def testBiasEnsembleMultiClass(self):
    with self.test_session():
      tree_ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      tree = tree_ensemble_config.trees.add()
      tree_ensemble_config.tree_metadata.add().is_finalized = True
      leaf = tree.nodes.add().leaf
      _append_to_leaf(leaf, 0, -0.4)
      _append_to_leaf(leaf, 1, 0.9)

      tree_ensemble_config.tree_weights.append(1.0)

      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=tree_ensemble_config.SerializeToString(),
          name="multiclass")
      resources.initialize_resources(resources.shared_resources()).run()

      # Prepare learner config.
      learner_config = learner_pb2.LearnerConfig()
      learner_config.num_classes = 3

      result, dropout_info = self._get_predictions(
          tree_ensemble_handle,
          learner_config=learner_config.SerializeToString(),
          reduce_dim=True)
      self.assertAllClose([[-0.4, 0.9], [-0.4, 0.9]], result.eval())

      # Empty dropout.
      self.assertAllEqual([[], []], dropout_info.eval())

  def testTreeFinalized(self):
    with self.test_session():
      tree_ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      # Depth 3 tree.
      tree1 = tree_ensemble_config.trees.add()
      _set_float_split(tree1.nodes.add().dense_float_binary_split, 0, 9.0, 1, 2)
      _set_float_split(tree1.nodes.add()
                       .sparse_float_binary_split_default_left.split, 0, -20.0,
                       3, 4)
      _append_to_leaf(tree1.nodes.add().leaf, 0, 0.2)
      _append_to_leaf(tree1.nodes.add().leaf, 0, 0.3)
      _set_categorical_id_split(tree1.nodes.add().categorical_id_binary_split,
                                0, 9, 5, 6)
      _append_to_leaf(tree1.nodes.add().leaf, 0, 0.5)
      _append_to_leaf(tree1.nodes.add().leaf, 0, 0.6)

      tree_ensemble_config.tree_weights.append(1.0)
      tree_ensemble_config.tree_metadata.add().is_finalized = True

      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=tree_ensemble_config.SerializeToString(),
          name="full_ensemble")
      resources.initialize_resources(resources.shared_resources()).run()

      result = prediction_ops.gradient_trees_partition_examples(
          tree_ensemble_handle, [self._dense_float_tensor], [
              self._sparse_float_indices1, self._sparse_float_indices2
          ], [self._sparse_float_values1, self._sparse_float_values2],
          [self._sparse_float_shape1,
           self._sparse_float_shape2], [self._sparse_int_indices1],
          [self._sparse_int_values1], [self._sparse_int_shape1])

      self.assertAllEqual([0, 0], result.eval())

  def testSaveRestoreBeforeFlush(self):
    save_dir = os.path.join(self.get_temp_dir(), "save_restore")
    save_path = os.path.join(tempfile.mkdtemp(prefix=save_dir), "hash")

    with self.cached_session() as sess:
      accumulator = boosted_trees_ops.QuantileAccumulator(
          num_streams=2, num_quantiles=3, epsilon=self.eps, name="q0")

      save = saver.Saver()
      resources.initialize_resources(resources.shared_resources()).run()

      summaries = accumulator.add_summaries([self._feature_0, self._feature_1],
                                            self._example_weights)
      self.evaluate(summaries)
      buckets = accumulator.get_bucket_boundaries()
      self.assertAllClose([], buckets[0].eval())
      self.assertAllClose([], buckets[1].eval())
      save.save(sess, save_path)
      self.evaluate(accumulator.flush())
      self.assertAllClose(self._feature_0_boundaries, buckets[0].eval())
      self.assertAllClose(self._feature_1_boundaries, buckets[1].eval())

    with self.session(graph=ops.Graph()) as sess:
      accumulator = boosted_trees_ops.QuantileAccumulator(
          num_streams=2, num_quantiles=3, epsilon=self.eps, name="q0")
      save = saver.Saver()
      save.restore(sess, save_path)
      buckets = accumulator.get_bucket_boundaries()
      self.assertAllClose([], buckets[0].eval())
      self.assertAllClose([], buckets[1].eval())

  def testAverageMoreThanNumTreesExist(self):
    with self.test_session():
      tree_ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      adjusted_tree_ensemble_config = (
          tree_config_pb2.DecisionTreeEnsembleConfig())
      # When we say to average over more trees than possible, it is averaging
      # across all trees.
      total_num = 100
      for i in range(0, total_num):
        tree = tree_ensemble_config.trees.add()
        _append_to_leaf(tree.nodes.add().leaf, 0, -0.4)

        tree_ensemble_config.tree_metadata.add().is_finalized = True
        tree_ensemble_config.tree_weights.append(1.0)
        # This is how the weight will look after averaging
        copy_tree = adjusted_tree_ensemble_config.trees.add()
        _append_to_leaf(copy_tree.nodes.add().leaf, 0, -0.4)

        adjusted_tree_ensemble_config.tree_metadata.add().is_finalized = True
        adjusted_tree_ensemble_config.tree_weights.append(
            1.0 * (total_num - i) / total_num)

      # Prepare learner config WITH AVERAGING.
      learner_config = learner_pb2.LearnerConfig()
      learner_config.num_classes = 2
      # We have only 100 trees but we ask to average over 250.
      learner_config.averaging_config.average_last_n_trees = 250

      # No averaging config.
      learner_config_no_averaging = learner_pb2.LearnerConfig()
      learner_config_no_averaging.num_classes = 2

      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=tree_ensemble_config.SerializeToString(),
          name="existing")

      # This is how our ensemble will "look" during averaging
      adjusted_tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=adjusted_tree_ensemble_config.SerializeToString(
          ),
          name="adjusted")

      resources.initialize_resources(resources.shared_resources()).run()

      result, dropout_info = self._get_predictions(
          tree_ensemble_handle,
          learner_config.SerializeToString(),
          apply_averaging=True,
          reduce_dim=True)

      pattern_result, pattern_dropout_info = self._get_predictions(
          adjusted_tree_ensemble_handle,
          learner_config_no_averaging.SerializeToString(),
          apply_averaging=False,
          reduce_dim=True)

      self.assertAllEqual(result.eval(), pattern_result.eval())
      self.assertAllEqual(dropout_info.eval(), pattern_dropout_info.eval())

 def testBasicCallableParams(self):
   for dtype in [dtypes.half, dtypes.float32, dtypes.float64]:
     with self.cached_session():
       var0 = resource_variable_ops.ResourceVariable([1.0, 2.0], dtype=dtype)
       var1 = resource_variable_ops.ResourceVariable([3.0, 4.0], dtype=dtype)
       grads0 = constant_op.constant([0.1, 0.1], dtype=dtype)
       grads1 = constant_op.constant([0.01, 0.01], dtype=dtype)
       lr = lambda: 3.0
       sgd_op = gradient_descent.GradientDescentOptimizer(lr).apply_gradients(
           zip([grads0, grads1], [var0, var1]))
       # TODO(apassos) calling initialize_resources on all resources here
       # doesn't work because the sessions and graph are reused across unit
       # tests and this would mean trying to reinitialize variables. Figure out
       # a long-term solution for this.
       resources.initialize_resources([var0, var1]).run()
       # Fetch params to validate initial values
       self.assertAllCloseAccordingToType([1.0, 2.0], var0.eval())
       self.assertAllCloseAccordingToType([3.0, 4.0], var1.eval())
       # Run 1 step of sgd
       sgd_op.run()
       # Validate updated params
       self.assertAllCloseAccordingToType([1.0 - 3.0 * 0.1, 2.0 - 3.0 * 0.1],
                                          var0.eval())
       self.assertAllCloseAccordingToType([3.0 - 3.0 * 0.01, 4.0 - 3.0 * 0.01],
                                          var1.eval())

  def testStreamingQuantileBuckets(self):
    """Sets up the quantile summary op test as follows.

    100 batches of data is added to the accumulator. The batches are in form:
    [0 1 .. 99]
    [100 101 .. 200]
    ...
    [9900 9901 .. 9999]
    All the batches have 1 for all the example weights.
    """
    with self.test_session() as sess:
      accumulator = quantile_ops.QuantileAccumulator(
          init_stamp_token=0, num_quantiles=3, epsilon=0.01, name="q1")
      resources.initialize_resources(resources.shared_resources()).run()
    weight_placeholder = array_ops.placeholder(dtypes.float32)
    dense_placeholder = array_ops.placeholder(dtypes.float32)
    update = accumulator.add_summary(
        stamp_token=0,
        column=dense_placeholder,
        example_weights=weight_placeholder)
    with self.test_session() as sess:
      for i in range(100):
        dense_float = np.linspace(
            i * 100, (i + 1) * 100 - 1, num=100).reshape(-1, 1)
        sess.run(update, {
            dense_placeholder: dense_float,
            weight_placeholder: np.ones(shape=(100, 1), dtype=np.float32)
        })

    with self.test_session() as sess:
      sess.run(accumulator.flush(stamp_token=0, next_stamp_token=1))
      are_ready_flush, buckets = (accumulator.get_buckets(stamp_token=1))
      buckets, are_ready_flush = (sess.run([buckets, are_ready_flush]))
      self.assertEqual(True, are_ready_flush)
      self.assertAllEqual([0, 3335., 6671., 9999.], buckets)

  def _testStreamingQuantileBucketsHelper(
      self, inputs, num_quantiles=3, expected_buckets=None):
    """Helper to test quantile buckets on different inputs."""

    # set generate_quantiles to True since the test will generate fewer
    # boundaries otherwise.
    with self.test_session() as sess:
      accumulator = quantile_ops.QuantileAccumulator(
          init_stamp_token=0, num_quantiles=num_quantiles,
          epsilon=0.001, name="q1", generate_quantiles=True)
      resources.initialize_resources(resources.shared_resources()).run()
    input_column = array_ops.placeholder(dtypes.float32)
    weights = array_ops.placeholder(dtypes.float32)
    update = accumulator.add_summary(
        stamp_token=0,
        column=input_column,
        example_weights=weights)

    with self.test_session() as sess:
      sess.run(update,
               {input_column: inputs,
                weights: [1] * len(inputs)})

    with self.test_session() as sess:
      sess.run(accumulator.flush(stamp_token=0, next_stamp_token=1))
      are_ready_flush, buckets = (accumulator.get_buckets(stamp_token=1))
      buckets, are_ready_flush = (sess.run(
          [buckets, are_ready_flush]))
      self.assertEqual(True, are_ready_flush)
      # By default, use 3 quantiles, 4 boundaries for simplicity.
      self.assertEqual(num_quantiles + 1, len(buckets))
      if expected_buckets:
        self.assertAllEqual(buckets, expected_buckets)

  def testBasicQuantileBucketsMultipleResources(self):
    with self.test_session() as sess:
      quantile_accumulator_handle_0 = self.create_resource("float_0", self.eps,
                                                           self.max_elements)
      quantile_accumulator_handle_1 = self.create_resource("float_1", self.eps,
                                                           self.max_elements)
      resources.initialize_resources(resources.shared_resources()).run()
      summaries = boosted_trees_ops.make_quantile_summaries(
          [self._feature_0, self._feature_1], self._example_weights,
          epsilon=self.eps)
      summary_op_0 = boosted_trees_ops.quantile_add_summaries(
          quantile_accumulator_handle_0,
          [summaries[0]])
      summary_op_1 = boosted_trees_ops.quantile_add_summaries(
          quantile_accumulator_handle_1,
          [summaries[1]])
      flush_op_0 = boosted_trees_ops.quantile_flush(
          quantile_accumulator_handle_0, self.num_quantiles)
      flush_op_1 = boosted_trees_ops.quantile_flush(
          quantile_accumulator_handle_1, self.num_quantiles)
      bucket_0 = boosted_trees_ops.get_bucket_boundaries(
          quantile_accumulator_handle_0, num_features=1)
      bucket_1 = boosted_trees_ops.get_bucket_boundaries(
          quantile_accumulator_handle_1, num_features=1)
      quantiles = boosted_trees_ops.boosted_trees_bucketize(
          [self._feature_0, self._feature_1], bucket_0 + bucket_1)
      sess.run([summary_op_0, summary_op_1])
      sess.run([flush_op_0, flush_op_1])
      self.assertAllClose(self._feature_0_boundaries, bucket_0[0].eval())
      self.assertAllClose(self._feature_1_boundaries, bucket_1[0].eval())

      self.assertAllClose(self._feature_0_quantiles, quantiles[0].eval())
      self.assertAllClose(self._feature_1_quantiles, quantiles[1].eval())

  def testCreate(self):
    with self.cached_session():
      tree_ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      tree = tree_ensemble_config.trees.add()
      _append_to_leaf(tree.nodes.add().leaf, 0, -0.4)
      tree_ensemble_config.tree_weights.append(1.0)

      # Prepare learner config.
      learner_config = learner_pb2.LearnerConfig()
      learner_config.num_classes = 2

      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=3,
          tree_ensemble_config=tree_ensemble_config.SerializeToString(),
          name="create_tree")
      resources.initialize_resources(resources.shared_resources()).run()

      result, _ = prediction_ops.gradient_trees_prediction(
          tree_ensemble_handle,
          self._seed, [self._dense_float_tensor], [
              self._sparse_float_indices1, self._sparse_float_indices2
          ], [self._sparse_float_values1, self._sparse_float_values2],
          [self._sparse_float_shape1,
           self._sparse_float_shape2], [self._sparse_int_indices1],
          [self._sparse_int_values1], [self._sparse_int_shape1],
          learner_config=learner_config.SerializeToString(),
          apply_dropout=False,
          apply_averaging=False,
          center_bias=False,
          reduce_dim=True)
      self.assertAllClose(result.eval(), [[-0.4], [-0.4]])
      stamp_token = model_ops.tree_ensemble_stamp_token(tree_ensemble_handle)
      self.assertEqual(stamp_token.eval(), 3)

  def _get_train_op_and_ensemble(self, head, config, is_classification,
                                 train_in_memory):
    """Calls bt_model_fn() and returns the train_op and ensemble_serialzed."""
    features, labels = _make_train_input_fn(is_classification)()
    estimator_spec = boosted_trees._bt_model_fn(  # pylint:disable=protected-access
        features=features,
        labels=labels,
        mode=model_fn.ModeKeys.TRAIN,
        head=head,
        feature_columns=self._feature_columns,
        tree_hparams=self._tree_hparams,
        example_id_column_name=EXAMPLE_ID_COLUMN,
        n_batches_per_layer=1,
        config=config,
        train_in_memory=train_in_memory)
    resources.initialize_resources(resources.shared_resources()).run()
    variables.global_variables_initializer().run()
    variables.local_variables_initializer().run()

    # Gets the train_op and serialized proto of the ensemble.
    shared_resources = resources.shared_resources()
    self.assertEqual(1, len(shared_resources))
    train_op = estimator_spec.train_op
    with ops.control_dependencies([train_op]):
      _, ensemble_serialized = (
          gen_boosted_trees_ops.boosted_trees_serialize_ensemble(
              shared_resources[0].handle))
    return train_op, ensemble_serialized

  def testCachedPredictionOnEmptyEnsemble(self):
    """Tests that prediction on a dummy ensemble does not fail."""
    with self.cached_session() as session:
      # Create a dummy ensemble.
      tree_ensemble = boosted_trees_ops.TreeEnsemble(
          'ensemble', serialized_proto='')
      tree_ensemble_handle = tree_ensemble.resource_handle
      resources.initialize_resources(resources.shared_resources()).run()

      # No previous cached values.
      cached_tree_ids = [0, 0]
      cached_node_ids = [0, 0]

      # We have two features: 0 and 1. Values don't matter here on a dummy
      # ensemble.
      feature_0_values = [67, 5]
      feature_1_values = [9, 17]

      # Grow tree ensemble.
      predict_op = boosted_trees_ops.training_predict(
          tree_ensemble_handle,
          cached_tree_ids=cached_tree_ids,
          cached_node_ids=cached_node_ids,
          bucketized_features=[feature_0_values, feature_1_values],
          logits_dimension=1)

      logits_updates, new_tree_ids, new_node_ids = session.run(predict_op)

      # Nothing changed.
      self.assertAllClose(cached_tree_ids, new_tree_ids)
      self.assertAllClose(cached_node_ids, new_node_ids)
      self.assertAllClose([[0], [0]], logits_updates)

 def testMinimizeResourceVariable(self):
   for dtype in [dtypes.half, dtypes.float32, dtypes.float64]:
     with self.cached_session():
       var0 = resource_variable_ops.ResourceVariable([[1.0, 2.0]], dtype=dtype)
       var1 = resource_variable_ops.ResourceVariable([3.0], dtype=dtype)
       x = constant_op.constant([[4.0], [5.0]], dtype=dtype)
       pred = math_ops.matmul(var0, x) + var1
       loss = pred * pred
       sgd_op = gradient_descent.GradientDescentOptimizer(1.0).minimize(loss)
       # TODO(apassos) calling initialize_resources on all resources here
       # doesn't work because the sessions and graph are reused across unit
       # tests and this would mean trying to reinitialize variables. Figure out
       # a long-term solution for this.
       resources.initialize_resources([var0, var1]).run()
       # Fetch params to validate initial values
       self.assertAllCloseAccordingToType([[1.0, 2.0]], var0.eval())
       self.assertAllCloseAccordingToType([3.0], var1.eval())
       # Run 1 step of sgd
       sgd_op.run()
       # Validate updated params
       np_pred = 1.0 * 4.0 + 2.0 * 5.0 + 3.0
       np_grad = 2 * np_pred
       self.assertAllCloseAccordingToType(
           [[1.0 - np_grad * 4.0, 2.0 - np_grad * 5.0]], var0.eval())
       self.assertAllCloseAccordingToType([3.0 - np_grad], var1.eval())

  def testContribsForOnlyABiasNode(self):
    """Tests case when, after training, only left with a bias node.

    For example, this could happen if the final ensemble contains one tree that
    got pruned up to the root.
    """
    with self.cached_session() as session:
      tree_ensemble_config = boosted_trees_pb2.TreeEnsemble()
      text_format.Merge(
          """
        trees {
          nodes {
            leaf {
              scalar: 1.72
            }
          }
        }
        tree_weights: 0.1
        tree_metadata: {
          num_layers_grown: 0
        }
      """, tree_ensemble_config)

      tree_ensemble = boosted_trees_ops.TreeEnsemble(
          'ensemble', serialized_proto=tree_ensemble_config.SerializeToString())
      tree_ensemble_handle = tree_ensemble.resource_handle
      resources.initialize_resources(resources.shared_resources()).run()

      # All features are unused.
      feature_0_values = [36, 32]
      feature_1_values = [13, -29]
      feature_2_values = [11, 27]

      # Expected logits are computed by traversing the logit path and
      # subtracting child logits from parent logits.
      bias = 1.72 * 0.1  # Root node of tree_0.
      expected_feature_ids = ((), ())
      expected_logits_paths = ((bias,), (bias,))

      bucketized_features = [
          feature_0_values, feature_1_values, feature_2_values
      ]

      debug_op = boosted_trees_ops.example_debug_outputs(
          tree_ensemble_handle,
          bucketized_features=bucketized_features,
          logits_dimension=1)

      serialized_examples_debug_outputs = session.run(debug_op)
      feature_ids = []
      logits_paths = []
      for example in serialized_examples_debug_outputs:
        example_debug_outputs = boosted_trees_pb2.DebugOutput()
        example_debug_outputs.ParseFromString(example)
        feature_ids.append(example_debug_outputs.feature_ids)
        logits_paths.append(example_debug_outputs.logits_path)

      self.assertAllClose(feature_ids, expected_feature_ids)
      self.assertAllClose(logits_paths, expected_logits_paths)

  def testDropout(self):
    with self.test_session():
      # Empty tree ensenble.
      tree_ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      # Add 1000 trees with some weights.
      for i in range(0, 999):
        tree = tree_ensemble_config.trees.add()
        tree_ensemble_config.tree_metadata.add().is_finalized = True
        _append_to_leaf(tree.nodes.add().leaf, 0, -0.4)
        tree_ensemble_config.tree_weights.append(i + 1)

      # Prepare learner/dropout config.
      learner_config = learner_pb2.LearnerConfig()
      learner_config.learning_rate_tuner.dropout.dropout_probability = 0.5
      learner_config.learning_rate_tuner.dropout.learning_rate = 1.0
      learner_config.num_classes = 2

      # Apply dropout.
      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=tree_ensemble_config.SerializeToString(),
          name="existing")
      resources.initialize_resources(resources.shared_resources()).run()

      result, dropout_info = self._get_predictions(
          tree_ensemble_handle,
          learner_config=learner_config.SerializeToString(),
          apply_dropout=True,
          apply_averaging=False,
          center_bias=False,
          reduce_dim=True)

      # We expect approx 500 trees were dropped.
      dropout_info = dropout_info.eval()
      self.assertIn(dropout_info[0].size, range(400, 601))
      self.assertEqual(dropout_info[0].size, dropout_info[1].size)

      for i in range(dropout_info[0].size):
        dropped_index = dropout_info[0][i]
        dropped_weight = dropout_info[1][i]
        # We constructed the trees so tree number + 1 is the tree weight, so
        # we can check here the weights for dropped trees.
        self.assertEqual(dropped_index + 1, dropped_weight)

      # Don't apply dropout.
      result_no_dropout, no_dropout_info = self._get_predictions(
          tree_ensemble_handle,
          learner_config=learner_config.SerializeToString(),
          apply_dropout=False,
          apply_averaging=False,
          center_bias=False,
          reduce_dim=True)

      self.assertEqual(result.eval().size, result_no_dropout.eval().size)
      for i in range(result.eval().size):
        self.assertNotEqual(result.eval()[i], result_no_dropout.eval()[i])

      # We expect none of the trees were dropped.
      self.assertAllEqual([[], []], no_dropout_info.eval())

  def testWithExistingEnsembleAndShrinkage(self):
    with self.test_session():
      # Add shrinkage config.
      learning_rate = 0.0001
      tree_ensemble = tree_config_pb2.DecisionTreeEnsembleConfig()
      # Add 10 trees with some weights.
      for i in range(0, 5):
        tree = tree_ensemble.trees.add()
        _append_to_leaf(tree.nodes.add().leaf, 0, -0.4)
        tree_ensemble.tree_weights.append(i + 1)
        meta = tree_ensemble.tree_metadata.add()
        meta.num_tree_weight_updates = 1
      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=tree_ensemble.SerializeToString(),
          name="existing")

      # Create non-zero feature importance.
      feature_usage_counts = variables.Variable(
          initial_value=np.array([4, 7], np.int64),
          name="feature_usage_counts",
          trainable=False)
      feature_gains = variables.Variable(
          initial_value=np.array([0.2, 0.8], np.float32),
          name="feature_gains",
          trainable=False)

      resources.initialize_resources(resources.shared_resources()).run()
      variables.initialize_all_variables().run()

      output_ensemble = tree_config_pb2.DecisionTreeEnsembleConfig()
      with ops.control_dependencies([
          ensemble_optimizer_ops.add_trees_to_ensemble(
              tree_ensemble_handle,
              self._ensemble_to_add.SerializeToString(),
              feature_usage_counts, [1, 2],
              feature_gains, [0.5, 0.3], [[], []],
              learning_rate=learning_rate)
      ]):
        output_ensemble.ParseFromString(
            model_ops.tree_ensemble_serialize(tree_ensemble_handle)[1].eval())

      # The weights of previous trees stayed the same, new tree (LAST) is added
      # with shrinkage weight.
      self.assertAllClose([1.0, 2.0, 3.0, 4.0, 5.0, learning_rate],
                          output_ensemble.tree_weights)

      # Check that all number of updates are equal to 1 (e,g, no old tree weight
      # got adjusted.
      for i in range(0, 6):
        self.assertEqual(
            1, output_ensemble.tree_metadata[i].num_tree_weight_updates)

      # Ensure feature importance was aggregated correctly.
      self.assertAllEqual([5, 9], feature_usage_counts.eval())
      self.assertArrayNear(
          [0.2 + 0.5 * learning_rate, 0.8 + 0.3 * learning_rate],
          feature_gains.eval(), 1e-6)

 def testCreate(self):
   with self.test_session():
     ensemble = boosted_trees_ops.TreeEnsemble('ensemble')
     resources.initialize_resources(resources.shared_resources()).run()
     stamp_token = ensemble.get_stamp_token()
     self.assertEqual(0, stamp_token.eval())
     (_, num_trees, num_finalized_trees,
      num_attempted_layers) = ensemble.get_states()
     self.assertEqual(0, num_trees.eval())
     self.assertEqual(0, num_finalized_trees.eval())
     self.assertEqual(0, num_attempted_layers.eval())

 def testCreate(self):
   with self.cached_session():
     ensemble = boosted_trees_ops.TreeEnsemble('ensemble')
     resources.initialize_resources(resources.shared_resources()).run()
     stamp_token = ensemble.get_stamp_token()
     self.assertEqual(0, self.evaluate(stamp_token))
     (_, num_trees, num_finalized_trees, num_attempted_layers,
      nodes_range) = ensemble.get_states()
     self.assertEqual(0, self.evaluate(num_trees))
     self.assertEqual(0, self.evaluate(num_finalized_trees))
     self.assertEqual(0, self.evaluate(num_attempted_layers))
     self.assertAllEqual([0, 1], self.evaluate(nodes_range))

  def testPredictFn(self):
    """Tests the predict function."""
    with self.test_session() as sess:
      # Create ensemble with one bias node.
      ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      text_format.Merge("""
          trees {
            nodes {
              leaf {
                vector {
                  value: 0.25
                }
              }
            }
          }
          tree_weights: 1.0
          tree_metadata {
            num_tree_weight_updates: 1
            num_layers_grown: 1
            is_finalized: true
          }""", ensemble_config)
      ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=3,
          tree_ensemble_config=ensemble_config.SerializeToString(),
          name="tree_ensemble")
      resources.initialize_resources(resources.shared_resources()).run()
      learner_config = learner_pb2.LearnerConfig()
      learner_config.learning_rate_tuner.fixed.learning_rate = 0.1
      learner_config.num_classes = 2
      learner_config.regularization.l1 = 0
      learner_config.regularization.l2 = 0
      learner_config.constraints.max_tree_depth = 1
      learner_config.constraints.min_node_weight = 0
      features = {}
      features["dense_float"] = array_ops.ones([4, 1], dtypes.float32)
      gbdt_model = gbdt_batch.GradientBoostedDecisionTreeModel(
          is_chief=False,
          num_ps_replicas=0,
          center_bias=True,
          ensemble_handle=ensemble_handle,
          examples_per_layer=1,
          learner_config=learner_config,
          features=features)

      # Create predict op.
      mode = model_fn.ModeKeys.EVAL
      predictions_dict = sess.run(gbdt_model.predict(mode))
      self.assertEquals(predictions_dict["ensemble_stamp"], 3)
      self.assertAllClose(predictions_dict["predictions"], [[0.25], [0.25],
                                                            [0.25], [0.25]])
      self.assertAllClose(predictions_dict["partition_ids"], [0, 0, 0, 0])

  def testSaveRestoreBeforeFlush(self):
    save_dir = os.path.join(self.get_temp_dir(), "save_restore")
    save_path = os.path.join(tempfile.mkdtemp(prefix=save_dir), "hash")

    with self.test_session(graph=ops.Graph()) as sess:
      accumulator = quantile_ops.QuantileAccumulator(
          init_stamp_token=0, num_quantiles=3, epsilon=0.33, name="q0")

      save = saver.Saver()
      resources.initialize_resources(resources.shared_resources()).run()

      sparse_indices_0 = constant_op.constant(
          [[1, 0], [2, 1], [3, 0], [4, 2], [5, 0]], dtype=dtypes.int64)
      sparse_values_0 = constant_op.constant(
          [2.0, 3.0, 4.0, 5.0, 6.0], dtype=dtypes.float32)
      sparse_shape_0 = constant_op.constant([6, 3], dtype=dtypes.int64)
      example_weights = constant_op.constant(
          [10, 1, 1, 1, 1, 1], dtype=dtypes.float32, shape=[6, 1])
      update = accumulator.add_summary(
          stamp_token=0,
          column=sparse_tensor.SparseTensor(sparse_indices_0, sparse_values_0,
                                            sparse_shape_0),
          example_weights=example_weights)
      update.run()
      save.save(sess, save_path)
      reset = accumulator.flush(stamp_token=0, next_stamp_token=1)
      with ops.control_dependencies([reset]):
        are_ready_flush, buckets = (accumulator.get_buckets(stamp_token=1))
      buckets, are_ready_flush = (sess.run([buckets, are_ready_flush]))
      self.assertEqual(True, are_ready_flush)
      self.assertAllEqual([2, 4, 6.], buckets)

    with self.test_session(graph=ops.Graph()) as sess:
      accumulator = quantile_ops.QuantileAccumulator(
          init_stamp_token=0, num_quantiles=3, epsilon=0.33, name="q0")
      save = saver.Saver()

      # Restore the saved values in the parameter nodes.
      save.restore(sess, save_path)
      are_ready_noflush = accumulator.get_buckets(stamp_token=0)[0]
      with ops.control_dependencies([are_ready_noflush]):
        reset = accumulator.flush(stamp_token=0, next_stamp_token=1)

      with ops.control_dependencies([reset]):
        are_ready_flush, buckets = accumulator.get_buckets(stamp_token=1)
      buckets, are_ready_flush, are_ready_noflush = (sess.run(
          [buckets, are_ready_flush, are_ready_noflush]))
      self.assertFalse(are_ready_noflush)
      self.assertTrue(are_ready_flush)
      self.assertAllEqual([2, 4, 6.], buckets)

  def testMetadataMissing(self):
    # Sometimes we want to do prediction on trees that are not added to ensemble
    # (for example in
    with self.test_session():
      tree_ensemble_config = tree_config_pb2.DecisionTreeEnsembleConfig()
      # Bias tree.
      tree1 = tree_ensemble_config.trees.add()
      _append_to_leaf(tree1.nodes.add().leaf, 0, -0.4)

      # Depth 3 tree.
      tree2 = tree_ensemble_config.trees.add()
      # We are not setting the tree_ensemble_config.tree_metadata in this test.
      _set_float_split(tree2.nodes.add().dense_float_binary_split, 0, 9.0, 1, 2)
      _set_float_split(tree2.nodes.add()
                       .sparse_float_binary_split_default_left.split, 0, -20.0,
                       3, 4)
      _append_to_leaf(tree2.nodes.add().leaf, 0, 0.5)
      _append_to_leaf(tree2.nodes.add().leaf, 0, 1.2)
      _set_categorical_id_split(tree2.nodes.add().categorical_id_binary_split,
                                0, 9, 5, 6)
      _append_to_leaf(tree2.nodes.add().leaf, 0, -0.9)
      _append_to_leaf(tree2.nodes.add().leaf, 0, 0.7)

      tree_ensemble_config.tree_weights.append(1.0)
      tree_ensemble_config.tree_weights.append(1.0)

      tree_ensemble_handle = model_ops.tree_ensemble_variable(
          stamp_token=0,
          tree_ensemble_config=tree_ensemble_config.SerializeToString(),
          name="full_ensemble")
      resources.initialize_resources(resources.shared_resources()).run()

      # Prepare learner config.
      learner_config = learner_pb2.LearnerConfig()
      learner_config.num_classes = 2

      result, dropout_info = self._get_predictions(
          tree_ensemble_handle,
          learner_config=learner_config.SerializeToString(),
          reduce_dim=True)

      # The first example will get bias -0.4 from first tree and
      # leaf 4 payload of -0.9 hence -1.3, the second example will
      # get the same bias -0.4 and leaf 3 payload (sparse feature missing)
      # of 1.2 hence 0.8.
      self.assertAllClose([[-1.3], [0.8]], result.eval())

      # Empty dropout.
      self.assertAllEqual([[], []], dropout_info.eval())