train.py

import os
from dotenv import load_dotenv

from src.preprocess import clean_smiles_in_csv, get_combined_dataset_csv
from src.train_model import train_model


data_path = "./data/combined_clean.csv"
config_path = "./config/config.toml"
save_model_path = "./logs"

# load and clean data
print("Loading Datasets...")
load_dotenv()
token = os.getenv("TOKEN")
target_cols = ["NR-AhR","NR-AR","NR-AR-LBD","NR-Aromatase","NR-ER","NR-ER-LBD","NR-PPAR-gamma","SR-ARE","SR-ATAD5","SR-HSE","SR-MMP","SR-p53"]
get_combined_dataset_csv(token, save_path="./data/combined_not_clean.csv")
clean_smiles_in_csv("./data/combined_not_clean.csv", data_path, "smiles", target_cols)

# train model
print("Starting Training...")
train_model(data_path, config_path, save_model_path)