import csv
import numpy as np
%matplotlib inline 
import matplotlib as plt
import pylab as pl

baseFileName = '2010.tab' #  dataset
with open(baseFileName, 'rb') as f:
    reader = csv.DictReader(f, dialect = 'excel', delimiter = '\t')
    base =  [dict([key, value] for key, value in row.iteritems()) for row in reader]

winners = [r['Winner'] for r in base]
losers = [r['Loser'] for r in base]
players = np.unique(winners + losers)
n = len(players)
print "number of players: ", n 

def getindex(str, a):
    return [i for (i, val) in enumerate(a) if val == str]

getindex('Williams V.',[r['Loser'] for r in base])

R = np.zeros((n,n))
pts = np.zeros((n,1))
for r in base:
    # get Winner and Loser. Assign 1 to winner row and loser column
    win = r['Winner']
    los = r['Loser']
    wind = getindex(win, players)
    lind = getindex(los, players)
    # Assign 1 to winner vs loser
    R[wind,lind] = 1
    if r['WPts'] != 'N/A':
        if int(r['WPts']) > pts[wind]:
            pts[wind] = int(r['WPts'])
    if r['LPts'] != 'N/A':
        if int(r['LPts']) > pts[lind]:
            pts[lind] = int(r['LPts'])


pl.imshow(R, interpolation='none')

r = np.ones((n,1))
for i in range(10):
    r = np.dot(R,r)
    r = r/np.linalg.norm(r)

eigenrank = r[:,0].argsort()
eigenrank = eigenrank[::-1]

wtp_rank = pts[:,0].argsort()
wtp_rank = wtp_rank[::-1]

print players[wtp_rank[:20]]

print players[eigenrank[:20]]

print 'eigen score ', r[getindex('Henin J.',players),0]
print 'WTP pts ', pts[getindex('Henin J.',players),0]
print 'eigen rank ', getindex(getindex('Henin J.',players),eigenrank)[0]+1
print 'WTP rank', getindex(getindex('Henin J.',players),wtp_rank)[0]+1

pl.plot(pts[:,0],r[:,0],'.')
pl.plot(range(8000),np.polyval(np.polyfit(pts[:,0],r[:,0],2),range(8000)))

for p in players[wtp_rank]:
    i = getindex(p,players)
    print p, pts[i,0][0], r[i,0][0], getindex(i,wtp_rank)[0]+1, getindex(i,eigenrank)[0]+1