Parallel optimal choropleth map classification in PySAL

Sergio J. Rey, Luc Anselin, Robert Pahle, Xing Kang, Philip Stephens

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

In this article, we report on our experiences with refactoring a spatial analysis library to support parallelization. Python Spatial Analysis Library (PySAL) is a library of spatial analytical functions written in the open-source language, Python. As part of a larger scale effort toward developing cyberinfrastructure of GIScience, we examine the particular case of choropleth map classification through alternative parallel implementations of the Fisher-Jenks optimal classification method using a multi-core, single desktop environment. The implementations rely on three different parallel Python libraries, PyOpenCL, Parallel Python, (PP) and Multiprocessing. Our results point to the dominance of the CPU-based Parallel Python and Multiprocessing implementations over the Graphical Processing Unit (GPU)-based PyOpenCL approach.

Original languageEnglish (US)
Pages (from-to)1023-1039
Number of pages17
JournalInternational Journal of Geographical Information Science
Volume27
Issue number5
DOIs
StatePublished - May 2013

Fingerprint

spatial analysis
Program processors
library
Processing
language
experience

Keywords

  • parallelization
  • PySAL
  • spatial analysis

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development
  • Library and Information Sciences

Cite this

Parallel optimal choropleth map classification in PySAL. / Rey, Sergio J.; Anselin, Luc; Pahle, Robert; Kang, Xing; Stephens, Philip.

In: International Journal of Geographical Information Science, Vol. 27, No. 5, 05.2013, p. 1023-1039.

Research output: Contribution to journalArticle

Rey, Sergio J. ; Anselin, Luc ; Pahle, Robert ; Kang, Xing ; Stephens, Philip. / Parallel optimal choropleth map classification in PySAL. In: International Journal of Geographical Information Science. 2013 ; Vol. 27, No. 5. pp. 1023-1039.
@article{ba839e511c4e415c86b364156c1196e9,
title = "Parallel optimal choropleth map classification in PySAL",
abstract = "In this article, we report on our experiences with refactoring a spatial analysis library to support parallelization. Python Spatial Analysis Library (PySAL) is a library of spatial analytical functions written in the open-source language, Python. As part of a larger scale effort toward developing cyberinfrastructure of GIScience, we examine the particular case of choropleth map classification through alternative parallel implementations of the Fisher-Jenks optimal classification method using a multi-core, single desktop environment. The implementations rely on three different parallel Python libraries, PyOpenCL, Parallel Python, (PP) and Multiprocessing. Our results point to the dominance of the CPU-based Parallel Python and Multiprocessing implementations over the Graphical Processing Unit (GPU)-based PyOpenCL approach.",
keywords = "parallelization, PySAL, spatial analysis",
author = "Rey, {Sergio J.} and Luc Anselin and Robert Pahle and Xing Kang and Philip Stephens",
year = "2013",
month = "5",
doi = "10.1080/13658816.2012.752094",
language = "English (US)",
volume = "27",
pages = "1023--1039",
journal = "International Journal of Geographical Information Science",
issn = "1365-8816",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

TY - JOUR

T1 - Parallel optimal choropleth map classification in PySAL

AU - Rey, Sergio J.

AU - Anselin, Luc

AU - Pahle, Robert

AU - Kang, Xing

AU - Stephens, Philip

PY - 2013/5

Y1 - 2013/5

N2 - In this article, we report on our experiences with refactoring a spatial analysis library to support parallelization. Python Spatial Analysis Library (PySAL) is a library of spatial analytical functions written in the open-source language, Python. As part of a larger scale effort toward developing cyberinfrastructure of GIScience, we examine the particular case of choropleth map classification through alternative parallel implementations of the Fisher-Jenks optimal classification method using a multi-core, single desktop environment. The implementations rely on three different parallel Python libraries, PyOpenCL, Parallel Python, (PP) and Multiprocessing. Our results point to the dominance of the CPU-based Parallel Python and Multiprocessing implementations over the Graphical Processing Unit (GPU)-based PyOpenCL approach.

AB - In this article, we report on our experiences with refactoring a spatial analysis library to support parallelization. Python Spatial Analysis Library (PySAL) is a library of spatial analytical functions written in the open-source language, Python. As part of a larger scale effort toward developing cyberinfrastructure of GIScience, we examine the particular case of choropleth map classification through alternative parallel implementations of the Fisher-Jenks optimal classification method using a multi-core, single desktop environment. The implementations rely on three different parallel Python libraries, PyOpenCL, Parallel Python, (PP) and Multiprocessing. Our results point to the dominance of the CPU-based Parallel Python and Multiprocessing implementations over the Graphical Processing Unit (GPU)-based PyOpenCL approach.

KW - parallelization

KW - PySAL

KW - spatial analysis

UR - http://www.scopus.com/inward/record.url?scp=84878161754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878161754&partnerID=8YFLogxK

U2 - 10.1080/13658816.2012.752094

DO - 10.1080/13658816.2012.752094

M3 - Article

AN - SCOPUS:84878161754

VL - 27

SP - 1023

EP - 1039

JO - International Journal of Geographical Information Science

JF - International Journal of Geographical Information Science

SN - 1365-8816

IS - 5

ER -