ugamma <- matrix(c(1,1,1,1), nrow = 2,byrow=TRUE)
Umean0 <- matrix(c(Inf,Inf))
Usd0 <- matrix(c(Inf,Inf))
Udelta0 <- c(1, 1)
Uvc <- matrices_to_vector(Ugamma, Umean0, Usd0, Udelta0)


lower_bounds <- Lvc
upper_bounds <- Uvc

generate REH data using “generate_rem” function

## code to prepare `covar` dataset 
# Generate the actors and their exogenous information for the 
# generated datasets

set.seed(27613)
covar <- data.frame(id = 1:10, time = 0, z = rnorm(n = 10))
colnames(covar)[colnames(covar) == "id"] <- "name"
# usethis::use_data(covar,overwrite = TRUE) 

## code to prepare `param` dataset 
# Normal variable (will be add)
param1 <- list(
    "baseline" = -4, 
    "inertia" = 0.1)

param2 <- list(
    "baseline" = -4, 
    "inertia" = 0.5)

REM data (MainTest(Event effect).Rmd)

# Generate REM of the current state
#num_var<-1 
#q<-num_var
#initial_probs
#transition_probs

hidden_states<-numeric(num_obs)
for (t in 1:num_obs) {
    if (t == 1) {
    # Initial state
    hidden_states[t] <- sample(1:m, 1, prob = initial_probs)
    } else {
    # Transition to the next state
      hidden_states[t] <- sample(1:m, 1, prob = transition_probs[hidden_states[t - 1], ])
    }
}

preparation to generate datasets

windows defenition

##  M<-200 specify M (N_relations at the beginning)
windows <- data.frame(
  start = seq(1, by = N_relations, length.out = num_obs),
  stop = seq(N_relations, by = N_relations, length.out = num_obs)
)

for calculating the effects. of the statistics

it based on the number of statistics. It should be modified

norm.HMM.mllk(vc, x, m,q)
## [1] 15.11015
Result<-norm.HMM.mle(x, m,q, vc,lower_bounds, upper_bounds)
## Warning in nloptr.add.default.options(opts.user = opts, x0 = x0,
## num_constraints_ineq = num_constraints_ineq, : No termination criterium
## specified, using default (relative x-tolerance = 1e-04)
Result
## $gamma
##           [,1]      [,2]
## [1,] 0.2268973 0.7731027
## [2,] 0.7725330 0.2274670
## 
## $mean
##            [,1]      [,2]
## [1,] 0.09266093 0.5023897
## 
## $sd
##           [,1]       [,2]
## [1,] 0.1990576 0.01363938
## 
## $delta
## [1] 0.5713172 0.4286828
Fstates<-norm.HMM.viterbi(x,Result,m,q)
#hidden_states
#x
cbind(x,hidden_states,Fstates)
##                    hidden_states Fstates
##   [1,]  0.49274652             2       2
##   [2,]  0.03256410             1       1
##   [3,]  0.50940753             2       2
##   [4,]  0.06028542             1       1
##   [5,]  0.51355557             2       2
##   [6,]  0.08674986             1       1
##   [7,]  0.50403092             2       2
##   [8,]  0.51904986             2       2
##   [9,]  0.49490613             2       2
##  [10,]  0.13837724             1       1
##  [11,]  0.48635982             2       2
##  [12,]  0.06365644             1       1
##  [13,]  0.48209168             2       2
##  [14,]  0.06478355             1       1
##  [15,]  0.49906671             2       2
##  [16,]  0.10766241             1       1
##  [17,]  0.50770941             2       2
##  [18,]  0.15248797             1       1
##  [19,]  0.51652893             2       2
##  [20,]  0.06257603             1       1
##  [21,]  0.51211759             2       2
##  [22,]  0.51416828             2       2
##  [23,]  0.48848176             2       2
##  [24,]  0.10794500             1       1
##  [25,]  0.08676196             1       1
##  [26,]  0.48204893             2       2
##  [27,]  0.51192392             2       2
##  [28,]  0.06287079             1       1
##  [29,]  0.02866174             1       1
##  [30,]  0.10727773             1       1
##  [31,]  0.51626549             2       2
##  [32,]  0.13819422             1       1
##  [33,]  0.48606101             2       2
##  [34,] -0.08260028             1       1
##  [35,]  0.51394992             2       2
##  [36,]  0.13757479             1       1
##  [37,]  0.51395826             2       2
##  [38,]  0.52057586             2       2
##  [39,]  0.50534270             2       2
##  [40,]  0.10705506             1       1
##  [41,]  0.48390016             2       2
##  [42,]  0.51385478             2       2
##  [43,]  0.49875251             2       2
##  [44,]  0.12330244             1       1
##  [45,]  0.51172535             2       2
##  [46,]  0.08733404             1       1
##  [47,]  0.52495422             2       2
##  [48,]  0.03174733             1       1
##  [49,]  0.49668453             2       2
##  [50,] -0.01461943             1       1
##  [51,]  0.52273581             2       2
##  [52,]  0.13855165             1       1
##  [53,]  0.51597690             2       2
##  [54,]  0.08668094             1       1
##  [55,]  0.49661313             2       2
##  [56,]  0.13817610             1       1
##  [57,]  0.49240050             2       2
##  [58,]  0.06258792             1       1
##  [59,]  0.49661979             2       2
##  [60,]  0.51379834             2       2
##  [61,]  0.08564502             1       1
##  [62,]  0.49021609             2       2
##  [63,]  0.08728806             1       1
##  [64,]  0.50300235             2       2
##  [65,]  0.12321235             1       1
##  [66,]  0.47749465             2       2
##  [67,]  0.10675151             1       1
##  [68,]  0.52713244             2       2
##  [69,]  0.51600528             2       2
##  [70,]  0.49438373             2       2
##  [71,]  0.08631044             1       1
##  [72,]  0.51376953             2       2
##  [73,]  0.08706425             1       1
##  [74,]  0.47110787             2       2
##  [75,]  0.12258366             1       1
##  [76,]  0.51386866             2       2
##  [77,]  0.10667489             1       1
##  [78,]  0.50504478             2       2
##  [79,]  0.52484056             2       2
##  [80,]  0.50508365             2       2
##  [81,]  0.50080411             2       2
##  [82,] -0.01124111             1       1
##  [83,]  0.49442367             2       2
##  [84,]  0.10635817             1       1
##  [85,]  0.48589748             2       2
##  [86,] -0.81564415             1       1
##  [87,]  0.49656001             2       2
##  [88,]  0.08726232             1       1
##  [89,]  0.47538349             2       2
##  [90,]  0.13809183             1       1
##  [91,]  0.48595070             2       2
##  [92,]  0.06317193             1       1
##  [93,]  0.49867832             2       2
##  [94,]  0.06308124             1       1
##  [95,]  0.47119219             2       2
##  [96,]  0.08773070             1       1
##  [97,]  0.51595027             2       2
##  [98,]  0.15151744             1       1
##  [99,]  0.03096112             1       1
## [100,]  0.48381489             2       2
sum(hidden_states==Fstates)
## [1] 100