R_basic 01

 class(1.2)numeric

 is.numeric("4")
#FALSE
 is.logical()
 is.charater()
 as.numeric()
 as.logical()
 as.charater()

[1] "normal" "normal" "normal"
 seq(from=3,to=21,by=3)
[1]  3  6  9 12 15 18 21
 rnorm(n=3)
[1]  0.1286680 -0.2964153  1.1241529
 #(4)通过组合,产生更为复杂的向量。
 paste0(rep("x",times=3),"_",1:3)  我不想自己数：1：nrow（a）
[1] "x_1" "x_2" "x_3"
！循环补齐思想
paste0("x",1:3)
[1] "x1" "x2" "x3"

[1] 1 3 5 1
 max(x) #最大值
 min(x) #最小值
 mean(x) #均值
 median(x) #中位数
 var(x) #方差
[1] 3.666667
 sd(x) #标准差
[1] 1.914854
 sum(x) #总和
[1] 10





 length(x) #长度，代表x里面有4个元素
[1] 4
 unique(x) #去重复
[1] 1 3 5
 duplicated(x) #对应元素是否重复   反一下？  ！
[1] FALSE FALSE FALSE  TRUE
 table(x) #重复值统计
x
1 3 5 
2 1 1 
 sort(x,decreasing = F)
[1] 1 1 3 5
 

 x = c(1,3,5,6,2)
 y = c(3,2,5)
 intersect(x,y)
[1] 3 5 2
 union(x,y)  #xy里都有
[1] 1 3 5 6 2
 setdiff(x,y)#   x有y没有
[1] 1 6    #如果取不出来会出现charater（0）错是numeric（0），logical（0）
 setdiff(y,x)
numeric(0)
 
 x %in% y #x的每个元素在y中存在吗
[1] FALSE  TRUE  TRUE FALSE  TRUE
 y %in% x #y的每个元素在x中存在吗
[1] TRUE TRUE TRUE

 c(1,"a") numeric-character    c("1","a")
 c(TRUE,"a") logical-charater    c("TRUE","a")
 c(TRUE,FALSE,4)  loogical-numeric  c(1,0,4)
 

 x <- 8:12;x
[1]  8  9 10 11 12
 x[x %in% c(9,13)]
[1] 9
 x[2:4]
[1]  9 10 11
 x[c(1,5)]
[1]  8 12
 x[-(2:4)]
[1]  8 12
所以所以[]可以取位置
 x==10
[1] FALSE FALSE  TRUE FALSE FALSE
 x<12
[1]  TRUE  TRUE  TRUE  TRUE FALSE
所以所以[]里可以取逻辑值  
 那[]只能取TRUE，我想取FALSE怎么办？全部()起来取！ 
 a
[1]  8  9 10 11 12
 !(a<10)
[1] FALSE FALSE  TRUE  TRUE  TRUE
 a[!(a<10)]
[1] 10 11 12

 k1 = rnorm(12);k1
 [1]  0.25904416  0.89879597  0.27646147
 [4] -0.04203781 -1.30432461 -0.91516370
 [7] -0.29382152  0.29779891  1.03620847
[10]  0.45334718  0.66758764  2.16318875
 k2 = rep(c("a","b","c","d"),each = 3);k2
 [1] "a" "a" "a" "b" "b" "b" "c" "c" "c" "d"
[11] "d" "d"
 plot(k1)
 boxplot(k1~k2) #课后试着搜索boxplot表达什么意思

 str(test)    #好习惯
'data.frame':	15 obs. of  3 variables:
 $ Petal.Length: num  4.6 5.9 4.5 6 4 4.7 1.3 1.4 5.1 5.8 ...
 $ Petal.Width : num  1.5 2.1 1.5 2.5 1.3 1.4 0.2 0.2 1.9 2.2 ...
 $ Species     : chr  "a" "b" "a" "b" ...
 class(test)
[1] "data.frame"


 LETTERS=="M"
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[13]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[25] FALSE FALSE
 which(LETTERS=="M")
[1] 13


如何筛选score>0的值？
 df1 <- data.frame(gene   = paste0("gene",1:4),
+                  change  = rep(c("up","down"),each = 2),
+                  score   = c(5,3,-2,-4))
 df1
   gene change score
1 gene1     up     5
2 gene2     up     3
3 gene3   down    -2
4 gene4   down    -4
 ## 按条件（逻辑值）
 df1[df1$score>0,]
   gene change score
1 gene1     up     5
2 gene2     up     3
如何筛选score>0的基因？
 df1$gene[df1$score>0]
[1] "gene1" "gene2"
 df1[df1$score>0,1]
[1] "gene1" "gene2"



 #如何取数据框的最后一列？
 df1[,3]
[1]  5  3 -2 -4
 df1[,ncol(df1)]
[1]  5  3 -2 -4
 #如何取数据框除了最后一列以外的其他列？
 df1[,-ncol(df1)]
   gene change
1 gene1     up
2 gene2     up
3 gene3   down
4 gene4   down


如何修改行名列名？
 #改行名和列名
 rownames(df1) <- c("r1","r2","r3","r4")
 #只修改某一行/列的名
 colnames(df1)[2] <- "CHANGE"



如何连接两个数据框？
 merge(test1,test3,by.x = "name",by.y = "NAME")
 merge(test1,test3,by.x = "name",by.y = "NAME",all.x = T)
 merge(test1,test3,by.x = "name",by.y = "NAME",all.y  = T)
 merge(test1,test3,by.x = "name",by.y = "NAME",all=T)
    name blood_type weight
1  Damon          O    140
2  jimmy          A    145
3 nicker          B    110
4 Sophie         AB     NA
5   tony       <NA>    138


Matrix
 m <- matrix(1:9, nrow = 3)
 colnames(m) <- c("a","b","c") #加列名
 m
     a b c
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9
 t(m)
  [,1] [,2] [,3]
a    1    2    3
b    4    5    6
c    7    8    9
 as.data.frame(m)
  a b c
1 1 4 7
2 2 5 8
3 3 6 9
 m
     a b c
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9


Matrix取子集
 l <- list(m1=matrix(1:9,nrow = 3),
+           m2=matrix(2:9,nrow = 2))
 l
$m1
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
$m2
     [,1] [,2] [,3] [,4]
[1,]    2    4    6    8
[2,]    3    5    7    9
 l$m2
     [,1] [,2] [,3] [,4]
[1,]    2    4    6    8
[2,]    3    5    7    9

vector添加名字
 scores <- c(100,59,73,95,450)
 names(scores) <- c("a","b","c","d","e")
 scores
  a   b   c   d   e 
100  59  73  95 450 
 scores[c("a","c")]
  a   c 
100  73 
那我就可以通过scores选小孩了
 names(scores)[scores>60]
[1] "a" "c" "d" "e"

 plot(rnorm(10))
 plot(seq(2,80,4))
 plot(iris[,1])
只要前面是numeric就可以画

 plot(iris[,1],col = iris[,5])
 plot(iris[,2],col = iris[,5])
 plot(iris[,3],col = iris[,5])
 plot(iris[,4],col = iris[,5])
根据第五列改颜色

 jimmy <- function(i){
+   plot(iris[,i],col=iris[,5])
+ }
 jimmy(1)
 jimmy(2)
 jimmy(3)
 jimmy(4)

R包安装
	options("repos"=c(CRAN="http://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
	options(BioC_mirror="http://mirrors.ustc.edu.cn/bioc/")
	install.packages()
	biocmanager::install()
	devtools::install_github()

	R包经常提示Update all/some/none?        update=F，ask=F
2.网络限制了你的进步：
	
	
	
	满分操作：
	!require(stringr)
[1] FALSE
	If(!require(stringr))install.packages("stringr")
	 #require可以转换为逻辑值，加载成功是T，失败是F
	  
	 as.logical(require(stringr))   
[1] TRUE


3.列出包里有哪些函数
	 library(tidyr)
 ls("package:tidyr")
 [1] "%>%"                      "all_of"                  
 [3] "any_of"                   "as_tibble"