deal.py 文件源码

def step4():
  key_vec = pickle.loads(open("key_vec.pkl", "rb").read()) 
  vecs = []
  for ev, vec in enumerate(key_vec.values()):
    x = np.array(vec)
    if np.isnan(x).any():
      # print(vec)
      continue
    vecs.append(x)
  vecs   = np.array(vecs)
  kmeans = KMeans(n_clusters=128, init='k-means++', n_init=10, max_iter=300,
                       tol=0.0001,precompute_distances='auto', verbose=0,
                       random_state=None, copy_x=True, n_jobs=1)
  print("now fitting...")
  kmeans.fit(vecs)

  open("kmeans.model", "wb").write( pickle.dumps(kmeans) )
  for p in kmeans.predict(vecs):
    print(p)