deprecations isort and flake8 fix

requirements.txt

@@ -5,12 +5,12 @@ google-auth-httplib2>=0.0.3
 google_api_python_client>=1.6.7
 google_auth_oauthlib>=0.2.0
 google-cloud-bigquery>=1.24.0
-googleads>=42.0.0
+googleads>=49.0.0
 isort==4.3.9
 lxml>=4.6.5
 mysql-connector-python==9.1.0
 numpy>=1.16.2
-pandas>=0.24.0
+pandas>=2.0.0
 pyarrow>=0.11.1
 qds_sdk>=1.10.1
 requests>=2.20

sroka/api/athena/athena_api.py

@@ -5,8 +5,9 @@
 from botocore.exceptions import ClientError, EndpointConnectionError
 
 import sroka.config.config as config
-from sroka.api.athena.athena_api_helpers import poll_status, download_file, return_on_exception, \
-    input_check
+from sroka.api.athena.athena_api_helpers import (download_file, input_check,
+                                                 poll_status,
+                                                 return_on_exception)
 
 
 def query_athena(query, filename=None):

sroka/api/athena/athena_api_helpers.py

@@ -5,7 +5,7 @@
 
 def input_check(input_to_check, expected_types):
     for expected_type in expected_types:
-        if type(input_to_check) == expected_type:
+        if isinstance(input_to_check, expected_type):
             if expected_type == str and len(input_to_check) == 0:
                 print('Function input must be a nonempty string.')
                 return False

sroka/api/google_ad_manager/gam_api.py

@@ -22,44 +22,44 @@
 
 def dict_type_checker(dict_argument, argument_name, mandatory=True):
     if mandatory:
-        if type(dict_argument) != dict:
+        if not isinstance(dict_argument, dict):
             print(f"""{argument_name} needs to be a dict""")
             return "Incorrect type"
     else:
-        if dict_argument and type(dict_argument) != dict:
+        if dict_argument and not isinstance(dict_argument, dict):
             print(f"""{argument_name} needs to be a dict""")
             return "Incorrect type"
 
 
 def int_type_checker(int_argument, argument_name, mandatory=True):
     if mandatory:
-        if type(int_argument) != int:
+        if not isinstance(int_argument, int):
             print(f"""{argument_name} needs to be an integer""")
             return "Incorrect type"
     else:
-        if int_argument and type(int_argument) != int:
+        if int_argument and not isinstance(int_argument, int):
             print(f"""{argument_name} needs to be an integer""")
             return "Incorrect type"
 
 
 def list_type_checker(list_argument, argument_name, mandatory=True):
     if mandatory:
-        if type(list_argument) != list:
+        if not isinstance(list_argument, list):
             print(f"""{argument_name} needs to be a list""")
             return "Incorrect type"
     else:
-        if list_argument and type(list_argument) != list:
+        if list_argument and not isinstance(list_argument, list):
             print(f"""{argument_name} needs to be a list""")
             return "Incorrect type"
 
 
 def str_type_checker(str_argument, argument_name, mandatory=True):
     if mandatory:
-        if type(str_argument) != str:
+        if not isinstance(str_argument, str):
             print(f"""{argument_name} needs to be a string""")
             return "Incorrect type"
     else:
-        if str_argument and type(str_argument) != str:
+        if str_argument and not isinstance(str_argument, str):
             print(f"""{argument_name} needs to be a string""")
             return "Incorrect type"
 
@@ -194,7 +194,7 @@ def get_users_from_admanager(query, dimensions, network_code=None):
                             print('Failed to generate user list. Incorrect dimension: {}'.format(e))
                             return
 
-                    user_df = user_df.append(dimensions_df, sort=False)
+                    user_df = pd.concat([user_df, dimensions_df], sort=False)
                 statement.offset += statement.limit
             else:
                 break
@@ -250,7 +250,7 @@ def get_companies_from_admanager(query, dimensions, network_code=None):
                             print('Failed to generate company list. Incorrect dimension: {}'.format(e))
                             return
 
-                    company_df = company_df.append(dimensions_df, sort=False)
+                    company_df = pd.concat([company_df, dimensions_df], sort=False)
                 statement.offset += statement.limit
             else:
                 break
@@ -404,7 +404,6 @@ def get_service_data_from_admanager(
             print("No more items found.")
             break
 
-
     print(
         f"Successfully fetched a total of {len(all_items)} '{service}' items.\n"
     )

sroka/api/google_bigquery/bigquery_api.py

@@ -1,20 +1,20 @@
 import pandas as pd
+from google.api_core.exceptions import BadRequest, Forbidden, NotFound
 from google.cloud import bigquery
-import sroka.config.config as config
-from google.api_core.exceptions import Forbidden, NotFound, BadRequest
 
+import sroka.config.config as config
 
 KEY_FILE = config.get_file_path('google_bigquery')
 
 
 def query_bigquery(input_query, filename=None):
 
     if filename:
-        if type(filename) != str:
+        if not isinstance(filename, str):
             print('filename needs to be a string')
             return None
 
-        if type(input_query) != str:
+        if not isinstance(input_query, str):
             print('input_query needs to be a string')
             return None
 
@@ -26,7 +26,7 @@ def query_bigquery(input_query, filename=None):
             return None
 
     else:
-        if type(input_query) != str:
+        if not isinstance(input_query, str):
             print('input_query needs to be a string')
             return pd.DataFrame([])
 
@@ -55,11 +55,11 @@ def query_bigquery(input_query, filename=None):
 def done_bigquery(job_id, filename=None):
 
     if filename:
-        if type(filename) != str:
+        if not isinstance(filename, str):
             print('filename needs to be a string')
             return None
 
-        if type(job_id) != str:
+        if not isinstance(job_id, str):
             print('input_query needs to be a string')
             return None
 
@@ -71,7 +71,7 @@ def done_bigquery(job_id, filename=None):
             return None
 
     else:
-        if type(job_id) != str:
+        if not isinstance(job_id, str):
             print('input_query needs to be a string')
             return pd.DataFrame([])
 

sroka/api/google_drive/google_drive_api.py

@@ -2,9 +2,10 @@
 
 import numpy as np
 import pandas as pd
-
 from googleapiclient.errors import HttpError
-from sroka.api.google_drive.google_drive_helpers import is_valid_email, service_builder
+
+from sroka.api.google_drive.google_drive_helpers import (is_valid_email,
+                                                         service_builder)
 
 
 def google_drive_sheets_read(sheetname_id: str, sheet_range: str, first_row_columns=False):
@@ -231,7 +232,7 @@ def google_drive_sheets_delete_tab(spreadsheet_id: str, tab_name: str):
 
     Args:
         spreadsheet_id (str): The ID of the spreadsheet.
-        tab_name (str): The name of the tab to delete.  
+        tab_name (str): The name of the tab to delete.
     Returns:
         str: The ID of the spreadsheet.
     """
@@ -274,10 +275,10 @@ def google_drive_sheets_delete_tab(spreadsheet_id: str, tab_name: str):
 def google_drive_get_file_parents(file_id: str):
     """
     Retrieves the parent folder IDs for a specified file on Google Drive.
-       
+
     Args:
         file_id (str): The ID of the file whose parent folders are to be retrieved.
-    
+
     Returns:
         list: A list of string IDs for the parent folder(s) of the file. Returns an empty list on failure.
     """
@@ -330,7 +331,7 @@ def google_drive_transfer_ownership(file_id: str, new_owner_email: str):
 
         # Create the permission, triggering the ownership transfer
         # pylint: disable=E1101
-        permission = service.permissions().create(
+        service.permissions().create(
             fileId=file_id,
             body=permission_body,
             transferOwnership=True,
@@ -373,7 +374,7 @@ def google_drive_change_file_permission(file_id: str, user_email: str, role: str
     except ValueError as er:
         print(f"An incorrect role has been used in the function - {er}")
         return False
-   
+
     try:
         if is_valid_email(user_email) is False:
             raise ValueError(f'The {user_email} is incorrect.')
@@ -390,10 +391,10 @@ def google_drive_change_file_permission(file_id: str, user_email: str, role: str
             'role': role.lower(),
             'emailAddress': user_email.lower()
         }
-        
+
         # Insert the new permission
         # pylint: disable=E1101
-        permission = service.permissions().create(
+        service.permissions().create(
             fileId=file_id,
             body=permission_body,
             fields='id'

sroka/api/google_drive/google_drive_helpers.py

@@ -1,6 +1,8 @@
 import os
 import re
+
 from googleapiclient.discovery import build
+
 import sroka.config.config as config
 
 
@@ -18,6 +20,7 @@ def is_valid_email(email_string: str):
         return True
     return False
 
+
 def service_builder(service_type: int, version: str):
     """
     Creates a service with proper credentials for a selected build from the service_type variable: 'sheets' or 'drive'
@@ -38,15 +41,15 @@ def service_builder(service_type: int, version: str):
     try:
         valid_service_type = [1, 2]
         if service_type not in valid_service_type:
-            raise ValueError('Available services: [1] sheets, [2] drive')   
+            raise ValueError('Available services: [1] sheets, [2] drive')
     except ValueError as e:
         print(f"An incorrect role has been used in the function - {e}")
         return False
-    
+
     try:
         valid_version = ['v2', 'v3', 'v4']
         if version.lower() not in valid_version:
-            raise ValueError('Available versions: v2, v3, v4')   
+            raise ValueError('Available versions: v2, v3, v4')
     except ValueError as er:
         print(f"An incorrect version has been used in the function - {er}")
         return False

sroka/api/moat/moat_api_helpers.py

@@ -14,7 +14,7 @@ def validate_input_dict(moat_dict):
             print('{} is not defined'.format(column))
             return False
 
-    if type(moat_dict['columns']) != list or moat_dict['columns'] == []:
+    if not isinstance(moat_dict['columns'], list) or moat_dict['columns'] == []:
         print('columns are not defined correctly')
         return False
 

sroka/api/mysql/mysql.py

@@ -1,11 +1,15 @@
 import os
-import mysql.connector
-import pandas as pd
 from configparser import NoSectionError
 from pathlib import Path
-from mysql.connector.errors import DatabaseError, OperationalError, InternalError
+
+import mysql.connector
+import pandas as pd
+from mysql.connector.errors import (DatabaseError, InternalError,
+                                    OperationalError)
 from retrying import retry
-from sroka.api.mysql.mysql_helpers import validate_options, get_options_from_config
+
+from sroka.api.mysql.mysql_helpers import (get_options_from_config,
+                                           validate_options)
 
 
 @retry(stop_max_attempt_number=1,

sroka/api/mysql/mysql_helpers.py

@@ -1,6 +1,7 @@
-import sroka.config.config as config
 from configparser import NoOptionError
 
+import sroka.config.config as config
+
 
 def get_options_from_config():
     # Set the options in a dictionary, in order to pass only the

sroka/api/neo4j/neo4j_api.py

@@ -1,21 +1,20 @@
 import pandas as pd
-from py2neo import Graph
-from py2neo import ClientError
+from py2neo import ClientError, Graph
 
 import sroka.config.config as config
 
 
 def neo4j_query_data(cypher, parameters=None, **kwparameters):
 
-    if type(cypher) != str:
+    if not isinstance(cypher, str):
         print('Cypher query needs to be a string')
         return pd.DataFrame([])
 
     if len(cypher) == 0:
         print('Cypher query cannot be empty')
         return pd.DataFrame([])
 
-    if parameters and type(parameters) != dict:
+    if parameters and not isinstance(parameters, dict):
         print('Parameters need to be a dictionary')
         return pd.DataFrame([])
 

sroka/api/qubole/qubole_api.py

@@ -4,12 +4,8 @@
 
 import pandas as pd
 from qds_sdk.commands import Command, HiveCommand, PrestoCommand
-from qds_sdk.exception import (
-    ForbiddenAccess,
-    ResourceInvalid,
-    ResourceNotFound,
-    UnauthorizedAccess,
-)
+from qds_sdk.exception import (ForbiddenAccess, ResourceInvalid,
+                               ResourceNotFound, UnauthorizedAccess)
 from qds_sdk.qubole import Qubole
 
 import sroka.config.config as config

sroka/api/s3_connection/s3_connection_api.py

@@ -3,8 +3,8 @@
 from io import BytesIO, StringIO
 
 import boto3
-import pandas as pd
 import numpy as np
+import pandas as pd
 import pyarrow.parquet as pq
 from botocore.exceptions import ClientError, ParamValidationError
 from pandas.errors import EmptyDataError
@@ -89,7 +89,7 @@ def s3_download_data(s3_filename, prefix=False, output_file=None, sep=',', skip_
 
     key_prefix = match.group(2)
 
-    if type(sep) == str and len(sep) == 1:
+    if isinstance(sep, str) and len(sep) == 1:
 
         data = _download_data(key_prefix, s3, bucket_name, prefix, sep, skip_empty_files,
                               first_row_columns)
@@ -111,15 +111,15 @@ def s3_upload_data(data, bucket, path, sep=','):
         aws_secret_access_key=access_key
     )
 
-    if type(sep) == str and len(sep) == 1:
+    if isinstance(sep, str) and len(sep) == 1:
 
         csv_buffer = StringIO()
 
-        if type(data) == pd.core.frame.DataFrame or type(data) == np.ndarray:
+        if isinstance(data, pd.core.frame.DataFrame) or isinstance(data, np.ndarray):
 
-            if type(data) == pd.core.frame.DataFrame:
+            if isinstance(data, pd.core.frame.DataFrame):
                 data.to_csv(csv_buffer, sep=sep)
-            elif type(data) == np.ndarray:
+            elif isinstance(data, np.ndarray):
                 np.savetxt(csv_buffer, data, delimiter=sep, fmt='%s')
 
             s3 = session.resource('s3')