Information retrieval basics in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to tokenize the input text into words.

NLP

tokens = text.[1]()

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

Asplit

Bjoin

Creplace

Dstrip

Attempts:

3 left

💡 Hint

Common Mistakes

Using join() instead of split()

Using replace() which changes characters but does not split

Using strip() which only removes whitespace from ends

The split() method breaks the text into words by spaces, which is the basic step in information retrieval.

2fill in blank

medium

Complete the code to count the frequency of each word in the list.

NLP

from collections import [1]
word_counts = [1](words)

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

Adeque

BCounter

COrderedDict

Ddefaultdict

Attempts:

3 left

💡 Hint

Common Mistakes

Using defaultdict which needs manual counting

Using OrderedDict which keeps order but doesn't count

Using deque which is for queues, not counting

Counter is a special dictionary to count hashable objects, perfect for word frequency.

3fill in blank

hard

Fix the error in the code to compute the term frequency (TF) for a word.

NLP

tf = word_counts[[1]] / sum(word_counts.values())

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

Aword_counts

Bword

Cwords

D'word'

Attempts:

3 left

💡 Hint

Common Mistakes

Using variable word without quotes causes a NameError

Using words or word_counts which are not keys

The key to access the count must be a string representing the word, so it needs quotes.

4fill in blank

hard

Fill both blanks to create a dictionary of words with frequency greater than 1.

NLP

freq_words = {word: count for word, count in word_counts.items() if count [1] [2]

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

A>

B1

C>=

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using >= 0 includes all words

Using > 0 includes words with count 1

Using wrong operators like < or ==

The condition filters words with count greater than 1, so use > and 1.

5fill in blank

hard

Fill all three blanks to compute inverse document frequency (IDF) for a word.

NLP

import math
idf = math.log([1] / (1 + [2][[3]]))

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

Atotal_docs

Bdoc_freq

C'word'

Dword_counts

Attempts:

3 left

💡 Hint

Common Mistakes

Using word_counts instead of doc_freq for document frequency

Not quoting the word key

Forgetting to add 1 in denominator

IDF is log of total documents divided by (1 + document frequency of the word). The word key must be a string.