'''
  This script aims in computing k-means for a given
  data set.
  '''
  
  import argparse
  import numpy as np
  from sklearn.cluster import KMeans
  from os import path

  from os import mkdir

  
  import pickle
  from data import read_file, index_by_id
  
  # -- ARGPARSE --
  parser = argparse.ArgumentParser(description="Cluster with kmeans")
  parser.add_argument("features", type=str, help="Features file")
  parser.add_argument("list", type=str, help="List on which apply kmeans")
  parser.add_argument("outdir", type=str, help="Output directory for k-means models")
  parser.add_argument("--kmin", type=int, help="minimum k", default=2)
  parser.add_argument("--kmax", type=int, help="maximum k", default=100)

  parser.add_argument("--allindir", type=bool, default=False,
                      help="all in same dir or separed ?")

  
  args = vars(parser.parse_args())
  FEATURES = args["features"]
  LST = args["list"]
  OUTDIR = args["outdir"]
  KMIN = args["kmin"]
  KMAX = args["kmax"]

  ALLINDIR = args["allindir"]

  
  # -- READE FILES --
  features = read_file(FEATURES)
  feat_ind = index_by_id(features)
  
  lst = read_file(LST)

  subdir = ""

  # -- TRANSFORM INTO NUMPY --
  X = np.asarray([feat_ind[x[0][0]][x[0][3]][1] for x in lst])

  Ks = range(KMIN, KMAX+1)
  for k in Ks:
      kmeans = KMeans(n_clusters=k, n_init=10, random_state=0).fit(X)

      if ALLINDIR is False:
          subdir = str(k)
          dirname=path.join(OUTDIR, subdir)
          if not path.exists(dirname):
              mkdir(dirname)
      pickle.dump(kmeans, open(path.join(OUTDIR, subdir, "clustering_" + str(k) + ".pkl"), "wb"))