生信学习第六天
学习R包
一. 安装和加载R包
1.镜像设置
你还在每次配置Rstudio的下载镜像吗？ (qq.com)
2.安装
install.packages(“包”)
BiocManager::install(“包”)
3. 加载
library(包)
require(包)
二. 安装加载三部曲
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/")
install.packages("dplyr")
library(dplyr)
示例数据直接使用内置数据集iris的简化版:
test <- iris[c(1:2,51:52,101:102),]
三. dplyr五个基础函数
1.mutate(),新增列
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
#51 7.0 3.2 4.7 1.4 versicolor 22.40
#52 6.4 3.2 4.5 1.5 versicolor 20.48
#101 6.3 3.3 6.0 2.5 virginica 20.79
#102 5.8 2.7 5.1 1.9 virginica 15.66
2. select(),按列筛选
(1) 按列号筛选
select(test,1)
# Sepal.Length
# 1 5.1
# 2 4.9
# 51 7.0
# 52 6.4
# 101 6.3
# 102 5.8
select(test,c(1,5))
# Sepal.Length Species
# 1 5.1 setosa
# 2 4.9 setosa
# 51 7.0 versicolor
# 52 6.4 versicolor
# 101 6.3 virginica
# 102 5.8 virginica
select(test,Sepal.Length)
# Sepal.Length
# 1 5.1
# 2 4.9
# 51 7.0
# 52 6.4
# 101 6.3
# 102 5.8
(2) 按列名筛选
select(test, Petal.Length, Petal.Width)
# Petal.Length Petal.Width
# 1 1.4 0.2
# 2 1.4 0.2
# 51 4.7 1.4
# 52 4.5 1.5
# 101 6.0 2.5
# 102 5.1 1.9
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
# Petal.Length Petal.Width
# 1 1.4 0.2
# 2 1.4 0.2
# 51 4.7 1.4
# 52 4.5 1.5
# 101 6.0 2.5
# 102 5.1 1.9
3. filter()筛选行
filter(test, Species == "setosa")
# 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
filter(test, Species == "setosa"&Sepal.Length > 5 )
# Sepal.Length Sepal.Width Petal.Length Petal.Width Species
# 1 5.1 3.5 1.4 0.2 setosa
filter(test, Species %in% c("setosa","versicolor"))
# 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
4. arrange(),按某一列或某几列对整个数据框进行排序
arrange(test, Sepal.Length) #默认从小到大排序
arrange(test, desc(Sepal.Length)) #用desc从大到小
5. summarise()：汇总
# 计算Sepal.Length的平均值和标准差
summarise(test, mean(Sepal.Length), sd(Sepal.Length))
# 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))
四. dplyr两个实用技能
1. 管道操作 %>%
下载任意一个tidyverse包即可用管道符号
install.packages("tidyverse")
test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length), sd(Sepal.Length))
2. count统计某列的unique值
count(test,Species)
五. dplyr处理关系数据
1. 创建两个数据框
options(stringsAsFactors = F)
test1 <- data.frame(x = c('b','e','f','x'), z = c("A","B","C",'D'), stringsAsFactors = F)
test2 <- data.frame(x = c('a','b','c','d','e','f'), y = c(1,2,3,4,5,6), stringsAsFactors = F)
2. 內连inner_join,取交集
inner_join(test1, test2, by = "x")
3. 左连left_join
left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')
4. 全连full_join
full_join( test1, test2, by = 'x')
5. 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 = 'x')
6. 反连接：返回无法与x表匹配的y表的所记录anti_join
anti_join(x = test2, y = test1, by = 'x')
7.简单合并
bind_rows()函数需要两个数据框列数相同，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))
test2 <- data.frame(x = c(5,6), y = c(50,60))
test3 <- data.frame(z = c(100,200,300,400))
bind_rows(test1, test2)
bind_cols(test1, test3)
