pyords 0.0.2

A python package for operations research and data science problems.

pyords

A library for operations research, data science, and financial engineering.

features

• pyords.transopt - transportation optimization
• pyords.netopt - network optimization
• pyords.schedopt - schedule optimization

implementations

• graph theory
• genetic algorithm
• simulation
• machine learning

motivation behind the project

Working solo in an engineering team, I want to dedicate a fair amount of time to productionalizing the different skills I've been working on. This library will help me expose myself more to the following:

1. Open-source software development.
2. Data Science.
3. Operations Research.
4. Financial Engineering.
5. Visualizations in Python or JavaScript.
6. Comprehensive self-education of tools such as NumPy, Pandas, D3.js, Matplotlib, IPython and jupyter, scikit-learn and SciPy, git, Google OR Tools (ortools), Pyomo, Supply Chain Guru, Keras and/or Hadoop, AWS, GCP, Vagrant.

Development & Documentation

Design is up for discussion. I'm going to start by just namespacing most of the unique features implemented. Some currently developed features include the following:

cluster

cluster is aimed at identifying groups in data. See clustering.

current scope

1. Greenfield Analysis - a facility location and operation problem. cluster will provide a clustering algorithm for heuristic solutions.

2. Route heuristic for clustering final-destination demand nodes by proximity.

genetic_algorithm

Genetic Algorithm.

solver

1. Route optimization.

distance

1. Haversine distance.
2. Distance matrix preprocessing.