Simple python trainable AI program for beginners

Here’s a simple trainable AI program using Python that utilizes a basic machine learning model. This example demonstrates a text classifier using the sklearn library, where the AI can be trained to classify text into different categories.

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
import joblib

def train_model():
    # Sample training data (text and labels)
    texts = ["hello", "hi", "greetings", "bye", "farewell", "see you"]
    labels = ["greeting", "greeting", "greeting", "farewell", "farewell", "farewell"]
    
    # Create a text classification pipeline
    model = make_pipeline(CountVectorizer(), MultinomialNB())
    
    # Train the model
    model.fit(texts, labels)
    
    # Save the trained model
    joblib.dump(model, "text_classifier.pkl")
    print("Model trained and saved as text_classifier.pkl")

def predict(text):
    # Load the trained model
    model = joblib.load("text_classifier.pkl")
    
    # Make a prediction
    label = model.predict([text])[0]
    print(f"Predicted category: {label}")
    return label

if __name__ == "__main__":
    train_model()
    
    # Test the model
    user_input = input("Enter a text to classify: ")
    predict(user_input)

This program:

1. Trains a simple text classifier using the Naïve Bayes algorithm.
2. Saves the trained model for future use.
3. Loads the model to classify user input.

Try running the script and entering words like “hello” or “bye” to see how it predicts the category.