Reducing test times

Author: harsh97

ads/feature_store/common/spark_session_singleton.py

@@ -11,6 +11,7 @@
 import os
 
 from ads.common.oci_client import OCIClientFactory
+from ads.feature_store.common.utils.utility import get_env_bool
 
 try:
     from delta import configure_spark_with_delta_pip
@@ -33,7 +34,7 @@
 
 
 def developer_enabled():
-    return os.getenv("DEVELOPER_MODE")
+    return get_env_bool("DEVELOPER_MODE", False)
 
 
 class SingletonMeta(type):

ads/feature_store/common/utils/utility.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
-
+import os
 # Copyright (c) 2023 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
@@ -60,6 +60,25 @@ def get_execution_engine_type(
         else ExecutionEngine.SPARK
     )
 
+def get_env_bool(env_var: str, default: bool = False) -> bool:
+    """
+    :param env_var: Environment variable name
+    :param default: Default environment variable value
+    :return: Value of the boolean env variable
+    """
+    env_val = os.getenv(env_var)
+    if env_val is None:
+        env_val = default
+    else:
+        env_val = env_val.lower()
+        if env_val == "true":
+            env_val = True
+        elif env_val == "false":
+            env_val = False
+        else:
+            raise ValueError("For environment variable: {0} only string values T/true or F/false are allowed but: \
+                {1} was provided.".format(env_var, env_val))
+    return env_val
 
 def get_metastore_id(feature_store_id: str):
     """

tests/integration/feature_store/test_datatype_pandas_mixed.py

@@ -5,15 +5,14 @@
 import numpy as np
 import pytest
 
-flights_df = pd.read_csv("https://objectstorage.us-ashburn-1.oraclecloud.com/p/hh2NOgFJbVSg4amcLM3G3hkTuHyBD-8aE_iCsuZKEvIav1Wlld-3zfCawG4ycQGN/n/ociodscdev/b/oci-feature-store/o/beta/data/flights/flights.csv")
-flights_df_mixed = pd.DataFrame(flights_df["CANCELLATION_REASON"])
 
 
 class TestDataTypePandasMixed(FeatureStoreTestCase):
+    flights_df = pd.read_csv("https://objectstorage.us-ashburn-1.oraclecloud.com/p/hh2NOgFJbVSg4amcLM3G3hkTuHyBD-8aE_iCsuZKEvIav1Wlld-3zfCawG4ycQGN/n/ociodscdev/b/oci-feature-store/o/beta/data/flights/flights.csv")
+    flights_df_mixed = pd.DataFrame(flights_df["CANCELLATION_REASON"])
 
     input_feature_details_mixed = [
-        FeatureDetail("CANCELLATION_REASON").with_feature_type(FeatureType.STRING).with_order_number(1)]
-
+            FeatureDetail("CANCELLATION_REASON").with_feature_type(FeatureType.STRING).with_order_number(1)]
     def define_feature_group_resource_with_pandas_mixed_infer_schema(
         self, entity_id, feature_store_id
     ):
@@ -27,7 +26,7 @@ def define_feature_group_resource_with_pandas_mixed_infer_schema(
                 .with_entity_id(entity_id)
                 .with_feature_store_id(feature_store_id)
                 .with_primary_keys([])
-                .with_schema_details_from_dataframe(flights_df_mixed)
+                .with_schema_details_from_dataframe(self.flights_df_mixed)
                 .with_statistics_config(False)
             )
 
@@ -76,7 +75,7 @@ def test_feature_group_pandas_mixed_with_schema(self):
         feature_group.create()
         assert feature_group.oci_feature_group.id
 
-        feature_group.materialise(flights_df_mixed)
+        feature_group.materialise(self.flights_df_mixed)
         df = feature_group.select().read()
         assert df