新建与读取数据框

新建数据框

> df <- data.frame(gene  = paste0("gene",1:3),
+                  sam   = paste0("sample",1:3),
+                  exp   = c(32,34,45))
> df
   gene     sam exp
1 gene1 sample1  32
2 gene2 sample2  34
3 gene3 sample3  45

读取数据框

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

数据框的属性

dim(df)
nrow(df)
ncol(df)
rownames(df)
colnames(df)

数据框取子集

df[2,2]
df[2,]
df[,2]
df[c(1,3),1:2]
df[,"gene"]
df[,c('gene','exp')]
df[,ncol(df)]
df[,-ncol(df)]

数据框编辑

#改一个格
df[3,3]<- 5
#改一整列
df$exp<-c(12,23,50)     
#改行名和列名
rownames(df) <- c("r1","r2","r3")
#只修改某一行/列的名
rownames(df)[2]="x"

两个表格的连接

tmp  =merge(test1,test2,by="name")
merge(test1,test3,by.x = "name",by.y = "NAME")

删除

#删除一个
rm(l)
#删除多个
rm(df,m)
#删除全部
rm(list = ls()) 
#删除含有NA的行
na.omit(df)

元素的名字

x=1:10
> names(x)=letters[1:10]
> x
 a  b  c  d  e  f  g  h  i  j 
 1  2  3  4  5  6  7  8  9 10 
> x["a"]
a 
1 

统计数据框中某一列有哪几个重复值，分别重复了多少次

table(iris$Species)

分割和合并

(library(tidyr))

#原始数据
test <- data.frame(x = c( "a,b", "a,d", "b,c"));test

 #分割
test_seprate <- separate(test,x, c("X", "Y"),sep = ",");test_seprate

 #合并
test_re <- unite(test_seprate,"x",X,Y,sep = ",")

表格拆分多次

y_seprate <- separate(y,source_name_ch1, c("X", "Y"),sep = ";") %>% 
separate(characteristics_ch1.10, c("Z", "W"),sep = ":")%>% 
  separate(W, c("A", "B"),sep = ";")

  
删除多余列
y_pd <- y_seprate[,c('Y','B')]

library(dplyr)

1.mutate(),新增列

mutate(test, new = Sepal.Length * Sepal.Width)

2.select(),按列筛选

(1)按列号筛选

select(test,1)
select(test,c(1,5))

(2)按列名筛选

select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))

一组来自tidyselect的有用函数

select(test, starts_with("Petal"))
select(test, ends_with("Width"))
select(test, contains("etal"))
select(test, matches(".t."))
select(test, everything())
select(test, last_col())
select(test, last_col(offset = 2))

(4)利用everything()，列名可以重排序

select(test,Species,everything())

3.filter()筛选行

filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))

4.arrange(),按某一列对整个表格进行排序

arrange(test, Sepal.Length)#默认从小到大排序
arrange(test, desc(Sepal.Length))#用desc从大到小
arrange(test, Sepal.Length, desc(Sepal.Width))

5.summarise()：汇总

对数据进行汇总操作,结合group_by使用实用性强

summarise(test, mean(Sepal.Length), sd(Sepal.Length))

计算Sepal.Length的平均值和标准差：

先按照Species分组，计算每组Sepal.Length的平均值和标准差

group_by(test, Species)
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))

两个实用技能

1：管道操作 %>% (cmd/ctr + shift + M)

library(dplyr)
x1 = filter(iris,Sepal.Width>3)
x2 = select(x1,c("Sepal.Length","Sepal.Width" ))
x3 = arrange(x2,Sepal.Length)
colnames(iris)
iris %>% 
  filter(Sepal.Width>3) %>% 
  select(c("Sepal.Length","Sepal.Width" ))%>%
  arrange(Sepal.Length)

2：count统计某列的unique值

count(test,Species)

处理关系数据:即将2个表进行连接，注意：不要引入factor

options(stringsAsFactors = F)

test1 <- data.frame(name = c('jimmy','nicker','doodle'), 
                    blood_type = c("A","B","O"))
test1
test2 <- data.frame(name = c('doodle','jimmy','nicker','tony'),
                    group = c("group1","group1","group2","group2"),
                    vision = c(4.2,4.3,4.9,4.5))
test2 

test3 <- data.frame(NAME = c('doodle','jimmy','lucy','nicker'),
                    weight = c(140,145,110,138))
merge(test1,test2,by="name")
merge(test1,test3,by.x = "name",by.y = "NAME")

1.內连inner_join,取交集

inner_join(test1, test2, by = "name")
inner_join(test1,test3,by = c("name"="NAME"))

2.左连left_join

left_join(test1, test2, by = 'name')
left_join(test2, test1, by = 'name')

3.全连full_join

full_join( test1, test2, by = 'name')

4.半连接：返回能够与y表匹配的x表所有记录semi_join

semi_join(x = test1, y = test2, by = 'name')

5.反连接：返回无法与y表匹配的x表的所记录anti_join

anti_join(x = test2, y = test1, by = 'name')

6.数据的简单合并

在相当于base包里的cbind()函数和rbind()函数;注意，bind_rows()函数需要两个表格列数相同，而bind_cols()函数则需要两个数据框有相同的行数

test1 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test1
test2 <- data.frame(x = c(5,6), y = c(50,60))
test2
test3 <- data.frame(z = c(100,200,300,400))
test3
bind_rows(test1, test2)
bind_cols(test1, test3)