gmm.py 文件源码

def do_kmeans(data, k):
  km = sklearn.cluster.KMeans(n_clusters=k)
  km.fit(data)

  means = km.cluster_centers_.reshape((-1,))

  #initialize standard deviations with distances between random cluster centers
  sds = []
  for i in range(means.shape[0]):
    # choose any 2 means and take half the distance between them
    x, y = np.random.choice(means, 2, replace=False)
    sds.append((x-y)/2)
  sds = np.abs(np.array(sds))

  return (means, sds)

# expectation maximization for gmm
# use_kmeans: whether to initialize using kmeans or randomly
# use_priors: whether to model the prior distribution;
# this attaches a weight to each distribution that tells us
# the percentage of points generated from that distribution