University of Maryland

EventAction: Distribution

Project Description

EventAction is a prescriptive analytics interface designed to present and explain recommendations of temporal event sequences. EventAction provides a visual analytics approach to (1) identify similar records, (2) explore potential outcomes, (3) review recommended temporal event sequences that might help achieve the users’ goals, and (4) interactively assist users as they define a personalized action plan associated with a probability of success. EventAction’s usage scenarios include student advisingtreatment formulatingcustomer retention, and sports coaching.

Requirements

EventAction requires the following software and packages to run:

  • Python 2.7 – a popular scripting programming language.
  • Numpy – a fundamental package for scientific computing with Python.
  • Flask – a Python framework for web applications.
  • A web browser – we recommend and test using Google Chrome.

EventAction is a web application based on the client-server model. The backend is developed in Python using the Flask web framework, which can be deployed remotely on a server machine or locally on a client machine. The frontend is developed in HTML, CSS, and JavaScript, and runs on a web browser. The locally installed version does not require internet and your data will not be transferred from your computer.

Installing EventAction

Request a Copy

  • Download the latest source: EventAction_v1.0.zip
  • Unzipping EventAction requires a password. If you do not have the password, please contact plaisant@cs.umd.edu and describe how you will use EventAction.

Instructions for Mac OS

1. Check Python Environment

  • python 2.7: python --version
  • pip: pip --version (if missing, install: easy_install pip)

2. Install Dependencies

  • flask: pip install flask
  • numpy: pip install numpy

3. Run EventAction

  • in command line run python EventAction.py
  • in browser (recommend Chrome) open http://127.0.0.1:5000

Instructions for Windows 7

1. Instal Python Environment

2. Install Dependencies

  • flask: <PATH TO WINPYTHON>/scripts/pip install flask
  • numpy: included in WinPython 2.7

3. Run EventAction

  • in command line run <PATH TO WINPYTHON>/scripts/python EventAction.py
  • in browser (recommend Chrome) open http://127.0.0.1:5000

Getting Started

After installing EventAction, you will have access to the following demos (datasets are synthetic):

  • Small Testing Dataset: http://127.0.0.1:5000/?data=students0
  • Student Advising: http://127.0.0.1:5000/?data=students1
  • Digital Marketing: http://127.0.0.1:5000/?data=marketing0
  • Demo with Usage Guidelines: http://127.0.0.1:5000/?data=students1&alert=true

Or, you can load your own dataset using the EventAction user interface.

Project Website