From 25a39906cef57f2ca6c1c672e8746bae66f5d8c3 Mon Sep 17 00:00:00 2001
From: jan-zajac-dt <jan.zajac@datatonic.com>
Date: Tue, 27 Jun 2023 14:42:49 +0200
Subject: [PATCH] remove underscore from suffix in env.sh.example and adjust
 pipelines to add it for BigQuery tables

---
 cloudbuild/e2e-test.yaml                                | 2 +-
 env.sh.example                                          | 4 ++--
 pipelines/src/pipelines/tensorflow/training/pipeline.py | 2 +-
 pipelines/src/pipelines/xgboost/training/pipeline.py    | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/cloudbuild/e2e-test.yaml b/cloudbuild/e2e-test.yaml
index 431bd515..b71430d2 100644
--- a/cloudbuild/e2e-test.yaml
+++ b/cloudbuild/e2e-test.yaml
@@ -45,7 +45,7 @@ steps:
       - PIPELINE_TEMPLATE=${_PIPELINE_TEMPLATE}
       - VERTEX_PIPELINE_ROOT=${_TEST_VERTEX_PIPELINE_ROOT}
       - PIPELINE_FILES_GCS_PATH=${_PIPELINE_PUBLISH_GCS_PATH}/${COMMIT_SHA}
-      - RESOURCE_SUFFIX=_${COMMIT_SHA}
+      - RESOURCE_SUFFIX=${COMMIT_SHA}
 
 options:
   logging: CLOUD_LOGGING_ONLY
diff --git a/env.sh.example b/env.sh.example
index 9041c783..3e747dfe 100644
--- a/env.sh.example
+++ b/env.sh.example
@@ -21,8 +21,8 @@ export VERTEX_LOCATION=europe-west2
 export VERTEX_NETWORK= # optional
 export VERTEX_PROJECT_ID=my-gcp-project
 
-# Suffix (e.g. '_<your name>') to facilitate running concurrent pipelines in the same Google Cloud project. Change if working in a team to avoid overwriting resources during development 
-export RESOURCE_SUFFIX=_default
+# Suffix (e.g. '<your name>') to facilitate running concurrent pipelines in the same Google Cloud project. Change if working in a team to avoid overwriting resources during development 
+export RESOURCE_SUFFIX=default
 
 # Leave as-is
 export VERTEX_SA_EMAIL=vertex-pipelines@${VERTEX_PROJECT_ID}.iam.gserviceaccount.com
diff --git a/pipelines/src/pipelines/tensorflow/training/pipeline.py b/pipelines/src/pipelines/tensorflow/training/pipeline.py
index f4474fb8..371928f5 100644
--- a/pipelines/src/pipelines/tensorflow/training/pipeline.py
+++ b/pipelines/src/pipelines/tensorflow/training/pipeline.py
@@ -75,7 +75,7 @@ def tensorflow_pipeline(
     label_column_name = "total_fare"
     time_column = "trip_start_timestamp"
     ingestion_table = "taxi_trips"
-    table_suffix = "_tf_training" + str(resource_suffix)  # suffix to table names
+    table_suffix = f"_tf_training_{resource_suffix}"  # suffix to table names
     ingested_table = "ingested_data" + table_suffix
     preprocessed_table = "preprocessed_data" + table_suffix
     train_table = "train_data" + table_suffix
diff --git a/pipelines/src/pipelines/xgboost/training/pipeline.py b/pipelines/src/pipelines/xgboost/training/pipeline.py
index e0e041a7..7db36231 100644
--- a/pipelines/src/pipelines/xgboost/training/pipeline.py
+++ b/pipelines/src/pipelines/xgboost/training/pipeline.py
@@ -74,7 +74,7 @@ def xgboost_pipeline(
     label_column_name = "total_fare"
     time_column = "trip_start_timestamp"
     ingestion_table = "taxi_trips"
-    table_suffix = "_xgb_training" + str(resource_suffix)  # suffix to table names
+    table_suffix = f"_xgb_training_{resource_suffix}"  # suffix to table names
     ingested_table = "ingested_data" + table_suffix
     preprocessed_table = "preprocessed_data" + table_suffix
     train_table = "train_data" + table_suffix