rkw/bank-fraud-baf-lakehouse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor bucket structure: baf-fraud/ prefix under lake bucket

Browse Source 
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>
This commit is contained in:
Rob Wiederstein
2026-02-22 05:36:25 -05:00
parent dac01da6cb
commit df978d042f
11 changed files with 63 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
man/clean_baf_base.Rd
View File

@@ -6,8 +6,8 @@
\usage{
clean_baf_base(
in_prefix,
out_prefix = "03_primary/variant=Base",
bucket_name = "baf-fraud",
out_prefix = "baf-fraud/03_primary/variant=Base",
bucket_name = "lake",
partitioning = "month",
existing_data_behavior = c("overwrite", "error", "delete_matching"),
verbose = TRUE
@@ -18,7 +18,7 @@ clean_baf_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{bucket_name}{Character. Bucket name. Default "lake".}
\item{partitioning}{Character vector of columns to partition by. Default "month". Set NULL to disable.}

6
man/convert_to_parquet.Rd
View File

@@ -4,14 +4,14 @@
\alias{convert_to_parquet}
\title{Convert BAF CSV to partitioned Parquet in MinIO (S3)}
\usage{
convert_to_parquet(from_prefix, to_prefix, bucket_name = "baf-fraud")
convert_to_parquet(from_prefix, to_prefix, bucket_name = "lake")
}
\arguments{
\item{from_prefix}{Character. Prefix/key under the bucket containing CSVs (e.g. \code{"01_raw"}).}
\item{to_prefix}{Character. Prefix/key under the bucket to write Parquet dataset (e.g. \code{"02_intermediate"}).}
\item{bucket_name}{Character. Bucket name. Default \code{"baf-fraud"}.}
\item{bucket_name}{Character. Bucket name. Default \code{"lake"}.}
}
\value{
A character string giving the destination dataset prefix (typically \code{to_prefix}).
@@ -36,6 +36,6 @@ Sys.setenv(
BAF_KEY = "YOUR_ACCESS_KEY",
BAF_SECRET = "YOUR_SECRET_KEY"
)
convert_to_parquet(from_prefix = "01_raw", to_prefix = "02_intermediate", bucket_name = "baf-fraud")
convert_to_parquet(from_prefix = "01_raw", to_prefix = "02_intermediate", bucket_name = "lake")
}
}

8
man/engineer_features.Rd
View File

@@ -5,9 +5,9 @@
\title{Engineer features for the BAF dataset}
\usage{
engineer_features(
in_prefix = "03_primary/variant=Base",
out_prefix = "04_feature/variant=Base",
bucket_name = "baf-fraud",
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
@@ -18,7 +18,7 @@ engineer_features(
\item{out_prefix}{Character. Output dataset prefix (e.g., "04_feature/variant=Base").}
\item{bucket_name}{Character. The S3/MinIO bucket name. Default "baf-fraud".}
\item{bucket_name}{Character. The S3/MinIO bucket name. Default "lake".}
\item{partitioning}{Character vector. Columns to partition by. Default "month".}

6
man/evaluate_final_model.Rd
View File

@@ -6,15 +6,15 @@
\usage{
evaluate_final_model(
params,
bucket_name = "baf-fraud",
inputs_prefix = "05_model_input"
bucket_name = "lake",
inputs_prefix = "baf-fraud/05_model_input"
)
}
\arguments{
\item{params}{A named list of LightGBM hyperparameters with elements:
\code{trees}, \code{tree_depth}, \code{learn_rate}, \code{loss_reduction}, \code{min_n}.}
\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
\item{bucket_name}{Character. Bucket name. Default "lake".}
\item{inputs_prefix}{Character. Model input prefix. Default "05_model_input".}
}

8
man/generate_model_inputs.Rd
View File

@@ -5,9 +5,9 @@
\title{Generate Resampled Model Inputs}
\usage{
generate_model_inputs(
feature_prefix = "04_feature/variant=Base",
out_prefix = "05_model_input",
bucket_name = "baf-fraud"
feature_prefix = "baf-fraud/04_feature/variant=Base",
out_prefix = "baf-fraud/05_model_input",
bucket_name = "lake"
)
}
\arguments{
@@ -15,7 +15,7 @@ generate_model_inputs(
\item{out_prefix}{Character. Output prefix base (e.g., "05_model_input").}
\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
\item{bucket_name}{Character. Bucket name. Default "lake".}
}
\value{
Character. The output prefix (for targets dependency tracking).

4
man/plot_fraud_by_month.Rd
View File

@@ -6,7 +6,7 @@
\usage{
plot_fraud_by_month(
dataset_prefix,
bucket_name = "baf-fraud",
bucket_name = "lake",
palette = "Dark 3",
title = ""
)
@@ -14,7 +14,7 @@ plot_fraud_by_month(
\arguments{
\item{dataset_prefix}{Character. Prefix inside the bucket, e.g. "03_primary/variant=Base".}
\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
\item{bucket_name}{Character. Bucket name. Default "lake".}
\item{palette}{Character. colorspace qualitative palette name. Default "Dark 3".}

6
man/run_imbalance_tournament.Rd
View File

@@ -8,8 +8,8 @@ run_imbalance_tournament(
tasks,
windows,
feature_prefix,
bucket_name = "baf-fraud",
inputs_prefix = "05_model_input"
bucket_name = "lake",
inputs_prefix = "baf-fraud/05_model_input"
)
}
\arguments{
@@ -19,7 +19,7 @@ run_imbalance_tournament(
\item{feature_prefix}{Character. The upstream dependency prefix (used to force DAG execution).}
\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
\item{bucket_name}{Character. Bucket name. Default "lake".}
\item{inputs_prefix}{Character. The folder containing the sampled data. Default "05_model_input".}
}

6
man/tune_lgbm.Rd
View File

@@ -6,8 +6,8 @@
\usage{
tune_lgbm(
imbalance_windows,
bucket_name = "baf-fraud",
inputs_prefix = "05_model_input",
bucket_name = "lake",
inputs_prefix = "baf-fraud/05_model_input",
grid_size = 30L,
seed = 42L
)
@@ -17,7 +17,7 @@ tune_lgbm(
\code{train_months}, and \code{test_month}, as produced by the
\code{imbalance_windows} target.}
\item{bucket_name}{Character. MinIO bucket name. Default \code{"baf-fraud"}.}
\item{bucket_name}{Character. MinIO bucket name. Default \code{"lake"}.}
\item{inputs_prefix}{Character. Prefix for the model input layer.
Default \code{"05_model_input"}.}