错误：逻辑索引向量的长度必须为 1

Question

我正在尝试使用 REEMtree 运行一个简单的 CART 风格混合效果模型。我不明白为什么它一直抛出错误：

"错误：逻辑索引向量的长度必须为1或1（ 列），而不是 120 英寸

这里是示例数据：

structure(list(avg_ipt = c(14, 8.666666667, 30, 3.857142857, 
2.153846154, 2.363636364, 2.071428571, 2.25, 1.636363636, 14, 
13.5, 30, 30, 12.5, 30, 30, 2.636363636, 1.588235294, 0.769230769, 
2.25, 2.416666667, 1.866666667, 6.5, 30, 14, 14, 14, 9, 3, 1.260869565, 
0.965517241, 1.588235294, 1.125, 14, 12, 30, 9.5, 13.5, 9.333333333, 
2.5, 2.5, 1.45, 1.6875, 1.666666667, 2.5, 9.333333333, 9.333333333, 
30, 12.5, 13.5, 9.333333333, 13, 3.222222222, 1.333333333, 2.444444444, 
2.5, 3.714285714, 14, 14, 30, 30, 5.5, 30, 30, 30, 30, 30, 30, 
12, 9.5, 30, 10.5, 30, 30, 30, 30, 10, 30, 30, 8, 1, 30, 30, 
10, 30, 8.5, 30, 30, 6, 30, 30, 12.5, 30, 30, 30, 30, 30, 30, 
30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 
30, 30, 30, 30, 30, 30), monthly_expense = c(2234.77, 6434, 0, 
170.2, 461.16, 1971.64, 918.45, 1280.06, 2584.93, 5676.95, 1350, 
0, 0, 6710.41, 0, 0, 692.01, 2521.26, 3481.25, 535.32, 195.45, 
22818.28, 1402.32, 0, 2232.17, 2232.17, 2683.57, 37.13, 525.54, 
2695.45, 4178.1, 1979.42, 1348.62, 5956.95, 1350, 0, 2325, 2325, 
2676.5, 166.41, 1084.69, 3594.95, 1291.39, 663.01, 610.77, 6014.49, 
2929.56, 0, 2161.25, 2161.25, 8995, 70.49, 1978.14, 2361.29, 
306.35, 994.91, 385.73, 5974.42, 2270.63, 0, 0, 239.04, 0, 0, 
0, 0, 0, 0, 183.46, 72.89, 0, 182.93, 0, 0, 0, 0, 523.91, 0, 
0, 239.54, 108.63, 0, 0, 192.21, 0, 30.03, 0, 0, 46.12, 0, 0, 
177.64, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0), time.period = c(1L, 2L, 3L, 4L, 
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 
19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 
32L, 33L, 34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 
45L, 46L, 47L, 48L, 49L, 50L, 51L, 52L, 53L, 54L, 55L, 56L, 57L, 
58L, 59L, 60L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 
12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 
25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 
38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 
51L, 52L, 53L, 54L, 55L, 56L, 57L, 58L, 59L, 60L), id = structure(c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("1", "2", "3", "4", "5", 
"6", "7", "8", "9", "10", "11", "12", "13", "14", "15", "16", 
"17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", 
"28", "29", "30", "31", "32", "33", "34", "35", "36", "37", "38", 
"39", "40", "41", "42", "43", "44", "45", "46", "47", "48", "49", 
"50", "51", "52", "53", "54", "55", "56", "57", "58", "59", "60", 
"61", "62", "63", "64", "65", "66", "67", "68", "69", "70", "71", 
"72", "73", "74", "75", "76", "77", "78", "79", "80", "81", "82", 
"83", "84", "85", "86", "87", "88", "89", "90", "91", "92", "93", 
"94", "95", "96", "97", "98", "99", "100"), class = "factor")), row.names = c(NA, 
-120L), class = c("tbl_df", "tbl", "data.frame"))

和代码：

library(REEMtree)
model <- REEMtree(monthly_expense ~ avg_ipt, data = sample_df, random =~1|id)

有谁知道它为什么会抛出错误？

Answer 1

确保sample_df 有data.frame 类，即它的S3 类有一个元素，即"data.frame"——而不是c("tbl_df", "tbl", "data.frame")。

library(REEMtree)

sample_df <- data.frame(sample_df)
model <- REEMtree(monthly_expense ~ avg_ipt, data = sample_df, random =~1|id)

给予：

> model
[1] "*** RE-EM Tree ***"
n= 120 

node), split, n, deviance, yval
      * denotes terminal node

1) root 120 670354400 1166.627 *
[1] "Estimated covariance matrix of random effects:"
            (Intercept)
(Intercept)     2474326
[1] "Estimated variance of errors: 5679196.50339722"
[1] "Log likelihood:  -1098.26101212641"

注意

REEMtree 中出现问题是因为这一行给出了不同的Target，具体取决于数据是普通数据帧还是tbl_df 对象（然后在代码中这种差异会导致错误）。

Target <- data[, toString(TargetName)]

如果data 是一个纯数据框，那么Target 是一个纯向量，但如果data 是一个tbl_df，那么Target 也是一个。

这会解决它：

Target <- data[, toString(TargetName), drop = TRUE]

或者toString(TargetName)只能是标量：

Target <- data[[toString(TargetName)]]