---
title: "scanstat"
output: pdf_document
date: '2022-05-09'
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
library("localScore")
library("latex2exp")
library("Rcpp")
library("caret")
library("ROCR")
```

```{r}
PoissonProcess <- function(lambda,T) {
  return(sort(runif(rpois(1,lambda*T),0,T)))
}
```

```{r}
SimulationH1 <- function(lambda0, lambda1,T,tau){
    ppH0=PoissonProcess(lambda0,T)
    ppH1.segt=PoissonProcess(lambda1,tau)
    dbt=runif(1,0,T-tau)
    ppH0bis=PoissonProcess(lambda0,T)
    ppH1.repo=dbt+ppH1.segt
    ppH0_avant=ppH0bis[which(ppH0bis<ppH1.repo[1])]
    ppH0_apres=ppH0bis[which(ppH0bis>ppH1.repo[length(ppH1.repo)])]
    ppH1=c(ppH0_avant,ppH1.repo,ppH0_apres)
    return (ppH1)
}
```

```{r}
TimeBetweenEvent <- function(pp){
    n=length(pp)
    tbe=pp[2:n]-pp[1:n1-1]
    tbe=c(0,tbe)
    return (tbe)
}

DataFrame <- function(pp,tbe){
    list=data.frame(ProcessusPoisson=pp, TimeBetweenEvent=tbe)
}
```

```{r}
ScanStat <- function(pp, T, tau){
    n=length(pp)
    stop=n-length(which(pp>(T-tau)))
    ScanStat=0
    for (i in (1:stop)) {
        x=which((pp>=pp[i])&(pp<=(pp[i]+tau)))
        scan=length(x)
        if (scan>ScanStat) {ScanStat=scan
        max=i}
  }   
    return (c(max,ScanStat))
}
```

```{r}
EmpDistrib <- function(lambda, n_sample,T,tau){
    pp=PoissonProcess(lambda,T)
    scan=c(ScanStat(pp,T, tau)[2])
    index=c(ScanStat(pp,T, tau)[1])
    for (i in 2:(n_sample)){
        pp=PoissonProcess(lambda,T)
        scan=rbind(scan,ScanStat(pp,T, tau)[2])
        index=rbind(index,ScanStat(pp,T, tau)[1])
    }
    min_scan=min(scan)-1
    max_scan=max(scan)
    table1=table(factor(scan, levels = min_scan:max_scan))
    EmpDis=data.frame(cdf=cumsum(table1)/sum(table1), proba=table1/sum(table1), index_scan=min_scan:max_scan)
    EmpDis<-EmpDis[,-2]
    return(EmpDis)
    }
```


```{r}
Plot_CDF <- function(lambda,n_sample,T,tau){
    Emp=EmpDistrib(lambda,n_sample,T,tau)
    title=TeX(paste(r'(Cumulative distribution function for $\lambda=$)', lambda))
    plot(Emp$index_scan, Emp$cdf,type="s",xlab="Number of occurrences",ylab="Probability", main=title, col="red")
    return(Emp)
}
```

```{r}
n_sample=10**4
lambda0=3
T=10
tau=1
ppH0=PoissonProcess(lambda0,T)
#CDF=Plot_CDF(lambda0,n_sample,T,tau)
```

```{r}
PValue <- function(Emp,ppH, T, tau){
    scanH1=ScanStat(ppH,T,tau)[2]
    index_scanH1=ScanStat(ppH,T,tau)[1]
    index=Emp$index_scan
    n=length(index)
    if (scanH1< min(Emp$index_scan)){
        return (c(scanH1,1,index_scanH1))
        } else{
            if(min(Emp$index_scan)<scanH1 && scanH1<=max(Emp$index_scan)){
                return(c(scanH1,1-Emp$cdf[scanH1-min(Emp$index_scan)+1],index_scanH1))
            } else{return (c(scanH1,0,index_scanH1))}}
    }
```

```{r}
NbSeqH0 = 10
NbSeqH1 = NbSeqH0
DataH0 = vector("list")
DataH1 = vector("list")
lambda0 = 2
lambda1 = 5
T = 10
tau = 1

#Creation of a sequence that contains the sequence simulated under the null hypothesis
for (i in 1:NbSeqH0) {
    ppi = PoissonProcess(lambda0,T)
    DataH0[[i]] = ppi
}

#Creation of a sequence that contains the sequence simulated under the alternative hypothesis
seqH1begin = c()
for (i in 1:NbSeqH1) {
    pphi = SimulationH1(lambda0, lambda1,T,tau)
    DataH1[[i]] = pphi
}

#Computation of the time between events
TimeBetweenEventList <- function(list,n_list){
    TBE = vector("list",length=n_list)
    for (i in (1:n_list)) {
        ppi = list[[i]]
        ni = length(ppi)
        tbei = ppi[2:ni]-ppi[1:ni-1]
        TBE[[i]] = tbei
    }
    return (TBE)
}
tbe0 = TimeBetweenEventList(DataH0,NbSeqH0)
```

```{r}
#We start by computing the empirical distribution for lambda0
Emp = EmpDistrib(lambda0,n_sample,T,tau)
scan = c()
pvalue = c()
index_scan = c()

#Then, we stock the p-value and the 
for (i in 1:NbSeqH0){
    ppi = DataH0[[i]]
    result = PValue(Emp,ppi,T,tau)
    scan = c(scan,result[1])
    pvalue = c(pvalue,result[2])
    index_scan = c(index_scan,result[3])
}

ScS_H0=data.frame(num=(1:NbSeqH0), scan_stat=scan, pvalue_scan=pvalue,class=c(pvalue<0.05)*1) 
head(ScS_H0)
sum(ScS_H0$class[which(ScS_H0$class=='1')])/NbSeqH0
```

```{r}
#We start by computing the empirical distribution for lambda0
scan=c()
pvalue=c()
index_scan=c()

#Then, we stock the p-value and the 
for (i in 1:NbSeqH1){
    ppi=DataH1[[i]]
    result=PValue(Emp,DataH1[[i]],T,tau)
    scan=c(scan,result[1])
    pvalue=c(pvalue,result[2])
    index_scan=c(index_scan,result[3])
}
ScS_H1 = data.frame(num=1:NbSeqH1, scan_stat=scan, pvalue_scan=pvalue, class=(pvalue<0.05)*1, begin_scan=index_scan)
head(ScS_H1)
sum(ScS_H1$class[which(ScS_H1$class=='1')])/NbSeqH1
```

```{r}
ScanStatMC <- function(NbSeq, T, tau, Emp, pp0){
    scan=c()
    pvalue=c()
    index_scan=c()

    for (i in 1:NbSeq){
        ppi=pp0[[i]]
        result=PValue(Emp,ppi,T,tau)
        scan=c(scan,result[1])
        pvalue=c(pvalue,result[2])
        index_scan=c(index_scan,result[3])
    }

    ScS_H0=data.frame(num=(1:NbSeq), scan_stat=scan, pvalue_scan=pvalue,class=c(pvalue<0.05)*1)
    return(ScS_H0)
}
```

```{r}
ComputeE <- function(lambda0, lambda1){
    E = 1
    maxXk = floor(E*(log(lambda1/lambda0)))
    while (maxXk < 3) {
        E = E+1
        maxXk = floor(E*(log(lambda1/lambda0)))
    }

    return (E)
    }
```

```{r}
ScoreDistribEmpiric <- function(lambda0, lambda1, n_sample, T){
    E = ComputeE(lambda0, lambda1)
    Score = c()
    
    for (i in 1:n_sample){
        ppH0 = PoissonProcess(lambda0,T)
        n1 = length(ppH0)
        tbe0 = ppH0[2:n1]-ppH0[1:n1-1]
        X = floor(E*(log(lambda1/lambda0)+(lambda0-lambda1)*tbe0))
        Score=c(Score,X)
    }
    min_X = min(Score)
    max_X = max(Score)

    P_X = table(factor(Score, levels = min_X:max_X))/sum(table(Score))
    df = data.frame("Score_X" = min(Score):max(Score), "P_X" = P_X)
    df <- df[,-2]

    return (df)
    }
```

```{r}
ScoreDistribElisa <- function(lambda0, lambda1, T){
    E = ComputeE(lambda0, lambda1)

    score_max = floor(E*log(lambda1/lambda0))

    ## score_min compute
    score_min_c = floor(E*log(lambda1/lambda0)+E*(lambda0-lambda1)*T)

    l = seq(score_min_c,score_max,1)
    borne_inf = (l-E*log(lambda1/lambda0))/(E*(lambda0-lambda1))
    borne_sup = (l+1-E*log(lambda1/lambda0))/(E*(lambda0-lambda1))
    proba.l = pexp(rate=lambda0,borne_inf)-pexp(rate=lambda0,borne_sup)
    S = sum(proba.l)
    new.proba.s = proba.l/S
    df = data.frame("Score_X" = l, "P_X" = new.proba.s)

    return (df)
}
```

```{r}
LocalScoreMC <- function(lambda0, lambda1, NbSeq, T, X_seq, P_X, tbe0){
    E = ComputeE(lambda0, lambda1)
    pvalue = c()
    X = c()
    min_X = min(X_seq)
    max_X = max(X_seq)
    NbSeq.NonNulles = 0
    for (i in 1:NbSeq){
        x = floor(E*log(dexp(tbe0[[i]], rate = lambda1)/dexp(tbe0[[i]], rate = lambda0)))
        if (length(x)!=0){
            X = c(X,x)
            LS = localScoreC(x)$localScore[1]
            daudin_result = daudin(localScore = LS, score_probabilities = P_X, sequence_length = length(x), sequence_min = min_X, sequence_max = max_X)
            options(warn = -1) # Disable warnings print
            pvalue = c(pvalue, daudin_result)
            NbSeq.NonNulles = NbSeq.NonNulles + 1

        }
  }
  LS_H0=data.frame(num=1:NbSeq.NonNulles, pvalue_scan=pvalue, class=(pvalue<0.05)*1)
  return(LS_H0)
}
```

```{r}
Nb = 10
tbe0 = vector("list",length = Nb)
pp0 =  vector("list", length = Nb)
pp1 =  vector("list", length = Nb)
tbe1 = vector("list", length =  Nb)

for (i in (1:Nb)) {
    #Simulation for sequences under H0
    ppi = PoissonProcess(lambda0,T)
    ni=length(ppi)
    pp0[[i]] = ppi
    tbei = ppi[2:ni]-ppi[1:ni-1]
    tbe0[[i]] = tbei
    
    #Simulation for sequences under H1
    ppj1 = SimulationH1(lambda0, lambda1, T, tau)
    nj = length(ppj1)
    pp1[[i]] = ppj1
    tbej = ppj1[2:nj]-ppj1[1:nj-1]
    tbe1[[i]] = tbej
}

Score = ScoreDistribEmpiric(lambda0, lambda1, Nb, T)
LocalScoreMC(2,3,Nb,10,Score$Score_X, Score$P_X, tbe0)
LocalScoreMC(2,3,Nb,10,Score$Score_X, Score$P_X, tbe1)
```

```{r}
CompareMethods <- function(lambda0, lambda1, NbSeq, T, tau){
    if (lambda0 < lambda1){
        
        cat("For T = ", T, ", Nb = ", NbSeq, ", lambda0 = ", lambda0, " and lambda1 = ", lambda1, ":\n", sep = "")
        tbe0 = vector("list",length=NbSeq)
        pp0 =  vector("list", length = NbSeq)
        pp1 =  vector("list", length = NbSeq)
        tbe1 = vector("list", length =  NbSeq)
        
        for (i in (1:NbSeq)) {
            #Simulation for sequences under H0
            ppi = PoissonProcess(lambda0,T)
            ni=length(ppi)
            pp0[[i]] = ppi
            tbei = ppi[2:ni]-ppi[1:ni-1]
            tbe0[[i]] = tbei
            
            #Simulation for sequences under H1
            ppj1 = SimulationH1(lambda0, lambda1, T, tau)
            nj = length(ppj1)
            pp1[[i]] = ppj1
            tbej = ppj1[2:nj]-ppj1[1:nj-1]
            tbe1[[i]] = tbej
        }
        
        #cat("- Empiric version:\n")
        Score = ScoreDistribEmpiric(lambda0, lambda1, NbSeq, T)
        LS_H0 = LocalScoreMC(lambda0, lambda1, NbSeq, T, Score$Score_X, Score$P_X, tbe0)
        LS_H1 = LocalScoreMC(lambda0, lambda1, NbSeq, T, Score$Score_X, Score$P_X, tbe1)
        LS_obtained = c(LS_H0$class, LS_H1$class)
        options(warn = -1) 
          
        Emp = EmpDistrib(lambda0,n_sample,T,tau)
        SS_H0 = ScanStatMC(NbSeq, T, tau, Emp, pp0)
        SS_H1 = ScanStatMC(NbSeq, T, tau, Emp, pp1)
        SS_obtained = c(SS_H0$class, SS_H1$class)
          
                    
        cat("--- Confusion matrix for scan statistic method --- \n")
        theoretical_results_SS = c(rep(0,length(SS_H0$num)), rep(1,length(SS_H1$num)))
        print(confusionMatrix(as.factor(SS_obtained), as.factor(theoretical_results_SS),
                              dnn = c("Prediction", "Reference"))$table)
          
        cat("--- Confusion matrix for local score method --- \n")
        theoretical_results_LS = c(rep(0,length(LS_H0$num)), rep(1,length(LS_H1$num)))
        print(confusionMatrix(as.factor(LS_obtained), as.factor(theoretical_results_LS),
                                dnn = c("Prediction", "Reference"))$table)
          
        #cat("--- Coube ROC associé")
        title_ROC = TeX(paste(r'(ROC curve for $H_0: \lambda_0=$)', lambda0, 
                                r'(against $H_1: \lambda_0=$)', lambda1))
        pred.SS = prediction(theoretical_results_SS,SS_obtained)
        pred.LS = prediction(theoretical_results_LS,LS_obtained)
        perf.SS = performance(pred.SS,"tpr", "fpr")
        perf.LS = performance(pred.LS,"tpr", "fpr")
        #plot(perf.SS, lty=1, col="coral")
        par(new=T)
        #plot(perf.LS, lty=2, col="coral", main=title_ROC)
        cat("-----------------------------------\n")
        
        
        result <- c('performance.SS'= perf.SS,'performance.LS'= perf.LS)
        return(result)
    }
}
```

```{r}
NbSeq = 100
T = 10
tau = 2
lambda0 = 0.3
lambda1 = 0.5

result1 = CompareMethods(lambda0, lambda1, NbSeq, T, tau)

lambda0 = 0.01
lambda1 = 1

result2 = CompareMethods(lambda0, lambda1, NbSeq, T, tau)

lambda0 = 1
lambda1 = 1.1

result3 = CompareMethods(lambda0, lambda1, NbSeq, T, tau)


lambda0 = 0.9
lambda1 = 2

result4 = CompareMethods(lambda0, lambda1, NbSeq, T, tau)


title_ROC = TeX(paste(r'(ROC curve for several values of $\lambda_0$ and $\lambda_1$)'))

perf1SS = result1[1]
perf1LS = result1[2]
                
perf2SS = result2[1]
perf2LS = result2[2]

perf3SS = result3[1]
perf3LS = result3[2]

perf4SS = result4[1]
perf4LS = result4[2]


plot(perf1SS$performance.SS, lty=1, col="coral", lwd = 2)
par(new=T)
plot(perf1LS$performance.LS, lty=2, col="coral",lwd = 2)

par(new=T)
plot(perf2SS$performance.SS, lty=1, col="cyan4", lwd = 2)
par(new=T)
plot(perf2LS$performance.LS, lty=2, col="cyan4", lwd = 2)

par(new=T)
plot(perf3SS$performance.SS, lty=1, col="magenta4", lwd = 2)
par(new=T)
plot(perf3LS$performance.LS, lty=2, col="magenta4", lwd = 2)

par(new=T)
plot(perf4SS$performance.SS, lty=1, col="olivedrab4", lwd = 2)
par(new=T)
plot(perf4LS$performance.LS, lty=2, col="olivedrab4", lwd = 2,main=title_ROC)

legend(0.5, 0.3, legend=c("lambda0 = 0.3, lambda1 = 0.5", "lambda0 = 1, lambda1 = 9", "lambda0 = 2, lambda1 = 6", "lambda0 = 8, lambda1 = 9", "lambda0 = 0.1, lambda1 = 0.2")
       ,col=c("coral", "cyan4", "magenta4", "olivedrab4", "lightgoldenrod3"),  lty=1, cex=0.9,lwd=4,
       box.lty=0)
```