使用tidyverse根据分类列计算差异

我有以下数据框：

library(tidyverse)

df <- data.frame(
  vars = rep(letters[1:2], 3),
  value = c(10,12,15,19,22,23),
  phase = rep(factor(c("pre","post1","post2"), levels = c("pre","post1","post2")),2)
) %>% 
  arrange(vars,phase)

您可以使用从tidyr开始的“扩散”和“聚集”，首先将相位转换为列，然后在计算完差值后再次转换为长格式：

library(dplyr)
library(tidyr)
df %>%
    spread(phase, value) %>%
    mutate("post1 - pre" = post1 - pre, "post2 - post1" = post2 - post1, "post2 - pre" = post2 - pre) %>%
    select(-pre, -post1, -post2) %>%
    gather("x", "diff", 2:4)

您可以使用从tidyr开始的“扩散”和“聚集”，首先将相位转换为列，然后在计算完差值后再次转换为长格式：

library(dplyr)
library(tidyr)
df %>%
    spread(phase, value) %>%
    mutate("post1 - pre" = post1 - pre, "post2 - post1" = post2 - post1, "post2 - pre" = post2 - pre) %>%
    select(-pre, -post1, -post2) %>%
    gather("x", "diff", 2:4)

---

以下是一种更加自动化的方法，在您指定差异必须遵循的顺序后，可以获得所需的所有组合：

library(tidyverse)

# example dataset
df <- data.frame(
  vars = rep(letters[1:2], 3),
  value = c(10,12,15,19,22,23),
  phase = rep(factor(c("pre","post1","post2"), levels = c("pre","post1","post2")),2)
) %>% 
  arrange(vars,phase)

# set the levels in the right order based on the differences you want to get
df$phase = factor(df$phase, levels = c("post2","post1","pre"))


data.frame(t(combn(as.character(sort(unique(df$phase))), 2)), stringsAsFactors = F) %>%  # create a dataframe of unique combinations of differences you want to investigate
  mutate(vars = list(unique(df$vars))) %>%          # add unique vars as a list
  unnest() %>%                                      # get all combinations
  group_by(id = row_number()) %>%                   # for each row
  nest() %>%                                        # nest data
  mutate(diffs = map(data, ~df$value[df$vars==.$vars & df$phase==.$X1] - 
                            df$value[df$vars==.$vars & df$phase==.$X2]),   # get differences based on corresponding values
         x = map(data, ~paste0(c(.$X1, .$X2), collapse = " - "))) %>%      # create your x column
  unnest() %>%                                      # unnest data
  select(vars, x, diffs)                            # keep relevant columns

# # A tibble: 6 x 3
#   vars  x             diffs
#   <fct> <chr>         <dbl>
# 1 a     post2 - post1    -7
# 2 b     post2 - post1    11
# 3 a     post2 - pre       5
# 4 b     post2 - pre       4
# 5 a     post1 - pre      12
# 6 b     post1 - pre      -7

---

以下是一种更加自动化的方法，在您指定差异必须遵循的顺序后，可以获得所需的所有组合：

library(tidyverse)

# example dataset
df <- data.frame(
  vars = rep(letters[1:2], 3),
  value = c(10,12,15,19,22,23),
  phase = rep(factor(c("pre","post1","post2"), levels = c("pre","post1","post2")),2)
) %>% 
  arrange(vars,phase)

# set the levels in the right order based on the differences you want to get
df$phase = factor(df$phase, levels = c("post2","post1","pre"))


data.frame(t(combn(as.character(sort(unique(df$phase))), 2)), stringsAsFactors = F) %>%  # create a dataframe of unique combinations of differences you want to investigate
  mutate(vars = list(unique(df$vars))) %>%          # add unique vars as a list
  unnest() %>%                                      # get all combinations
  group_by(id = row_number()) %>%                   # for each row
  nest() %>%                                        # nest data
  mutate(diffs = map(data, ~df$value[df$vars==.$vars & df$phase==.$X1] - 
                            df$value[df$vars==.$vars & df$phase==.$X2]),   # get differences based on corresponding values
         x = map(data, ~paste0(c(.$X1, .$X2), collapse = " - "))) %>%      # create your x column
  unnest() %>%                                      # unnest data
  select(vars, x, diffs)                            # keep relevant columns

# # A tibble: 6 x 3
#   vars  x             diffs
#   <fct> <chr>         <dbl>
# 1 a     post2 - post1    -7
# 2 b     post2 - post1    11
# 3 a     post2 - pre       5
# 4 b     post2 - pre       4
# 5 a     post1 - pre      12
# 6 b     post1 - pre      -7