diff tvii/dataset/rand.py @ 87:9d5a5e9f5c3b

add kmeans + dataset
author Jeff Hammel <k0scist@gmail.com>
date Sun, 17 Dec 2017 14:05:57 -0800
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tvii/dataset/rand.py	Sun Dec 17 14:05:57 2017 -0800
@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+generate a random dataset
+"""
+
+import csv
+import random
+import sys
+from .cli import DatasetGenerationParser
+
+
+class RandomDataset(object):
+
+    def __init__(self, N, D, bounds=(0., 1.)):
+        assert len(bounds) == 2
+        self.N = N
+        self.D = D
+        self.bounds = bounds
+        self.length = bounds[-1] - bounds[0]
+
+        self.points = [self() for _ in xrange(self.N)]
+
+    def translate(self, fraction):
+        return self.length*fraction + self.bounds[0]
+
+    def __call__(self):
+        """generate one `D`-dimensional point of data"""
+
+        return [self.translate(random.random()) for i in xrange(self.D)]
+
+
+def main(args=sys.argv[1:]):
+    """CLI"""
+
+    # parse command line
+    parser = DatasetGenerationParser(description=__doc__)
+    options = parser.parse_args(args)
+
+    # make some random points
+    points = RandomDataset(N=options.number, D=options.dimensions)
+
+    # output them
+    parser.writer().writerows(points.points)
+
+
+if __name__ == '__main__':
+    main()