config.py

import torch
import os

DATA_PATH = './synthetic_transactions_samples_5000.csv'
TOKENIZER_PATH = './tokenizer/'
LABEL_ENCODERS_PATH = './label_encoders.pkl'
MODEL_SAVE_DIR = './saved_models/'
PREDICTIONS_SAVE_DIR = './predictions/'

TEXT_COLUMN = "Sanction_Context"
LABEL_COLUMNS = [
    "Red_Flag_Reason",
    "Maker_Action",
    "Escalation_Level",
    "Risk_Category",
    "Risk_Drivers",
    "Investigation_Outcome"
]
METADATA_COLUMNS = []

MAX_LEN = 128
BATCH_SIZE = 16
LEARNING_RATE = 2e-5
NUM_EPOCHS = 3
DROPOUT_RATE = 0.3

DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

BERT_MODEL_NAME = 'bert-base-uncased'
ROBERTA_MODEL_NAME = 'roberta-base'
DEBERTA_MODEL_NAME = 'microsoft/deberta-base'

TFIDF_MAX_FEATURES = 5000

FIELD_STRATEGIES = {}
os.makedirs(MODEL_SAVE_DIR, exist_ok=True)
os.makedirs(PREDICTIONS_SAVE_DIR, exist_ok=True)
os.makedirs(TOKENIZER_PATH, exist_ok=True)