Tokenization and vocabulary in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to split the sentence into words using whitespace.

Prompt Engineering / GenAI

tokens = sentence.[1]()

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

Astrip

Bjoin

Csplit

Dreplace

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 the ends.

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

2fill in blank

medium

Complete the code to create a vocabulary set from the list of tokens.

Prompt Engineering / GenAI

vocab = set([1])

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

Asentence

Btokens

Cvocab

Dwords

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the original sentence string instead of the token list.

Passing the vocabulary variable itself which is not defined yet.

Passing an undefined variable like words.

The set() function creates a collection of unique items from the list tokens.

3fill in blank

hard

Fix the error in the code to count the frequency of each token.

Prompt Engineering / GenAI

freq = {}
for token in tokens:
    freq[token] = freq.get([1], 0) + 1

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

Atoken

Btokens

Cfreq

Dcount

Attempts:

3 left

💡 Hint

Common Mistakes

Using the whole list tokens as the key.

Using the dictionary freq as the key.

Using an undefined variable like count.

The get() method needs the current token as the key to get its count.

4fill in blank

hard

Fill both blanks to create a dictionary of token lengths for tokens longer than 3 characters.

Prompt Engineering / GenAI

lengths = {token: [1] for token in tokens if len(token) [2] 3}

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

Alen(token)

B>

C<

Dtoken

Attempts:

3 left

💡 Hint

Common Mistakes

Using the token itself as the value instead of its length.

Using less than (<) instead of greater than (>) in the condition.

The dictionary comprehension maps each token to its length if the token length is greater than 3.

5fill in blank

hard

Fill all three blanks to create a frequency dictionary for tokens longer than 2 characters.

Prompt Engineering / GenAI

freq_filtered = {token: [1] for token in tokens if len(token) [2] 2 and token in [3]

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

Afreq[token]

B>

Cvocab

Dtokens

Attempts:

3 left

💡 Hint

Common Mistakes

Using the list of tokens instead of the vocabulary set for membership check.

Using less than (<) instead of greater than (>) in the length condition.

Using the token itself instead of its frequency as the value.

This comprehension creates a dictionary with tokens as keys and their frequencies as values, filtering tokens longer than 2 characters and present in the vocabulary set.