R language data analysis

Overview of R language and data analysis

R language is an open source scripting language, born in 1993, R system is open source and free.
Data analysis process:
data import-data cleaning-data exploration-data modeling-visualization-report discovery

Basic operation commands

Note: write the package name at *

function	Description
getwed()	Show current working directory
set ()	Modify the current working directory
ls ()	Show all objects in the current workspace
str ()	Display object structure
ls.str ()	Display the structure of each variable in the object
exists ()	Whether there is an object in the current workspace
rm ()	Delete one or more objects
q ()	Exit R. Before this will ask whether to save the workspace
.libPaths ()	View the specific path of the folder in the computer
install.packages ()	Installation package
library ()	Display the list of installed packages
search()	Display the list of loaded packages
library("*")	Load this package
detach(“packages:*”)	Remove package
remove.packages(“*”)	Uninstall package

Basic data type

Types of	Description	Judgment function	R language form
Logical	The binary data that represents the logical value has only two values, TRUE or FALSE. In R, the assignment of logical expressions will result in logical data, such as comparing the size of two numbers 2>1 equals TRUE	is.logocal()	TRUE ， 2 <= 1
Floating point	Real numbers expressed in decimal, such as 1, 1.1, etc., are the basic data form used for calculation	is.double ()	3.14
Integer	Used to describe integers, such as 1, 2, 3. It should be noted that in the R language, the character L is added after the integer to represent the integer, otherwise it will be regarded as a floating point	is.integer()	3L
Character type	Used to represent a string	is.character ()	“Hello”,“3.14”
Plural	Used to represent complex values, where the imaginary part is represented by i, for example 2+3i	is.complex ()	1+i
Primitive	Used to save the original bytes, where each byte is represented by two hexadecimal numbers, such as A3	is.raw ()	00

Data type conversion

Logical type-integer type-floating point type-character type

Operator

Data structure in R

➢ Vector ➢ Matrix ➢ Array ➢ List ➢ Data frame ➢ Factor
Vector function:
✓Create vector
✓Access element
✓Add element
✓Delete element
✓Get vector length

Code display

#基本数据类型
getwd()

install.packages("stringr")
.libPaths()
library()
search()
library("stringr")
str_length ("Hello R!")

detach("package:stringr")
str_length ("Hello R!")

remove.packages("stringr")
library("stringr")


#基本数据类型
num <- 100;num
is.integer(num)#?
is.double(num)#?
typeof(num)
num2 <- 100L
typeof(num2)


is.logical(TRUE)
is.logical(T)
is.logical(5)#?
is.logical(0)#?
is.character("R program")



#数据类型转换
logi_vec <- T
typeof(logi_vec)
int_vec <- c(100L,200L)
typeof(int_vec)
double_vec <- c(10,20)
typeof(double_vec)
chr_vec <-c("伟大的","中国人民")
typeof(chr_vec)
typeof(c(logi_vec,int_vec))#?验证逻辑型和整数型
typeof(c(int_vec,double_vec))#?验证逻辑型和整数型
typeof(c(double_vec,chr_vec))#?验证逻辑型和整数型
typeof(c(logi_vec,int_vec,double_vec,chr_vec))#?验证逻辑型和整数型

1 == '1' 



#在运算过程中，数据类型自动转换
2*T  #？
10+FALSE #？
10+TRUE
exp(F) #？
10 & 0 #？
10 | 0 #？


#使用as***函数强制转换数据类型
as.numeric(F)
as.numeric("1000.01")
as.numeric("你好")
as.logical(0)
as.logical(10)
as.logical(-10)
as.logical("T")
as.logical("F")
as.character(c(T,F,TRUE,FALSE))
as.character(10.99)



#特殊值
#NA
a <- 100
a[1]
a[2]
num_vec <- c(1,2)
length(num_vec) <- 4
num_vec
#Inf 无穷大
10/0
-10/0

0/0
Inf-Inf

num_vec1 <- c(1,5,NaN)
length(num_vec1)
num_vec2 <- c(1,5,NULL)
length(num_vec2)


#运算符
#逻辑运算 & vs &&
logi_vec1 <- c(T,F,T)
logi_vec2 <- c(F,T,T)
logi_vec1 & logi_vec2
logi_vec1 && logi_vec2

logi_vec1 <- c(T,F,T) #向量长度不同，短的循环补齐
logi_vec2 <- c(T,T,T,F)
logi_vec1 & logi_vec2
logi_vec1 && logi_vec2


logi_vec1 <- c(T,F,T)

#逻辑运算| vs ||
logi_vec1 <- c(T,F,T)
logi_vec2 <- c(F,T,T)
logi_vec1 | logi_vec2
logi_vec1  || logi_vec2


a <-T
b <- 10L
c <- 20
d <-"R";
typeof(c(a,b,c,d))



#向量
vec <- c(1,5,6,8,9)

#访问元素
vec[1]
vec[0]
vec[2:3]
vec[2:5]
vec[c(1,3)]#访问不连续的怎么办
vec[c(1,3,2)] #想重复访问
#添加元素
vec
vec <- c(vec[1:2],10,vec[3])
vec
#删除元素
vec
vec <-vec[-3]
vec
#获取向量长度
vec <- letters
vec
length(vec)
vec[-length(vec)] #删除x,y,z怎么做？
vec[-length(vec):-length(vec)+2]
-length(vec):-length(vec)+2#注意加括号
-length(vec):(-length(vec)+2)
vec[-length(vec) : (-length(vec)+2)]

#创建向量
#Q：创建向量的方法
1:5
1:-5
c(1L,2.0,"a")
67#1，3，5，7，9，创建等差数列
?seq
example(seq)
seq(1,9,by =2)

#将某向量重复多次，创建向量
vec <-1:3
#1 2 3 1 2 3 1 2 3 
?rep
example(rep)
rep(vec,3)
#111222333
rep(vec,each = 3)
#创建长度为0的向量
new.vec <- c()
length(new.vec)
new.vec
#判断某班级的学生的年龄是不是都是18岁以上？
stu <- sample(c(17,18,19),10,replace = T)
stu
all(stu >= 18)
stu <- sample(c(18,19),10,replace = T)
stu
any(stu<18)

#any all 你想想可以应用到什么场景中？

#向量运算，算术运算，关运算，逻辑运算
vec1 <- c(1,2)
vec2<- c(10,20)
vec1 * vec2
vec1 == vec2
vec | vec2

#向量运算–循环补齐
vec1 <- c (1,2)
vec2<-c (10,20,30)
vec1 + vec2
vec2<- c(10,20,30,40)
vec1 + vec2

Doraemon welcomes you!