NLP Basics

# INTRODUCTION TO NLP

import numpy as np

print("="*60)
print("NLP: TEXT TO NUMBERS")
print("="*60)

# The fundamental challenge
text = "Machine learning is amazing!"
print(f"\nOriginal text: '{text}'")

# Computers see ASCII codes
ascii_codes = [ord(char) for char in text]
print(f"ASCII codes: {ascii_codes[:10]}...")

# We need meaningful representations
print("\n" + "="*60)
print("NLP PIPELINE EXAMPLE")
print("="*60)

sample_reviews = [
    "This movie is amazing! Best film of the year 🎬",
    "Waste of time. Terrible acting. Don't watch! 👎",
    "Average movie. Nothing special but watchable.",
    "Mind-blowing performance by the lead actor! 🔥"
]

print("\nSample Reviews:")
for i, review in enumerate(sample_reviews, 1):
    print(f"  {i}. {review}")

# Simple preprocessing
import re

def preprocess(text):
    # Lowercase
    text = text.lower()
    # Remove emojis and special chars
    text = re.sub(r'[^a-z\s]', '', text)
    # Remove extra spaces
    text = ' '.join(text.split())
    return text

print("\nAfter Preprocessing:")
for i, review in enumerate(sample_reviews, 1):
    print(f"  {i}. {preprocess(review)}")

# Why preprocessing matters
print("\n💡 Key Insight:")
print("   'Amazing', 'AMAZING', 'amazing!' → should all be the same")
print("   Preprocessing normalizes text for consistent analysis")