model.py

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

# Function to remove unwanted tags from the text
def remove_tags(text):
    tags = ['\n', '\'']
    for tag in tags:
        text = text.replace(tag, '')
    return text

# Assuming the data is loaded into a DataFrame 'df' at some point
def load_data():
    # Dummy loading mechanism, replace with actual data loading
    df = pd.read_csv('path_to_your_dataset.csv')
    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=0.3, random_state=42)
    return X_train, X_test, y_train, y_test

# Build and train the pipeline
def create_pipeline(X_train, y_train):
    pipeline = Pipeline([
        ('count_vectorizer', CountVectorizer()),  # Step 1: Convert text to count vectors
        ('tfidf_transformer', TfidfTransformer()),  # Step 2: Transform count vectors to TF-IDF
        ('classifier', MultinomialNB())  # Step 3: Train a classifier, here using Naive Bayes
    ])
    pipeline.fit(X_train, y_train)
    return pipeline

# Function to predict new inputs using the trained pipeline
def predict_text(text, pipeline):
    return pipeline.predict([text])[0]  # Return the classification result

# Main routine to train the model if this file is executed directly (for testing)
if __name__ == "__main__":
    df = load_data()
    X_train, X_test, y_train, y_test = split_data(df)
    pipeline = create_pipeline(X_train, y_train)
    print(f"Model trained. Test accuracy: {pipeline.score(X_test, y_test)}")