Rcmdr.kr: An R Commander User in Korea

도움말 > 활성 데이터셋에 대한 도움말 (만약 이용가능하다면)

Help > Help on active data set (if available)

R에는 많은 패키지가 있으며, 그 패키지에는 많은 경우 데이터셋을 포함하고 있다. 그 데이터셋에 대한 도움말을 볼 수 있는 기능이다. 생각해보라. 예제 데이터셋을 통하여 함수를 연습하는데, 데이터셋의 특성을 알지 못한다면 분석과 시각화에 필요한 통찰력을 얻을 수 있겠는가.

위의 화면은 MASS 패키지가 적재되었고, 또 그 안에 포함된 housing 이라는 데이터셋이 활성화된 상태에서 '도움말 > 활성 데이터셋에 관한 도움말 (만약 이용가능하다면)' 메뉴 기능을 이용할 수 있다는 것이다. 해당 메뉴를 선택하면, 새로운 웹 브라우저 창이 등장하면서, 활성 데이터셋의 도움말이 제공될 것이다.

help("housing")  # housing 데이터셋 도움말 보기
?housing         # housing 데이터셋 도움말 보기 (? 활용)

MASS::housing()

require(MASS)
?housing  # housing 데이터셋 도움말 보기

# 아래는 example(housing) 입니다.

options(contrasts = c("contr.treatment", "contr.poly"))

# Surrogate Poisson models
house.glm0 <- glm(Freq ~ Infl*Type*Cont + Sat, family = poisson,
                  data = housing)
## IGNORE_RDIFF_BEGIN
summary(house.glm0, cor = FALSE)
## IGNORE_RDIFF_END

addterm(house.glm0, ~. + Sat:(Infl+Type+Cont), test = "Chisq")

house.glm1 <- update(house.glm0, . ~ . + Sat*(Infl+Type+Cont))
summary(house.glm1, cor = FALSE)

1 - pchisq(deviance(house.glm1), house.glm1$df.residual)

dropterm(house.glm1, test = "Chisq")

addterm(house.glm1, ~. + Sat:(Infl+Type+Cont)^2, test  =  "Chisq")

hnames <- lapply(housing[, -5], levels) # omit Freq
newData <- expand.grid(hnames)
newData$Sat <- ordered(newData$Sat)
house.pm <- predict(house.glm1, newData,
                    type = "response")  # poisson means
house.pm <- matrix(house.pm, ncol = 3, byrow = TRUE,
                   dimnames = list(NULL, hnames[[1]]))
house.pr <- house.pm/drop(house.pm %*% rep(1, 3))
cbind(expand.grid(hnames[-1]), round(house.pr, 2))

# Iterative proportional scaling
loglm(Freq ~ Infl*Type*Cont + Sat*(Infl+Type+Cont), data = housing)


# multinomial model
library(nnet)
(house.mult<- multinom(Sat ~ Infl + Type + Cont, weights = Freq,
                       data = housing))
house.mult2 <- multinom(Sat ~ Infl*Type*Cont, weights = Freq,
                        data = housing)
anova(house.mult, house.mult2)

house.pm <- predict(house.mult, expand.grid(hnames[-1]), type = "probs")
cbind(expand.grid(hnames[-1]), round(house.pm, 2))

# proportional odds model
house.cpr <- apply(house.pr, 1, cumsum)
logit <- function(x) log(x/(1-x))
house.ld <- logit(house.cpr[2, ]) - logit(house.cpr[1, ])
(ratio <- sort(drop(house.ld)))
mean(ratio)

(house.plr <- polr(Sat ~ Infl + Type + Cont,
                   data = housing, weights = Freq))

house.pr1 <- predict(house.plr, expand.grid(hnames[-1]), type = "probs")
cbind(expand.grid(hnames[-1]), round(house.pr1, 2))

Fr <- matrix(housing$Freq, ncol  =  3, byrow = TRUE)
2*sum(Fr*log(house.pr/house.pr1))

house.plr2 <- stepAIC(house.plr, ~.^2)
house.plr2$anova

house.glm0 <- glm(Freq ~ Infl*Type*Cont + Sat, family = poisson, data = housing)
summary(house.glm0, cor = FALSE)

house.glm1 <- update(house.glm0, . ~ . + Sat*(Infl+Type+Cont))
summary(house.glm1, cor = FALSE)

# multinomial model
library(nnet)
house.mult<- multinom(Sat ~ Infl + Type + Cont, weights = Freq,
                       data = housing)
house.mult2 <- multinom(Sat ~ Infl*Type*Cont, weights = Freq,
                        data = housing)
anova(house.mult, house.mult2)
Anova(house.mult2, type="II")

house.plr <- polr(Sat ~ Infl + Type + Cont,
                   data = housing, weights = Freq)
house.plr2 <- stepAIC(house.plr, ~.^2)
house.plr2$anova

lme4::sleepstudy()

require(lme4)
?sleepstudy  # sleepstudy 데이터셋 도움말 보기

아래는 example(sleepstudy) 입니다.

str(sleepstudy)
require(lattice)
xyplot(Reaction ~ Days | Subject, sleepstudy, type = c("g","p","r"),
       index = function(x,y) coef(lm(y ~ x))[1],
       xlab = "Days of sleep deprivation",
       ylab = "Average reaction time (ms)", aspect = "xy")
(fm1 <- lmer(Reaction ~ Days + (Days|Subject), sleepstudy))
(fm2 <- lmer(Reaction ~ Days + (1|Subject) + (0+Days|Subject), sleepstudy))

fm1 <- lmer(Reaction ~ Days + (Days|Subject), sleepstudy)
fm2 <- lmer(Reaction ~ Days + (1|Subject) + (0+Days|Subject), sleepstudy)

datasets::swiss()

?swiss  # swiss 데이터셋 도움말 보기

# 아래는 example(swiss) 입니다.

require(stats); require(graphics)
pairs(swiss, panel = panel.smooth, main = "swiss data",
      col = 3 + (swiss$Catholic > 50))
summary(lm(Fertility ~ . , data = swiss))

pairs(swiss, panel = panel.smooth, main = "swiss data",
      col = 3 + (swiss$Catholic > 50))

pairs(swiss, panel = panel.smooth, main = "swiss data")  # 두 그래프를 비교해 보기

LinearModel.1 <- lm(Fertility ~ . , data = swiss)
summary(LinearModel.1)

datasets::warpbreaks

?warpbreaks  # warpbreaks 도움말 보기

# 아래는 example(warpbreaks) 입니다.

require(stats); require(graphics)
summary(warpbreaks)
opar <- par(mfrow = c(1, 2), oma = c(0, 0, 1.1, 0))
plot(breaks ~ tension, data = warpbreaks, col = "lightgray",
     varwidth = TRUE, subset = wool == "A", main = "Wool A")
plot(breaks ~ tension, data = warpbreaks, col = "lightgray",
     varwidth = TRUE, subset = wool == "B", main = "Wool B")
mtext("warpbreaks data", side = 3, outer = TRUE)
par(opar)
summary(fm1 <- lm(breaks ~ wool*tension, data = warpbreaks))
anova(fm1)

datasets::USArrests()

?USArrests  # USArrests 데이터셋 도움말 보기

# 아래는 example(USArrests) 입니다.

summary(USArrests)

require(graphics)
pairs(USArrests, panel = panel.smooth, main = "USArrests data")

## Difference between 'USArrests' and its correction
USArrests["Maryland", "UrbanPop"] # 67 -- the transcription error
UA.C <- USArrests
UA.C["Maryland", "UrbanPop"] <- 76.6

## also +/- 0.5 to restore the original  <n>.5  percentages
s5u <- c("Colorado", "Florida", "Mississippi", "Wyoming")
s5d <- c("Nebraska", "Pennsylvania")
UA.C[s5u, "UrbanPop"] <- UA.C[s5u, "UrbanPop"] + 0.5
UA.C[s5d, "UrbanPop"] <- UA.C[s5d, "UrbanPop"] - 0.5

# USArrests 원자료를 수정한 UA.C 데이터셋

pairs(UA.C, panel = panel.smooth, main = "USArrests data (corrected)")

datasets::sleep()

?sleep #sleep 데이터셋 도움말 보기

# 아래는 example(sleep) 입니다.

require(stats)
## Student's paired t-test
with(sleep,
     t.test(extra[group == 1],
            extra[group == 2], paired = TRUE))

## The sleep *prolongations*
sleep1 <- with(sleep, extra[group == 2] - extra[group == 1])
summary(sleep1)
stripchart(sleep1, method = "stack", xlab = "hours",
           main = "Sleep prolongation (n = 10)")
boxplot(sleep1, horizontal = TRUE, add = TRUE,
        at = .6, pars = list(boxwex = 0.5, staplewex = 0.25))

datasets::airquality()

?airquality # airquality 데이터셋 도움말 보기

# 아래는 example(airquality) 입니다.

require(graphics)
pairs(airquality, panel = panel.smooth, main = "airquality data")

carData::OBrienKaiserLong()

?OBrienKaiserLong # OBrienKaiserLong 데이터셋 도움말 보기

# 아래는 example(OBrienKaiserLong) 입니다.

head(OBrienKaiserLong, 15) # first subject

carData::OBrienKaiser()

?OBrienKaiser # OBrienKaiser 대이터셋 도움말 보기

# 아래는 example(OBrienKaiser) 입니다.

OBrienKaiser
contrasts(OBrienKaiser$treatment)
contrasts(OBrienKaiser$gender)