Fix ruff check issues.

Author: np-complete0

apps/bfd-model-idr/claims_generator.py

@@ -10,7 +10,6 @@
 
 import pandas as pd
 from faker import Faker
-
 from generator_util import GeneratorUtil
 
 generator = GeneratorUtil()

apps/bfd-model-idr/dd_helper_script.py

@@ -1,7 +1,9 @@
-'''
+"""
 This script can be used, with the requisite copybooks from the IDR, to do some comparisons for accuracy on given profiles/applicability in BFD v3.
 This will be used as part of future work to enhance the IDR copybooks and improve the quality of our data dictionary.
-'''
+"""
+from collections import Counter
+
 import pandas as pd
 import yaml
 
@@ -39,27 +41,25 @@
 
 #If we pull more than the current CLM_FISS / CLM_MCS fields (1 and 0, respectively) then we'll need to profile 
 #the individual claim types within PAC data. Otherwise, this just updates the source
-for cur_source in otherSources:
+for cur_source in other_sources:
     df = pd.read_excel(other_sources[cur_source], sheet_name='Claim Header',header=3, usecols=['Target Table','Target Column'])
     for _, row in df.iterrows():
         element_concatenated = f"{str(row['Target Table']).strip()}.{str(row['Target Column']).strip()}"
         #there are newlines in some, we should ask IDR to consider changing the DD structure?
         if row['Target Table'] != '-' and row['Target Column'] != '-' and "\n" not in element_concatenated:
             if element_concatenated in applies_to and cur_source not in applies_to[element_concatenated]['sources']:
                 applies_to[element_concatenated]['sources'].append(cur_source)
-            pass
     df = pd.read_excel(other_sources[cur_source], sheet_name='Claim Line',header=3, usecols=['Target Table','Target Column'])
     for _, row in df.iterrows():
         element_concatenated = f"{str(row['Target Table']).strip()}.{str(row['Target Column']).strip()}"
         #there are newlines in some, we should ask IDR to consider changing the DD structure?
         if row['Target Table'] != '-' and row['Target Column'] != '-' and "\n" not in element_concatenated:
-            if element_concatenated in appliesTo and cur_source not in applies_to[element_concatenated]['sources']:
+            if element_concatenated in applies_to and cur_source not in applies_to[element_concatenated]['sources']:
                 applies_to[element_concatenated]['sources'].append(cur_source)
-            pass
 
 #this is more of a heuristic. for example, HCPCS_5_MDFR_CD appears to be missing from the copybook but it's there in reality. 
 profile_divergence_counter = 0
-with open(eob_dict_yaml, "r") as f:
+with open(eob_dict_yaml) as f:
     data = yaml.safe_load(f)
 for i in data:
     if 'sourceView' in i:
@@ -72,7 +72,7 @@
 print("remaining diverging for profiles:",profile_divergence_counter)
 
 source_divergence_counter = 0
-with open(eob_dict_yaml, "r") as f:
+with open(eob_dict_yaml) as f:
     data = yaml.safe_load(f)
 for i in data:
     if 'sourceView' in i:

apps/bfd-model-idr/gen_dd.py

@@ -82,7 +82,7 @@
             data = yaml.safe_load(file)
             current_resource_type = file_name[0 : len(file_name) - 5]
             for entry in data:
-                if 'suppressInDD' in entry and entry['suppressInDD']:
+                if entry.get('suppressInDD'):
                     continue
                 if "fhirPath" in entry:
                     entry["appliesTo"].sort()

apps/bfd-model-idr/patient_generator.py

@@ -7,7 +7,6 @@
 
 import pandas as pd
 from faker import Faker
-
 from generator_util import GeneratorUtil
 
 fake = Faker()

apps/bfd-model/bfd-model-rif/src/main/resources/db/scripts/BFD-1700-remove-synthetic/make_sql.py

@@ -1,10 +1,8 @@
 #!/usr/bin/python3
-'''Create SQL scripts to delete synthetic data.
-'''
+"""Create SQL scripts to delete synthetic data.
+"""
 
 import sys
-from typing import List
-
 
 # List of predefined Beneficiary IDs to delete and pattern of bene_ids to match in a NOT LIKE
 # clause. Source: https://jira.cms.gov/browse/BFD-1686
@@ -58,10 +56,9 @@
 # Helpers
 
 
-def make_bene_id_pattern(bene_ids: List[str], pattern: str, cast_id: bool = False) -> str:
-    '''Make the WHERE clause to handle bene_ids that are in the list or fit the pattern.
-    '''
-
+def make_bene_id_pattern(bene_ids: list[str], pattern: str, cast_id: bool = False) -> str:
+    """Make the WHERE clause to handle bene_ids that are in the list or fit the pattern.
+    """
     output = '  bene_id IN (\'' + '\', \''.join(bene_ids) + '\')'
     if pattern is not None:
         bene_id = 'CAST(bene_id AS CHARACTER VARYING(15))' if cast_id else 'bene_id'
@@ -72,12 +69,11 @@ def make_bene_id_pattern(bene_ids: List[str], pattern: str, cast_id: bool = Fals
 
 def make_claims_sql(bene_id_clause: str, claims_table: str, claim_lines_table: str,
     is_count: bool) -> str:
-    '''Create SQL to count or delete from a claims table and its corresponding claim_lines table.
+    """Create SQL to count or delete from a claims table and its corresponding claim_lines table.
 
     We want to run the claims table after the claim_lines table, because we couldn't join / union
     if we don't.
-    '''
-
+    """
     # Generate SQL for Claims Lines
     output  = f"-- {claim_lines_table}\n\n"
     if is_count:
@@ -101,8 +97,8 @@ def make_claims_sql(bene_id_clause: str, claims_table: str, claim_lines_table: s
 
 
 def make_base_sql(bene_id_clause: str, base_table: str, is_count: bool) -> str:
-    '''Create SQL to count or delete from a table containing a bene_id clause.
-    '''
+    """Create SQL to count or delete from a table containing a bene_id clause.
+    """
     output  = f"-- {base_table}\n\n"
 
     output += f"SELECT COUNT(*) AS {base_table}\n" if is_count else 'DELETE\n'
@@ -113,19 +109,17 @@ def make_base_sql(bene_id_clause: str, base_table: str, is_count: bool) -> str:
 
 
 def help_text() -> str:
-    '''Provide help text if the user does not provide valid arguments or asks for help.
-    '''
-
+    """Provide help text if the user does not provide valid arguments or asks for help.
+    """
     return 'Usage: make_sql.py [count | delete] [test|prod-sbx|prod]'
 
 
 # Main
 
 
-def main(args: List):
-    '''Main function, called from the command line.
-    '''
-
+def main(args: list):
+    """Main function, called from the command line.
+    """
     if not args or len(args) < 2:
         print(help_text(), file=sys.stderr)
         sys.exit()

apps/bfd-pipeline/bfd-pipeline-idr/extractor.py

@@ -6,13 +6,12 @@
 
 import psycopg
 import snowflake.connector
+from constants import DEFAULT_MIN_DATE
 from cryptography.hazmat.backends import default_backend
 from cryptography.hazmat.primitives import serialization
+from model import DbType, LoadProgress, T, get_min_transaction_date
 from psycopg.rows import class_row
 from snowflake.connector import DictCursor, SnowflakeConnection
-
-from constants import DEFAULT_MIN_DATE
-from model import DbType, LoadProgress, T, get_min_transaction_date
 from timer import Timer
 
 cursor_execute_timer = Timer("cursor_execute")

apps/bfd-pipeline/bfd-pipeline-idr/load_synthetic.py

@@ -4,7 +4,6 @@
 from pathlib import Path
 
 import psycopg
-
 from loader import get_connection_string
 
 tables = [

apps/bfd-pipeline/bfd-pipeline-idr/loader.py

@@ -4,7 +4,6 @@
 from datetime import UTC, date, datetime
 
 import psycopg
-
 from constants import DEFAULT_MIN_DATE
 from model import DbType, LoadProgress, T
 from timer import Timer

apps/bfd-pipeline/bfd-pipeline-idr/model.py

@@ -4,9 +4,8 @@
 from datetime import UTC, date, datetime, timedelta
 from typing import Annotated, TypeVar
 
-from pydantic import BaseModel, BeforeValidator
-
 from constants import CLAIM_TYPE_CODES, DEFAULT_MAX_DATE, DEFAULT_MIN_DATE, PART_D_CLAIM_TYPE_CODES
+from pydantic import BaseModel, BeforeValidator
 
 type DbType = str | float | int | bool | date | datetime
 

apps/bfd-pipeline/bfd-pipeline-idr/pipeline_nodes.py

@@ -1,7 +1,6 @@
 # ruff: noqa: ARG001
 # type: ignore [reportUntypedFunctionDecorator]
 from hamilton.function_modifiers import config, parameterize, value
-
 from model import (
     IdrBeneficiary,
     IdrBeneficiaryDualEligibility,