import lime
import lime.lime_text
from sklearn.pipeline import make_pipeline
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
import numpy as np

def explain_prediction(text):
    """
    Explains the prediction of a text classification model using LIME.
    """
    # Create a dummy dataset
    data = ["I love this product", "This is a terrible movie", "The book was okay", "I hate this"]
    labels = [1, 0, 0, 0]

    # Create a simple text classification pipeline
    vectorizer = TfidfVectorizer()
    classifier = LogisticRegression()
    pipeline = make_pipeline(vectorizer, classifier)
    pipeline.fit(data, labels)

    # Create a LIME explainer
    explainer = lime.lime_text.LimeTextExplainer(class_names=['negative', 'positive'])
    
    # Explain the prediction for the given text
    explanation = explainer.explain_instance(text, pipeline.predict_proba, num_features=6)
    return explanation.as_list()

if __name__ == '__main__':
    text_to_explain = "This is a fantastic and innovative AI model."
    explanation = explain_prediction(text_to_explain)
    print("LIME explanation:", explanation)