Logistic Regression

noun

say it: “loh-JIS-tik rih-GRESH-un” /loʊˈdʒɪstɪk rɪˈɡrɛʃən/

A statistical model that gives the probability that an example belongs to a category, used to sort examples into classes.

What is logistic regression?

Logistic regression is a classification model, despite its name. It adds up the features times their coefficients, as linear regression does, then squeezes the total into a probability between 0 and 1 with the logistic function, and picks the positive class at 0.5 or more. scikit-learn's is LogisticRegression.

from sklearn.linear_model import LogisticRegression
links = [[0], [1], [2], [6], [8], [9]]   # links in each email
spam = [0, 0, 0, 1, 1, 1]
model = LogisticRegression().fit(links, spam)
print(model.predict([[1], [7]]))   # [0 1]: not spam, spam

In a sentence

  • “Logistic regression gave the email a 0.92 chance of being spam.”
  • “Despite the name, logistic regression sorts examples into categories.”

Level: Journeyman · More AI Basics terms at this level

Updated