Day6-学习R包-Lydia

# options函数就是设置R运行过程中的一些选项设置
options("repos" = c(CRAN="https://mirrors.tuna.tsinghua.edu.cn/CRAN/")) #对应清华源
options(BioC_mirror="https://mirrors.ustc.edu.cn/bioc/") #对应中科大源
#安装
install.packages(“dplyr”)
BiocManager::install(“dplyr”)
#加载
library(dplyr)
> test <- iris[c(1:2,51:52,101:102),]
> mutate(test, new = Sepal.Length * Sepal.Width)#新增列
    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
> select(test,1)#按列筛选,按列号筛选
    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))#按列号筛选
    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)#按列名筛选
    Sepal.Length
1            5.1
2            4.9
51           7.0
52           6.4
101          6.3
102          5.8
> select(test, Petal.Length, Petal.Width)#按列名筛选
    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
> filter(test, Species == "setosa")#筛选行
  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
> arrange(test, Sepal.Length)#默认从小到大排序,按某1列或某几列对整个表格进行排序
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          4.9         3.0          1.4         0.2     setosa
2          5.1         3.5          1.4         0.2     setosa
3          5.8         2.7          5.1         1.9  virginica
4          6.3         3.3          6.0         2.5  virginica
5          6.4         3.2          4.5         1.5 versicolor
6          7.0         3.2          4.7         1.4 versicolor
> arrange(test, desc(Sepal.Length))#用desc从大到小
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          7.0         3.2          4.7         1.4 versicolor
2          6.4         3.2          4.5         1.5 versicolor
3          6.3         3.3          6.0         2.5  virginica
4          5.8         2.7          5.1         1.9  virginica
5          5.1         3.5          1.4         0.2     setosa
6          4.9         3.0          1.4         0.2     setosa

> summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差
  mean(Sepal.Length) sd(Sepal.Length)
1           5.916667        0.8084965
## 先按照Species分组,计算每组Sepal.Length的平均值和标准差
> group_by(test, Species)#对数据进行汇总操作,结合group_by使用实用性强
# A tibble: 6 × 5
# Groups:   Species [3]
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species   
         <dbl>       <dbl>        <dbl>       <dbl> <fct>     
1          5.1         3.5          1.4         0.2 setosa    
2          4.9         3            1.4         0.2 setosa    
3          7           3.2          4.7         1.4 versicolor
4          6.4         3.2          4.5         1.5 versicolor
5          6.3         3.3          6           2.5 virginica 
6          5.8         2.7          5.1         1.9 virginica 
> summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
# A tibble: 3 × 3
  Species    `mean(Sepal.Length)` `sd(Sepal.Length)`
  <fct>                     <dbl>              <dbl>
1 setosa                     5                 0.141
2 versicolor                 6.7               0.424
3 virginica                  6.05              0.354
#管道操作 %>%,加载任意一个tidyverse包
> library(tidyverse)
> test %>% 
+     group_by(Species) %>% 
+     summarise(mean(Sepal.Length), sd(Sepal.Length))
# A tibble: 3 × 3
  Species    `mean(Sepal.Length)` `sd(Sepal.Length)`
  <fct>                     <dbl>              <dbl>
1 setosa                     5                 0.141
2 versicolor                 6.7               0.424
3 virginica                  6.05              0.354
#count统计某列的unique值
> count(test,Species)
     Species n
1     setosa 2
2 versicolor 2
3  virginica 2
#dplyr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(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)
> inner_join(test1, test2, by = "x")#內连inner_join,取交集
  x z y
1 b A 2
2 e B 5
3 f C 6
> left_join(test1, test2, by = 'x')#左连left_join
  x z  y
1 b A  2
2 e B  5
3 f C  6
4 x D NA
> left_join(test2, test1, by = 'x')
  x y    z
1 a 1 <NA>
2 b 2    A
3 c 3 <NA>
4 d 4 <NA>
5 e 5    B
6 f 6    C
> full_join( test1, test2, by = 'x')#全连full_join
  x    z  y
1 b    A  2
2 e    B  5
3 f    C  6
4 x    D NA
5 a <NA>  1
6 c <NA>  3
7 d <NA>  4
> semi_join(x = test1, y = test2, by = 'x')#半连接:返回能够与y表匹配的x表所有记录semi_join
  x z
1 b A
2 e B
3 f C
> anti_join(x = test2, y = test1, by = 'x')#反连接:返回无法与y表匹配的x表的所记录anti_join
  x y
1 a 1
2 c 3
3 d 4
#简单合并,相当于base包里的cbind()函数和rbind()函数
> 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_rows()函数需要两个表格列数相同
  x  y
1 1 10
2 2 20
3 3 30
4 4 40
5 5 50
6 6 60
> bind_cols(test1, test3)#bind_cols()函数则需要两个数据框有相同的行数
  x  y   z
1 1 10 100
2 2 20 200
3 3 30 300
4 4 40 400
©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容