Difference between AI machine learning and deep learning

from openai import OpenAI
import os

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# AI approach (rule-based example)
rules = ["free money", "win now", "click here"]
email = "You have won free money! Click here to claim."

is_spam_ai = any(rule in email.lower() for rule in rules)

print(f"AI rule-based spam detection: {is_spam_ai}")

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression

emails = ["Win money now", "Meeting schedule", "Free prize click here"]
labels = [1, 0, 1]  # 1=spam, 0=not spam

vectorizer = CountVectorizer()
X = vectorizer.fit_transform(emails)

model = LogisticRegression()
model.fit(X, labels)

new_email = ["Claim your free prize now"]
X_new = vectorizer.transform(new_email)
prediction = model.predict(X_new)

print(f"ML spam prediction: {bool(prediction[0])}")

import torch
import torch.nn as nn
from torchtext.vocab import GloVe
from torchtext.data.utils import get_tokenizer

class SpamClassifier(nn.Module):
    def __init__(self, embedding_dim, hidden_dim):
        super().__init__()
        self.embedding = nn.EmbeddingBag.from_pretrained(GloVe(name='6B', dim=embedding_dim).vectors)
        self.fc = nn.Linear(embedding_dim, hidden_dim)
        self.out = nn.Linear(hidden_dim, 1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, text):
        embedded = self.embedding(text)
        hidden = torch.relu(self.fc(embedded))
        output = self.sigmoid(self.out(hidden))
        return output

# This is a simplified example; training code omitted for brevity.