Test page

import os

import pandas as pd

import re

# Input Paths

INPUT_directory = r'D:\Data\OneDrive\ipradhan\OneDrive - CFTC\Ish-OneDrive\_SwapsErrorData\Testing'

input_file = 'Staging_v2_5_23_2025_Copy.csv'

input_path = os.path.join(INPUT_directory, input_file)

# Output Paths

OUTPUT_directory = r'D:\Data\OneDrive\ipradhan\OneDrive - CFTC\Ish-OneDrive\_SwapsErrorData\Testing'

output_file = 'Text_output_swap_asset_class_4.csv'

output_path = os.path.join(OUTPUT_directory, output_file)

# Load the csv file into the pandas dataframe

df_csv = pd.read_csv(input_path, dtype=str)

# Create a list of new columns that will be added to the DataFrame

new_columns = ['acl_credit', 'acl_equity', 'acl_fx', 'acl_ir', 'acl_comm', 'acl_other']

for col in new_columns:

df_csv[col] = ''

# Function to assign asset classes

def assign_asset_classes_to_column(col_val: str) -> dict:

result = {

'acl_credit': '',

'acl_equity': '',

'acl_fx': '',

'acl_ir': '',

'acl_comm': '',

'acl_other': ''

}

if pd.isna(col_val):

return result

col_upper = col_val.upper()

pattern = r'\b(?:FX|CO|IR|EQ|CR|COMMODITY|INTEREST RATE|FOREIGN EXCHANGE|COMMODITIES|' \

r'LOAN|SWAP|OPTION|EQUITY DERIVATIVE|CREDIT DEFAULT SWAP|FUTURES)\b'

known_matches = re.findall(pattern, col_upper)

all_words = re.findall(r'\b[A-Z][A-Z ]*\b', col_upper)

unknown_matches = [word for word in all_words if word not in known_matches]

for ac in known_matches:

if ac in ['FX', 'FOREIGN EXCHANGE']:

result['acl_fx'] = 'FX'

elif ac in ['CO', 'COMMODITY', 'COMMODITIES']:

result['acl_comm'] = 'CO'

elif ac in ['IR', 'INTEREST RATE']:

result['acl_ir'] = 'IR'

elif ac == 'EQ':

result['acl_equity'] = 'EQ'

elif ac == 'CR':

result['acl_credit'] = 'CR'

else:

result['acl_other'] = ac

if unknown_matches:

result['acl_other'] = 'OTHER'

return result

# Apply logic row-wise

asset_class_data = df_csv['swap_asset_class_4'].apply(assign_asset_classes_to_column)

asset_df = pd.DataFrame(asset_class_data.tolist())

df_csv.update(asset_df)

# Save to new CSV

df_csv.to_csv(output_path, index=False)

print(f'Processed file saved to: {output_path}')