Learn R 专题1-3

if(!require(stringr))install.packages('stringr')
library(stringr)
x <- "The birch canoe slid on the smooth planks."
x
[1] "The birch canoe slid on the smooth planks."
str_length(x)
[1] 42 ### 1.检测字符串长度,包含空格和符号
length(x) #返回的是向量中元素的个数，即x中只有一个元素
[1] 1
y = c("jimmy 150","nicker 140","tony 152")
    #y是字符型向量，由三个字符串组成的向量
    #“jimmy 150”：字符串，一个引号中所有的东西
    #引号内的单个字母/数字/符号：字符

>str_split(x," ") #以空格为分隔符号把x拆分开
[[1]] #[[1]] 列表
[1] "The"     "birch"   "canoe"   "slid"    
[5]"on"      "the"  "smooth"  "planks."

> x2 = str_split(x," ")[[1]];x2 #拆掉[[1]]
[1] "The"     "birch"   "canoe"   "slid"    "on"      "the"    
[7] "smooth"  "planks."

> y = c("jimmy 150","nicker 140","tony 152")
> str_split(y," ")
[[1]] #列表1
[1] "jimmy" "150"  
[[2]]
[1] "nicker" "140"   
[[3]]
[1] "tony" "152" 
> str_split(y," ",simplify = T) #和上个代码区别一下
>     [ ,1]      [ ,2]
[1,] "jimmy"  "150"
[2,]"nicker" "140"
[3,] "tony"   "152"

str_sub(x,5,9) #提取从第5位到第9位
[1] "birch"

> str_detect(x2,"h")   #看看x2中是否含有“h”
[1]  TRUE  TRUE FALSE FALSE FALSE  TRUE  TRUE FALSE
> str_starts(x2,"T")  #看看x2中是否以“T”开头
[1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
> str_ends(x2,"e")  #看看x2中是否以“e”结尾
[1]  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE

> x2
[1] "The"     "birch"   "canoe"   "slid"    "on"  "the"    
[7] "smooth"  "planks."
> str_replace(x2,"o","A") #把x2中的o替换成A
[1] "The"     "birch"   "canAe"   "slid"    "An"  "the"    
[7] "smAoth"  "planks."
> str_replace_all(x2,"o","A") #把x2中的所有o替换成A
[1] "The"     "birch"   "canAe"   "slid"    "An"   "the"    
[7] "smAAth"  "planks."

> x
[1] "The birch canoe slid on the smooth planks."
> str_remove(x," ") #删除x中的第一个空格
[1] "Thebirch canoe slid on the smooth planks."
> str_remove_all(x," ") #删除x中的所有空格
[1] "Thebirchcanoeslidonthesmoothplanks."

#加载数据
> test <- iris[c(1:2,51:52,101:102),]
> rownames(test) =NULL # 去掉行名，NULL是“什么都没有”
> test
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          5.1         3.5          1.4         0.2     setosa
2          4.9         3.0          1.4         0.2     setosa
3          7.0         3.2          4.7         1.4 versicolor
4          6.4         3.2          4.5         1.5 versicolor
5          6.3         3.3          6.0         2.5  virginica
6          5.8         2.7          5.1         1.9  virginica

> library(dplyr)
> arrange(test, Sepal.Length) #arrange() 以“Sepal.Length”这一列从小到大（默认）排序 列名大多数不需要加“”
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          4.9         3.0          1.4         0.2     setosa
2          5.1         3.5          1.4         0.2     setosa
3          5.8         2.7          5.1         1.9  virginica
4          6.3         3.3          6.0         2.5  virginica
5          6.4         3.2          4.5         1.5 versicolor
6          7.0         3.2          4.7         1.4 versicolor
> arrange(test, desc(Sepal.Length)) #以“Sepal.Length”这一列从大到小排序
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          7.0         3.2          4.7         1.4 versicolor
2          6.4         3.2          4.5         1.5 versicolor
3          6.3         3.3          6.0         2.5  virginica
4          5.8         2.7          5.1         1.9  virginica
5          5.1         3.5          1.4         0.2     setosa
6          4.9         3.0          1.4         0.2     setosa

> distinct(test,Species,.keep_all = T) #按照species这一列去重复，只保留第一次出现的值 .keep_all = T（把其余的列对应的值都保留下来）
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          5.1         3.5          1.4         0.2     setosa
2          7.0         3.2          4.7         1.4 versicolor
3          6.3         3.3          6.0         2.5  virginica

> mutate(test, new = Sepal.Length * Sepal.Width)
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species   new
1          5.1         3.5          1.4         0.2     setosa 17.85
2          4.9         3.0          1.4         0.2     setosa 14.70
3          7.0         3.2          4.7         1.4 versicolor 22.40
4          6.4         3.2          4.5         1.5 versicolor 20.48
5          6.3         3.3          6.0         2.5  virginica 20.79
6          5.8         2.7          5.1         1.9  virginica 15.66
#注意此时test仍为5列 因为没有赋值
> test$new=test$Sepal.Length*test$Sepal.Width
#以这种方式才是真正的添加新的一列
-------注意：R语言中的修改，都要赋值，没有赋值就没有发生过-------

x1 = filter(iris,Sepal.Width>3) #从iris出发先筛选行
x2 = select(x1, Sepal.Length,Sepal.Width) #再筛选列
x3 = arrange(x2,Sepal.Length) #再进行排序
# 2.管道符号传递，简洁明了
x = iris %>%  #control+shift 代表把前面的数据传递给后面的函数的第一个参数 省掉多次赋值
  filter(Sepal.Width>3) %>% 
  select(Sepal.Length,Sepal.Width)%>%
  arrange(Sepal.Length) 
#3. 嵌套，代码不易读
arrange(select(filter(iris,Sepal.Width>3),
               Sepal.Length,Sepal.Width),
        Sepal.Length)

load('test1.Rdata')
library(dplyr)
x=arrange(dat,logFC);head(x)

> a=read.csv("../R_04/group.csv")
> a
          ID                           title
1 GSM1052615     A375 cells 24h Control rep1
2 GSM1052616     A375 cells 24h Control rep2
3 GSM1052617     A375 cells 24h Control rep3
4 GSM1052618 A375 cells 24h Vemurafenib rep1
5 GSM1052619 A375 cells 24h Vemurafenib rep2
6 GSM1052620 A375 cells 24h Vemurafenib rep3
> g=str_split(a$title," ",simplify = T)
> g
     [,1]   [,2]    [,3]  [,4]          [,5]  
[1,] "A375" "cells" "24h" "Control"     "rep1"
[2,] "A375" "cells" "24h" "Control"     "rep2"
[3,] "A375" "cells" "24h" "Control"     "rep3"
[4,] "A375" "cells" "24h" "Vemurafenib" "rep1"
[5,] "A375" "cells" "24h" "Vemurafenib" "rep2"
[6,] "A375" "cells" "24h" "Vemurafenib" "rep3"
> g[,4]
[1] "Control"     "Control"     "Control"     "Vemurafenib"
[5] "Vemurafenib" "Vemurafenib"

x=merge(dat,ids,by = "probe_id")
x2=inner_join(dat,ids,by = "probe_id")

> tolower(g[,4])
[1] "control"     "control"     "control"     "vemurafenib"
[5] "vemurafenib" "vemurafenib"
#或者
>str_to_lower(g[,4])

#### (1)只有if没有else，那么条件是FALSE时就什么都不做
> i = -1
> if (i<0) print('up')
[1] "up"
> if (i>0) print('up')

> #理解下面代码
> if(!require(tidyr)) install.packages('tidyr')

i =1
if (i>0){
  print('+')
} else {
  print("-")
}

i = 1
ifelse(i>0,"+","-")
> ifelse(i>0,"+","-")
[1] "+"
> x = rnorm(3)
> x
[1]  0.5108486  0.7382251 -2.0977172
> ifelse(x>0,"+","-")
[1] "+" "+" "-"

> samples = c("tumor1","tumor2","tumor3","normal1","normal2","normal3")
> k1 = str_detect(samples,"tumor");k1 #看samples里面有哪些是包含tumor的
[1]  TRUE  TRUE  TRUE FALSE FALSE FALSE
> ifelse(k1,"tumor","normal") #ifelse()是用来替换的把T替换成tumor输出，F替换成normal输出
[1] "tumor"  "tumor"  "tumor"  "normal" "normal" "normal"
#换一种写法，检测normal
> k2 = str_detect(samples,"normal");k2
[1] FALSE FALSE FALSE  TRUE  TRUE  TRUE
> ifelse(k2,"normal","tumor")
[1] "tumor"  "tumor"  "tumor"  "normal" "normal" "normal"
-----注意：yes和no的位置一定不能反-----

i = 0
if (i>0){
  print('+')
} else if (i==0) {
  print('0')
} else if (i< 0){
  print('-')
}
[1] "0"

> ifelse(i>0,"+",ifelse(i<0,"-","0")) #嵌套写法 先里后外
[1] "0"

x=c(1,5,7,3)
for (i in x) {
  print(i)
}
[1] 1
[1] 5
[1] 7
[1] 3
# i 分别等于1，5，7，3 输出为1，5，7，3

x=c(1,5,7,3)
for (i in x) {
  print(rnorm(i))
}
[1] 1.341562
[1] 0.38916084 0.38170028 0.04550988 1.85500644 0.33939643
[1] -1.348085038  1.011728972  0.951139408 -1.109823986 -0.479132462
[6] -0.134466769 -0.007759876
[1] -0.1804468 -1.4743407 -0.2882833
# i 分别等于1，5，7，3，相对应在rnorm中取1,5,7,3个数

#例子
> x <- c(5,6,0,3)
> s = 0
> for (i in 1:length(x)){
+   s=s+x[[i]]
+   print(c(x[[i]],s))
+ }
[1] 5 5
[1]  6 11
[1]  0 11
[1]  3 14

load("deg.Rdata")
k1 = deg$a< -1 & deg$b<0.05;table(k1) #不能直接写a（它是一个列名，要用$）
k1
FALSE  TRUE 
26094  4681 
k2 = deg$a>1 & deg$b<0.05;table(k2)
k2
FALSE 
30775 
x = ifelse(k1,"down",ifelse(k2,"up","no"))
table(x) # 统计up、down、no各重复了多少次
x
 down    no 
 4681 26094 

x <- c(5,6,0,3) #元素循环 对x元素进行循环
s=0
for (i in x){
  s=s+i
  print(c(i,s))
}
[1] 5 5
[1]  6 11
[1]  0 11
[1]  3 14

x <- c(5,6,0,3)
s = 0
for (i in 1:length(x))} #下标循环（元素的长度）1:length(x)=1:4
  s=s+x[[i]]             #把i写成对应的元素即可x[[i]]
  print(c(x[[i]],s))
}
[1] 5 5
[1]  6 11
[1]  0 11
[1]  3 14

s = 0
result = list()            #先生成一个listlist()
for(i in 1:length(x)){
  s=s+x[[i]]                    
  result[[i]] = c(x[[i]],s). #每次都在列表里面加一个元素
}
result    #一列表的形式储存了结果
[[1]]
[1]  5 5
[[2]]
[1]  6 11
[[3]]
[1]  0 11
[[4]]
[1]  3 14
do.call(cbind,result) #将列表组成为矩阵
     [,1] [,2] [,3] [,4]
[1,]    5    6    0    3
[2,]    5   11   11   14
#do.call 将列表里的元素进行批量的操作；cbind是按列拼接起来（向量长度得是相同的）

if(T){} #运行{}中的代码;可折叠
if(F){} #跳过{}中的代码

set.seed(10086) #设置随机种子，保证每次运行的随机值（与其他人以及每次登录时）都 一样
exp = matrix(rnorm(18),ncol = 6) #18个随机数分布在六列里形成矩阵
exp = round(exp,2) #round() 取小数点后2位数字
rownames(exp) = paste0("gene",1:3) #矩阵加上行名
colnames(exp) = paste0("test",1:6)  #矩阵加上列名
exp[,1:3] = exp[,1:3]+1 #在前三列原有的基础上加上1
exp

library(tidyr)
library(tibble)
library(dplyr)
dat = t(exp) %>%  #数据转置 行列互换
  as.data.frame() %>%  #矩阵转换为数据框
  rownames_to_column() %>%  #把行名变成数据框里的一列
  mutate(group = rep(c("control","treat"),each = 3)) #加上分组3个control 和三个treat 前三行control后三行treat

pdat = dat%>% 
  pivot_longer(cols = starts_with("gene"), #宽变长函数 col=是指把gene合并成一列
               names_to = "gene", #宽边长 原来的列名出来对应的数据名字
               values_to = "count") #原来数值对应的一列 新的命名

library(ggplot2)
p = ggplot(pdat,aes(gene,count))+
  geom_boxplot(aes(fill = group))+
  theme_bw() #取掉灰色背景
p
p + facet_wrap(~gene,scales = "free") #分区
#scales = “fixed”    x和y的标度在所用平面中都相同
scales = “free”    x和y的标度在每个版面都可以变化
scales = “free_x    固定y轴，x轴自由变化
scales = “free_y”    类似，同上

apply(x,MARGIN,FUN...) #X 是数据框/矩阵名；MARGING为1表示行；为2表示列，FUN是函数 ；对x的每一行/列进行FUN这个函数;...用于写函数的参数
> test<- iris[1:6,1:4]
> apply(test, 2, mean)
Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
   4.9500000    3.3833333    1.4500000    0.2333333 
> apply(test, 1, sum)
   1    2    3    4    5    6 
10.2  9.5  9.4  9.4 10.2 11.4 

sort(a)[16:20]
head(a)#默认取前6个数
head(a,5)#取前5个
head(sort(a,decreasing = T),5)#与下面结果一致
tail(sort(a),5)#从小到大排序，取最后的5个

load("test2.Rdata")
tail(sort(apply(test,1,var)),1000) #每个基因的方差排序 每行计算方差,取后1000个
names(tail(sort(apply(test,1,var)),1000)) # 将后1000个的基因名称提取出来

> test <- list(x = 36:33,y = 32:35,z = 30:27);test
$x
[1] 36 35 34 33
$y
[1] 32 33 34 35
$z
[1] 30 29 28 27

> lapply(test,mean) #输出结果仍为列表
$x
[1] 34.5
$y
[1] 33.5
$z
[1] 28.5
> lapply(test,fivenum)
$x
[1] 33.0 33.5 34.5 35.5 36.0
$y
[1] 32.0 32.5 33.5 34.5 35.0
$z
[1] 27.0 27.5 28.5 29.5 30.0

> sapply(test,mean)
   x    y    z 
34.5 33.5 28.5 
> sapply(test,fivenum) #fivenum():返回五个数据：最小值、下四分位数、中位数、上四分位数、最大值
        x    y    z
[1,] 33.0 32.0 27.0
[2,] 33.5 32.5 27.5
[3,] 34.5 33.5 28.5
[4,] 35.5 34.5 29.5
[5,] 36.0 35.0 30.0
> class(sapply(test,fivenum))
[1] "matrix" "array" 

#数据载入
> test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'), 
+                     blood_type = c("A","B","O","AB"))
> test1
    name blood_type
1  jimmy          A
2 nicker          B
3  Damon          O
4 Sophie         AB
> test2 <- data.frame(name = c('Damon','jimmy','nicker','tony'),
+                     group = c("group1","group1","group2","group2"),
+                     vision = c(4.2,4.3,4.9,4.5))
> test2
    name  group vision
1  Damon group1    4.2
2  jimmy group1    4.3
3 nicker group2    4.9
4   tony group2    4.5
> View(test)
> library(dplyr)
Attaching package: ‘dplyr’
> inner_join(test1,test2,by="name") #交集连接
    name blood_type  group vision
1  jimmy          A group1    4.3
2 nicker          B group2    4.9
3  Damon          O group1    4.2
> right_join(test1,test2,by="name") #右连接，以右边的name为准将两个数据框进行连接，有右边名字的连接上，没有的不连接
    name blood_type  group vision
1  jimmy          A group1    4.3
2 nicker          B group2    4.9
3  Damon          O group1    4.2
4   tony       <NA> group2    4.5
> full_join(test1,test2,by="name") #全连接，都连接上，没有的写NA
    name blood_type  group vision
1  jimmy          A group1    4.3
2 nicker          B group2    4.9
3  Damon          O group1    4.2
4 Sophie         AB   <NA>     NA
5   tony       <NA> group2    4.5
> semi_join(test1,test2,by="name") #半连接，基本用不上 把test1中的name也在test2中包含的人取出来 %in%
    name blood_type
1  jimmy          A
2 nicker          B
3  Damon          O
> anti_join(test1,test2,by="name") #反连接，基本用不上 把test1中的name不在test2中包含的人取出来
    name blood_type
1 Sophie         AB

sort()/table()/length()
unique()/duplicated()
names()
ifelse和str_detect() #分组
arrange() # 排序
distinct() #去重-数据框
merge() #连接