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

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:
2026-02-22 05:36:25 -05:00
parent dac01da6cb
commit df978d042f
11 changed files with 63 additions and 63 deletions

View File

@@ -32,9 +32,9 @@ list(
tar_target(
baf_parquet_prefix,
convert_to_parquet(
from_prefix = "01_raw",
to_prefix = "02_intermediate",
bucket_name = "baf-fraud"
from_prefix = "baf-fraud/01_raw",
to_prefix = "baf-fraud/02_intermediate",
bucket_name = "lake"
)
),
@@ -42,8 +42,8 @@ list(
baf_primary_prefix,
clean_baf_base(
in_prefix = baf_parquet_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 = "delete_matching",
verbose = TRUE
@@ -54,8 +54,8 @@ list(
baf_feature_prefix,
engineer_features(
in_prefix = baf_primary_prefix,
out_prefix = "04_feature/variant=Base",
bucket_name = "baf-fraud",
out_prefix = "baf-fraud/04_feature/variant=Base",
bucket_name = "lake",
partitioning = "month",
existing_data_behavior = "delete_matching",
verbose = TRUE
@@ -67,8 +67,8 @@ list(
baf_model_input_prefix,
generate_model_inputs(
feature_prefix = baf_feature_prefix,
out_prefix = "05_model_input",
bucket_name = "baf-fraud"
out_prefix = "baf-fraud/05_model_input",
bucket_name = "lake"
)
),
@@ -104,7 +104,7 @@ list(
# ---- Fraud Prevalence ----
tar_target(
fig_fraud_by_month,
plot_fraud_by_month(baf_primary_prefix, bucket_name = "baf-fraud")
plot_fraud_by_month(baf_primary_prefix, bucket_name = "lake")
),
tar_target(