# L-6 MCS 275 25 Jan 2010 : kmeans.py

# Reads the file generated by makedata.py, shuffles the list,
# and applies the k-means algorithm.

import random, turtle
from math import sqrt
from makedata import Distance, Centroids, Radii, ShowData, ShowCentroids

def ReadList(file):
   """
   Attempts to read a list from file
   and will return this list.
   Returns the empty list if exceptions occur.
   """
   try:
      s = file.readline()
      L = eval(s)
      if isinstance(L,list):
         return L
      else:
         print s
         print "no list on file..."
         return []
   except:
      print "exception occurred during reading..."
      return []

def ReadData():
   """
   Prompts the user for a name of a file,
   tries to open the file and to read a list.
   If all goes well, the list is returned.
   """
   L = []
   while True:
      name = raw_input("give file name : ")
      try:
         f = open(name,'r')
         L = ReadList(f)
         f.close()
         return L
      except IOError:
         print 'cound not open file ' + name
         print 'please try again' 
   return L

def Flatten(L):
   """
   Flattens the list of lists into one list.
   """
   R = []
   for each in L:
      for e in each:
         R.append(e)
   return R

def ClassifyPoint(C,p):
   """
   Returns the index of the point q in C,
   closest to C.
   """
   d = [Distance(p,q) for q in C]
   m = min(d)
   return d.index(m)

def ClassifyData(L,k,C):
   """
   Returns a lists of k lists, using the centroids
   in C to classify all points in L.
   """
   R = [ [] for i in range(0,k) ]
   for p in L:
      i = ClassifyPoint(C,p)
      R[i].append(p)
   return R 

def kmeans(L,k):
   """
   Applies the K-means algorithm 3 times to divide 
   the data in L into k clusters.
   """
   C0 = random.sample(L,k) # k unique random elements from L
   K0 = ClassifyData(L,k,C0)
   C1 = Centroids(K0); R1 = Radii(K0,C1)
   turtle.color('red','red')
   ShowCentroids(C1,R1)
   ans = raw_input("hit enter to continue ...")
   K1 = ClassifyData(L,k,C1)
   C2 = Centroids(K1); R2 = Radii(K1,C2)
   turtle.color('green','green')
   ShowCentroids(C2,R2)
   ans = raw_input("hit enter to continue ...")
   K2 = ClassifyData(L,k,C2)
   C3 = Centroids(K2); R3 = Radii(K2,C3)
   turtle.color('blue','blue')
   ShowCentroids(C3,R3)

def main():
   """
   Prompts the user for a file to read a list of lists
   of points of integer coordinates (generated by makedata).
   """ 
   D = ReadData()
   ShowData(D)
   L = Flatten(D)
   print "the flattened list : ", L
   random.shuffle(L)
   k = input("Give number of clusters : ");
   kmeans(L,k)
   ans = raw_input("exit ? (y/n) ")

main()