Appendix. Popular machine-learning algorithms

Name

Type

Use

Linear/nonlinear

Requires normalization

Linear regression Regression Model a scalar target with one or more quantitative features. Although regression computes a linear combination, features can be transformed by nonlinear functions if relationships are known or can be guessed. R: www.inside-r.org/r-doc/stats/lm Python: http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html#sklearn.linear_model.LinearRegression Linear Yes
Logistic regression Classification Categorize observations based on quantitative features; predict target class or probabilities of target classes. R: www.statmethods.net/advstats/glm.html Python: http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html ...

Get Real-World Machine Learning now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.