#!/usr/bin/python
import sys
import numpy as np

#in place modification !
def normalize(a):
    print a
    for i in range(a.shape[1]):
        column = a[:,i]
        weights = np.mean(column), np.std(column)
        a[:,i] = (column-weights[0])/weights[1]
        return a

def knn_search(names,d1,d2,k):
    for i,row2 in enumerate(d2):
        distance = []
        for row1 in d1:
            distance += [((row2-row1)**2).sum()]
        indexes = np.argsort(np.array(distance))[:k]
        nn = map(int,names[indexes])
        name = int(names[i])
        print str(name)+"|"+ ",".join(map(str,nn))+"|"+str(name in nn)

if __name__ == "__main__":
    np.random.seed()
    var = float(sys.argv[2])
    sk_data  = np.loadtxt(sys.argv[1],comments="#",delimiter=",")
    names = sk_data[:,0]
    sk_data = sk_data[:,1:]
    noise1 = np.random.normal(0,var,sk_data.shape)
    noise2 = np.random.normal(0,var,sk_data.shape)
    sk1 = normalize(sk_data+noise1)
    sk2 = normalize(sk_data+noise2)
    knn_search(names,sk1,sk2,1)