-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Closed
Labels
Description
Problem: Fail to call catboost.cv
catboost version: catboost R package (0.16)
Operating System: Win10
CPU: 6 cores
GPU: 0
When I try to run catboost.cv and use AUC metrics like following:
library(catboost)
library(dplyr)
cat_tr = catboost.load_pool(data = train %>% select(-c(ID_code, target)),
label = train$target)
catboost.cv(cat_tr,
params = list(loss_function='Logloss',
eval_metric='AUC',
iterations=5,
l2_leaf_reg=100,
depth=5,
use_best_model=T),
fold_count = 3,
stratified = T,
)
Error in (function (..., row.names = NULL, check.rows = FALSE, check.names = TRUE, :
arguments imply differing number of rows: 0, 5
However, if I remove the "eval_metric", the error disappears.