Data Vectorization

What

Data Vectorization is the process of translating real life information into mathematical representation. This translation makes it possible for machine to learn.

Vector Space Model

Bag of Words

TF-IDF

N-Gram

Kernel Hashing

Data Attribute Types

Nominal/Unordered Qualitative

E.g. (blue, yellow, green), (republic, democratic)

Ordinal/Ordered Qualitative

E.g. (short, medium, tall), (average, good, excellent)

Interval/Discrete Quantitative

E.g. year

Ratio/Continuous Quantitative

E.g. speed

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.