我正在构建一个有偏差的相关随机游走,我已经设法构建RW,并将其偏向西方运动.
问题:我需要将步行绑定在一个(或所有)侧面.
目前的代码是:
walk<-function(n.times){
plot(524058:542800,2799758:2818500,type="n",
xlab="Easting",ylab="Northing")#aren??a
y<-2815550 ##startY
x<-542800 #startX
N<-4000
E<-4000
points(x,y,pch=16,col="red",cex=1)
for (i in 1:n.times) {
yi <- sample(c(N,N/2,N/4,N/8,N/12,N/16,
0,-N,-N/2,-N/4,-N/8,-N/12,-N/16),1)
xi<-sample(c(E,E/12,E/16, 0,-E,-E/2,-E/4,-E/8,-E/12,-E/16),1)
lines(c(x,x+xi),c(y,y+yi),col="blue")
x<-x+xi
y<-y+yi
}
}
iterations<-125
walk(iterations)
Run Code Online (Sandbox Code Playgroud)
到目前为止,我最接近的是使用
if(y>2818500 | y<2799758 | x>542800 | x<524058) break
Run Code Online (Sandbox Code Playgroud)
如果它离开竞技场,它就会停止行走.
一个略微清理的函数版本:主要的变化是添加一个repeat {}循环,重新选择步骤,直到新位置在限制范围内(也可以使用while() {}循环).
更新:没有仔细阅读问题陈述,忘了偏见.该代码以与OP代码相同的方式包含偏差.对于NS运动,平均步长为0; 对于EW运动,通过省略一些积极的步骤可能性,我们得到mean(steps.x)等于-0.0875; 由于步进可能性是均匀采样的,因此步行向左漂移0.0875*stepsize[1]每步的平均单位.
walk <- function(n.times=125,
xlim=c(524058,542800),
ylim=c(2799758,2818500),
start=c(542800,2815550),
stepsize=c(4000,4000)) {
## blank plot of arena
plot(c(0,0),type="n",xlim=xlim,ylim=ylim,
xlab="Easting",ylab="Northing")
## extract starting point
x <- start[1]
y <- start[2]
## define potential step sizes
steps <- 1/c(1,2,4,8,12,16)
## all possible positive or negative steps for N-S movement
steps.y <- c(steps,-steps,0)
## bias E-W movement by leaving out some positive steps
steps.x <- c(steps[c(1,5,6)],-steps,0)
## plot starting location
points(x,y,pch=16,col="red",cex=1)
for (i in 1:n.times) {
repeat {
## pick jump sizes
xi <- stepsize[1]*sample(steps.x,1)
yi <- stepsize[2]*sample(steps.y,1)
## new candidate locations
newx <- x+xi
newy <- y+yi
## IF new locations are within bounds, then
## break out of the repeat{} loop (otherwise
## try again)
if (newx>xlim[1] && newx<xlim[2] &&
newy>ylim[1] && newy<ylim[2]) break
}
lines(c(x,newx),c(y,newy),col="blue") ## draw move
## set new location to candidate location
x <- newx
y <- newy
}
}
set.seed(101)
walk(1000)
Run Code Online (Sandbox Code Playgroud)
