HamNN

This repo, as well as the associated cli app VHamNN, have been superseded by the repo VHamML.

A machine learning (ML) library for classification using a nearest neighbor algorithm based on Hamming distances. hamnn documentation

There is an associated Command Line Interface app, VHamNN, which facilitates using the hamnn library.

You can use the library with your own datasets, or with a selection of publicly available datasets that are widely used for demonstrating and testing ML classifiers, in the datasets directory. These files are either in ARFF (Attribute-Relation File Format) or in Orange file format.

Classification accuracy with datasets in the datasets directory: See this table

Do we really need another ML library? Read this!

And have a look here for a more complete description and potential use cases.

To use the HamNN library

This assumes you already have V installed on your system. If not, please refer to the VHamNN readme for instructions on installing V.

v install holder66.hamnn

And (optionally) libraries used by HamNN for generating plots and for colored output on the console:

v install vsl
v install Mewzax.chalk

In your V code:

import holder66.hamnn

Example source code:

module main

import hamnn
import os

fn main() {
    opts := hamnn.Options{
        show_flag: true
    }
    datafile_path := os.home_dir() + '/.vmodules/holder66/hamnn/datasets/iris.tab'
    println(datafile_path)

    ds := hamnn.load_file(datafile_path)
    result := hamnn.analyze_dataset(ds, opts)
    println(result)
}

Getting help:

The V lang community meets on Discord

For bug reports, feature requests, etc., please raise an issue on github:

for HamNN

for VHamNN

MNIST dataset

The mnist_train.tab file is too large to keep in the repository. If you wish to experiment with it, it can be downloaded by right-clicking on this link in a web browser, or downloaded via the command line:

wget http://henry.olders.ca/datasets/mnist_train.tab

Previous versions

The most recent version of the HamNN algorithm (2012) was written in python; one can experiment with it via a web-based interface. I’ve posted test results using this classifier with a number of publicly accessible datasets. Here are some additional test results with genomics datasets.

The process of development in its early stages is described in this essay written in 1989.

Copyright (c) 2017, 2022: Henry Olders.