Created
April 11, 2019 08:26
-
-
Save vtta/4040eb0d20d3ef1bfe6f2d8850e1722f to your computer and use it in GitHub Desktop.
GNU Octave script to test my k-means algorithm using the iris data set
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
% usage: | |
% octave-cli iris.m | |
fid = fopen('iris.data'); | |
irisTextData = textscan(fid,'%f %f %f %f %s', 200, 'Delimiter',','); | |
fclose (fid); | |
irisMatrix = cell2mat(irisTextData(:,1:4)); | |
k = 3; | |
clusterID = kMeans(irisMatrix, k); | |
result = cell2mat(irisTextData(:,5)); | |
for i = 1:size(result, 1) | |
result(i, 2) = clusterID(i); | |
end | |
rightSampleCnt = 0; | |
clusterNameMap = cellstr(["Iris-virginica"; "Iris-versicolor"; "Iris-setosa"]); | |
for i = 1:size(result, 1) | |
printf("%.1f %.1f %.1f %.1f %s\t%d", ... | |
irisMatrix(i,:), cell2mat(result(i, 1)) , cell2mat(result(i, 2)) ); | |
if strcmp(result(i, 1), clusterNameMap(cell2mat(result(i, 2))) ) | |
rightSampleCnt = rightSampleCnt+1; | |
% printf(" √"); | |
else | |
printf(" X"); | |
end | |
printf("\n"); | |
end | |
printf("Total Sample: %d\nRight Sample: %d\nAccuracy: %f\n", ... | |
size(result, 1), rightSampleCnt, rightSampleCnt / size(result, 1) ); | |
% writetable(cell2table(result), 'result.csv') % only avaliable in Matlab 😒 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment