GLM 解析分类系数

Question

我正在尝试创建整洁的数据，并且正在尝试将章程值与字段名称分开

#Example: 

data(mtcars)
library(broom)

#Adding some new character variables
mtcars1 <- mtcars
mtcars1$has_leter_yn <- ifelse(grepl("[[:digit:]]"
                                 , rownames(mtcars))==TRUE, "1 Y", "2 N")

mtcars1$first_letter <- substr(rownames(mtcars), 1,1)

mtcars1$cyl_yn <- ifelse(mtcars$cyl > 5, "Y", "N") 

mtcars1$am_yn <- ifelse(mtcars$am > 0.5, "N", "Y") 

mtcars1$hp_yn <- ifelse(mtcars$hp > 200, "POWER", "WEAK") 

#model 
mod <- glm(mpg ~ wt + first_letter + has_leter_yn + cyl_yn +am_yn + hp_yn
       , data =  mtcars1)

#broom tidy function
tidy(mod)

             term    estimate std.error   statistic      p.value
1      (Intercept) 25.46529192  5.155178  4.93974994 0.0001243241
2               wt -2.38861746  1.338905 -1.78400876 0.0922815327
3    first_letterC  4.63900549  3.751079  1.23671244 0.2330073046
4    first_letterD  0.95497914  3.332624  0.28655476 0.7779162451
5    first_letterF  3.78125890  3.337474  1.13297017 0.2729534747
6    first_letterH  4.74971469  3.163074  1.50161363 0.1515430178
7    first_letterL  4.21825272  3.570943  1.18127128 0.2537575961
8    first_letterM  2.81979616  3.149218  0.89539568 0.3830789592
9    first_letterP  3.44802708  3.445036  1.00086826 0.3309248121
10   first_letterT  4.24503396  3.581256  1.18534795 0.2521854417
11   first_letterV  0.90257581  3.474959  0.25973711 0.7981860095
12 has_leter_yn2 N  0.06314099  1.394756  0.04527028 0.9644194087
13         cyl_ynY -4.51802483  1.637415 -2.75924279 0.0134056327
14          am_ynY -1.33513554  1.827695 -0.73050238 0.4750310328
15       hp_ynWEAK  3.72962845  2.042696  1.82583649 0.0854925603

有没有办法将 first_letter 和 C 分开？

我想在数据框中使用估计值、术语和字符以供将来使用。任何帮助，将不胜感激！

Answer 1

这样的吗？

xy <- tidy(mod)

data.frame(letter = gsub(pattern = "^(*.|first_letter)([A-Z])", replacement = "\\2", x = xy$term),
           prepend = gsub(pattern = "^(*.|first_letter)([A-Z])", replacement = "\\1", x = xy$term),
           oldterm = xy$term)

            letter         prepend         oldterm
1       Intercept)      (ntercept)     (Intercept)
2               wt              wt              wt
3                C    first_letter   first_letterC
4                D    first_letter   first_letterD
5                F    first_letter   first_letterF
6                H    first_letter   first_letterH
7                L    first_letter   first_letterL
8                M    first_letter   first_letterM
9                P    first_letter   first_letterP
10               T    first_letter   first_letterT
11               V    first_letter   first_letterV
12 has_leter_yn2 N has_leter_yn2 N has_leter_yn2 N
13         cyl_ynY         cyl_ynY         cyl_ynY
14          am_ynY          am_ynY          am_ynY
15       hp_ynWEAK       hp_ynWEAK       hp_ynWEAK