% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/functions.R
\name{engineer_features}
\alias{engineer_features}
\title{Engineer features for the BAF dataset}
\usage{
engineer_features(
  in_prefix = "baf-fraud/03_primary/variant=Base",
  out_prefix = "baf-fraud/04_feature/variant=Base",
  bucket_name = "lake",
  partitioning = "month",
  existing_data_behavior = "delete_matching",
  verbose = TRUE
)
}
\arguments{
\item{in_prefix}{Character. Input dataset prefix (e.g., "03_primary/variant=Base").}

\item{out_prefix}{Character. Output dataset prefix (e.g., "04_feature/variant=Base").}

\item{bucket_name}{Character. The S3/MinIO bucket name. Default "lake".}

\item{partitioning}{Character vector. Columns to partition by. Default "month".}

\item{existing_data_behavior}{Character. Behavior when data exists. Default "delete_matching".}

\item{verbose}{Logical. Whether to print progress messages. Default TRUE.}
}
\value{
Character. The output prefix path for downstream targets.
}
\description{
Reads the primary BAF dataset and engineers new features, such as
\code{n_missing}, which counts the number of missing values across key
tenure and financial columns. This calculation is performed out-of-memory
using Arrow compute.
}