xgb.cv没有折叠，并根据数据的分割返回结果

Question

我有一些类似的数据：

# A tibble: 50 x 28
   sanchinarro date       holiday weekday weekend workday_on_holi… weekend_on_holi… protocol_active
         <dbl> <date>       <dbl>   <dbl>   <dbl>            <dbl>            <dbl>           <dbl>
 1      -1.01  2010-01-01       1       1       0                1                0               0
 2       0.832 2010-01-02       0       0       1                0                0               0
 3       1.29  2010-01-03       0       0       1                0                0               0
 4       1.04  2010-01-04       0       1       0                0                0               0
 5       0.526 2010-01-05       0       1       0                0                0               0
 6      -0.292 2010-01-06       1       1       0                1                0               0
 7      -0.394 2010-01-07       0       1       0                0                0               0
 8      -0.547 2010-01-08       0       1       0                0                0               0
 9      -0.139 2010-01-09       0       0       1                0                0               0
10       0.628 2010-01-10       0       0       1                0                0               0

我想在前40行运行xgb.cv，并在后10行进行验证。

我尝试以下操作：

library(xgboost)
library(dplyr)
X_Val <- ddd %>% select(-c(1:2))
Y_Val <- ddd %>% select(c(1)) %>% pull()

dVal <- xgb.DMatrix(data = as.matrix(X_Val), label = as.numeric(Y_Val))
xgb.cv(data = dVal, nround = 30, folds = NA, params = list(eta = 0.1, max_depth = 5))

这给我这个错误：

xgb.cv（data = dVal，nround = 30，folds = NA，eta = 0.1，max_depth = 5）：“ folds”必须是包含2个或更多元素的列表是每个CV折叠的索引向量

如何在前40行运行简单的xgb.cv，并在后10行进行测试。

我最终希望使用带有参数列表的网格搜索并将结果保存在列表中。因为我正在处理时间序列数据，所以我不想混合使用折叠，所以我只想进行40:10的简单训练和样本内测试。

数据：

        ddd <- structure(list(sanchinarro = c(-1.00742964973274, 0.832453587904369, 
1.29242439731365, 1.03688505875294, 0.525806381631517, -0.291919501762755, 
-0.394135237187039, -0.547458840323464, -0.138595898626329, 0.628022117055801, 
1.19020866188936, 1.5990716035865, 1.5990716035865, -0.70078244345989, 
2.11015028070792, 1.95682667757149, 0.985777191040795, 0.883561455616511, 
0.985777191040795, 0.270267043070807, 2.51901322240505, 2.41679748698077, 
0.372482778495091, -0.291919501762755, -0.905213914308458, -0.905213914308458, 
-0.649674575747748, 1.2413165296015, 1.54796373587436, -0.70078244345989, 
-0.905213914308458, -0.0363801632020448, 1.54796373587436, 2.00793454528363, 
1.54796373587436, -0.445243104899181, -0.445243104899181, 1.03688505875294, 
0.628022117055801, -0.496350972611323, 0.168051307646523, -0.649674575747748, 
0.0658355722222391, -1.00742964973274, -0.291919501762755, 0.0147277045100972, 
0.168051307646523, -0.189703766338471, 0.219159175358665, 0.679129984767943
), date = structure(c(14610, 14611, 14612, 14613, 14614, 14615, 
14616, 14617, 14618, 14619, 14620, 14621, 14622, 14623, 14624, 
14625, 14626, 14627, 14628, 14629, 14630, 14631, 14632, 14633, 
14634, 14635, 14636, 14637, 14638, 14639, 14640, 14641, 14642, 
14643, 14644, 14645, 14646, 14647, 14648, 14649, 14650, 14651, 
14652, 14653, 14654, 14655, 14656, 14657, 14658, 14659), class = "Date"), 
    holiday = c(1, 0, 0, 0, 0, 1, 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, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), weekday = c(1, 
    0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 
    1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 
    1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1), weekend = c(0, 1, 1, 0, 
    0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 
    1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 
    0, 1, 1, 0, 0, 0, 0, 0), workday_on_holiday = c(1, 0, 0, 
    0, 0, 1, 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, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0), weekend_on_holiday = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0), protocol_active = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0), text_broken_clouds = c(0, 
    1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 
    0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 
    1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1), text_clear = c(0, 0, 0, 
    0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 
    0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 1, 1), text_fog = c(0, 1, 0, 1, 1, 0, 
    0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 
    0, 0, 1, 0, 1, 0), text_partly_cloudy = c(0, 1, 0, 0, 0, 
    1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0), text_partly_sunny = c(1, 1, 1, 1, 1, 
    0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0, 
    0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 
    0, 0, 0, 0, 1, 1, 1), text_passing_clouds = c(1, 1, 1, 1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 
    0, 0, 0, 0, 0, 1, 1, 1), text_scattered_clouds = c(1, 1, 
    0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 
    0, 1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 
    0, 0, 0, 0, 0, 0, 0, 0, 1, 1), text_sunny = c(0, 0, 0, 0, 
    0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 
    0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 1), month_1 = c(1, 1, 1, 1, 1, 1, 1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 
    1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0), month_2 = c(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, 0, 
    0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 
    1, 1), month_3 = c(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, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_4 = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_5 = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0), month_6 = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0), month_7 = c(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, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0), month_8 = c(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, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_9 = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_10 = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0), month_11 = c(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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0), month_12 = c(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, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0)), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-50L)) 

编辑：列表数据：

最终数据以列表的形式出现。

datalst <- list(structure(list(sanchinarro = c(-1.00742964973274, 0.832453587904369, 
1.29242439731365, 1.03688505875294, 0.525806381631517, -0.291919501762755, 
-0.394135237187039, -0.547458840323464, -0.138595898626329, 0.628022117055801, 
1.19020866188936, 1.5990716035865, 1.5990716035865, -0.70078244345989
), date = structure(c(14610, 14611, 14612, 14613, 14614, 14615, 
14616, 14617, 14618, 14619, 14620, 14621, 14622, 14623), class = "Date"), 
    holiday = c(1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0), weekday = c(1, 
    0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1), weekend = c(0, 1, 
    1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0), workday_on_holiday = c(1, 
    0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0), weekend_on_holiday = c(0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), protocol_active = c(0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), text_broken_clouds = c(0, 
    1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), text_clear = c(0, 
    0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0), text_fog = c(0, 1, 
    0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0), text_partly_cloudy = c(0, 
    1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0), text_partly_sunny = c(1, 
    1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1), text_passing_clouds = c(1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), text_scattered_clouds = c(1, 
    1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1), text_sunny = c(0, 
    0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0), month_1 = c(1, 1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), month_2 = c(0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_3 = c(0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_4 = c(0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0), month_5 = c(0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0), month_6 = c(0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0), month_7 = c(0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0), month_8 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0), month_9 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0), month_10 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0), month_11 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0), month_12 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0)), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-14L)), structure(list(sanchinarro = c(0.832179838392013, 1.29225734336885, 
1.03665872949283, 0.525461501740789, -0.292454062662475, -0.394693508212883, 
-0.548052676538495, -0.139094894336863, 0.627700947291197, 1.19001789781844, 
1.59897568002007, 1.59897568002007, -0.701411844864107, 2.11017290777211
), date = structure(c(14611, 14612, 14613, 14614, 14615, 14616, 
14617, 14618, 14619, 14620, 14621, 14622, 14623, 14624), class = "Date"), 
    holiday = c(0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0), weekday = c(0, 
    0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1), weekend = c(1, 1, 
    0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0), workday_on_holiday = c(0, 
    0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0), weekend_on_holiday = c(0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), protocol_active = c(0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), text_broken_clouds = c(1, 
    0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0), text_clear = c(0, 
    0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1), text_fog = c(1, 0, 
    1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0), text_partly_cloudy = c(1, 
    0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0), text_partly_sunny = c(1, 
    1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), text_passing_clouds = c(1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), text_scattered_clouds = c(1, 
    0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0), text_sunny = c(0, 
    0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1), month_1 = c(1, 1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), month_2 = c(0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_3 = c(0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_4 = c(0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0), month_5 = c(0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0), month_6 = c(0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0), month_7 = c(0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0), month_8 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0), month_9 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0), month_10 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0), month_11 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0), month_12 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0)), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-14L)), structure(list(sanchinarro = c(1.29293502084952, 1.03729933727253, 
0.526027970118536, -0.292006217327851, -0.394260490758649, -0.547641900904846, 
-0.138624807181653, 0.628282243549334, 1.19068074741873, 1.59969784114192, 
1.59969784114192, -0.701023311051044, 2.11096920829591, 1.95758779814971
), date = structure(c(14612, 14613, 14614, 14615, 14616, 14617, 
14618, 14619, 14620, 14621, 14622, 14623, 14624, 14625), class = "Date"), 
    holiday = c(0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), weekday = c(0, 
    1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0), weekend = c(1, 0, 
    0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1), workday_on_holiday = c(0, 
    0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), weekend_on_holiday = c(0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), protocol_active = c(0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), text_broken_clouds = c(0, 
    1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1), text_clear = c(0, 
    0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0), text_fog = c(0, 1, 
    1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0), text_partly_cloudy = c(0, 
    0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0), text_partly_sunny = c(1, 
    1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1), text_passing_clouds = c(1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), text_scattered_clouds = c(0, 
    0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0), text_sunny = c(0, 
    0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0), month_1 = c(1, 1, 
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), month_2 = c(0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_3 = c(0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0), month_4 = c(0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0), month_5 = c(0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0), month_6 = c(0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0), month_7 = c(0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0), month_8 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0), month_9 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0), month_10 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0), month_11 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0), month_12 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0)), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-14L)))

编辑：

我思考这给了我我想要的-我需要仔细检查两次。 （如果您看到任何错误，请告诉我）

splt <- 0.80 * nrow(ddd)
ddd[c(1:splt), "id"] = 1
ddd$id[is.na(ddd$id)] = 2


fold.ids <- unique(ddd$id)

custom.folds <- vector("list", length(fold.ids))
i <- 1
for( id in fold.ids){
  custom.folds[[i]] <- which( ddd$id %in% id )
  i <- i+1
}

custom.folds

cv <- xgb.cv(params = list(eta = 0.1, max_depth = 5), dVal, nround = 10, folds = custom.folds, prediction = TRUE)
cv$evaluation_log

我现在需要找到一种方法将其应用于添加的“新”数据中的所有3个列表。

Answer 1

首先，应将数据分为dtrain（前40行）和dval（后10行）。其次，您需要xgb.train，而不是xgb.cv。

因此，您的代码应修改为类似的内容：