DEV-10756 removed unused imports that were being flagged by flake8

usaspending_api/common/helpers/download_csv_strategies.py

@@ -124,7 +124,6 @@ def download_to_csv(
         #   we do not want to force all containers where
         #   other strategies run to have pyspark installed when the strategy
         #   doesn't require it.
-        from pyspark.sql import SparkSession
         from usaspending_api.common.etl.spark import hadoop_copy_merge, write_csv_file
         from usaspending_api.common.helpers.spark_helpers import configure_spark_session, get_active_spark_session
 
@@ -149,7 +148,7 @@ def download_to_csv(
             self.spark_created_by_command = False
             if not self.spark:
                 self.spark_created_by_command = True
-                self.spark = configure_spark_session(**extra_conf, spark_context=self.spark)  # type: SparkSession
+                self.spark = configure_spark_session(**extra_conf, spark_context=self.spark)
             if source_df is not None:
                 df = source_df
             else:

usaspending_api/common/helpers/spark_helpers.py

@@ -23,7 +23,6 @@
 from pyspark.java_gateway import launch_gateway
 from pyspark.serializers import read_int, UTF8Deserializer
 from pyspark.sql import SparkSession
-from pyspark.sql.conf import RuntimeConfig
 from typing import Sequence, Set
 
 from usaspending_api.awards.delta_models.awards import AWARDS_COLUMNS
@@ -247,7 +246,7 @@ def configure_spark_session(
     # Now that the SparkSession was created, check whether certain provided config values were ignored if given a
     # pre-existing SparkContext, and error-out if so
     if spark_context:
-        built_conf = spark.conf  # type: RuntimeConfig
+        built_conf = spark.conf
         provided_conf_keys = [item[0] for item in conf.getAll()]
         non_modifiable_conf = [k for k in provided_conf_keys if not built_conf.isModifiable(k)]
         if non_modifiable_conf:

usaspending_api/etl/management/commands/create_delta_table.py

@@ -1,5 +1,4 @@
 from django.core.management.base import BaseCommand
-from pyspark.sql import SparkSession
 
 from usaspending_api.config import CONFIG
 from usaspending_api.common.helpers.spark_helpers import (
@@ -64,7 +63,7 @@ def handle(self, *args, **options):
         spark_created_by_command = False
         if not spark:
             spark_created_by_command = True
-            spark = configure_spark_session(**extra_conf, spark_context=spark)  # type: SparkSession
+            spark = configure_spark_session(**extra_conf, spark_context=spark)
 
         # Setup Logger
         logger = get_jvm_logger(spark)

usaspending_api/etl/management/commands/elasticsearch_indexer_for_spark.py

@@ -1,6 +1,5 @@
 import logging
 
-from pyspark.sql import SparkSession
 
 from usaspending_api.common.helpers.spark_helpers import get_active_spark_session, configure_spark_session
 from usaspending_api.etl.management.commands.elasticsearch_indexer import AbstractElasticsearchIndexer
@@ -35,6 +34,6 @@ def create_controller(self, config: dict) -> AbstractElasticsearchIndexerControl
         spark = get_active_spark_session()
         if not spark:
             spark_created_by_command = True
-            spark = configure_spark_session(**extra_conf, spark_context=spark)  # type: SparkSession
+            spark = configure_spark_session(**extra_conf, spark_context=spark)
 
         return DeltaLakeElasticsearchIndexerController(config, spark, spark_created_by_command)

usaspending_api/etl/management/commands/load_table_to_delta.py

@@ -1,5 +1,4 @@
 from django.core.management import BaseCommand
-from pyspark.sql import SparkSession
 
 from usaspending_api.awards.delta_models import (
     AWARDS_COLUMNS,
@@ -351,8 +350,7 @@ def handle(self, *args, **options):
         spark_created_by_command = False
         if not spark:
             spark_created_by_command = True
-            spark = configure_spark_session(**extra_conf, spark_context=spark)  # type: SparkSession
-
+            spark = configure_spark_session(**extra_conf, spark_context=spark)
         # Setup Logger
         logger = get_jvm_logger(spark)
 

usaspending_api/etl/management/commands/load_zips_from_broker.py

@@ -1,7 +1,6 @@
 from datetime import datetime
 
 from django.core.management import BaseCommand, call_command
-from pyspark.sql import SparkSession
 
 from usaspending_api.broker.helpers.last_load_date import get_last_load_date, update_last_load_date
 from usaspending_api.common.etl.spark import create_ref_temp_views
@@ -49,7 +48,7 @@ def handle(self, *args, **options):
         spark_created_by_command = False
         if not spark:
             spark_created_by_command = True
-            spark = configure_spark_session(**extra_conf, spark_context=spark)  # type: SparkSession
+            spark = configure_spark_session(**extra_conf, spark_context=spark)
 
         # Setup Logger
         logger = get_jvm_logger(spark)