inference_main.py

import torch
import pandas as pd
from preprocessing import preprocess_text, load_tokenizer, prepare_data
from data_loader import create_data_loader
from inference import load_model, evaluate_model

version = 7


def run_evaluation(model_path, tokenizer_path, device):
    cleaned_path = f'./output/version_{version}/cleaned_inference_data_{version}.csv'
    # Load data
    try:
        df = pd.read_csv(cleaned_path)
        df.dropna(inplace=True)
        print("Cleaned data found.")
    except:
        print("No cleaned data found. Cleaning data now...")
        # Load the datasets
        true_news = pd.read_csv('data_1/True.csv')
        fake_news = pd.read_csv('data_1/Fake.csv')

        # Add labels
        true_news['label'] = 1
        fake_news['label'] = 0

        # Combine the datasets
        df = pd.concat([true_news, fake_news], ignore_index=True)

        # Drop unnecessary columns
        df.drop(columns=['subject', 'date'], inplace=True)

        df['title'] = df['title'].apply(preprocess_text)
        df['text'] = df['text'].apply(preprocess_text)

        df.to_csv(cleaned_path, index=False)
        df.dropna(inplace=True)
        print("Cleaned data saved.")

    labels = df['label'].values

    # Load tokenizer and model
    tokenizer = load_tokenizer(tokenizer_path)
    model = load_model(model_path, len(tokenizer.word_index) + 1)

    # Prepare data
    titles = prepare_data(df['title'], tokenizer)
    texts = prepare_data(df['text'], tokenizer)

    # Create DataLoader
    data_loader = create_data_loader(
        titles, texts, batch_size=32, shuffle=False)

    # Evaluate
    accuracy, f1, auc_roc = evaluate_model(model, data_loader, device, labels)
    return accuracy, f1, auc_roc


if __name__ == "__main__":
    model_path = f'./output/version_{version}/best_model_{version}.pth'
    tokenizer_path = f'./output/version_{version}/tokenizer_{version}.pickle'
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    print(f"Device: {device}")

    accuracy, f1, auc_roc = run_evaluation(model_path, tokenizer_path, device)
    print(
        f'Accuracy: {accuracy:.4f}, F1 Score: {f1:.4f}, AUC-ROC: {auc_roc:.4f}')