##1
NTtoUS <- function(){
money <- readline(prompt = " NT$ :")
cat("$", as.numeric(money)/29.32, " US dollars\n", sep = "")
}
NTtoUS()
## NT$ :
## $NA US dollars
##2
dta2 <- ChickWeight
sapply(split(dta2, dta2$Chick),
function(x) lm(weight ~ Time, data = x)$coef)
## 18 16 15 13 9 20 10
## (Intercept) 39 43.392857 46.83333 43.384359 52.094086 37.667826 38.695054
## Time -2 1.053571 1.89881 2.239601 2.663137 3.732718 4.066102
## 8 17 19 4 6 11
## (Intercept) 43.727273 43.030706 31.21222 32.86568 44.123431 47.921948
## Time 4.827273 4.531538 5.08743 6.08864 6.378006 7.510967
## 3 1 12 2 5 14
## (Intercept) 23.17955 24.465436 21.939797 24.724853 16.89563 20.52488
## Time 8.48737 7.987899 8.440629 8.719861 10.05536 11.98245
## 7 24 30 22 23 27
## (Intercept) 5.842535 53.067766 39.109666 40.082590 38.428074 29.858569
## Time 13.205264 1.207533 5.898351 5.877931 6.685978 7.379368
## 28 26 25 29 21 33
## (Intercept) 23.984874 20.70715 19.65119 5.882771 15.56330 45.830283
## Time 9.703676 10.10316 11.30676 12.453487 15.47512 5.855241
## 37 36 31 39 38 32
## (Intercept) 29.608834 25.85403 19.13099 17.03661 10.67282 13.69173
## Time 6.677053 9.99047 10.02617 10.73710 12.06051 13.18091
## 40 34 35 44 45 43
## (Intercept) 10.83830 5.081682 4.757979 44.909091 35.673121 52.185751
## Time 13.44229 15.000151 17.258811 6.354545 7.686432 8.318863
## 41 47 49 46 50 42
## (Intercept) 39.337922 36.489790 31.662986 27.771744 23.78218 19.86507
## Time 8.159885 8.374981 9.717894 9.738466 11.33293 11.83679
## 48
## (Intercept) 7.947663
## Time 13.714718
##3
t2z <- function(df){
curve(dnorm(x), -4, 4, col = 2, ylab = "dnorm(x)", lwd = 2)
for(i in 1:length(df)) curve(dt(x, df[[i]]), col = 3, lty = 2, add = TRUE)
}
t2z(df = 1:32)
##4
library(pacman)
## Warning: package 'pacman' was built under R version 3.4.4
pacman::p_load(MASS, tidyverse)
## method 1, dataframe, 簡單易懂
a <-
aggregate( . ~ Type, data = Cushings, mean)
## method 2, 形式為矩陣，輸出為數值
b <-
sapply(split(Cushings[,-3], Cushings$Type),
function(x) apply(x, 2, mean))
## method 3, matrix, long format
c <-
do.call("rbind", as.list(
by(Cushings, list(Cushings$Type), function(x) {
y <- subset(x, select = -Type)
apply(y, 2, mean)
}
)))
## method 4, tibble, 語法易懂，輸出為list
d <-
Cushings %>%
group_by(Type) %>%
summarize( t_m = mean(Tetrahydrocortisone), p_m = mean(Pregnanetriol))
## method 5, tibble, 在更改資料的同時保留了原本的data
e <-
Cushings %>%
nest(-Type) %>%
mutate(avg = map(data, ~ apply(., 2, mean)),
res_1 = map_dbl(avg, "Tetrahydrocortisone"),
res_2 = map_dbl(avg, "Pregnanetriol"))
## 檢視屬性
lapply(list(a, b, c, d, e), function(x) cbind(attributes(x), class(x)))
## [[1]]
## [,1] [,2]
## names Character,3 "data.frame"
## row.names Integer,4 "data.frame"
## class "data.frame" "data.frame"
##
## [[2]]
## [,1] [,2]
## dim Integer,2 "matrix"
## dimnames List,2 "matrix"
##
## [[3]]
## [,1] [,2]
## dim Integer,2 "matrix"
## dimnames List,2 "matrix"
##
## [[4]]
## [,1] [,2]
## class Character,3 "tbl_df"
## names Character,3 "tbl"
## row.names Integer,4 "data.frame"
##
## [[5]]
## [,1] [,2]
## names Character,5 "tbl_df"
## class Character,3 "tbl"
## row.names Integer,4 "data.frame"
##5
lawLN <- function(n, mu, s){
set.seed(0221)
random.sample <- rnorm(n, mu, s)
plot(x = 1:n, y = cumsum(random.sample)/1:n, type = "l", col = 3,
xlab = "Sample Size", ylab = "Running Average")
abline(h = mu, col = 2, lty = 2)
grid()
}
lawLN(4000, 100, 10)
##6
dta6 <- read.table("cstat.txt", header = TRUE)
# function
c.stat <- function(data, n = length(data)){
cden <- 1-(sum(diff(dta6[1:n,1])^2)/(2*(n-1)*var(dta6[1:n,1])))
sc <- sqrt((n-2)/((n-1)*(n+1)))
pval <- 1-pnorm(cden/sc)
return(list(c = cden, z = cden/sc, pvalue = pval))
}
# run
c.stat(dta6, 42)
## $c
## [1] 0.6450652
##
## $z
## [1] 4.282524
##
## $pvalue
## [1] 9.239272e-06
##7
library(rgl)
## Warning: package 'rgl' was built under R version 3.4.4
# read the math score in the high school data set
hsdata = read.table("hs0.txt", header=TRUE) # read text file
math_score <- hsdata$math
# define ssq and vssq functions
ssq <- function(mu, sigma, y) {sum(((y - mu) / sigma)^2)}
vssq <- Vectorize(ssq, c("mu", "sigma"))
# find minimun of the ssq and the sigma
math_mu = sum(math_score)/length(math_score)
math_sigma = sqrt(sum((math_score - math_mu)^2) / (length(math_score) - 1))
math_ssq = ssq(math_mu, math_sigma, math_score)
# calculate ssq for several mu and sigma
my_mu <- seq(math_mu - 5, math_mu + 5,by=0.2)
my_sigma <- math_sigma
vssq_result <- vssq(my_mu, my_sigma, math_score)
# visualized
open3d()
## wgl
## 1
plot3d(my_mu, my_sigma, vssq_result,
xlab = "mu", ylab = "sigma", zlab = "ssq",
col = rainbow(length(my_mu)))
# log
cat('The ideal minimum of ssq is ', math_ssq, '.\n', sep='')
## The ideal minimum of ssq is 199.
cat('The minimum in vssq is ', min(vssq_result), '.', sep='')
## The minimum in vssq is 199.