如何使用R中的数据框列创建分类变量？
如果变量是数字变量，则可以通过定义下限和上限将其转换为类别变量。例如，年龄从21开始到25结束可以转换为21-25类别。要将R数据帧列转换为分类变量，可以使用cut函数。
例1
考虑以下数据帧-
set.seed(141) x1<−rnorm(20,2,0.3) x2<−LETTERS[1:20] df1<−data.frame(x1,x2) df1输出结果
x1 x2 1 2.154308 A 2 1.966167 B 3 2.019302 C 4 1.803427 D 5 2.150517 E 6 1.749425 F 7 1.797508 G 8 1.949084 H 9 2.147742 I 10 1.895026 J 11 1.922780 K 12 1.755871 L 13 2.410873 M 14 2.580489 N 15 1.910219 O 16 1.805713 P 17 2.166996 Q 18 2.074431 R 19 1.749257 S 20 2.004867 T
在df1中为x1创建分类列-
示例
df1$x1_category<−cut(df1$x1,c(0,1,2,3)) df1输出结果
x1 x2 x1_category 1 2.154308 A (2,3] 2 1.966167 B (1,2] 3 2.019302 C (2,3] 4 1.803427 D (1,2] 5 2.150517 E (2,3] 6 1.749425 F (1,2] 7 1.797508 G (1,2] 8 1.949084 H (1,2] 9 2.147742 I (2,3] 10 1.895026 J (1,2] 11 1.922780 K (1,2] 12 1.755871 L (1,2] 13 2.410873 M (2,3] 14 2.580489 N (2,3] 15 1.910219 O (1,2] 16 1.805713 P (1,2] 17 2.166996 Q (2,3] 18 2.074431 R (2,3] 19 1.749257 S (1,2] 20 2.004867 T (2,3]
例2
y1<−sample(c("Child","Teen","Adult","Old"),20,replace=TRUE)
y2<−rpois(20,5)
df2<−data.frame(y1,y2)
df2输出结果y1 y2 1 Old 6 2 Teen 3 3 Old 2 4 Teen 5 5 Adult 6 6 Teen 6 7 Old 5 8 Adult 6 9 Child 5 10 Child 3 11 Child 9 12 Old 8 13 Teen 2 14 Teen 2 15 Teen 5 16 Adult 7 17 Adult 4 18 Teen 4 19 Adult 2 20 Child 8
在df2中为x2创建分类列-
示例
df2$y2_category<−cut(df2$y2,c(0,1,2,3,4,5,6,7,8,9,10)) df2输出结果
y1 y2 y2_category 1 Old 6 (5,6] 2 Teen 3 (2,3] 3 Old 2 (1,2] 4 Teen 5 (4,5] 5 Adult 6 (5,6] 6 Teen 6 (5,6] 7 Old 5 (4,5] 8 Adult 6 (5,6] 9 Child 5 (4,5] 10 Child 3 (2,3] 11 Child 9 (8,9] 12 Old 8 (7,8] 13 Teen 2 (1,2] 14 Teen 2 (1,2] 15 Teen 5 (4,5] 16 Adult 7 (6,7] 17 Adult 4 (3,4] 18 Teen 4 (3,4] 19 Adult 2 (1,2] 20 Child 8 (7,8]