r - 如何在 r 中处理具有超过 500 万个观测值的数据帧时加速迭代？

Question

我试图在数百万次观察中为超过 7 个变量生成值，当我编写 for 循环来实现这一点时，它需要永远。下面是我试图实现的一个例子。在这种情况下，它很快，因为它只有几千个观察值:

# Load dplyr


library(tidyverse)
set.seed(50)

df <- data_frame(SlNo = 1:2000,
                 Scenario = rep(c(1, 2, 3, 4),500),
                 A = round(rnorm(2000, 11, 6)),
                 B = round(rnorm(2000, 15, 4))) %>%
      arrange(Scenario) 

#splitting data-frame to add multiple rows in the data-frame

df<- df %>% split(f = .$Scenario) %>%
  map_dfr(~bind_rows(tibble(Scenario = 0), .x)) 

#observations for certain variables in the newly added rows have specific values

df <- df %>% mutate(C = if_else(Scenario != 0, 0, 4),
                    E = if_else(Scenario != 0, 0, 6))

for(i in 2:nrow(df)) {

df$C[i] <- if_else(df$Scenario[i] != 0, (1-0.5) * df$C[i-1] + 3 + 2 + df$B[i] + df$E[i-1],
              df$C[i])
df$E[i] <- if_else(df$Scenario[i] != 0, df$C[i] + df$B[i] - 50, df$E[i])


}

df

# A tibble: 2,004 x 6
   Scenario  SlNo     A     B     C      E
      <dbl> <int> <dbl> <dbl> <dbl>  <dbl>
 1        0    NA    NA    NA   4     6   
 2        1     1    14    19  32     1   
 3        1     5     1    13  35    -2   
 4        1     9    17    20  40.5  10.5 
 5        1    13     8     7  42.8  -0.25
 6        1    17    10    16  42.1   8.12
 7        1    21     9    12  46.2   8.19
 8        1    25    14    18  54.3  22.3 
 9        1    29    14    15  69.4  34.4 
10        1    33     4    17  91.1  58.1 
# ... with 1,994 more rows

我想在处理更大的数据框时快速产生类似的结果。我很感激这方面的任何帮助。先感谢您!!

Answer 1

在 tidyverse您可以使用 purrr::accumulate像这样

library(tidyverse)
set.seed(50)

df <- data.frame(SlNo = 1:2000,
                 Scenario = rep(c(1, 2, 3, 4),500),
                 A = round(rnorm(2000, 11, 6)),
                 B = round(rnorm(2000, 15, 4))) %>%
  arrange(Scenario)

df %>%
  nest(data = B) %>%
  group_by(Scenario) %>%
  mutate(new = accumulate(data, 
                          .init = tibble(C = 4, E = 6),
                          ~ tibble(C = (1 -0.5)* .x$C + 5 + .y$B + .x$E,
                                   E = 0.5 * .x$C + 5 + .x$E + 2 * .y$B - 50
                                   )
                          )[-1]
         ) %>% ungroup %>%
  unnest_wider(data) %>%
  unnest_wider(new)

#> # A tibble: 2,000 x 6
#>     SlNo Scenario     A     B     C     E
#>    <int>    <dbl> <dbl> <dbl> <dbl> <dbl>
#>  1     1        1    14    19  32    1   
#>  2     5        1     1    13  35   -2   
#>  3     9        1    17    20  40.5 10.5 
#>  4    13        1     8     7  42.8 -0.25
#>  5    17        1    10    16  42.1  8.12
#>  6    21        1     9    12  46.2  8.19
#>  7    25        1    14    18  54.3 22.3 
#>  8    29        1    14    15  69.4 34.4 
#>  9    33        1     4    17  91.1 58.1 
#> 10    37        1    13    15 124.  88.7 
#> # ... with 1,990 more rows

创建于 2021-07-05 由 reprex package (v2.0.0)