时间戳

首页 > 解决方案 > 分组时从函数中分配多个结果

r - 分组时从函数中分配多个结果

问题描述

我有这段代码，它完全符合我的要求，但我必须为每个组调用我的函数三次，这似乎非常低效。

library(data.table)

myRegr = function(x, y) {
    regr = lm.fit(cbind(1, x), y)
    coefs = regr$coef
    k = coefs[[2]]
    m = coefs[[1]]
    r2 = 1 - var(regr$residuals) / var(y)

    return (c(k = k, m = m, r2 = r2))
}

dt = data.table(a = c(0, 0, 0, 1, 1, 1), 
                x = c(12, 21, 15, 34, 32, 31), 
                y = c(3, 1, 6, 4, 2, 8))

result = dt[,list(minX = min(x),
                    minY = min(y),
                    k = myRegr(x, y)["k"],
                    m = myRegr(x, y)["m"],
                    r2 = myRegr(x, y)["r2"]
                ),
                by = list(a)]


print(result)

输出：

a minX minY          k         m        r2
0   12    1 -0.3095238  8.285714 0.3176692
1   31    2 -1.0000000 37.000000 0.2500000

知道如何将其重写为仅调用该函数一次吗？

更新：我的示例没有涵盖完整的问题，因为我选择了第四列，这是一个更好的示例：

library(data.table)

myRegr = function(x, y) {
    regr = lm.fit(cbind(1, x), y)
    coefs = regr$coef
    k = coefs[[2]]
    m = coefs[[1]]
    r2 = 1 - var(regr$residuals) / var(y)

    return (c(k = k, m = m, r2 = r2))
}

df = data.frame(a = c(0, 0, 0, 1, 1, 1), 
                x = c(12, 21, 15, 34, 32, 31), 
                y = c(3, 1, 6, 4, 2, 8),
                time = as.POSIXct(c("2019-01-01 08:12:00", "2019-01-01 08:13:00", "2019-01-01 08:14:00", "2019-01-01 08:12:00", "2019-01-01 08:13:00", "2019-01-01 08:14:00")))

dt = data.table(df)

result = dt[, list(firstX = x[time == min(time)],
                firstY = y[time == min(time)],
                k = myRegr(x, y)["k"],
                m = myRegr(x, y)["m"],
                r2 = myRegr(x, y)["r2"]
            ),
            by = a]


print(result)

输出：

a firstX firstY          k         m        r2
0     12      3 -0.3095238  8.285714 0.3176692
1     34      4 -1.0000000 37.000000 0.2500000

尝试将它全部包装在一个函数中，但它实际上减慢了速度：

library(data.table)

myRegrList = function(group) {
    firstX = group[,x[time == min(time)]]
    firstY = group[,y[time == min(time)]]

    regr = lm.fit(cbind(1, group$x), group$y)
    coefs = regr$coef
    k = coefs[[2]]
    m = coefs[[1]]
    r2 = 1 - var(regr$residuals) / var(group$y)

    return (list(firstX = firstX, firstY = firstY, k = k, m = m, r2 = r2))
}

result = dt[, myRegrList(.SD), by = a]

print(result)

标签： rdata.table

解决方案

如果你让你的函数返回一个列表，你只需要调用

dt[, myRegr(x, y), by = a]
#   a minX minY          k         m        r2
#1: 0   12    1 -0.3095238  8.285714 0.3176692
#2: 1   31    2 -1.0000000 37.000000 0.2500000

和

myRegr = function(x, y) {
  regr = lm.fit(cbind(1, x), y)
  coefs = regr$coef
  k = coefs[[2]]
  m = coefs[[1]]
  r2 = 1 - var(regr$residuals) / var(y)

  return (list(# minX = min(x),
               # minY = min(y),
               k = k,
               m = m,
               r2 = r2))
}

更新

您可以对x和y值进行子集化，然后加入函数的结果

result <- dt[dt[, .I[which.min(time)], by = a]$V1, .(a, x, y)]
result <- result[dt[, myRegr(x, y), by = a], on = .(a)]
result
#   a  x y          k         m        r2
#1: 0 12 3 -0.3095238  8.285714 0.3176692
#2: 1 34 4 -1.0000000 37.000000 0.2500000

推荐阅读