?? ???? Amazon?? ? ?? ??? ??? ????. ???? ??? ????? ???? Medium?? ?? ??????. ??? ?? ??????!

??? ??? ?? ? ??? ??? ? Python ??? ?? ???? ??? ???? ?????. ? ????? NLP ???? ??? ??? ?? ?? ?? ???? 6?? ?? Python ??? ?????.

?? ???(re ??)

?? ???? ?? ??? ??? ??? ??????. Python? re ??? ??? ??? ?????. ???? ??? ??? ??? ??? ??????.

?? ?? ??? ?? ??:

import re

text = "Contact us at info@example.com or support@example.com"
email_pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
emails = re.findall(email_pattern, text)
print(emails)

??: ['info@example.com', 'support@example.com']

Regex? ??? ???? ?????. ?? ??? ??? ??:

text = "The price is .99"
new_text = re.sub(r'$(\d+\.\d{2})', lambda m: f"€{float(m.group(1))*0.85:.2f}", text)
print(new_text)

??: "The price is €9.34"

??? ?? ????

Python? string ??? re?? ?? ??? ??? ?? ??? ???? ??? ?? ??? ?? ??? ??? ??? ??? ??? ?????.

??? ??:

import string

text = "Hello, World! How are you?"
translator = str.maketrans("", "", string.punctuation)
cleaned_text = text.translate(translator)
print(cleaned_text)

??: "Hello World How are you"

??? ??? ?? difflib

???? ????? ???? ???? ?? ??????. difflib? ??? ??? ???? ?? ?? ????? ?????.

??? ?? ??:

from difflib import get_close_matches

words = ["python", "programming", "code", "developer"]
similar = get_close_matches("pythonic", words, n=1, cutoff=0.6)
print(similar)

??: ['python']

SequenceMatcher? ? ??? ??? ?????.

from difflib import SequenceMatcher

def similarity(a, b):
    return SequenceMatcher(None, a, b).ratio()

print(similarity("python", "pyhton"))

??: (??) 0.83

?? ??? ?? Levenshtein ??

Levenshtein ?? ????(?? python-Levenshtein ????? ??)? ?? ?? ? ?? ??? ??????.

??? ??:

import Levenshtein

def spell_check(word, dictionary):
    return min(dictionary, key=lambda x: Levenshtein.distance(word, x))

dictionary = ["python", "programming", "code", "developer"]
print(spell_check("progamming", dictionary))

??: "programming"

??? ??? ??:

def find_similar(word, words, max_distance=2):
    return [w for w in words if Levenshtein.distance(word, w) <= max_distance]

print(find_similar("code", ["code", "coder", "python"]))

??: ['code', 'coder']

??? ??? ??? ?? ftfy

ftfy ?????? ??? ??? ???? mojibake? ?? ???? ??? ???? ???? ?????.

???? ??:

import ftfy

text = "The Mona Lisa doesn?￠a??a?￠t have eyebrows."
fixed_text = ftfy.fix_text(text)
print(fixed_text)

??: "The Mona Lisa doesn't have eyebrows."

???? ???:

weird_text = "Ｔｈｉｓ ｉｓ Ｆｕｌｌｗｉｄｔｈ ｔｅｘｔ"
normal_text = ftfy.fix_text(weird_text)
print(normal_text)

??: "This is Fullwidth text"

spaCy ? NLTK? ?? ???? ???

???? NLP? ?????. spaCy ? NLTK? ??? split() ??? ?? ??? ??? ?????.

spaCy? ??? ???:

import re

text = "Contact us at info@example.com or support@example.com"
email_pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
emails = re.findall(email_pattern, text)
print(emails)

??: ['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog', '.']

NLTK? word_tokenize:

text = "The price is .99"
new_text = re.sub(r'$(\d+\.\d{2})', lambda m: f"€{float(m.group(1))*0.85:.2f}", text)
print(new_text)

??: (spaCy? ??)

?? ?? ? ?? ??

??? ??? ??? ??, ?? ?? ? ?? ??? ?? ?????. ??? ??? ??? ?? ??? ???(???)? ?????, CPU ??? ??? ?? ??? ????, ??? ??? ??(??? ???? ?? ??)? ????, ?? ??? ?? ???? ?????, CSV ??? ?? ??? ?? ?????? ?????.

??? ??? ?? ??? ???? ??? ?? ?????? ???? ??? ?? ???? ? ????. ??? ??? ??? ???? ???? ??? ??? ????? ?? ?????.

101?

Aarav Joshi? ?? ??? AI ?? ???? 101 Books? ?? AI ?? ??? ???? ??? ???? ??? ?????. Amazon?? Golang Clean Code? ??????. ? ?? ???? ?? ??? ??? "Aarav Joshi"? ?????!

??? ???

Investor Central, Investor Central(????/???), Smart Living, Epochs & Echoes, Puzzling Mysteries, Hindutva, Elite Dev, JS Schools

Medium? ????

Tech Koala Insights, Epochs & Echoes World, Investor Central ??, Puzzling Mysteries ??, Science & Epochs ??, Modern Hindutva

? ??? ???? ??? ?? ? ??? ?? ?? Python ??? ?? ?????. ??? ??? PHP ??? ????? ?? ?? ??? ?????!