Rob Wiederstein
df978d042f
All functions now default to bucket_name = "lake" with "baf-fraud/" prepended to all layer prefixes, matching the contemporary lakehouse naming convention (one bucket per environment, project as prefix). Migration: copy baf-fraud/ data to lake/baf-fraud/ on analyticsvm, update BAF_BUCKET env var from "baf-fraud" to "lake". Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
28 lines
874 B
R
28 lines
874 B
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/functions.R
|
|
\name{generate_model_inputs}
|
|
\alias{generate_model_inputs}
|
|
\title{Generate Resampled Model Inputs}
|
|
\usage{
|
|
generate_model_inputs(
|
|
feature_prefix = "baf-fraud/04_feature/variant=Base",
|
|
out_prefix = "baf-fraud/05_model_input",
|
|
bucket_name = "lake"
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{feature_prefix}{Character. Input prefix (e.g., "04_feature/variant=Base").}
|
|
|
|
\item{out_prefix}{Character. Output prefix base (e.g., "05_model_input").}
|
|
|
|
\item{bucket_name}{Character. Bucket name. Default "lake".}
|
|
}
|
|
\value{
|
|
Character. The output prefix (for targets dependency tracking).
|
|
}
|
|
\description{
|
|
Reads the engineered feature layer, prepares a base tidymodels recipe,
|
|
and generates resampled datasets (Baseline, Under, SMOTE, Adasyn, Tomek)
|
|
across all months, saving them to the 05_model_input prefix.
|
|
}
|