Generator Hashtag dari Teks

import re
from collections import Counter

STOP_WORDS = {
    "a","an","the","and","or","but","in","on","at","to","for","of","with",
    "by","from","is","are","was","were","be","been","have","has","had",
    "do","does","did","will","would","could","should","this","that","it",
    "i","you","he","she","we","they","not","so","if","as","up","out",
    "about","into","just","also","get","make","go","come","see","use"
}

def generate_hashtags(text, min_length=3, max_count=20, remove_stop=True):
    words = re.findall(r"[a-z0-9']+", text.lower())
    cleaned = [w.strip("'") for w in words if len(w.strip("'")) >= min_length]
    if remove_stop:
        cleaned = [w for w in cleaned if w not in STOP_WORDS]
    freq = Counter(cleaned)
    top = freq.most_common(max_count)
    return [f"#{word}" for word, _ in top]

text = """Machine learning is transforming the software industry.
AI tools help developers write better code faster and improve productivity."""

hashtags = generate_hashtags(text)
print(" ".join(hashtags))