Document processing pipeline in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a document as a string.

NLP

with open('document.txt', 'r') as file:
    text = file.[1]()

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

Areadlines

Breadline

Cread

Dopen

Attempts:

3 left

💡 Hint

Common Mistakes

Using readline() reads only one line, not the full document.

Using readlines() returns a list of lines, not a single string.

The read() method reads the entire file content as a single string, which is needed to process the whole document.

2fill in blank

medium

Complete the code to split the document text into sentences.

NLP

import nltk
nltk.download('punkt')
sentences = nltk.tokenize.[1](text)

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

Aword_tokenize

Bsplit

Ctokenize

Dsent_tokenize

Attempts:

3 left

💡 Hint

Common Mistakes

Using word_tokenize splits text into words, not sentences.

Using split is a basic string method and won't handle sentence boundaries properly.

The sent_tokenize function splits text into sentences, which is essential for sentence-level processing.

3fill in blank

hard

Fix the error in the code to remove stopwords from the token list.

NLP

from nltk.corpus import stopwords
stop_words = set(stopwords.words('english'))
tokens = ['this', 'is', 'a', 'test']
filtered = [word for word in tokens if word [1] stop_words]

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

Ain

Bnot in

C==

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using in keeps only stopwords, which is the opposite of what we want.

We want to keep words that are not in the stopwords list, so we use not in.

4fill in blank

hard

Fill both blanks to create a dictionary of word counts from tokens.

NLP

word_counts = [1]()
for word in tokens:
    word_counts[word] = word_counts.get(word, [2]) + 1

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

Adict

B0

C1

Dlist

Attempts:

3 left

💡 Hint

Common Mistakes

Using list() instead of dict() causes errors.

Using 1 as default count causes counts to start at 2.

We start with an empty dictionary dict(). The get method returns 0 if the word is not yet counted, then we add 1.

5fill in blank

hard

Fill all three blanks to create a TF-IDF vectorizer and transform documents.

NLP

from sklearn.feature_extraction.text import [1]
vectorizer = [2](stop_words='english')
X = vectorizer.[3](documents)

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

ATfidfVectorizer

Cfit_transform

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using fit alone returns the model, not the transformed data.

Using wrong class names causes import errors.

TfidfVectorizer converts text to TF-IDF features. We create an instance and then call fit_transform to learn and transform the documents.