mltk: A Machine Learning Toolkit

mltk is a library of utilities dedicated to streamlining the analysis of supervised and unsupervised classifiers. Built on top of common libraries including numpy, scipy, and supporting functions from sklearn, mltk includes methods to visualize, analyze, and optimize existing models in a more efficient manner.

Starting with mltk is quite simple: simply install the latest release from PyPI with pip install mltk and begin development with

# import any one of the sub-directories of mltk
from mltk.metrics import *

# use exposed functionality within parameter requirements
print auroc([0,1], [.5, .5])

Installation

Install mltk by running:

$> pip install mltk

Support

If you are having issues, please let Manan Shah know at manan.shah.777@gmail.com. The project is licensed under the MIT license.