Question

我正在使用for循环。 for循环的目标是简单地测试条件并适当地编码数据。该循环必须迭代503,288个唯一值，并包括三个if语句。有没有一种方法可以加快for循环？

代码如下：

count<- 0
for(i in unique(Data$ID)){ #503288

  #Subset Relevant Data
  Loop_Before<- subset(Primary_Before, ID == i); Loop_After <- subset(Primary_After, ID == i)

  if(nrow(Loop_Before) >= 1 & nrow(Loop_After) >= 1){
    Data$Status[Data$ID == i] <- "Both Elections"

  }

  if(nrow(Loop_Before) >= 1 & nrow(Loop_After) == 0){
    Data$Status[Data$ID == i] <- "Only Primary Election"

  }

  if(nrow(Loop_Before) >= 0 & nrow(Loop_After) == 1){
    Data$Status[Data$ID == i] <- "Only General Election"

  }

  message(count<- count +1)

}



table(Data$Status)

谢谢您的帮助！

Answer 1

完全避免for循环。我不知道您的数据集，但以下内容应该快10倍甚至100倍：

library(tidyverse) # load some packages that will help

# let's create some sample data
Data <- data.frame(ID = c(1,1,1,1,2,2,2,3,3))
Primary_before <- data.frame(ID = c(0,1,2,2,3,3,3))
Primary_after <- data.frame(ID = c(1,3))

# now for every ID we count the nr of rows in both dataframes
summarised_before <- Primary_before %>%
    group_by(ID) %>%
    summarise(nrRows = n())

     ID nrRows
  <dbl>  <int>
1     0      1
2     1      1
3     2      2
4     3      3

summarised_after <- Primary_after %>%
    group_by(ID) %>%
    summarise(nrRows = n())

     ID nrRows
  <dbl>  <int>
1     1      1
2     3      1

# now we join them together
summarised_both <- summarised_after %>%
    full_join(summarised_before, by = "ID", suffix = c("_after", "_before"))

# and now we do the final calculation
summarised_both %>%
    mutate(nrRows_after = replace_na(nrRows_after, 0)) %>%
    mutate(Status = case_when(nrRows_before >= 1 & nrRows_after >= 1    ~ "Both elections"
                              , nrRows_before >= 1 & nrRows_after == 0  ~ "Only primary election"
                              , nrRows_before >= 0 & nrRows_after == 1  ~ "Only general election")) %>%
    filter(ID %in% Data$ID)

我保存了中间结果，但是您也可以一口气做到这一点，就像这样：

Primary_before %>%
    group_by(ID) %>%
    summarise(nrRows = n()) %>%
    full_join(Primary_after %>%
                  group_by(ID) %>%
                  summarise(nrRows = n())
              , by = "ID"
              , suffix = c("_after", "_before")) %>%
    mutate(nrRows_after = replace_na(nrRows_after, 0)) %>%
    mutate(Status = case_when(nrRows_before >= 1 & nrRows_after >= 1    ~ "Both elections"
                              , nrRows_before >= 1 & nrRows_after == 0  ~ "Only primary election"
                              , nrRows_before >= 0 & nrRows_after == 1  ~ "Only general election")) %>%
    filter(ID %in% Data$ID)

有没有办法加快for循环的速度？

1 个答案: