OrdinalEncoder

noun

say it: “OR-dih-nul en-KOH-der” /ˈɔrdənəl ɛnˈkoʊdər/

A scikit-learn tool that replaces each category in a column with a whole number, in a set order.

What is OrdinalEncoder?

OrdinalEncoder is scikit-learn's tool that turns each category into one number: 0, 1, 2 and so on. It suits categories with a real order, such as small, medium and large, given with categories=; for categories with no order, one-hot encoding is safer.

from sklearn.preprocessing import OrdinalEncoder
encoder = OrdinalEncoder(categories=[["small", "medium", "large"]])
print(encoder.fit_transform([["large"], ["small"], ["medium"]]).ravel())   # [2. 0. 1.]

In a sentence

  • “Using an OrdinalEncoder on species would have told the model rabbits come after dogs.”
  • “The OrdinalEncoder turned small, medium and large into 0, 1 and 2.”

Level: Journeyman · More Python terms at this level

Updated