Text feature basics (CountVectorizer, TF-IDF) in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a CountVectorizer instance.

ML Python

from sklearn.feature_extraction.text import [1]
vectorizer = [1]()

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

ALabelEncoder

BTfidfVectorizer

CCountVectorizer

DDictVectorizer

Attempts:

3 left

💡 Hint

Common Mistakes

Using TfidfVectorizer instead of CountVectorizer

Using LabelEncoder which is for labels, not text features

The CountVectorizer converts text into a matrix of token counts.

2fill in blank

medium

Complete the code to transform text data into a count matrix.

ML Python

texts = ['hello world', 'hello machine learning']
count_matrix = vectorizer.[1](texts)

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

Afit

Bpredict

Ctransform

Dfit_transform

Attempts:

3 left

💡 Hint

Common Mistakes

Using fit only, which does not return the matrix

Using predict, which is not a method here

fit_transform learns the vocabulary and returns the count matrix in one step.

3fill in blank

hard

Fix the error in the code to create a TF-IDF vectorizer.

ML Python

from sklearn.feature_extraction.text import [1]
tfidf_vectorizer = [1]()

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

ACountVectorizer

BTfidfVectorizer

CTfidfTransformer

DHashingVectorizer

Attempts:

3 left

💡 Hint

Common Mistakes

Using TfidfTransformer which needs counts first

Using CountVectorizer which only counts words

TfidfVectorizer directly converts text to TF-IDF features.

4fill in blank

hard

Fill both blanks to create a dictionary of word counts for words longer than 3 letters.

ML Python

words = ['data', 'science', 'is', 'fun']
word_counts = {word: [1] for word in words if len(word) [2] 3}

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

A1

B>

C>=

Dlen(word)

Attempts:

3 left

💡 Hint

Common Mistakes

Using len(word) as count instead of 1

Using >= instead of > causing inclusion of 3-letter words

We assign count 1 for each word longer than 3 letters using len(word) > 3.

5fill in blank

hard

Fill all three blanks to create a TF-IDF matrix from text data.

ML Python

from sklearn.feature_extraction.text import [1]
texts = ['machine learning', 'deep learning', 'machine intelligence']
tfidf = [2]()
matrix = tfidf.[3](texts)

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

ATfidfVectorizer

BTfidfTransformer

Cfit_transform

DCountVectorizer

Attempts:

3 left

💡 Hint

Common Mistakes

Using TfidfTransformer which requires count matrix input

Using CountVectorizer which does not compute TF-IDF

Use TfidfVectorizer to create the vectorizer and call fit_transform to get the TF-IDF matrix.