inference_main.py

import torch
import pandas as pd
from preprocessing import (
    preprocess_text,
    load_tokenizer,
    prepare_data,
    load_glove_embeddings,
)
from data_loader import create_data_loader
from inference import load_model, evaluate_model
from sklearn.metrics import confusion_matrix
import os

version = 2


def run_evaluation(model_path, tokenizer_path, device):
    cleaned_path = f"./output/version_{version}/cleaned_inference_data_{version}.csv"
    # Load data
    if os.path.exists(cleaned_path):
        df = pd.read_csv(cleaned_path)
        df.dropna(inplace=True)
        print("Cleaned data found.")
    else:
        print("No cleaned data found. Cleaning data now...")

        df = pd.read_csv("./data_3/news_articles.csv")
        df.drop(
            columns=[
                "author",
                "published",
                "site_url",
                "main_img_url",
                "type",
                "text_without_stopwords",
                "title_without_stopwords",
                "hasImage",
            ],
            inplace=True,
        )
        # Map Real to 1 and Fake to 0
        df["label"] = df["label"].map({"Real": 1, "Fake": 0})
        df = df[df["label"].isin([1, 0])]

        # Drop rows where the language is not 'english'
        df = df[df["language"] == "english"]
        df.drop(columns=["language"], inplace=True)

        # Convert "no title" to empty string
        df["title"] = df["title"].apply(lambda x: "" if x == "no title" else x)

        df.dropna(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
    tokenizer = load_tokenizer(tokenizer_path)

    embedding_matrix = load_glove_embeddings(
        "./GloVe/glove.6B.300d.txt", tokenizer.word_index, embedding_dim=300
    )

    model = load_model(model_path, embedding_matrix)
    model.to(device)

    # 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, y_true, y_pred = evaluate_model(
        model, data_loader, device, labels
    )

    # Generate and save confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    cm_df = pd.DataFrame(cm)
    cm_filename = f"./output/version_{version}/confusion_matrix_inference_{version}.csv"
    cm_df.to_csv(cm_filename, index=False)
    print(f"Confusion Matrix saved to {cm_filename}")
    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}")