Text preprocessing pipelines in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to convert all text to lowercase.

NLP

text = "Hello World!"
processed_text = text.[1]()

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

Alower

Bupper

Ccapitalize

Dtitle

Attempts:

3 left

💡 Hint

Common Mistakes

Using upper() instead of lower()

Using capitalize() which only changes the first letter

Using lower() converts all characters in the string to lowercase, which is a common first step in text preprocessing.

2fill in blank

medium

Complete the code to split the text into words.

NLP

text = "Machine learning is fun"
words = text.[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

Using replace() which changes characters

The split() method breaks a string into a list of words using spaces by default.

3fill in blank

hard

Fix the error in the code to remove punctuation from the text.

NLP

import string
text = "Hello, world!"
clean_text = text.translate(str.maketrans('', '', [1]))

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

Astring.punctuation

Bstring.whitespace

Cstring.ascii_letters

Dstring.digits

Attempts:

3 left

💡 Hint

Common Mistakes

Using whitespace which removes spaces

Using ascii_letters which removes letters

string.punctuation contains all punctuation characters. Removing them cleans the text.

4fill in blank

hard

Fill both blanks to create a list of words without stopwords.

NLP

stopwords = {'is', 'the', 'and'}
words = ['this', 'is', 'fun']
filtered = [word for word in words if word [1] stopwords]

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

A==

Bin

Cnot in

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'in' which keeps stopwords

Using '==' which compares equality

Using not in filters out words that are in the stopwords set.

5fill in blank

hard

Fill all three blanks to create a dictionary of word counts from a list.

NLP

words = ['apple', 'banana', 'apple']
word_counts = [1]((word, [2]) for word in words if words.count(word) [3] 1)

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

Adict

Bwords.count(word)

C>

Dlist

Attempts:

3 left

💡 Hint

Common Mistakes

Using list instead of dict

Using '<' instead of '>' in condition

We use dict to create a dictionary, count each word with words.count(word), and filter words that appear more than once with >.