import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report


def remove_tags(text):
    tags = ['\n', '\'']
    for tag in tags:
        text = text.replace(tag, '')
    return text


def load_data(filepath):
    df = pd.read_csv(filepath)
    df['text'] = df['text'].apply(remove_tags)
    return df


def split_data(df):
    y = df['generated']
    x = df['text']
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
    return x_train, x_test, y_train, y_test


def create_pipeline(x_train, y_train):
    pipeline = Pipeline([
        ('count_vectorizer', CountVectorizer()),
        ('tfidf_transformer', TfidfTransformer()),
        ('classifier', MultinomialNB())
    ])
    pipeline.fit(x_train, y_train)
    return pipeline


def predict_text(text, pipeline):
    processed_text = remove_tags(text)
    prediction = pipeline.predict([processed_text])[0]
    return "AI-generated" if prediction else "Human-written"