Refactoring of clustering code

week09/improvement/clustering.py

@@ -1,15 +1,15 @@
 """This code implements the k-means clustering algorithm for 2 dimensions."""
 
-from math import *
-from random import *
+from math import sqrt
+from random import randrange
 
-k=3
+num_clusters=3
 
 lines = open('samples.csv', 'r').readlines()
 ps=[]
 for line in lines: ps.append(tuple(map(float, line.strip().split(','))))
 
-m=[ps[randrange(len(ps))], ps[randrange(len(ps))], ps[randrange(len(ps))]]
+m=[ps[randrange(len(ps))] for i in range(num_clusters)]
 
 alloc=[None]*len(ps)
 n=0
@@ -21,12 +21,12 @@
     d[1]=sqrt((p[0]-m[1][0])**2 + (p[1]-m[1][1])**2)
     d[2]=sqrt((p[0]-m[2][0])**2 + (p[1]-m[2][1])**2)
     alloc[i]=d.index(min(d))
-  for i in range(3):
+  for i in range(num_clusters):
     alloc_ps=[p for j, p in enumerate(ps) if alloc[j] == i]
     new_mean=(sum([a[0] for a in alloc_ps]) / len(alloc_ps), sum([a[1] for a in alloc_ps]) / len(alloc_ps))
     m[i]=new_mean
   n=n+1
 
-for i in range(3):
+for i in range(num_clusters):
   alloc_ps=[p for j, p in enumerate(ps) if alloc[j] == i]
   print("Cluster " + str(i) + " is centred at " + str(m[i]) + " and has " + str(len(alloc_ps)) + " points.")

week09/improvement/samples.csv

@@ -0,0 +1,12 @@
+342,4454
+34,5
+34,34
+45,56
+453,67
+34,6
+7,45
+45,7
+45,6
+65654,456
+54,564
+456,56