SPAETH2
Cluster Analysis Datasets

SPAETH2 is a second collection of data for testing cluster analysis algorithms. The programs come from reference 1.

Related Data and Programs:

PLOT_POINTS is a FORTRAN90 program used to make images of some of the datasets.

SPAETH is a dataset directory for cluster analysis.

SPAETH2 is a FORTRAN90 library of cluster analysis tools designed to work with data such as that in this directory.

TABLE is a file format used for the files in this dataset.

Reference:

1. Helmuth Spaeth,
   Cluster Dissection and Analysis,
   Theory, FORTRAN Programs, Examples,
   Ellis Horwood, 1985,
   QA278 S68213.
2. Helmuth Spaeth,
   Cluster Analysis Algorithms for Data Reduction and Classification of Objects,
   Ellis Horwood, 1980,
   QA278 S6813.

Data files:

• spaeth2_01.txt, a sample data set of 15 1D points.
• spaeth2_02.txt, the same data as spaeth2_01.txt, but in a different order.
• spaeth2_03.txt, a sample data set of 22 2D points, representing the relative locations of cities in West Germany.
• spaeth2_03.png, a PNG image of the data.
• spaeth2_04.txt, 10 points in the plane (2D).
• spaeth2_04.png, a PNG image of the data.
• spaeth2_05.txt, a sample data set of 59 2D points, representing the relative locations of cities in West Germany.
• spaeth2_05.png, a PNG image of the data.
• spaeth2_06.txt, a sample data set of 23 12D points, representing the monthly values of 23 seasonal quantities.
• spaeth2_07.txt, for each of 89 Bavarian postal codes, the area, population, and population density.
• spaeth2_08.txt, for each of 89 Bavarian postal codes, the number of workers in 4 categories.
• spaeth2_09.txt, a "distance" matrix representing the perceived pairwise distance between 11 car models.
• spaeth2_10.txt, a "distance" matrix representing the rank ordering of 15 breakfasts.
• spaeth2_11.txt, the values of 5 socio-economic variables in 12 municipalities.
• spaeth2_12.txt, a 4 by 4 matrix of 0's and 1's, which is to be symmetrically permuted so that the 1's form blocks.
• spaeth2_13.txt, a 27 by 27 matrix of 0's, 1's, 2's and 3's, which is to be symmetrically permuted so equal numbers form blocks as far as possible.

You can go up one level to the DATASETS directory.