1.tidyverse
(1)tidyr 核心函数
1)数据清理
### 原始数据
test <- data.frame(geneid = paste0("gene",1:4),
sample1 = c(1,4,7,10),
sample2 = c(2,5,0.8,11),
sample3 = c(0.3,6,9,12))
test
### 扁变长
test_gather <- gather(data = test,
key = sample_nm,
value = exp,
- geneid)
head(test_gather)
### 长变扁
test_re <- spread(data = test_gather,
key = sample_nm,
value = exp)
head(test_re)
1
2)分割和合并
### 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 = ",")
3)处理NA
### 原始数据
X<-data.frame(X1 = LETTERS[1:5],X2 = 1:5)
X[2,2] <- NA
X[4,1] <- NA
### 1.去掉含有NA的行,可以选择只根据某一列来去除
drop_na(X)
drop_na(X,X1)
drop_na(X,X2)
### 2.替换NA
replace_na(X$X2,0)
### 3.用上一行的值填充NA
X
fill(X,X2)
2.dplyr
(1)五个基础函数
1)新增列
rm(list = ls())
## 包和数据的准备
if(!require(dplyr))install.packages("dplyr")
library(dplyr)
test <- iris[c(1:2,51:52,101:102),]
rownames(test) =NULL
###1.mutate(),新增列
mutate(test, new = Sepal.Length * Sepal.Width)
2)按列筛选
###2.select(),按列筛选
####(1)按列号筛选
select(test,1)
select(test,c(1,5))
####(2)按列名筛选
select(test,Sepal.Length)
select(test, Petal.Length, Petal.Width)
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
#####一组来自tidyselect的有用函数
select(test, starts_with("Petal"))
select(test, ends_with("Width"))
select(test, contains("etal"))
select(test, matches(".t."))
select(test, everything())
select(test, last_col())
select(test, last_col(offset = 1))
####(4)利用everything(),列名可以重排序
select(test,Species,everything())
3)按行筛选
###3.filter()筛选行
filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))
4)按某一列对整个表格进行排序
###4.arrange(),按某一列对整个表格进行排序
arrange(test, Sepal.Length)#默认从小到大排序,逗号再加一列就是按两列排序
arrange(test, desc(Sepal.Length))#用desc从大到小
arrange(test, desc(Sepal.Width),Sepal.Length)
#基础包里(?)
test=iris[c(1,2,51,52,101,102),]
o=order(test$Sepal.Length)
test$Sepal.Length[o]
x[order(x)]
sort(x)
test[o,]
5)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)
tmp = summarise(group_by(test, Species),
mean(Sepal.Length),
sd(Sepal.Length))#分组汇总
(2)两个实用技能
1)管道操作
###1:管道操作 %>% (cmd/ctrl + shift + M)
#上一步的输出作为下一步的输入
library(dplyr)
x1 = filter(iris,Sepal.Width>3)
x2 = select(x1,c("Sepal.Length","Sepal.Width" ))
x3 = arrange(x2,Sepal.Length)
#管道符号的作用可变成下面的
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
###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)
3.stringr
rm(list = ls())
if(!require(stringr))install.packages('stringr')
library(stringr)
x <- "The birch canoe slid on the smooth planks."
x
###1.检测字符串长度
length(x)#返回几个字符串
str_length(x)#返回字符串里有几个字符
###2.字符串拆分与组合
str_split(x," ")#按照空格对x进行拆分
x2 = str_split(x," ")[[1]]#拆出来是个列表,只要列表的第一个元素
y2 = str_split(y," ",simplify = T)#把拆出来的列表变成矩阵
str_c(x2,collapse = " ")#连接组合在一起 ,内部连接连成一个元素
str_c(x2,1234,sep = "+")#各自连接,连成八个新的元素
###3.提取字符串的一部分
str_sub(x,5,9)#从第五位提取到第九位
###4.大小写转换
str_to_upper(x2)#全大写
str_to_lower(x2)#全小写
str_to_title(x2)#首字母大写
###5.字符串排序
str_sort(x2)
###6.字符检测
str_detect(x2,"h")#检测向量里每一个元素里是否含有h这个字母,有就是True不含有就是false
str_starts(x2,"T")#判断是否以T开头
str_ends(x2,"e")#判断是否以e结尾
###与sum和mean连用,可以统计匹配的个数和比例
sum(str_detect(x2,"h"))
mean(str_detect(x2,"h"))
as.numeric(str_detect(x2,"h"))
###7.提取匹配到的字符串
str_subset(x2,"h")
###8.字符计数
str_count(x," ")#数x里有多少个空格
str_count(x2,"o")
###9.字符串替换
str_replace(x2,"o","A")#把x里的o变成A,但多个o只会替换第一个
str_replace_all(x2,"o","A")#在上面的基础上全部替换为A
###结合正则表达式更加强大
4.条件语句和循环语句
(1)ifelse函数
x可以为逻辑值也可以为向量,因为ifelse支持循环
2rm(list = ls())
## 一.条件语句
###1.if(){ }
#### (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')
if (i>0) print('up')
#理解下面代码
if(!require(tidyr)) install.packages('tidyr')
#### (2)有else,做A这件事还是做B这件事的区别
i =1
if (i>0){
cat('+')
} else {
print("-")
}#cat是打印出本来样子,print是带着引号之类的代表它是向量的一个字符串的因素
ifelse(x,yes,no)
ifelse(i>0,"+","-")
x=rnorm(10)
y=ifelse(x>0,"+","-")
y
#### (3)多个条件
i = 0
if (i>0){
print('+')
} else if (i==0) {
print('0')
} else if (i< 0){
print('-')
}
ifelse(i>0,"+",ifelse((i<0),"-","0"))
case_when()#自己探索
### 2.switch()
cd = 3
foo <- switch(EXPR = cd,
#EXPR = "aa",
aa=c(3.4,1),
bb=matrix(1:4,2,2),
cc=matrix(c(T,T,F,T,F,F),3,2),
dd="string here",
ee=matrix(c("red","green","blue","yellow")))
foo
(2)长脚本管理方式
3 4(3)For 循环
1.for循环
#**顺便看一下next和break**
x <- c(5,6,0,3)
s=0
for (i in x){
s=s+i
#if(i == 0) next #next为进行下一轮循环,跳过次轮
#if (i == 0) break #循环终止
print(c(which(x==i),i,1/i,s))
}#i在第一轮是x里的第一个元素,第二轮是x的第二个元素...以此类推
x <- c(5,6,0,3)
s = 0
for (i in 1:length(x)){
s=s+x[[i]]
#if(i == 3) next
#if (i == 3) break
print(c(i,x[[i]],1/i,s))
}
#如何将结果存下来?
s = 0
result = list()
for(i in 1:length(x)){
s=s+x[[i]]
result[[i]] = c(i,x[[i]],1/i,s)
}
do.call(cbind,result)#把他变成矩阵
### 2.while 循环(危险)
i = 0
while (i < 5){
print(c(i,i^2))
i = i+1
}
### 3.repeat 语句
#注意:必须有break
i=0L
s=0L
repeat{
i = i + 1
s = s + i
print(c(i,s))
if(i==50) break
}
5.apply函数
5rm(list = ls())
## apply()族函数
### 1.apply 处理矩阵或数据框
#apply(X, MARGIN, FUN, …)
#其中X是数据框/矩阵名;
#MARGIN为1表示取行,为2表示取列,FUN是函数
test<- iris[,1:4]
apply(test, 2, mean)#对test的列求平均值
apply(test, 1, sum)
res <- c()
for(i in 1:nrow(test)){
res[[i]] <- sum(test[i,])
}
res#这一段可代替apply的作用,没啥用
### 2.lapply(list, FUN, …)
# 对列表/向量中的每个元素(向量)实施相同的操作
test <- list(x = 36:33,
y = 32:35,
z = 30:27)
#返回值是列表,对列表中的每个元素(向量)求均值(试试方差var,分位数quantile)
lapply(test,mean)
class(lapply(test,mean))
x <- unlist(lapply(test,mean));x#取消列表变成向量
class(x)
### 3.sapply 处理列表,简化结果,直接返回矩阵和向量
#sapply(X, FUN, …) 注意和lapply的区别,返回值不一样
lapply(test,min)
sapply(test,min)
lapply(test,range)#range取最大值和最小值
sapply(test,range)
class(sapply(test,range))
网友评论