How to use the census.tf-keras.trainer.model.create_keras_model function in census

Uses the Keras model defined in model.py and trains on data loaded and
  preprocessed in util.py. Saves the trained model in TensorFlow SavedModel
  format to the path defined in part by the --job-dir argument.

  Args:
    args: dictionary of arguments - see get_args() for details
  """

  train_x, train_y, eval_x, eval_y = util.load_data()

  # dimensions
  num_train_examples, input_dim = train_x.shape
  num_eval_examples = eval_x.shape[0]

  # Create the Keras Model
  keras_model = model.create_keras_model(
      input_dim=input_dim, learning_rate=args.learning_rate)

  # Pass a numpy array by passing DataFrame.values
  training_dataset = model.input_fn(
      features=train_x.values,
      labels=train_y,
      shuffle=True,
      num_epochs=args.num_epochs,
      batch_size=args.batch_size)

  # Pass a numpy array by passing DataFrame.values
  validation_dataset = model.input_fn(
      features=eval_x.values,
      labels=eval_y,
      shuffle=False,
      num_epochs=args.num_epochs,