[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
ONSdigital · Jun 20, 2023 · 9c217cc · 9c217cc
1 parent e719bf9
commit 9c217cc
Show file tree

Hide file tree

Showing 34 changed files with 2 additions and 35 deletions.
diff --git a/cishouseholds/derive.py b/cishouseholds/derive.py
@@ -454,7 +454,6 @@ def assign_datetime_from_coalesced_columns_and_log_source(
     reference_datetime_days_offset_value: int = -2,
     final_fallback_column: str = None,
 ):
-
     """
     Assign a timestamp column from coalesced list of columns with a default timestamp if timestamp missing in column
 
@@ -1827,7 +1826,6 @@ def assign_completion_status(
     df: DataFrame,
     column_name_to_assign: str,
 ) -> DataFrame:
-
     """
     Function to assign a completion status equivalent for PHM
     questionnaire responses from pre-defined variables

diff --git a/cishouseholds/phm/json_decode.py b/cishouseholds/phm/json_decode.py
@@ -21,7 +21,6 @@ def decode_phm_json(json_str: Union[str, bytes]) -> List[Tuple]:
     # table = json_dict["submission"]
     answers_list = []
     for table in json_list:
-
         meta = table.pop("survey_metadata")
         data = table.pop("data")
         meta.update(table)

diff --git a/cishouseholds/pipeline/pipeline_stages.py b/cishouseholds/pipeline/pipeline_stages.py
@@ -861,7 +861,6 @@ def update_vaccine_types(input_survey_table: str, output_survey_table: str, vacc
     df = extract_from_table(input_survey_table)
     lookup_df = extract_from_table(vaccine_type_lookup)
     for vaccine_number in range(0, 7):
-
         vaccine_type_other_col = "cis_covid_vaccine_type_other"
         vaccine_type_col = "cis_covid_vaccine_type"
         vaccine_date_col = "cis_covid_vaccine_date"

diff --git a/cishouseholds/pipeline/run.py b/cishouseholds/pipeline/run.py
@@ -48,7 +48,6 @@ def check_conditions(stage_responses: dict, stage_config: dict):
 
 
 def check_dependencies(stages_to_run, stages_config):  # TODO: ensure check in order. look before current stage only
-
     available_tables = []
     for stage in stages_to_run:  # generate available and required tables from stage config
         required_tables = stages_config[stage].get("input_tables", {})

diff --git a/cishouseholds/pipeline/translate.py b/cishouseholds/pipeline/translate.py
@@ -53,7 +53,6 @@ def translate_welsh_survey_responses(df: DataFrame) -> DataFrame:
     translation_lookup_path_in_pipeline_config = translation_lookup_path != "inactive"
 
     if translation_settings_in_pipeline_config:
-
         translation_directory = translation_settings.get("translation_directory", None)
         translation_lookup_directory = translation_settings.get("translation_lookup_directory", None)
         translation_backup_directory = translation_settings.get("translation_backup_directory", None)

diff --git a/cishouseholds/pipeline/vaccine_transformations.py b/cishouseholds/pipeline/vaccine_transformations.py
@@ -138,7 +138,6 @@ def deduplication(df: DataFrame):
 
 
 def first_second_doses(df: DataFrame):
-
     # assign first dose based on visit
     df = assign_nth_dose(
         df=df,

diff --git a/cishouseholds/pipeline/version_specific_processing/v1_transformations.py b/cishouseholds/pipeline/version_specific_processing/v1_transformations.py
@@ -11,7 +11,6 @@
 
 
 def clean_survey_responses_version_1(df: DataFrame) -> DataFrame:
-
     health_care_area_map = {
         "Primary care for example in a GP or dentist": "Primary",
         "Secondary care for example in a hospital": "Secondary",

diff --git a/cishouseholds/pipeline/version_specific_processing/v2_transformations.py b/cishouseholds/pipeline/version_specific_processing/v2_transformations.py
@@ -125,7 +125,6 @@ def derive_work_status_columns(df: DataFrame) -> DataFrame:
 
 
 def clean_survey_responses_version_2(df: DataFrame) -> DataFrame:
-
     # Map to digital from raw V2 values, before editing them to V1 below
     df = assign_from_map(
         df,

diff --git a/cishouseholds/pipeline/visit_transformations.py b/cishouseholds/pipeline/visit_transformations.py
@@ -19,7 +19,6 @@ def visit_transformations(df: DataFrame):
 
 
 def visit_derivations(df: DataFrame):
-
     df = assign_fake_id(df, "ordered_household_id_new", "ons_household_id")
     df = assign_visit_order(
         df=df,

diff --git a/cishouseholds/validate.py b/cishouseholds/validate.py
@@ -405,7 +405,6 @@ def validate_config_stages(pipeline_stage_functions: Dict, stages_to_run: List[s
             not in str(inspect.signature(pipeline_stage_functions[function_name]).parameters[arg])
         ]
         if not (set(function_config_other_params) == set(input_arguments_needed)):
-
             list_not_passed_arg = [x for x in input_arguments_needed if x not in function_config_other_params]
             list_of_unrecognised_arg = [
                 x

diff --git a/dummy_data_generation/helpers.py b/dummy_data_generation/helpers.py
@@ -162,7 +162,6 @@ class Meta:
         name = "custom_random"
 
     def __init__(self, *args: Any, **kwargs: Any) -> None:
-
         super().__init__(*args, **kwargs)
 
     def random_date(self, start, end, format="%d/%m/%Y"):

diff --git a/dummy_data_generation/helpers_weight.py b/dummy_data_generation/helpers_weight.py
@@ -22,7 +22,6 @@ class Meta:
         name = "base_stats"
 
     def __init__(self, *args: Any, **kwargs: Any) -> None:
-
         super().__init__(*args, **kwargs)
 
         np.random.seed(self.seed)
@@ -106,7 +105,6 @@ class Meta:
         name = "distribution"
 
     def __init__(self, *args: Any, **kwargs: Any) -> None:
-
         super().__init__(*args, **kwargs)
 
     def generic_distribution(self, func: Callable, null_prop: float = 0, null_value: Any = None, **kwargs: Any) -> Any:

diff --git a/tests/compare/test_prepare_for_union.py b/tests/compare/test_prepare_for_union.py
@@ -4,7 +4,6 @@
 
 
 def test_prepare_for_union(spark_session):
-
     example_ref = spark_session.createDataFrame(
         data=[
             ("ABC123", 1, "ABC7673", 1, 2, 2),

diff --git a/tests/derive/test_aggregated_output.py b/tests/derive/test_aggregated_output.py
@@ -6,7 +6,6 @@
 
 
 def test_aggregated_output(spark_session):
-
     input_df = spark_session.createDataFrame(
         data=[
             # fmt: off

diff --git a/tests/derive/test_assign_column_to_date_string.py b/tests/derive/test_assign_column_to_date_string.py
@@ -10,7 +10,6 @@
     [("1966-07-30 15:00:00", "1966-07-30"), (None, None)],
 )
 def test_convert_to_date(spark_session, expected_data):
-
     expected_schema = "time_example string, date_example string"
 
     expected_df = (

diff --git a/tests/derive/test_assign_school_year.py b/tests/derive/test_assign_school_year.py
@@ -80,7 +80,6 @@ def school_year_lookup(spark_session):
     # fmt: on
 )
 def test_assign_school_year(spark_session, expected_data, school_year_lookup):
-
     expected_schema = "visit_date string, dob string, country string, school_year integer"
 
     expected_df = (

diff --git a/tests/derive/test_at_childcare_coding.py b/tests/derive/test_at_childcare_coding.py
@@ -35,7 +35,6 @@
 
 
 def test_childcare_identifier(prepare_regex_test_cases, spark_session):
-
     test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, in_childcare boolean")

diff --git a/tests/derive/test_at_school_coding.py b/tests/derive/test_at_school_coding.py
@@ -48,7 +48,6 @@
 
 
 def test_add_at_school_identifier(prepare_regex_test_cases, spark_session):
-
     at_school_test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(at_school_test_cases, schema="test_case string, at_school boolean")

diff --git a/tests/derive/test_at_university_coding.py b/tests/derive/test_at_university_coding.py
@@ -42,7 +42,6 @@
 
 
 def test_add_at_university_identifier(prepare_regex_test_cases, spark_session):
-
     at_university_test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(

diff --git a/tests/derive/test_derive_from_list.py b/tests/derive/test_derive_from_list.py
@@ -4,7 +4,6 @@
 
 
 def test_assign_isin_list(spark_session):
-
     column_names = "pattern string, outcome integer"
 
     expected_df = spark_session.createDataFrame(

diff --git a/tests/derive/test_derive_regex_match.py b/tests/derive/test_derive_regex_match.py
@@ -9,7 +9,6 @@
     [("A1", True), ("AA", False), ("11", False), ("", False), ("?", False), (None, None)],
 )
 def test_derive_regex_match(spark_session, expected_data):
-
     expected_schema = "reference_column string, match boolean"
     expected_df = spark_session.createDataFrame([expected_data], schema=expected_schema)
 

diff --git a/tests/derive/test_flag_records_patient_facing_rules.py b/tests/derive/test_flag_records_patient_facing_rules.py
@@ -43,7 +43,6 @@
 
 
 def test_patient_facing_identifier(prepare_regex_test_cases, spark_session):
-
     test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, patient_facing boolean")

diff --git a/tests/derive/test_furlough_coding.py b/tests/derive/test_furlough_coding.py
@@ -30,7 +30,6 @@
 
 
 def test_furloughed_identifier(prepare_regex_test_cases, spark_session):
-
     test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, furloughed boolean")

diff --git a/tests/derive/test_in_college_or_further_education_coding.py b/tests/derive/test_in_college_or_further_education_coding.py
@@ -31,7 +31,6 @@
 
 
 def test_add_at_school_identifier(prepare_regex_test_cases, spark_session):
-
     test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(

diff --git a/tests/derive/test_not_working_coding.py b/tests/derive/test_not_working_coding.py
@@ -52,7 +52,6 @@
 
 
 def test_add_not_working_identifier(prepare_regex_test_cases, spark_session):
-
     test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, is_not_working boolean")

diff --git a/tests/derive/test_retired_coding.py b/tests/derive/test_retired_coding.py
@@ -34,7 +34,6 @@
 
 
 def test_add_retired_identifier(prepare_regex_test_cases, spark_session):
-
     retired_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(retired_cases, schema="test_case string, is_retired boolean")

diff --git a/tests/derive/test_self_employed_coding.py b/tests/derive/test_self_employed_coding.py
@@ -23,7 +23,6 @@
 
 
 def test_add_self_employed_identifier(prepare_regex_test_cases, spark_session):
-
     test_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, is_self_employed boolean")

diff --git a/tests/derive/test_working_from_home_coding.py b/tests/derive/test_working_from_home_coding.py
@@ -38,7 +38,6 @@
 
 
 def test_add_work_from_home_identifier(prepare_regex_test_cases, spark_session):
-
     wfh_cases = prepare_regex_test_cases(test_data)
 
     expected_df = spark_session.createDataFrame(wfh_cases, schema="test_case string, is_working_from_home boolean")

diff --git a/tests/edit/test_apply_lower_case_to_columns.py b/tests/edit/test_apply_lower_case_to_columns.py
@@ -4,7 +4,6 @@
 
 
 def test_update_strings_to_sentence_case(spark_session):
-
     input_df = spark_session.createDataFrame(
         data=[
             ("good MORning", "word soup"),

diff --git a/tests/edit/test_cast_columns_from_string.py b/tests/edit/test_cast_columns_from_string.py
@@ -4,7 +4,6 @@
 
 
 def test_re_cast_columns_from_string(spark_session):
-
     schema_input_df = """col_to_cast_1 string,
                          col_to_cast_2 string,
                          col_to_cast_3 string"""

diff --git a/tests/edit/test_clean_work_main_job_role.py b/tests/edit/test_clean_work_main_job_role.py
@@ -4,7 +4,6 @@
 
 
 def test_clean_work_main_job_role(spark_session):
-
     input_df = spark_session.createDataFrame(
         data=[
             (1, "good&MORning  "),

diff --git a/tests/edit/test_convert_columns_to_timestamps.py b/tests/edit/test_convert_columns_to_timestamps.py
@@ -18,7 +18,6 @@
     ],
 )
 def test_convert_to_timestamp(spark_session, input_data, column_map):
-
     input_schema = "time_example string, ID string, second_time_example string"
 
     expected_schema = StructType(

diff --git a/tests/edit/test_translate_column_regex_replace.py b/tests/edit/test_translate_column_regex_replace.py
@@ -4,7 +4,6 @@
 
 
 def test_translate_column_regex_replace(spark_session):
-
     expected_df = spark_session.createDataFrame(
         data=[
             # fmt: off

diff --git a/tests/validate/test_sparkvalidate.py b/tests/validate/test_sparkvalidate.py
@@ -74,6 +74,7 @@ def test_sparkvalidate(spark_session):
         "non_existent_col": {"contains": "a"},
     }
     validate_df.validate_column(operations=validation_checks_dict)
+
     # user defined function external definition
     def function_add_up_to(error_message, column_1, column_2):
         return (F.col(column_1) + F.col(column_2)) < 10, error_message
@@ -119,6 +120,7 @@ def test_sparkvalidate_multiple_column_checks(spark_session):
     )
     df_input = df_expected.drop("error")
     validate_df = SparkValidate(df_input, "error")  # initialise dataframe
+
     # user defined function external definition
     def function_add_up_to(error_message, column_1, column_2):
         return (F.col(column_1) + F.col(column_2)) < 10, error_message
-Original file line number
+Diff line change
@@ Expand Up / @@ -138,7 +138,6 @@ def deduplication(df: DataFrame): @@
     def first_second_doses(df: DataFrame):
         # assign first dose based on visit
         df = assign_nth_dose(
             df=df,
@@ Expand Down @@
Original file line number	Diff line number	Diff line change
Expand Up		@@ -35,7 +35,6 @@


		def test_childcare_identifier(prepare_regex_test_cases, spark_session):

		test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, in_childcare boolean")
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -48,7 +48,6 @@


		def test_add_at_school_identifier(prepare_regex_test_cases, spark_session):

		at_school_test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(at_school_test_cases, schema="test_case string, at_school boolean")
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -42,7 +42,6 @@


		def test_add_at_university_identifier(prepare_regex_test_cases, spark_session):

		at_university_test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -4,7 +4,6 @@


		def test_assign_isin_list(spark_session):

		column_names = "pattern string, outcome integer"

		expected_df = spark_session.createDataFrame(
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -43,7 +43,6 @@


		def test_patient_facing_identifier(prepare_regex_test_cases, spark_session):

		test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, patient_facing boolean")
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -30,7 +30,6 @@


		def test_furloughed_identifier(prepare_regex_test_cases, spark_session):

		test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, furloughed boolean")
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -31,7 +31,6 @@


		def test_add_at_school_identifier(prepare_regex_test_cases, spark_session):

		test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -52,7 +52,6 @@


		def test_add_not_working_identifier(prepare_regex_test_cases, spark_session):

		test_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(test_cases, schema="test_case string, is_not_working boolean")
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -34,7 +34,6 @@


		def test_add_retired_identifier(prepare_regex_test_cases, spark_session):

		retired_cases = prepare_regex_test_cases(test_data)

		expected_df = spark_session.createDataFrame(retired_cases, schema="test_case string, is_retired boolean")
Expand Down