如何根据多列中的值有条件地改变R中的变量？

Question

最近没有使用当前tidyverse动词来回答这个问题（R 4.1

library(tidyverse)
set.seed(195)

# create dataframe
response_id <- rep(1:461)
questions <- c("overall","drought","domestic","livestock","distance")
answers <- c("a","b","c","d","e")
colnames <- apply(expand.grid(questions, answers), 1, paste, collapse="_")
df <- tibble(response_id)
# data is actually an unknown mix of TRUE and FALSE values in all columns but just doing that for one column for now for simplicity
df[,colnames] = FALSE
df$overall_a[sample(nrow(df),100)] <- TRUE

# using ifelse and select if to filter which columns to sum
df %>%
 mutate(positive = ifelse(select_if(isTRUE), sum(str_detect(colnames(df), "a|b")), NA)) %>%
 mutate(negative = ifelse(select_if(isTRUE), sum(str_detect(colnames(df), "c|d|e")), NA)) %>%
 select(response_id, positive, negative)

# using case_when
df %>%
 mutate(positive = case_when(TRUE ~ sum(str_detect(colnames(df), "a|b"))), NA) %>%
 mutate(negative = case_when(TRUE ~ sum(str_detect(colnames(df), "c|d|e"))), NA) %>%
 select(response_id, positive, negative)

所需的输出应如下所示。感谢您对此的任何帮助！

# A tibble: 461 × 3
   response_id positive negative
         <int>    <int>    <int>
 1           1       0       0
 2           2       0       0
 3           3       0       0
 4           4       0       0
 5           5       1       0
 6           6       1       0
 7           7       0       0
 8           8       1       0
 9           9       0       0
10          10       1       0
# … with 451 more rows

Answer 1

将数据放在列名中不被认为是“整洁的”，而“整洁的”最适合整洁的数据。旋转方法将最符合整洁的理念，而不是攻击列名。此外，它将更好地扩展更多类别。例如

df %>% 
  pivot_longer(-response_id) %>% 
  separate(name, into=c("category", "code")) %>% 
  mutate(sentiment=case_when(
    code %in% c("a", "b") ~ "positive", 
    code %in% c("c", "d", "e") ~ "negative")) %>% 
  group_by(response_id, sentiment) %>% 
  summarize(count=sum(value)) %>% 
  pivot_wider(response_id, names_from=sentiment, values_from=count)

它没有那么简洁，但更直接地说明了它在做什么。

但是如果你真的想把数据保留在行名中，你可以使用c_across（）和最新的dplyr执行逐行摘要

df %>% 
  rowwise() %>% 
  mutate(
    positive=sum(c_across(ends_with(c("_a", "_b")))),
    negative=sum(c_across(ends_with(c("_c", "_d", "_e"))))) %>% 
  select(response_id, positive, negative)