From 721cefe10ebd085a64cc0777e62c99999ece55ff Mon Sep 17 00:00:00 2001
From: Pieter Noordhuis <pieter.noordhuis@databricks.com>
Date: Fri, 17 Jan 2025 11:31:16 +0100
Subject: [PATCH 1/6] Format Python code with ruff

---
 .gitignore                                    |  1 +
 .ruff.toml                                    |  8 +++++++
 contrib/data_engineering/scripts/add_asset.py |  5 ++++-
 .../{{.project_name}}/scripts/add_asset.py    |  5 ++++-
 default_python/setup.py                       | 18 +++++++--------
 default_python/src/default_python/main.py     | 22 +++++++++++--------
 default_python/src/dlt_pipeline.ipynb         |  6 +++--
 .../src/my_custom_wheel1/__init__.py          |  2 ++
 .../src/my_custom_wheel2/__init__.py          |  2 ++
 .../src/call_wheel.py                         |  2 +-
 .../private_wheel_packages/src/main.py        |  4 ++--
 .../src/python_wheel_poetry/hello.py          |  2 ++
 .../deployment/batch_inference/predict.py     |  6 ++---
 .../deployment/model_deployment/deploy.py     | 12 ++++------
 .../mlops_stacks/validation/validation.py     |  5 +++--
 15 files changed, 62 insertions(+), 38 deletions(-)
 create mode 100644 .gitignore
 create mode 100644 .ruff.toml

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..b25701b2
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.ruff_cache
diff --git a/.ruff.toml b/.ruff.toml
new file mode 100644
index 00000000..08229033
--- /dev/null
+++ b/.ruff.toml
@@ -0,0 +1,8 @@
+[format]
+exclude = [
+    # Databricks notebooks with % magic commands don't parse as valid Python.
+    "mlops_stacks/mlops_stacks/deployment/batch_inference/notebooks/BatchInference.py",
+    "mlops_stacks/mlops_stacks/deployment/model_deployment/notebooks/ModelDeployment.py",
+    "mlops_stacks/mlops_stacks/training/notebooks/Train.py",
+    "mlops_stacks/mlops_stacks/validation/notebooks/ModelValidation.py",
+]
diff --git a/contrib/data_engineering/scripts/add_asset.py b/contrib/data_engineering/scripts/add_asset.py
index 72991a81..1a20ae53 100644
--- a/contrib/data_engineering/scripts/add_asset.py
+++ b/contrib/data_engineering/scripts/add_asset.py
@@ -11,7 +11,10 @@
 
 
 def init_bundle(asset_type: AssetType) -> None:
-    cmd = f"databricks bundle init https://github.com/databricks/bundle-examples --template-dir contrib/templates/data-engineering/assets/{asset_type} " + " ".join(sys.argv[2:])
+    cmd = (
+        f"databricks bundle init https://github.com/databricks/bundle-examples --template-dir contrib/templates/data-engineering/assets/{asset_type} "
+        + " ".join(sys.argv[2:])
+    )
     subprocess.run(cmd, shell=True)
 
 
diff --git a/contrib/templates/data-engineering/template/{{.project_name}}/scripts/add_asset.py b/contrib/templates/data-engineering/template/{{.project_name}}/scripts/add_asset.py
index 72991a81..1a20ae53 100644
--- a/contrib/templates/data-engineering/template/{{.project_name}}/scripts/add_asset.py
+++ b/contrib/templates/data-engineering/template/{{.project_name}}/scripts/add_asset.py
@@ -11,7 +11,10 @@
 
 
 def init_bundle(asset_type: AssetType) -> None:
-    cmd = f"databricks bundle init https://github.com/databricks/bundle-examples --template-dir contrib/templates/data-engineering/assets/{asset_type} " + " ".join(sys.argv[2:])
+    cmd = (
+        f"databricks bundle init https://github.com/databricks/bundle-examples --template-dir contrib/templates/data-engineering/assets/{asset_type} "
+        + " ".join(sys.argv[2:])
+    )
     subprocess.run(cmd, shell=True)
 
 
diff --git a/default_python/setup.py b/default_python/setup.py
index 6ba5b7b4..c193bbd4 100644
--- a/default_python/setup.py
+++ b/default_python/setup.py
@@ -5,10 +5,12 @@
 be executed directly. See README.md for how to deploy, test, and run
 the default_python project.
 """
+
 from setuptools import setup, find_packages
 
 import sys
-sys.path.append('./src')
+
+sys.path.append("./src")
 
 import datetime
 import default_python
@@ -17,17 +19,15 @@
     name="default_python",
     # We use timestamp as Local version identifier (https://peps.python.org/pep-0440/#local-version-identifiers.)
     # to ensure that changes to wheel package are picked up when used on all-purpose clusters
-    version=default_python.__version__ + "+" + datetime.datetime.utcnow().strftime("%Y%m%d.%H%M%S"),
+    version=default_python.__version__
+    + "+"
+    + datetime.datetime.utcnow().strftime("%Y%m%d.%H%M%S"),
     url="https://databricks.com",
     author="user@company.com",
     description="wheel file based on default_python/src",
-    packages=find_packages(where='./src'),
-    package_dir={'': 'src'},
-    entry_points={
-        "packages": [
-            "main=default_python.main:main"
-        ]
-    },
+    packages=find_packages(where="./src"),
+    package_dir={"": "src"},
+    entry_points={"packages": ["main=default_python.main:main"]},
     install_requires=[
         # Dependencies in case the output wheel file is used as a library dependency.
         # For defining dependencies, when this package is used in Databricks, see:
diff --git a/default_python/src/default_python/main.py b/default_python/src/default_python/main.py
index c514c6dc..5ae344c7 100644
--- a/default_python/src/default_python/main.py
+++ b/default_python/src/default_python/main.py
@@ -1,21 +1,25 @@
 from pyspark.sql import SparkSession, DataFrame
 
+
 def get_taxis(spark: SparkSession) -> DataFrame:
-  return spark.read.table("samples.nyctaxi.trips")
+    return spark.read.table("samples.nyctaxi.trips")
 
 
 # Create a new Databricks Connect session. If this fails,
 # check that you have configured Databricks Connect correctly.
 # See https://docs.databricks.com/dev-tools/databricks-connect.html.
 def get_spark() -> SparkSession:
-  try:
-    from databricks.connect import DatabricksSession
-    return DatabricksSession.builder.getOrCreate()
-  except ImportError:
-    return SparkSession.builder.getOrCreate()
+    try:
+        from databricks.connect import DatabricksSession
+
+        return DatabricksSession.builder.getOrCreate()
+    except ImportError:
+        return SparkSession.builder.getOrCreate()
+
 
 def main():
-  get_taxis(get_spark()).show(5)
+    get_taxis(get_spark()).show(5)
+
 
-if __name__ == '__main__':
-  main()
+if __name__ == "__main__":
+    main()
diff --git a/default_python/src/dlt_pipeline.ipynb b/default_python/src/dlt_pipeline.ipynb
index 4216a065..6bd508a2 100644
--- a/default_python/src/dlt_pipeline.ipynb
+++ b/default_python/src/dlt_pipeline.ipynb
@@ -34,6 +34,7 @@
     "# Import DLT and src/default_python\n",
     "import dlt\n",
     "import sys\n",
+    "\n",
     "sys.path.append(spark.conf.get(\"bundle.sourcePath\", \".\"))\n",
     "from pyspark.sql.functions import expr\n",
     "from default_python import main"
@@ -55,11 +56,12 @@
    "source": [
     "@dlt.view\n",
     "def taxi_raw():\n",
-    "  return main.get_taxis(spark)\n",
+    "    return main.get_taxis(spark)\n",
+    "\n",
     "\n",
     "@dlt.table\n",
     "def filtered_taxis():\n",
-    "  return dlt.read(\"taxi_raw\").filter(expr(\"fare_amount < 30\"))"
+    "    return dlt.read(\"taxi_raw\").filter(expr(\"fare_amount < 30\"))"
    ]
   }
  ],
diff --git a/knowledge_base/job_with_multiple_wheels/my_custom_wheel1/src/my_custom_wheel1/__init__.py b/knowledge_base/job_with_multiple_wheels/my_custom_wheel1/src/my_custom_wheel1/__init__.py
index 79981ae4..7b614d08 100644
--- a/knowledge_base/job_with_multiple_wheels/my_custom_wheel1/src/my_custom_wheel1/__init__.py
+++ b/knowledge_base/job_with_multiple_wheels/my_custom_wheel1/src/my_custom_wheel1/__init__.py
@@ -3,5 +3,7 @@
 """
 Function to be called by [my_custom_wheel2].
 """
+
+
 def hello():
     cowsay.cow("Hello, world!")
diff --git a/knowledge_base/job_with_multiple_wheels/my_custom_wheel2/src/my_custom_wheel2/__init__.py b/knowledge_base/job_with_multiple_wheels/my_custom_wheel2/src/my_custom_wheel2/__init__.py
index 51b098ad..02569d40 100644
--- a/knowledge_base/job_with_multiple_wheels/my_custom_wheel2/src/my_custom_wheel2/__init__.py
+++ b/knowledge_base/job_with_multiple_wheels/my_custom_wheel2/src/my_custom_wheel2/__init__.py
@@ -3,5 +3,7 @@
 """
 Function that calls into [my_custom_wheel1].
 """
+
+
 def hello():
     my_custom_wheel1.hello()
diff --git a/knowledge_base/job_with_multiple_wheels/src/call_wheel.py b/knowledge_base/job_with_multiple_wheels/src/call_wheel.py
index 45ba8989..26a6bbab 100644
--- a/knowledge_base/job_with_multiple_wheels/src/call_wheel.py
+++ b/knowledge_base/job_with_multiple_wheels/src/call_wheel.py
@@ -1,4 +1,4 @@
 import my_custom_wheel2
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     my_custom_wheel2.hello()
diff --git a/knowledge_base/private_wheel_packages/src/main.py b/knowledge_base/private_wheel_packages/src/main.py
index 06d5e490..ef3a0e61 100644
--- a/knowledge_base/private_wheel_packages/src/main.py
+++ b/knowledge_base/private_wheel_packages/src/main.py
@@ -2,5 +2,5 @@
 # include an arbitrary wheel file in your bundle directory, deploy it, and use it from within your code.
 import cowsay
 
-if __name__ == '__main__':
-    cowsay.cow('Hello, world!')
+if __name__ == "__main__":
+    cowsay.cow("Hello, world!")
diff --git a/knowledge_base/python_wheel_poetry/src/python_wheel_poetry/hello.py b/knowledge_base/python_wheel_poetry/src/python_wheel_poetry/hello.py
index 5a0d7c3a..6e4200da 100644
--- a/knowledge_base/python_wheel_poetry/src/python_wheel_poetry/hello.py
+++ b/knowledge_base/python_wheel_poetry/src/python_wheel_poetry/hello.py
@@ -10,5 +10,7 @@
 The value is the path to the function that is called when the command is run.
 The key is referred to in the `python_wheel_task` section in `databricks.yml`.
 """
+
+
 def hello():
     cowsay.cow("Hello, world!")
diff --git a/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py b/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py
index c08b61d2..00d311e1 100644
--- a/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py
+++ b/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py
@@ -11,7 +11,7 @@ def predict_batch(
     """
     mlflow.set_registry_uri("databricks-uc")
     table = spark_session.table(input_table_name)
-    
+
     predict = mlflow.pyfunc.spark_udf(
         spark_session, model_uri, result_type="string", env_manager="virtualenv"
     )
@@ -20,8 +20,8 @@ def predict_batch(
         .withColumn("model_version", lit(model_version))
         .withColumn("inference_timestamp", to_timestamp(lit(ts)))
     )
-    
+
     output_df.display()
     # Model predictions are written to the Delta table provided as input.
     # Delta is the default format in Databricks Runtime 8.0 and above.
-    output_df.write.format("delta").mode("overwrite").saveAsTable(output_table_name)
\ No newline at end of file
+    output_df.write.format("delta").mode("overwrite").saveAsTable(output_table_name)
diff --git a/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py b/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py
index 8dd72990..0add6e44 100644
--- a/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py
+++ b/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py
@@ -22,18 +22,14 @@ def deploy(model_uri, env):
     target_alias = "Champion"
     if target_alias not in mv.aliases:
         client.set_registered_model_alias(
-            name=model_name,
-            alias=target_alias, 
-            version=version)
+            name=model_name, alias=target_alias, version=version
+        )
         print(f"Assigned alias '{target_alias}' to model version {model_uri}.")
-        
+
         # remove "Challenger" alias if assigning "Champion" alias
         if target_alias == "Champion" and "Challenger" in mv.aliases:
             print(f"Removing 'Challenger' alias from model version {model_uri}.")
-            client.delete_registered_model_alias(
-                name=model_name,
-                alias="Challenger")
-
+            client.delete_registered_model_alias(name=model_name, alias="Challenger")
 
 
 if __name__ == "__main__":
diff --git a/mlops_stacks/mlops_stacks/validation/validation.py b/mlops_stacks/mlops_stacks/validation/validation.py
index ac4f2eac..ced8329d 100644
--- a/mlops_stacks/mlops_stacks/validation/validation.py
+++ b/mlops_stacks/mlops_stacks/validation/validation.py
@@ -1,11 +1,11 @@
 import numpy as np
 from mlflow.models import make_metric, MetricThreshold
 
+
 # Custom metrics to be included. Return empty list if custom metrics are not needed.
 # Please refer to custom_metrics parameter in mlflow.evaluate documentation https://mlflow.org/docs/latest/python_api/mlflow.html#mlflow.evaluate
 # TODO(optional) : custom_metrics
 def custom_metrics():
-
     # TODO(optional) : define custom metric function to be included in custom_metrics.
     def squared_diff_plus_one(eval_df, _builtin_metrics):
         """
@@ -23,7 +23,8 @@ def squared_diff_plus_one(eval_df, _builtin_metrics):
 def validation_thresholds():
     return {
         "max_error": MetricThreshold(
-            threshold=500, higher_is_better=False  # max_error should be <= 500
+            threshold=500,
+            higher_is_better=False,  # max_error should be <= 500
         ),
         "mean_squared_error": MetricThreshold(
             threshold=20,  # mean_squared_error should be <= 20

From eab04865e71a70ef1c9363979cd8ad0e9f326eba Mon Sep 17 00:00:00 2001
From: Pieter Noordhuis <pieter.noordhuis@databricks.com>
Date: Fri, 17 Jan 2025 11:33:29 +0100
Subject: [PATCH 2/6] Run ruff format in workflow

---
 .github/workflows/fmt.yml | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 .github/workflows/fmt.yml

diff --git a/.github/workflows/fmt.yml b/.github/workflows/fmt.yml
new file mode 100644
index 00000000..0210813d
--- /dev/null
+++ b/.github/workflows/fmt.yml
@@ -0,0 +1,23 @@
+name: fmt
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+  merge_group:
+    types: [checks_requested]
+
+jobs:
+  ruff:
+    runs-on:
+      group: databricks-protected-runner-group
+      labels: linux-ubuntu-latest
+
+    steps:
+      - name: Checkout repository and submodules
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install ruff
+        uses: astral-sh/ruff-action@31a518504640beb4897d0b9f9e50a2a9196e75ba # v3.0.1
+        with:
+          version: "0.9.1"
+          args: "format --check"

From 5033784b3b4d8449a7db31b46e3127d5cee516d3 Mon Sep 17 00:00:00 2001
From: Pieter Noordhuis <pieter.noordhuis@databricks.com>
Date: Fri, 17 Jan 2025 11:37:31 +0100
Subject: [PATCH 3/6] Skip formatting of templates

---
 .ruff.toml                                    | 10 ++++-----
 default_python/setup.py                       | 18 +++++++--------
 default_python/src/default_python/main.py     | 22 ++++++++-----------
 default_python/src/dlt_pipeline.ipynb         |  6 ++---
 .../deployment/batch_inference/predict.py     |  6 ++---
 .../deployment/model_deployment/deploy.py     | 12 ++++++----
 .../mlops_stacks/validation/validation.py     |  5 ++---
 7 files changed, 38 insertions(+), 41 deletions(-)

diff --git a/.ruff.toml b/.ruff.toml
index 08229033..093fc8d9 100644
--- a/.ruff.toml
+++ b/.ruff.toml
@@ -1,8 +1,8 @@
 [format]
 exclude = [
-    # Databricks notebooks with % magic commands don't parse as valid Python.
-    "mlops_stacks/mlops_stacks/deployment/batch_inference/notebooks/BatchInference.py",
-    "mlops_stacks/mlops_stacks/deployment/model_deployment/notebooks/ModelDeployment.py",
-    "mlops_stacks/mlops_stacks/training/notebooks/Train.py",
-    "mlops_stacks/mlops_stacks/validation/notebooks/ModelValidation.py",
+    # Templates are responsible for formatting at the source.
+    "dbt_sql",
+    "default_python",
+    "default_sql",
+    "mlops_stacks",
 ]
diff --git a/default_python/setup.py b/default_python/setup.py
index c193bbd4..6ba5b7b4 100644
--- a/default_python/setup.py
+++ b/default_python/setup.py
@@ -5,12 +5,10 @@
 be executed directly. See README.md for how to deploy, test, and run
 the default_python project.
 """
-
 from setuptools import setup, find_packages
 
 import sys
-
-sys.path.append("./src")
+sys.path.append('./src')
 
 import datetime
 import default_python
@@ -19,15 +17,17 @@
     name="default_python",
     # We use timestamp as Local version identifier (https://peps.python.org/pep-0440/#local-version-identifiers.)
     # to ensure that changes to wheel package are picked up when used on all-purpose clusters
-    version=default_python.__version__
-    + "+"
-    + datetime.datetime.utcnow().strftime("%Y%m%d.%H%M%S"),
+    version=default_python.__version__ + "+" + datetime.datetime.utcnow().strftime("%Y%m%d.%H%M%S"),
     url="https://databricks.com",
     author="user@company.com",
     description="wheel file based on default_python/src",
-    packages=find_packages(where="./src"),
-    package_dir={"": "src"},
-    entry_points={"packages": ["main=default_python.main:main"]},
+    packages=find_packages(where='./src'),
+    package_dir={'': 'src'},
+    entry_points={
+        "packages": [
+            "main=default_python.main:main"
+        ]
+    },
     install_requires=[
         # Dependencies in case the output wheel file is used as a library dependency.
         # For defining dependencies, when this package is used in Databricks, see:
diff --git a/default_python/src/default_python/main.py b/default_python/src/default_python/main.py
index 5ae344c7..c514c6dc 100644
--- a/default_python/src/default_python/main.py
+++ b/default_python/src/default_python/main.py
@@ -1,25 +1,21 @@
 from pyspark.sql import SparkSession, DataFrame
 
-
 def get_taxis(spark: SparkSession) -> DataFrame:
-    return spark.read.table("samples.nyctaxi.trips")
+  return spark.read.table("samples.nyctaxi.trips")
 
 
 # Create a new Databricks Connect session. If this fails,
 # check that you have configured Databricks Connect correctly.
 # See https://docs.databricks.com/dev-tools/databricks-connect.html.
 def get_spark() -> SparkSession:
-    try:
-        from databricks.connect import DatabricksSession
-
-        return DatabricksSession.builder.getOrCreate()
-    except ImportError:
-        return SparkSession.builder.getOrCreate()
-
+  try:
+    from databricks.connect import DatabricksSession
+    return DatabricksSession.builder.getOrCreate()
+  except ImportError:
+    return SparkSession.builder.getOrCreate()
 
 def main():
-    get_taxis(get_spark()).show(5)
-
+  get_taxis(get_spark()).show(5)
 
-if __name__ == "__main__":
-    main()
+if __name__ == '__main__':
+  main()
diff --git a/default_python/src/dlt_pipeline.ipynb b/default_python/src/dlt_pipeline.ipynb
index 6bd508a2..4216a065 100644
--- a/default_python/src/dlt_pipeline.ipynb
+++ b/default_python/src/dlt_pipeline.ipynb
@@ -34,7 +34,6 @@
     "# Import DLT and src/default_python\n",
     "import dlt\n",
     "import sys\n",
-    "\n",
     "sys.path.append(spark.conf.get(\"bundle.sourcePath\", \".\"))\n",
     "from pyspark.sql.functions import expr\n",
     "from default_python import main"
@@ -56,12 +55,11 @@
    "source": [
     "@dlt.view\n",
     "def taxi_raw():\n",
-    "    return main.get_taxis(spark)\n",
-    "\n",
+    "  return main.get_taxis(spark)\n",
     "\n",
     "@dlt.table\n",
     "def filtered_taxis():\n",
-    "    return dlt.read(\"taxi_raw\").filter(expr(\"fare_amount < 30\"))"
+    "  return dlt.read(\"taxi_raw\").filter(expr(\"fare_amount < 30\"))"
    ]
   }
  ],
diff --git a/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py b/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py
index 00d311e1..c08b61d2 100644
--- a/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py
+++ b/mlops_stacks/mlops_stacks/deployment/batch_inference/predict.py
@@ -11,7 +11,7 @@ def predict_batch(
     """
     mlflow.set_registry_uri("databricks-uc")
     table = spark_session.table(input_table_name)
-
+    
     predict = mlflow.pyfunc.spark_udf(
         spark_session, model_uri, result_type="string", env_manager="virtualenv"
     )
@@ -20,8 +20,8 @@ def predict_batch(
         .withColumn("model_version", lit(model_version))
         .withColumn("inference_timestamp", to_timestamp(lit(ts)))
     )
-
+    
     output_df.display()
     # Model predictions are written to the Delta table provided as input.
     # Delta is the default format in Databricks Runtime 8.0 and above.
-    output_df.write.format("delta").mode("overwrite").saveAsTable(output_table_name)
+    output_df.write.format("delta").mode("overwrite").saveAsTable(output_table_name)
\ No newline at end of file
diff --git a/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py b/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py
index 0add6e44..8dd72990 100644
--- a/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py
+++ b/mlops_stacks/mlops_stacks/deployment/model_deployment/deploy.py
@@ -22,14 +22,18 @@ def deploy(model_uri, env):
     target_alias = "Champion"
     if target_alias not in mv.aliases:
         client.set_registered_model_alias(
-            name=model_name, alias=target_alias, version=version
-        )
+            name=model_name,
+            alias=target_alias, 
+            version=version)
         print(f"Assigned alias '{target_alias}' to model version {model_uri}.")
-
+        
         # remove "Challenger" alias if assigning "Champion" alias
         if target_alias == "Champion" and "Challenger" in mv.aliases:
             print(f"Removing 'Challenger' alias from model version {model_uri}.")
-            client.delete_registered_model_alias(name=model_name, alias="Challenger")
+            client.delete_registered_model_alias(
+                name=model_name,
+                alias="Challenger")
+
 
 
 if __name__ == "__main__":
diff --git a/mlops_stacks/mlops_stacks/validation/validation.py b/mlops_stacks/mlops_stacks/validation/validation.py
index ced8329d..ac4f2eac 100644
--- a/mlops_stacks/mlops_stacks/validation/validation.py
+++ b/mlops_stacks/mlops_stacks/validation/validation.py
@@ -1,11 +1,11 @@
 import numpy as np
 from mlflow.models import make_metric, MetricThreshold
 
-
 # Custom metrics to be included. Return empty list if custom metrics are not needed.
 # Please refer to custom_metrics parameter in mlflow.evaluate documentation https://mlflow.org/docs/latest/python_api/mlflow.html#mlflow.evaluate
 # TODO(optional) : custom_metrics
 def custom_metrics():
+
     # TODO(optional) : define custom metric function to be included in custom_metrics.
     def squared_diff_plus_one(eval_df, _builtin_metrics):
         """
@@ -23,8 +23,7 @@ def squared_diff_plus_one(eval_df, _builtin_metrics):
 def validation_thresholds():
     return {
         "max_error": MetricThreshold(
-            threshold=500,
-            higher_is_better=False,  # max_error should be <= 500
+            threshold=500, higher_is_better=False  # max_error should be <= 500
         ),
         "mean_squared_error": MetricThreshold(
             threshold=20,  # mean_squared_error should be <= 20

From 137faf1c2d798922d1607359734b25f4348bacaa Mon Sep 17 00:00:00 2001
From: Pieter Noordhuis <pieter.noordhuis@databricks.com>
Date: Fri, 17 Jan 2025 11:44:58 +0100
Subject: [PATCH 4/6] Include glob in exclude pattern

---
 .ruff.toml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.ruff.toml b/.ruff.toml
index 093fc8d9..6845a35c 100644
--- a/.ruff.toml
+++ b/.ruff.toml
@@ -1,8 +1,8 @@
 [format]
 exclude = [
     # Templates are responsible for formatting at the source.
-    "dbt_sql",
-    "default_python",
-    "default_sql",
-    "mlops_stacks",
+    "dbt_sql/*",
+    "default_python/*",
+    "default_sql/*",
+    "mlops_stacks/*",
 ]

From 5f17c0efb4289abdd3a3cb54ad096557ff741a57 Mon Sep 17 00:00:00 2001
From: Pieter Noordhuis <pieter.noordhuis@databricks.com>
Date: Fri, 17 Jan 2025 11:45:51 +0100
Subject: [PATCH 5/6] Format again

---
 .../streamlit-app/template/{{.project_name}}/app/app.py     | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/contrib/templates/streamlit-app/template/{{.project_name}}/app/app.py b/contrib/templates/streamlit-app/template/{{.project_name}}/app/app.py
index 8cec20ae..ba338ed2 100644
--- a/contrib/templates/streamlit-app/template/{{.project_name}}/app/app.py
+++ b/contrib/templates/streamlit-app/template/{{.project_name}}/app/app.py
@@ -5,9 +5,9 @@
 import pandas as pd
 
 # Ensure environment variable is set correctly
-assert os.getenv(
-    "DATABRICKS_WAREHOUSE_ID"
-), "DATABRICKS_WAREHOUSE_ID must be set in app.yaml."
+assert os.getenv("DATABRICKS_WAREHOUSE_ID"), (
+    "DATABRICKS_WAREHOUSE_ID must be set in app.yaml."
+)
 
 
 def sqlQuery(query: str) -> pd.DataFrame:

From 54c73e1c8c989b4f52e26b181a496f134505ea50 Mon Sep 17 00:00:00 2001
From: Pieter Noordhuis <pieter.noordhuis@databricks.com>
Date: Fri, 17 Jan 2025 11:47:10 +0100
Subject: [PATCH 6/6] Install -> Run

---
 .github/workflows/fmt.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/fmt.yml b/.github/workflows/fmt.yml
index 0210813d..265ab493 100644
--- a/.github/workflows/fmt.yml
+++ b/.github/workflows/fmt.yml
@@ -16,7 +16,7 @@ jobs:
       - name: Checkout repository and submodules
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
-      - name: Install ruff
+      - name: Run ruff
         uses: astral-sh/ruff-action@31a518504640beb4897d0b9f9e50a2a9196e75ba # v3.0.1
         with:
           version: "0.9.1"