Content-based filtering in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a TF-IDF matrix from the item descriptions.

ML Python

from sklearn.feature_extraction.text import TfidfVectorizer

items = ['Action movie with explosions', 'Romantic comedy with love', 'Sci-fi thriller with aliens']
tfidf = TfidfVectorizer()
item_matrix = tfidf.[1](items)

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

Afit

Btransform

Cfit_transform

Dfit_predict

Attempts:

3 left

💡 Hint

Common Mistakes

Using transform before fitting the vectorizer.

Using fit without transforming the data.

We use fit_transform to learn the vocabulary and transform the items into TF-IDF vectors in one step.

2fill in blank

medium

Complete the code to compute cosine similarity between item vectors.

ML Python

from sklearn.metrics.pairwise import [1]

similarity_matrix = cosine_similarity(item_matrix)

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

Acosine_similarity

Beuclidean_distances

Cmanhattan_distances

Dpairwise_distances

Attempts:

3 left

💡 Hint

Common Mistakes

Using distance functions instead of similarity.

Confusing cosine_similarity with pairwise_distances.

cosine_similarity computes similarity scores between vectors, which is used in content-based filtering.

3fill in blank

hard

Fix the error in the code to get the top 2 similar items for the first item.

ML Python

import numpy as np

similarities = similarity_matrix[0]
top_indices = np.argsort(similarities)[[1]][:2]

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

A:

B-1:

C1:

D::-1

Attempts:

3 left

💡 Hint

Common Mistakes

Not reversing the sorted indices, resulting in lowest scores first.

Using incorrect slice syntax causing errors.

We reverse the sorted indices with [::-1] to get the highest similarity scores first.

4fill in blank

hard

Fill both blanks to create a dictionary of item indices and their similarity scores above 0.5.

ML Python

similar_items = {i: similarities[i] for i in range(len(similarities)) if similarities[i][1] 0.5 and i != [2]

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

A>

B0

C<

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using < instead of > causing wrong filtering.

Not excluding the item itself leading to self-similarity.

We want similarities greater than 0.5 and exclude the item itself at index 0.

5fill in blank

hard

Fill all three blanks to sort the similar items by score descending and get their indices.

ML Python

sorted_items = sorted(similar_items.items(), key=lambda x: x[1], reverse=[2])
top_similar_indices = [item[[3]] for item in sorted_items]

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

A[1]

BTrue

C0

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Sorting ascending by mistake with reverse=False.

Extracting wrong tuple element for indices.

We sort by the similarity score at index 1 descending (reverse=True) and extract the item indices at position 0.