Which AI are we talking about?

Choose an AI Type

Type	Description	Example
Rule-Based AI	Follows predefined if-else rules	Chatbot, Decision Tree
Machine Learning (ML) AI	Learns from data	Image classifier, Spam detector
Chatbot (NLP)	Uses natural language processing	Customer support bot

1. Build a Simple Rule-Based AI (No ML)

A basic AI that responds based on rules (like a chatbot).

Example: A Weather Advice Bot

python

def weather_advisor(weather):
    weather = weather.lower()
    if weather == "sunny":
        return "Wear sunscreen and sunglasses!"
    elif weather == "rainy":
        return "Take an umbrella and a raincoat."
    elif weather == "cold":
        return "Wear a warm jacket and gloves."
    else:
        return "I'm not sure, check the weather again."

# Test the AI
user_input = input("What's the weather today? (sunny/rainy/cold): ")
print(weather_advisor(user_input))

Output:

text

What's the weather today? (sunny/rainy/cold): sunny  
Wear sunscreen and sunglasses!

---

2. Build a Simple ML-Based AI (Using Scikit-Learn)

A machine learning model that predicts outcomes from data.

Example: A Spam Detector

Step 1: Install Required Libraries

bash

pip install scikit-learn pandas numpy

Step 2: Train a Model

python

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB

# Sample dataset (message, label: 0=Not Spam, 1=Spam)
data = {
    "message": [
        "Free prize! Click now!", 
        "Meeting at 3 PM", 
        "Win a million dollars!", 
        "Project update"
    ],
    "label": [1, 0, 1, 0]
}

df = pd.DataFrame(data)

# Convert text to numbers (Bag of Words)
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(df["message"])

# Train a Naive Bayes classifier
model = MultinomialNB()
model.fit(X, df["label"])

# Test the AI
test_message = ["Free vacation offer!"]
test_X = vectorizer.transform(test_message)
prediction = model.predict(test_X)

print("Spam" if prediction[0] == 1 else "Not Spam")

Output:

text

Spam

---

3. Build a Simple AI Chatbot (Using NLP)

A chatbot that responds to user input (using NLTK or ChatterBot).

Example: A Basic Chatbot with ChatterBot

bash

pip install chatterbot chatterbot_corpus

python

from chatterbot import ChatBot
from chatterbot.trainers import ChatterBotCorpusTrainer

# Create a chatbot
chatbot = ChatBot("SimpleBot")

# Train it on English data
trainer = ChatterBotCorpusTrainer(chatbot)
trainer.train("chatterbot.corpus.english")

# Chat with the AI
while True:
    user_input = input("You: ")
    if user_input.lower() == "exit":
        break
    response = chatbot.get_response(user_input)
    print("Bot:", response)

Output:

text

You: Hello  
Bot: Hi there!  
You: How are you?  
Bot: I am doing well, thank you!  
You: exit  

---

4. Next Steps

• Improve with more data (for ML models).
• Use deep learning (TensorFlow/PyTorch) for complex AI.
• Deploy as a web app (Flask, FastAPI).