[R] [Johns Hopkins] R Programming -- week 4

#Generating normal distribution (Pseudo) random number
x<-rnorm(10)
x

x2<-rnorm(10,2,1)
x2

set.seed()
#Generating Poisson data

rpois(10,1)
rpois(10,2)
rpois(10,20)

ppois(2,2) #Cumulative distribution ##P r(x <= 2) 平均發生率為2
ppois(4,2) #Cumulative distribution ##P r(x <= 4) 平均發生率為4

#線性 y = B0+B1X+e
#e~N(0,2^2) 標準差為2正態分布
#assume x~N(0,1^2)  B0=o.5  B1=2
set.seed(20)
x <- rnorm(100)
e <- rnorm(100,0,2)
y <- 0.5 + 2 * x + e
summary(y)
plot(x,y)

# 若x為binary ex性別
set.seed(20)
x <- rbinom(100,1,0.5)   #得到1的機率為0.5
e <- rnorm(100,0,2)
y <- 0.5 + 2 * x + e
summary(y)
plot(x,y)

#廣義線性模組可能服從poisson分布 Y~Poisson(m)
#log mu = B0 + B1X       #log mu 服從線性
#B0 = 0.5  B1 =0.3       #y服從 平均值為mu 的 PD
set.seed(20)
x <- rnorm(100)
log.mu <- 0.5 + 0.3 * x
y <- rpois(100,exp(log.mu))
summary(y)
plot(x,y)

# sample(range vector, numbers)
# sample(range vector)  重新排列
# sample(range vector, replace = T)  重複性抽樣

#Profiler   profiling is better than guessing
#Premature optimization is the root of all evil
system.time()   #proc_time  (class)
#user time: time charged to the CPU(s) for this expression
#elapsed time: "wall clock" time 運行時間
#parallel processing via  parallel package

##elapsed time > user time
system.time(readlines("http://www.google.com"))

#elapsed time < user time
hilbert <- function(n){
  i <- 1:n
  1/outer(i -1, i, "+")
}
x <- hilbert(1000)
system.time(svd(x))    # svd 多線程線性代數