R语言基础2

> class(iris)
[1] "data.frame"
> class(volcano)
[1] "matrix" "array"

df1 <- data.frame(gene   = paste0("gene",1:4),
                 change  = rep(c("up","down"),each = 2),
                 score   = c(5,3,-2,-4))
df1

df2 <- read.csv("gene.csv")
df2

#
dim(df1)  ##数据的维度
nrow(df1)
ncol(df1)
#
rownames(df1)
colnames(df1)

df1$score  #删掉score，按tab键试试
mean(df1$score)

## 按坐标,第几行第几列
df1[2,2]
df1[2,]
df1[,2]
df1[c(1,3),1:2]
## 按名字
df1[,"gene"]
df1[,c('gene','change')]

## 代码思维
#如何取数据框的最后一列？
df1[,3]
df1[,ncol(df1)]
#如何取数据框除了最后一列以外的其他列？
df1[,-ncol(df1)]

#改一个格
df1[3,3] <- 5
df1
#改一整列
df1$score <- c(12,23,50,2)     
df1
#新增一列
df1$p.value <- c(0.01,0.02,0.07,0.05) 
df1

#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"

test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'), 
                    blood_type = c("A","B","O","AB"))
test1
> 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
> 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
> test3
    NAME weight
1  Damon    140
2  jimmy    145
3 nicker    110
4   tony    138
merge(test1,test2,by="name")
    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")
    name blood_type weight
1  Damon          O    140
2  jimmy          A    145
3 nicker          B    110

m <- matrix(1:9, nrow = 3)
colnames(m) <- c("a","b","c") #加列名
m
m[2,]
m[,1]
m[2,3]
m[2:3,1:2]
m
t(m)###矩阵转置
as.data.frame(m)###转换为数据框

install.packages("pheatmap")
library(pheatmap)
pheatmap::pheatmap(m)
pheatmap::pheatmap(m,pheatmap::pheatmap(m,cluster_rows = F,cluster_cols = F))

x <- list(m1 = matrix(1:9, nrow = 3),
          m2 = matrix(2:9, nrow = 2))
x
> 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

###取子集方法
x[[1]]
x$m1

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

names(scores)[scores>60]

## 按条件（逻辑值）
df1 <- data.frame(gene   = paste0("gene",1:4),
                  change  = rep(c("up","down"),each = 2),
                  score   = c(5,3,-2,-4))
df1[df1$score>0,]

#筛选score > 0的基因
df1[df1$score > 0,1]
df1$gene[df1$score > 0]##筛选score大于0的基因。
df1[df1$score > 0,1]##筛选score大于0的基因。

##筛选score大于0的行。
df1$score 
df1$score > 0
df1$score[df1$score > 0]]
df1[df1$score > 0,]

rm(x)###删除一个
rm(df1,df2)###删除多个
rm(list = ls()) ###删除全部
##清空控制台  ctrl+L