R Language Learn Notes

One

#install package
install.packages("ggplot2")

#load library
library(ggplot2)
#update.packages()

#vector
v=c(1,4,4,3,2,2,3)
#get vector elements, index is 2,3,4
v[c(2,3,4)]
#get vector elements, index range is 2 to 4
v[2:4]
#get vector elements, index is 2,4,3
v[c(2,4,3)]
#delete vector elements index is 2
v[-2]
#delete vector elements index range is 2 to 4
v[-2:-4]
#get vector elements, which value < 3
v[v<3]
#get vector elements index, which value = 3
which(v==3)
#get vector max element index
which.max(v)
#get vector min element index
which.min(v)

#get random values
set.seed(250)
a=runif(3,min = 0, max = 100)

floor(a)
ceiling(a)
round(a, 3)

#read data from file
data1=read.table(file = "/Users/hwgt/workspace/Rlang/data_1.txt", header = TRUE)
#header to variable
attach(data1)

#draw
set.seed(123)
x=rnorm(100, mean = 100, sd = 10)
set.seed(234)
y=rnorm(100, mean = 100, sd = 10)
hist(x, breaks = 20)
plot(density(x))
plot(x)
boxplot(x, y)
boxplot(yage)
qqnorm(x)
qqline(x)
qqplot(x, y)

Two

# vector
a = c(1, 2, 3, 4, 5)
b = c("one", "two", "three")
c = c(TRUE, FALSE)

# matrix
x = matrix(1:20, nrow = 5, ncol = 4, byrow = TRUE)
x
y = matrix(1:20, nrow = 5, ncol = 4, byrow = FALSE)
y

x[2,]
x[,2]
x[1,4]
x[2,c(2,4)]
x[3:5,2]

rnames = c("apple", "banana", "orange", "melon", "corn")
cnames = c("cat", "dog", "bird", "pig")
m = matrix(1:20, 5, 4, TRUE)
rownames(m) = rnames
colnames(m) = cnames
m

dim1 = c("A1", "A2")
dim2 = c("B1", "B2", "B3")
dim3 = c("C1", "C2", "C3", "C4")
dim4 = c("D1", "D2", "D3")
z = array(1:72, c(2,3,4,3), dimnames = list(dim1, dim2, dim3, dim4))
z
z[1,2,3,]

# data frame
patientID = c(1,2,3,4)
age = c(25,26,27,28)
diabetes = c("Type1", "Type2", "Type1", "Type2")
status = c("Poor", "Improved", "Excellent", "Poor")
patientData = data.frame(patientID, age, diabetes, status)
patientData

# list
listData = list(patientData, x)
listData[1]
listData[2]

# graphs
par(mfrow=c(2,2))
plot(rnorm(50), pch=17)
plot(rnorm(20), type="l", lty=5)
plot(rnorm(100), cex=0.5)
plot(rnorm(200), lwd=2)

Three

# operator

# control flow
# for loop
for(a in 1:10) {
  print(a)
}

# while loop
i = 1
while(i <= 10) {
  print(i)
  i = i + 1
}

# if
i = 2
if (i == 1) {
  print("hello r")
} else if(i == 2){
  print("goodbye r")
} else {
  print("good r")
}

# switch
feelings = c("sad", "afraid")
for(i in feelings) {
  print(
    switch(i,
           a = "a",
           sad = "b",
           c = "c",
           afraid = "d",
           e = "e")
  )
}
# function
numSum = function(a, b) {
  return(a + b)
}
print(numSum(1,2))

Four

# Bar Chart
#install.packages("vcd")
library(vcd)
counts = table(Arthritis$Improved)
counts
par(mfrow=c(2,2))

barplot(counts,
        main="Simple Bar Plot",
        xlab = "Improvement",
        ylab = "Frequency")

barplot(counts,
        main="Horizontal Bar Plot",
        xlab = "Frequency",
        ylab = "Improvement",
        horiz = TRUE)

counts <- table(Arthritis$Improved, Arthritis$Treatment)
counts

barplot(counts,
        main="Stacked Bar Plot",
        xlab = "Treatment",
        ylab = "Frequency",
        col = c("red", "yellow", "green"),
        legend = rownames(counts))

barplot(counts,
        main="Grouped Bar Plot",
        xlab = "Treatment",
        ylab = "Frequency",
        col = c("red", "yellow", "green"),
        legend = rownames(counts),
        beside = TRUE)

# Pie Chart
#install.packages("plotrix")
library(plotrix)
par(mfrow=c(2,2))
slices <- c(10,12,4,16,8)
lbls <- c("US", "UK", "AU", "GE", "FR")
pie(slices, lbls, main = "Simple Pie Chart", edges = 300, radius = 1)

pct <- round(slices/sum(slices)*100)
lbls2 <- paste(lbls, " ", pct, "%", sep = " ")
pie(slices, lbls2, main = "Simple Pie Chart With Progress", edges = 300, radius = 1)

pie3D(slices,labels =  lbls, explode = 0.1, main = "3D Pie Chart", edges = 300, radius = 1)

# Fan Plot
slices3 = c(10, 12, 4, 16, 8)
lbls3 = c("US", "UK", "DE", "KR", "CN")
fan.plot(slices3, labels = lbls3, main = "Fan Plot")

# Dot Chart
dotchart(mtcars$mpg, labels = row.names(mtcars), cex = 0.7,main = "Dot Chart", xlab = "Miles Per Gallon")

# Summary
head(mtcars)
summary(mtcars)

# Tables
attach(mtcars)
table(cyl)
summary(mpg)
table(cut(mpg, seq(10, 34, by=2)))

# Correlations
states = state.x77[, 1:6]
cov(states)
var(states)
cor(states)

# T Test
x = rnorm(100, mean = 0, sd = 1)
y = rnorm(100, mean = 30, sd = 1)
t.test(x, y, alt="two.sided", paired = TRUE)

# Wilcoxon
wilcox.test(x, y, alt="less")