/comparing-classifiers

a short program for comparing approaches for classifying numeric data

Primary LanguagePython

comparing-classifiers

Description

A simple application which trains and tests three classifiers on the same dataset and compares results

Data

Retrieved from: http://archive.ics.uci.edu/ml/datasets/banknote+authentication#

Multi-variate data set comprising of 4 attributes and a binary class variable. The data contains features from images of genuine and forged banknote-like specimen.

Attributes
  1. variance
  2. skewness
  3. curtosis
  4. entropy
Classes (Binary)
  • real
  • fake
Citation

Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.

Classifiers

  • Logistic Regression
  • Support Vector Machine
  • Adaboost