Warning in asMethod(object) : sparse->dense coercion: allocating vector of size 13.0 GiB about quanteda HOT 4 CLOSED

It only says that conversion is using a lot of space in RAM. What the value of scheme?

from quanteda.

Not sure what scheme is and how to report it. Could you please help?

from quanteda.

@koheiw means we need at a minimum, the call to dfm_weight() to understand what you did, and ideally, reproducible code. We also need to know the version numbers that are shown when starting quanteda. Can you produce this output using reprex::reprex()?

By "scheme" we mean the scheme argument from dfm_weight():

dfm_weight(
  x,
  scheme = c("count", "prop", "propmax", "logcount", "boolean", "augmented", "logave"),
  weights = NULL,
  base = 10,
  k = 0.5,
  smoothing = 0.5,
  force = FALSE
)

from quanteda.

Thank you.

I am using both count and weights. Not sure which is causing the issue.

    if(!weighted){
      dfm_count = dfm_weight(dfm_custom, scheme = "count")
    } else {
      dfm_count= dfm_weight(dfm_custom, weights= list_weights)

from quanteda.