Lesson 2 of 4

Text as numbers

Watch, read the card, then practise. Bag of words and TF-IDF · Word embeddings

Video coming soon

The video for this lesson is being recorded.

Meanwhile, the notes below and the 60-second cards cover the same ideas.

Bag of words and TF-IDF
Bag-of-words counts each word in a document. TF-IDF also lowers the weight of words that appear everywhere.
Remember: TF-IDF + logistic regression is a strong, cheap baseline.
Word embeddings
Embeddings turn words into vectors, so words with similar meanings sit close together.
Remember: Close vectors = similar meaning.

Try the example in Code Lab

import math
tf = 2 / 10                  # 2 times in a 10-word document
idf = math.log10(100 / 10)   # in 10 of 100 documents
print(round(tf * idf, 2))

← Natural language processing

Lesson 2 of 4

Text as numbers

Watch, read the card, then practise. Bag of words and TF-IDF · Word embeddings

Video coming soon

The video for this lesson is being recorded.

Meanwhile, the notes below and the 60-second cards cover the same ideas.

Practise this topic

Bag of words and TF-IDF
Bag-of-words counts each word in a document. TF-IDF also lowers the weight of words that appear everywhere.
Remember: TF-IDF + logistic regression is a strong, cheap baseline.
Word embeddings
Embeddings turn words into vectors, so words with similar meanings sit close together.
Remember: Close vectors = similar meaning.

Try the example in Code Lab

import math
tf = 2 / 10                  # 2 times in a 10-word document
idf = math.log10(100 / 10)   # in 10 of 100 documents
print(round(tf * idf, 2))