计算文本中的字母R.

Question

我有一个程序可以对文本中的字母和字符进行计数，但它无法正常工作。从下面的示例中可以看出，程序不计算列索引。我不知道如何在行中的最后一个字母（字符）之后设置程序以转到下一行并从1开始计数。你能帮助我吗？我有两个不同的程序，一个不计行。

我的代码：

library(tidyverse)
library(stringr)
str_split(text, "")[[1]] %>%
  tibble(char = .) %>% 
  rownames_to_column('rn') %>% 
  group_by(char) %>% 
  summarise(Count = n(), row = 1, col = toString(rn))

unique(unlist(strsplit(text, ""))) %>%
  sapply(gregexpr, text, fixed = TRUE) %>%
  unlist() %>%
  data.frame(letter = names(.), col = .) %>%
  group_by(letter = gsub("^(.).*", "\\1", letter)) %>%
  summarize(count = n(),
            col = paste(col, collapse = ","))


text <- "Only two things are infinite, 
the universe and human stupidity, 
and I'm not sure about the former. (A. Einstein)"

结果：

# A tibble: 31 x 4
    char Count   row                                                                    col
   <chr> <int> <dbl>                                                                  <chr>
 1     '     1     1                                                                     72
 2          18     1 5, 9, 16, 20, 30, 35, 44, 48, 54, 65, 70, 74, 78, 83, 89, 93, 101, 105
 3  "\n"     2     1                                                                 31, 66
 4     (     1     1                                                                    102
 5     )     1     1                                                                    114
 6     ,     2     1                                                                 29, 64
 7     .     2     1                                                               100, 104
 8     a     5     1                                                     17, 45, 52, 67, 84
 9     A     1     1                                                                    103
10     b     1     1                                                                     85
# ... with 21 more rows

Answer 1

你可以尝试

library(tidyverse)
library(stringr)
library(stringi)

data.frame(Text=str_split(text, pattern = "\n")[[1]]) %>%
  group_by(n=row_number()) %>% 
  mutate(letters=sum(stri_count_fixed(tolower(Text), letters))) %>%
  mutate(marks=sum(stri_count_regex(tolower(Text), "[[:punct:]]"))) %>% 
  mutate(spaces=sum(stri_count_regex(tolower(Text),"[[:blank:]]"))) 
# A tibble: 3 x 5
# Groups:   n [3]
                                              Text     n letters marks spaces
                                            <fctr> <int>   <int> <int>  <int>
1                   Only two things are infinite,      1      24     1      5
2               the universe and human stupidity,      2      28     1      5
3 and I'm not sure about the former. (A. Einstein)     3      35     5      8