Visualizing topics (pyLDAvis) in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the pyLDAvis library.

NLP

import [1]

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

ApyLDAvis

Bmatplotlib

Csklearn

Dpandas

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated libraries like matplotlib or pandas.

Misspelling the library name.

pyLDAvis is the library used to visualize topic models like LDA.

2fill in blank

medium

Complete the code to prepare the visualization data for an LDA model.

NLP

vis_data = pyLDAvis.[1](lda_model, corpus, dictionary)

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

Aplot

Bprepare

Cshow

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using plot or show instead of prepare.

Confusing model fitting with visualization preparation.

The prepare function creates the data needed for visualization from the model, corpus, and dictionary.

3fill in blank

hard

Fix the error in the code to display the pyLDAvis visualization in a Jupyter notebook.

NLP

pyLDAvis.[1](vis_data)

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

Ashow

Bdisplay

Crender

Dplot

Attempts:

3 left

💡 Hint

Common Mistakes

Using display which is not a pyLDAvis function.

Trying to use plot or render which do not exist.

The show function displays the interactive visualization in Jupyter notebooks.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that filters topics with probability greater than 0.1.

NLP

filtered_topics = {topic: prob for topic, prob in topic_probs.items() if prob [1] [2]

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

A>

B0.1

C<

D0.5

Attempts:

3 left

💡 Hint

Common Mistakes

Using less than symbol instead of greater than.

Using 0.5 instead of 0.1 as threshold.

The comprehension keeps topics where the probability is greater than 0.1.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps topic names to their top words if the word frequency is above 0.05.

NLP

top_words = {topic[1]: word for topic, words in topic_word_dist.items() for word, freq in words if freq [2] [3]

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

A.upper()

B>

C0.05

D.lower()

Attempts:

3 left

💡 Hint

Common Mistakes

Using lowercase instead of uppercase for topic names.

Using less than symbol or wrong threshold for frequency.

This comprehension creates a dictionary with topic names in uppercase as keys and words as values, filtering words with frequency greater than 0.05.