Release 2.1.4

CHANGELOG.md

@@ -1,6 +1,10 @@
 # Change Log
 All notable changes to this project will be documented in this file.
 
+## 2.1.4 - 2026-02
+ ### Common
+ - table reader optimization
+
 ## 2.1.3 - 2026-02
  ### Runner
  - Separate writer from runner, sorting schema to align to written table

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "rialto"
-version = "2.1.3"
+version = "2.1.4"
 description = "Rialto is a framework for building and deploying machine learning features in a scalable and reusable way. It provides a set of tools that make it easy to define and deploy features and models, and it provides a way to orchestrate the execution of these features and models."
 authors = [
     { name = "Marek Dobransky", email = "marekdobr@gmail.com" },

rialto/common/table_reader.py

@@ -88,9 +88,7 @@ def _uppercase_column_names(self, df: DataFrame) -> DataFrame:
         :param df: Dataframe
         :return: renamed Dataframe
         """
-        for col in df.columns:
-            df = df.withColumnRenamed(col, col.upper())
-        return df
+        return df.select(*[F.col(c).alias(c.upper()) for c in df.columns])
 
     def _get_latest_available_date(self, df: DataFrame, date_col: str, until: Optional[datetime.date]) -> datetime.date:
         if until:

tests/common/test_reader.py

@@ -0,0 +1,33 @@
+#  Copyright 2022 ABSA Group Limited
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+import pytest
+
+from rialto.common.table_reader import TableReader
+
+
+@pytest.fixture
+def sample_df(spark):
+    df = spark.createDataFrame(
+        [(1, 2.33, "str", 4.55, 5.66), (1, 2.33, "str", 4.55, 5.66), (1, 2.33, "str", 4.55, 5.66)],
+        schema="a long, b float, c string, d float, e float",
+    )
+
+    return df
+
+
+def test_uppercase_columns(spark, sample_df):
+    tr = TableReader(spark)
+    df = tr._uppercase_column_names(sample_df)
+    assert df.columns == ["A", "B", "C", "D", "E"]