import numpy as np
import pylab as pl

class SOM(object):
  def __init__(self, X, output, iteration, batch_size):
    """
    :param X: 形狀是N*D， 輸入樣本有N個(gè),每個(gè)D維
    :param output: (n,m)一個(gè)元組，為輸出層的形狀是一個(gè)n*m的二維矩陣
    :param iteration:迭代次數(shù)
    :param batch_size:每次迭代時(shí)的樣本數(shù)量
    初始化一個(gè)權(quán)值矩陣，形狀為D*(n*m)，即有n*m權(quán)值向量，每個(gè)D維
    """
    self.X = X
    self.output = output
    self.iteration = iteration
    self.batch_size = batch_size
    self.W = np.random.rand(X.shape[1], output[0] * output[1])
    print (self.W.shape)

  def GetN(self, t):
    """
    :param t:時(shí)間t, 這里用迭代次數(shù)來表示時(shí)間
    :return: 返回一個(gè)整數(shù)，表示拓?fù)渚嚯x，時(shí)間越大，拓?fù)溧徲蛟叫?
    """
    a = min(self.output)
    return int(a-float(a)*t/self.iteration)

  def Geteta(self, t, n):
    """
    :param t: 時(shí)間t, 這里用迭代次數(shù)來表示時(shí)間
    :param n: 拓?fù)渚嚯x
    :return: 返回學(xué)習(xí)率，
    """
    return np.power(np.e, -n)/(t+2)

  def updata_W(self, X, t, winner):
    N = self.GetN(t)
    for x, i in enumerate(winner):
      to_update = self.getneighbor(i[0], N)
      for j in range(N+1):
        e = self.Geteta(t, j)
        for w in to_update[j]:
          self.W[:, w] = np.add(self.W[:,w], e*(X[x,:] - self.W[:,w]))

  def getneighbor(self, index, N):
    """
    :param index:獲勝神經(jīng)元的下標(biāo)
    :param N: 鄰域半徑
    :return ans: 返回一個(gè)集合列表，分別是不同鄰域半徑內(nèi)需要更新的神經(jīng)元坐標(biāo)
    """
    a, b = self.output
    length = a*b
    def distence(index1, index2):
      i1_a, i1_b = index1 // a, index1 % b
      i2_a, i2_b = index2 // a, index2 % b
      return np.abs(i1_a - i2_a), np.abs(i1_b - i2_b)

    ans = [set() for i in range(N+1)]
    for i in range(length):
      dist_a, dist_b = distence(i, index)
      if dist_a <= N and dist_b <= N: ans[max(dist_a, dist_b)].add(i)
    return ans



  def train(self):
    """
    train_Y:訓(xùn)練樣本與形狀為batch_size*(n*m)
    winner:一個(gè)一維向量，batch_size個(gè)獲勝神經(jīng)元的下標(biāo)
    :return:返回值是調(diào)整后的W
    """
    count = 0
    while self.iteration > count:
      train_X = self.X[np.random.choice(self.X.shape[0], self.batch_size)]
      normal_W(self.W)
      normal_X(train_X)
      train_Y = train_X.dot(self.W)
      winner = np.argmax(train_Y, axis=1).tolist()
      self.updata_W(train_X, count, winner)
      count += 1
    return self.W

  def train_result(self):
    normal_X(self.X)
    train_Y = self.X.dot(self.W)
    winner = np.argmax(train_Y, axis=1).tolist()
    print (winner)
    return winner

def normal_X(X):
  """
  :param X:二維矩陣，N*D，N個(gè)D維的數(shù)據(jù)
  :return: 將X歸一化的結(jié)果
  """
  N, D = X.shape
  for i in range(N):
    temp = np.sum(np.multiply(X[i], X[i]))
    X[i] /= np.sqrt(temp)
  return X
def normal_W(W):
  """
  :param W:二維矩陣，D*(n*m)，D個(gè)n*m維的數(shù)據(jù)
  :return: 將W歸一化的結(jié)果
  """
  for i in range(W.shape[1]):
    temp = np.sum(np.multiply(W[:,i], W[:,i]))
    W[:, i] /= np.sqrt(temp)
  return W

#畫圖
def draw(C):
  colValue = ['r', 'y', 'g', 'b', 'c', 'k', 'm']
  for i in range(len(C)):
    coo_X = []  #x坐標(biāo)列表
    coo_Y = []  #y坐標(biāo)列表
    for j in range(len(C[i])):
      coo_X.append(C[i][j][0])
      coo_Y.append(C[i][j][1])
    pl.scatter(coo_X, coo_Y, marker='x', color=colValue[i%len(colValue)], label=i)

  pl.legend(loc='upper right')
  pl.show()

#數(shù)據(jù)集：每三個(gè)是一組分別是西瓜的編號(hào)，密度，含糖量
data = """
1,0.697,0.46,2,0.774,0.376,3,0.634,0.264,4,0.608,0.318,5,0.556,0.215,
6,0.403,0.237,7,0.481,0.149,8,0.437,0.211,9,0.666,0.091,10,0.243,0.267,
11,0.245,0.057,12,0.343,0.099,13,0.639,0.161,14,0.657,0.198,15,0.36,0.37,
16,0.593,0.042,17,0.719,0.103,18,0.359,0.188,19,0.339,0.241,20,0.282,0.257,
21,0.748,0.232,22,0.714,0.346,23,0.483,0.312,24,0.478,0.437,25,0.525,0.369,
26,0.751,0.489,27,0.532,0.472,28,0.473,0.376,29,0.725,0.445,30,0.446,0.459"""

a = data.split(',')
dataset = np.mat([[float(a[i]), float(a[i+1])] for i in range(1, len(a)-1, 3)])
dataset_old = dataset.copy()

som = SOM(dataset, (5, 5), 1, 30)
som.train()
res = som.train_result()
classify = {}
for i, win in enumerate(res):
  if not classify.get(win[0]):
    classify.setdefault(win[0], [i])
  else:
    classify[win[0]].append(i)
C = []#未歸一化的數(shù)據(jù)分類結(jié)果
D = []#歸一化的數(shù)據(jù)分類結(jié)果
for i in classify.values():
  C.append(dataset_old[i].tolist())
  D.append(dataset[i].tolist())
draw(C)
draw(D)