生信技能树DAY 3 R语言入门

# 使用save()函数保存为RData文件
# 创建一些要保存的变量
study1.df <- data.frame(id = 1:5, 
                        sex = c("m", "m", "f", "f", "m"), 
                        score = c(51, 20, 67, 52, 42))

score.by.sex <- aggregate(score ~ sex, 
                          FUN = mean, 
                          data = study1.df)

study1.htest <- t.test(score ~ sex, 
                       data = study1.df)
# save(变量1,变量2, ..., file = "文件名.RData") 保存于当前工作目录
save(study1.df, score.by.sex, study1.htest,
     file = "study1.RData")
# 如果有多个变量想要保存，使用save函数比较繁琐因为必须要输入每个变量名称，可使用save.image()函数保存工作目录下所有的变量。
save.image(file = "study1.RData")
# 使用load()函数加载RData文件
load(file = "study1.RData")
# 删除变量rm()见后文

# 生成10个随机数: rnorm(n=10,mean=0,sd=18)，用向量取子集的方法，取出其中小于-2的值
x <- rnorm(n=10,mean=0,sd=18)
x[x< -2]# x[x<-2]会把2赋值给x 要加空格或者加括号

## [1] -30.627262  -5.327866 -18.030441  -3.135825 -16.232720

x[x<(-2)]

## [1] -30.627262  -5.327866 -18.030441  -3.135825 -16.232720

# data.frame 函数
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

# 读取文件
df2 <- read.csv("gene.csv")

#维度 行数 列数
dim(df1)

## [1] 4 3

nrow(df1)

## [1] 4

ncol(df1)

## [1] 3

#行名 列名
rownames(df1)

## [1] "1" "2" "3" "4"

colnames(df1)

## [1] "gene"  "change" "score"

# $取列
df1$gene  

## [1] "gene1" "gene2" "gene3" "gene4"

mean(df1$score)#删掉score，按tab键试试 自动显示列名

## [1] 0.5

## 按坐标
df1[2,2]# 第二行第二列数据

## [1] "up"

df1[2,]# 第二行 带行名列名，还是数据框

##    gene change score
## 2 gene2     up     3

df1[,2]# 第二列 不带行名列名，是向量

## [1] "up"   "up"   "down" "down"

df1[c(1,3),1:2] # 多行多列 数据框

##    gene change
## 1 gene1     up
## 3 gene3   down

df1[,ncol(df1)] # 取最后一列

## [1]  5  3 -2 -4

## 按名字
df1[,"gene"]

## [1] "gene1" "gene2" "gene3" "gene4"

df1[,c('gene','change')]

##    gene change
## 1 gene1     up
## 2 gene2     up
## 3 gene3   down
## 4 gene4   down

### 后置的难点，按条件（逻辑值）取子集：1. 根据筛选条件得到逻辑值向量（与被筛选的列向量相对应）2. 用该向量筛选列向量
df1 <- data.frame(gene   = paste0("gene",1:4),
                  change  = rep(c("up","down"),each = 2),
                  score   = c(5,3,-2,-4))
k = df1$score>0;k # 返回逻辑值向量，每个逻辑值对标每行

## [1]  TRUE  TRUE FALSE FALSE

df1[k,]# TRUE的行被保留

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3

#筛选score > 0的基因
df1[k,1]

## [1] "gene1" "gene2"

df1$gene[k] # 也可以先取基因名列再用逻辑值向量筛选

## [1] "gene1" "gene2"

df1$gene[df1$score>0]

## [1] "gene1" "gene2"

#改一个格
df1[3,3] <- 5
df1

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down     5
## 4 gene4   down    -4

#改一整列
df1$score <- c(12,23,50,2)     
df1

##    gene change score
## 1 gene1     up    12
## 2 gene2     up    23
## 3 gene3   down    50
## 4 gene4   down     2

#新增一列
df1$p.value <- c(0.01,0.02,0.07,0.05) 
df1

##    gene change score p.value
## 1 gene1     up    12    0.01
## 2 gene2     up    23    0.02
## 3 gene3   down    50    0.07
## 4 gene4   down     2    0.05

#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" # 修改第二列的列名，就是修改列名这个向量的第二个元素

# 建立要连接的数据框
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

test3 <- data.frame(NAME = c('Damon','jimmy','nicker','tony'),
                    weight = c(140,145,110,138))
test3

##     NAME weight
## 1  Damon    140
## 2  jimmy    145
## 3 nicker    110
## 4   tony    138

merge(test1,test2,by="name") # 根据指定的列连接

##     name blood_type  group vision
## 1  Damon          O group1    4.2
## 2  jimmy          A group1    4.3
## 3 nicker          B group2    4.9

merge(test1,test3,by.x = "name",by.y = "NAME")# 要合并的列名不一致，注意x y的顺序和test的顺序一致

##     name blood_type weight
## 1  Damon          O    140
## 2  jimmy          A    145
## 3 nicker          B    110

m <- matrix(1:9, nrow = 3) # 创建矩阵
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

m[2,] # 取子集不支持$

## a b c 
## 2 5 8

m[,1]

## [1] 1 2 3

m[2,3]

## c 
## 8

m[2:3,1:2]

##      a b
## [1,] 2 5
## [2,] 3 6

m

##      a b c
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9

t(m) # 转置

##   [,1] [,2] [,3]
## a    1    2    3
## b    4    5    6
## c    7    8    9

as.data.frame(m) # 转换为数据框，注意赋值给新变量

##   a b c
## 1 1 4 7
## 2 2 5 8
## 3 3 6 9

pheatmap::pheatmap(m) # pheatmap可以接受矩阵也可以接受数据框，heatmap只能接受矩阵，看函数说明

#列表建立
x <- list(m1 = matrix(1:9, nrow = 3),
          m2 = matrix(2:9, nrow = 2))
x

## $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

# 取第一个元素 双中括号或$， 只用一个中括号取出来的是只有一个元素的列表
x[[1]]

##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

x$m1

##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

scores = c(100,59,73,95,45)
names(scores) = c("jimmy","nicker","Damon","Sophie","tony")
scores

##  jimmy nicker  Damon Sophie   tony 
##    100     59     73     95     45

scores["jimmy"]

## jimmy 
##   100

scores[c("jimmy","nicker")]

##  jimmy nicker 
##    100     59

names(scores)[scores>60]

## [1] "jimmy"  "Damon"  "Sophie"

rm(x)
rm(df1,df2)

rm(list = ls())
# 清空控制台 快捷键ctrl+L