R：使循环更“高效”

Question

我正在使用 R。我在这里编写了以下循环（使用一些随机创建的数据），它遍历一些数据操作步骤并生成一个名为“final_results”的所需表：

#load library
    library(dplyr)

library(data.table)

set.seed(123)

# create some data for this example
a1 = rnorm(1000,100,10)
b1 = rnorm(1000,100,5)
c1 = sample.int(1000, 1000, replace = TRUE)
train_data = data.frame(a1,b1,c1)


####
results_table <- data.frame()

for (i in 1:10 ) {
    
    #generate random numbers
    random_1 =  runif(1, 80, 120)
    random_2 =  runif(1, random_1, 120)
    random_3 =  runif(1, 85, 120)
    random_4 =  runif(1, random_3, 120)
    
    #bin data according to random criteria
    train_data <- train_data %>% mutate(cat = ifelse(a1 <= random_1 & b1 <= random_3, "a", ifelse(a1 <= random_2 & b1 <= random_4, "b", "c")))
    
    train_data$cat = as.factor(train_data$cat)
    
    #new splits
    a_table = train_data %>%
        filter(cat == "a") %>%
        select(a1, b1, c1, cat)
    
    b_table = train_data %>%
        filter(cat == "b") %>%
        select(a1, b1, c1, cat)
    
    c_table = train_data %>%
        filter(cat == "c") %>%
        select(a1, b1, c1, cat)
    
    split_1 =  runif(1,0, 1)
    split_2 =  runif(1, 0, 1)
    split_3 =  runif(1, 0, 1)
    
    #calculate 60th quantile ("quant") for each bin
    
    table_a = data.frame(a_table%>% group_by(cat) %>%
                             mutate(quant = quantile(c1, prob = split_1)))
    
    table_b = data.frame(b_table%>% group_by(cat) %>%
                             mutate(quant = quantile(c1, prob = split_2)))
    
    table_c = data.frame(c_table%>% group_by(cat) %>%
                             mutate(quant = quantile(c1, prob = split_3)))
    
    
    
    
    #create a new variable ("diff") that measures if the quantile is bigger tha the value of "c1"
    table_a$diff = ifelse(table_a$quant > table_a$c1,1,0)
    table_b$diff = ifelse(table_b$quant > table_b$c1,1,0)
    table_c$diff = ifelse(table_c$quant > table_c$c1,1,0)
    
    #group all tables
    
    final_table = rbind(table_a, table_b, table_c)
    
    #create a table: for each bin, calculate the average of "diff"
    final_table_2 = data.frame(final_table %>%
                                   group_by(cat) %>%
                                   summarize(
                                       mean = mean(diff)
                                   ))
    
    #add "total mean" to this table
    final_table_2 = data.frame(final_table_2 %>% add_row(cat = "total", mean = mean(final_table$diff)))
    
    #format this table: add the random criteria to this table for reference
    final_table_2$random_1 = random_1
    
    final_table_2$random_2 = random_2
    
    final_table_2$random_3 = random_3
    
    final_table_2$random_4 = random_4
    
    final_table_2$split_1 = split_1
    
    final_table_2$split_2 = split_2
    
    final_table_2$split_3 = split_3
    
    final_table_2$iteration_number = i
    
    
    results_table <- rbind(results_table, final_table_2)
    
    final_results = dcast(setDT(results_table), iteration_number + random_1 + random_2 + random_3 + random_4 + split_1 + split_2 + split_3 ~ cat, value.var = 'mean')
    
}

在上面的代码中，我运行了 10 次循环。 将来，我会对运行这个循环大约 1,000,000 次感兴趣。 除了购买更强大的计算机之外，是否有可能以这种方式重新编写此代码，使计算机处理起来不那么“繁重”？ 是否可以通过以不同方式存储中间步骤来提高此代码的效率？ 有什么办法可以加快这段代码的运行时间吗？

谢谢

Answer 1

好吧，您可以尝试摆脱这些 ifelse() 行。 例如

#table_a$diff = ifelse(table_a$quant > table_a$c1,1,0)
table_a <- 0L 
table_a[table_a$quant > table_a$c1, "diff"] <- 1L

同样适用于此：

#a_table <- train_data %>%
#        filter(cat == "a") %>%
#        select(a1, b1, c1, cat) 
a_table <- train_data[train_data$cat == "a", c("a1","b1","c1","cat")]

它使代码更加混乱，但与 dplyr 等效项相比，基本操作通常更快。