I am using sparklyr ml function
I want to ft_bucketizer some features with a split_conf file.
raw_ft_wide_sdf %>%
ft_bucketizer(input_cols = feature_list,
output_cols = paste0("bin_",feature_list),
uid = "user_id",
splits_array = perctl_conf %>%
purrr::map(unlist,use.names=T) #breaks,
)
however, I dont know how to pass splits_array
parameter correctly, and fail to find the answer through internet.