#LESSON 2 (DESCRIPTIVE STATISTICS) (29/03/2021)

#Calling Library
library(ISwR)
attach(thuesen)
thuesen
help(package="ISwR")
intake
intake.pre<-c(5260, 5470, 5640, 6180, 6390, 6515, 6815, 7515, 7515, 8230, 8770)
intake.post<-c(3910, 4220, 3885, 5160, 5645, 4680, 5265, 5975, 6790, 6900, 7335)
d<-data.frame(intake.pre, intake.post)
d
d$intake.pre
d$intake.post
intake.pre[5]
intake.pre[1:5]
intake.post[intake.pre>7000]

help(package="ISwR")
data(thuesen)
thuesen
thue2<-subset(thuesen, blood.glucose<7)
thue2
data(energy)
energy
exp.lean<-energy$expend[energy$stature=="lean"]
exp.obese<-energy$expend[energy$stature=="obese"]
l<-split(energy$expend, energy$stature)
l

#Sampling
sample(1:40, 5)

#Generating numbers from Normal Distrubiton
rnorm(100)
x<-rnorm(100)

#Histogram
hist(x, freq=F)
curve(dnorm(x), add=T)

w<-rnorm(100)
hist(w, freq=F)
curve(dnorm(w), add=T)
curve(dnorm(w), add=T)

#Boxplot
x<-rnorm(100)
boxplot(x)

#DESCRIPTIVE STATISTICS
weight<-c(60, 72, 57, 90, 95, 72)

mean(weight)

(60+72+57+90+95+72)/6

median(weight)
quantile(weight)
sd(weight)

15.42293*15.42293

var(weight)

table(weight)
max(table(weight))
name(sort(table(weight)))
names(sort(table(weight)))

x<-rnorm(50)
x
mean(x)
sd(x)
v<-rnorm(1000)
mean(v)
sd(v)
min(v)
g<-rnorm(5000)
g
mean(g)
mean(v)
sd(g)
quantile(g)

library(ISwR)
help(package="ISwR")

data(juul)
juul
attach(juul)

mean(igf1)
mean(igf1, na.rm=T)
summary(igf1)
summary(juul)
boxplot(igf1)
summary(juul)

juul
help(package="ISwR")
detach(juul)

juul$sex<-factor(juul$sex, labels=c("M", "F"))
juul$menarche<-factor(juul$menarche, labels=c("No", "Yes"))
juul$tanner<-factor(juul$tanner, labels=c("I", "II", "III", "IV", "V"))

attach(juul)
summary(juul)

juul<-transform(juul, sex=factor(sex, labels=c("M", "F")), menarche=factor(menarche, labels=c("No", "Yes")), tanner=factor(tanner, labels=c("I", "II", "III", "IV", "V")))
summary(juul)