Rob Wiederstein
33d0fc31c7
End-to-end LightGBM fraud detection pipeline built as an R package, orchestrated by targets with data stored in MinIO via Apache Arrow. Includes 6-layer Lakehouse architecture, class imbalance tournament, formally tuned hyperparameters (PR-AUC 0.198), and Quarto RevealJS slides. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
35 lines
1.1 KiB
R
35 lines
1.1 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/functions.R
|
|
\name{clean_baf_base}
|
|
\alias{clean_baf_base}
|
|
\title{Clean the BAF Base dataset and write to 03_primary}
|
|
\usage{
|
|
clean_baf_base(
|
|
in_prefix,
|
|
out_prefix = "03_primary/variant=Base",
|
|
bucket_name = "baf-fraud",
|
|
partitioning = "month",
|
|
existing_data_behavior = c("overwrite", "error", "delete_matching"),
|
|
verbose = TRUE
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{in_prefix}{Character. Input dataset prefix inside bucket (e.g. "02_intermediate/variant=Base").}
|
|
|
|
\item{out_prefix}{Character. Output dataset prefix inside bucket (e.g. "03_primary/variant=Base").}
|
|
|
|
\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
|
|
|
|
\item{partitioning}{Character vector of columns to partition by. Default "month". Set NULL to disable.}
|
|
|
|
\item{existing_data_behavior}{One of "overwrite", "error", "delete_matching". Default "overwrite".}
|
|
|
|
\item{verbose}{Logical. Emit progress messages. Default TRUE.}
|
|
}
|
|
\value{
|
|
Character. out_prefix (for downstream targets).
|
|
}
|
|
\description{
|
|
Clean the BAF Base dataset and write to 03_primary
|
|
}
|