What NLP actually does - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to tokenize the sentence into words.

NLP

words = sentence.[1]()

Drag options to blanks, or click blank then click option'

Astrip

Bjoin

Creplace

Dsplit

Attempts:

3 left

💡 Hint

Common Mistakes

Using join() which combines words instead of splitting.

Using replace() which changes characters but does not split.

Using strip() which removes spaces only at ends.

The split() method breaks a sentence into words by spaces, which is the basic step in NLP called tokenization.

2fill in blank

medium

Complete the code to convert all words to lowercase for uniformity.

NLP

lower_words = [word.[1]() for word in words]

Drag options to blanks, or click blank then click option'

Acapitalize

Blower

Cupper

Dtitle

Attempts:

3 left

💡 Hint

Common Mistakes

Using upper() which makes letters uppercase.

Using capitalize() which only changes the first letter.

Using title() which capitalizes first letters of words.

Using lower() converts all letters to lowercase, helping NLP models treat words like 'Apple' and 'apple' the same.

3fill in blank

hard

Fix the error in the code to remove punctuation from each word.

NLP

import string
clean_words = [word.strip(string.[1]) for word in lower_words]

Drag options to blanks, or click blank then click option'

Apunctuation

Bdigits

Cwhitespace

Dascii_letters

Attempts:

3 left

💡 Hint

Common Mistakes

Using digits which removes numbers, not punctuation.

Using whitespace which removes spaces, not punctuation.

Using ascii_letters which removes letters, not punctuation.

The string.punctuation constant contains all punctuation characters, which strip() removes from the start and end of each word.

4fill in blank

hard

Fill both blanks to create a dictionary counting word frequencies.

NLP

word_counts = {word: words.[1](word) for word in [2]

Drag options to blanks, or click blank then click option'

Acount

Bindex

Cset

Dlist

Attempts:

3 left

💡 Hint

Common Mistakes

Using index which finds position, not count.

Using list which includes duplicates, causing repeated keys.

Using count with list keys causing repeated counting.

Using count counts how many times each word appears. Using set gets unique words to avoid repeated counting.

5fill in blank

hard

Fill all three blanks to filter words longer than 3 letters and create a frequency dictionary.

NLP

filtered_counts = {word: words.[1](word) for word in [2] if len(word) [3] 3}

Drag options to blanks, or click blank then click option'

Acount

Bset

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' which filters shorter words.

Using list instead of set causing duplicate keys.

Using index instead of count causing errors.

This code counts words using count, iterates over unique words with set, and filters words longer than 3 letters using >.