pdp partials fail with latest xgboost version

[Martin-Jung]

Likey due to internal parameter change, see migration guide for latest xgboost.

Reproducible code:

library(xgboost)
library(pdp)
data(ToothGrowth)
xgboost(
    ToothGrowth[, c("len", "dose")],
    ToothGrowth$supp,
    eval_metric = c("auc", "logloss"),
    eval_set = 0.2,
    monitor_training = TRUE,
    verbosity = 1,
    nthreads = 1,
    nrounds = 3
) -> mod

p1 <- pdp::partial(mod, "len")

Error in match.call(f, call = mcall) : invalid 'call' argument

Versions:
xgboost_3.1.3.1
pdp_0.8.2

[bgreenwell]

Thanks @Martin-Jung working on it this week for CRAN.

[bgreenwell]

@Martin-Jung I'm confused by your specific example. You store the model i fi but call partial() on an object called mod that I don't see defined here?

[Martin-Jung]

@Martin-Jung I'm confused by your specific example. You store the model i fi but call partial() on an object called mod that I don't see defined here?

Typo. Edited above. Simply call partial on xgboost trained object.
Haven't tested on the new xgb.train() call.