def _get_default_head(params, weights_name, output_type, name=None):
  """Creates a default head based on a type of a problem."""
  if output_type == ModelBuilderOutputType.MODEL_FN_OPS:
    if params.regression:
      return head_lib.regression_head(
          weight_column_name=weights_name,
          label_dimension=params.num_outputs,
          enable_centered_bias=False,
          head_name=name)
    else:
      return head_lib.multi_class_head(
          params.num_classes,
          weight_column_name=weights_name,
          enable_centered_bias=False,
          head_name=name)
  else:
    if params.regression:
      return core_head_lib._regression_head(  # pylint:disable=protected-access
          weight_column=weights_name,
          label_dimension=params.num_outputs,
          name=name,
          loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
    else:
      return core_head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint:disable=protected-access
          n_classes=params.num_classes,
          weight_column=weights_name,
          name=name,
          loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)

  def testWithFeatureColumns(self):
    head_fn = head_lib._multi_class_head_with_softmax_cross_entropy_loss(
        n_classes=3, loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)

    hparams = tensor_forest.ForestHParams(
        num_trees=3,
        max_nodes=1000,
        num_classes=3,
        num_features=4,
        split_after_samples=20,
        inference_tree_paths=True)

    est = random_forest.CoreTensorForestEstimator(
        hparams.fill(),
        head=head_fn,
        feature_columns=[core_feature_column.numeric_column('x')])

    iris = base.load_iris()
    data = {'x': iris.data.astype(np.float32)}
    labels = iris.target.astype(np.int32)

    input_fn = numpy_io.numpy_input_fn(
        x=data, y=labels, batch_size=150, num_epochs=None, shuffle=False)

    est.train(input_fn=input_fn, steps=100)
    res = est.evaluate(input_fn=input_fn, steps=1)

    self.assertEqual(1.0, res['accuracy'])
    self.assertAllClose(0.55144483, res['loss'])

  def testTrainEvaluateInferDoesNotThrowErrorForClassifier(self):
    head_fn = head_lib._multi_class_head_with_softmax_cross_entropy_loss(
        n_classes=3, loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)

    hparams = tensor_forest.ForestHParams(
        num_trees=3,
        max_nodes=1000,
        num_classes=3,
        num_features=4,
        split_after_samples=20,
        inference_tree_paths=True)

    est = random_forest.CoreTensorForestEstimator(hparams.fill(), head=head_fn)

    input_fn, predict_input_fn = _get_classification_input_fns()

    est.train(input_fn=input_fn, steps=100)
    res = est.evaluate(input_fn=input_fn, steps=1)

    self.assertEqual(1.0, res['accuracy'])
    self.assertAllClose(0.55144483, res['loss'])

    predictions = list(est.predict(input_fn=predict_input_fn))
    self.assertAllClose([[0.576117, 0.211942, 0.211942]],
                        [pred['probabilities'] for pred in predictions])

  def __init__(self,
               hidden_units,
               feature_columns,
               model_dir=None,
               n_classes=2,
               weight_feature_key=None,
               optimizer='Adagrad',
               activation_fn=nn.relu,
               dropout=None,
               input_layer_partitioner=None,
               config=None):
    """Initializes a `DNNClassifier` instance.

    Args:
      hidden_units: Iterable of number hidden units per layer. All layers are
        fully connected. Ex. `[64, 32]` means first layer has 64 nodes and
        second one has 32.
      feature_columns: An iterable containing all the feature columns used by
        the model. All items in the set should be instances of classes derived
        from `_FeatureColumn`.
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator to
        continue training a previously saved model.
      n_classes: Number of label classes. Defaults to 2, namely binary
        classification. Must be > 1.
      weight_feature_key: A string defining feature column name representing
        weights. It is used to down weight or boost examples during training. It
        will be multiplied by the loss of the example.
      optimizer: An instance of `tf.Optimizer` used to train the model. If
        `None`, will use an Adagrad optimizer.
      activation_fn: Activation function applied to each layer. If `None`, will
        use `tf.nn.relu`.
      dropout: When not `None`, the probability we will drop out a given
        coordinate.
      input_layer_partitioner: Optional. Partitioner for input layer. Defaults
        to `min_max_variable_partitioner` with `min_slice_size` 64 << 20.
      config: `RunConfig` object to configure the runtime settings.
    """
    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_feature_key=weight_feature_key)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes, weight_feature_key=weight_feature_key)
    def _model_fn(features, labels, mode, config):
      return _dnn_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          hidden_units=hidden_units,
          feature_columns=tuple(feature_columns or []),
          optimizer=optimizer,
          activation_fn=activation_fn,
          dropout=dropout,
          input_layer_partitioner=input_layer_partitioner,
          config=config)
    super(DNNClassifier, self).__init__(
        model_fn=_model_fn, model_dir=model_dir, config=config)

  def __init__(self,
               model_dir=None,
               n_classes=2,
               weight_column=None,
               label_vocabulary=None,
               optimizer='Ftrl',
               config=None,
               loss_reduction=losses.Reduction.SUM):
    """Initializes a BaselineClassifier instance.

    Args:
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator to
        continue training a previously saved model.
      n_classes: number of label classes. Default is binary classification.
        It must be greater than 1. Note: Class labels are integers representing
        the class index (i.e. values from 0 to n_classes-1). For arbitrary
        label values (e.g. string labels), convert to class indices first.
      weight_column: A string or a `_NumericColumn` created by
        `tf.feature_column.numeric_column` defining feature column representing
         weights. It will be multiplied by the loss of the example.
      label_vocabulary: Optional list of strings with size `[n_classes]`
        defining the label vocabulary. Only supported for `n_classes` > 2.
      optimizer: String, `tf.Optimizer` object, or callable that creates the
        optimizer to use for training. If not specified, will use
        `FtrlOptimizer` with a default learning rate of 0.3.
      config: `RunConfig` object to configure the runtime settings.
      loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how
        to reduce training loss over batch. Defaults to `SUM`.
    Returns:
      A `BaselineClassifier` estimator.

    Raises:
      ValueError: If `n_classes` < 2.
    """
    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes, weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)
    def _model_fn(features, labels, mode, config):
      return _baseline_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          optimizer=optimizer,
          weight_column=weight_column,
          config=config)
    super(BaselineClassifier, self).__init__(
        model_fn=_model_fn,
        model_dir=model_dir,
        config=config)

def multi_class_head(n_classes,
                     weight_column=None,
                     label_vocabulary=None,
                     loss_reduction=losses.Reduction.SUM,
                     name=None):
  """Creates a `_Head` for multi class classification.

  Uses `sparse_softmax_cross_entropy` loss.

  The head expects `logits` with shape `[D0, D1, ... DN, n_classes]`.
  In many applications, the shape is `[batch_size, n_classes]`.

  `labels` must be a dense `Tensor` with shape matching `logits`, namely
  `[D0, D1, ... DN, 1]`. If `label_vocabulary` given, `labels` must be a string
  `Tensor` with values from the vocabulary. If `label_vocabulary` is not given,
  `labels` must be an integer `Tensor` with values specifying the class index.

  If `weight_column` is specified, weights must be of shape
  `[D0, D1, ... DN]`, or `[D0, D1, ... DN, 1]`.

  The loss is the weighted sum over the input dimensions. Namely, if the input
  labels have shape `[batch_size, 1]`, the loss is the weighted sum over
  `batch_size`.

  Args:
    n_classes: Number of classes, must be greater than 2 (for 2 classes, use
      `binary_classification_head`).
    weight_column: A string or a `_NumericColumn` created by
      `tf.feature_column.numeric_column` defining feature column representing
      weights. It is used to down weight or boost examples during training. It
      will be multiplied by the loss of the example.
    label_vocabulary: A list or tuple of strings representing possible label
      values. If it is not given, that means labels are already encoded as an
      integer within [0, n_classes). If given, labels must be of string type and
      have any value in `label_vocabulary`. Note that errors will be raised if
      `label_vocabulary` is not provided but labels are strings.
    loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
      reduce training loss over batch. Defaults to `SUM`.
    name: name of the head. If provided, summary and metrics keys will be
      suffixed by `"/" + name`. Also used as `name_scope` when creating ops.

  Returns:
    An instance of `_Head` for multi class classification.

  Raises:
    ValueError: if `n_classes`, `label_vocabulary` or `loss_reduction` is
      invalid.
  """
  return head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint:disable=protected-access
      n_classes=n_classes,
      weight_column=weight_column,
      label_vocabulary=label_vocabulary,
      loss_reduction=loss_reduction,
      name=name)

def core_multiclass_head(n_classes):
  """Core head for multiclass problems."""

  def loss_fn(labels, logits):
    result = losses.per_example_maxent_loss(
        labels=labels, logits=logits, weights=None, num_classes=n_classes)
    return result[0]

  # pylint:disable=protected-access
  head_fn = core_head_lib._multi_class_head_with_softmax_cross_entropy_loss(
      n_classes=n_classes,
      loss_fn=loss_fn,
      loss_reduction=core_losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
  # pylint:enable=protected-access

  return head_fn

  def testEarlyStopping(self):
    head_fn = head_lib._multi_class_head_with_softmax_cross_entropy_loss(
        n_classes=3, loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)

    hparams = tensor_forest.ForestHParams(
        num_trees=3,
        max_nodes=1000,
        num_classes=3,
        num_features=4,
        split_after_samples=20,
        inference_tree_paths=True)

    est = random_forest.CoreTensorForestEstimator(
        hparams.fill(),
        head=head_fn,
        # Set a crazy threshold - 30% loss change.
        early_stopping_loss_threshold=0.3,
        early_stopping_rounds=2)

    input_fn, _ = _get_classification_input_fns()
    est.train(input_fn=input_fn, steps=100)
    # We stopped early.
    self._assert_checkpoint(est.model_dir, global_step=8)

def multi_class_head(n_classes,
                     weight_column=None,
                     label_vocabulary=None,
                     name=None):
  """Creates a `_Head` for multi class classification.

  Uses `sparse_softmax_cross_entropy` loss.

  This head expects to be fed integer labels specifying the class index.

  Args:
    n_classes: Number of classes, must be greater than 2 (for 2 classes, use
      `binary_classification_head`).
    weight_column: A string or a `_NumericColumn` created by
      `tf.feature_column.numeric_column` defining feature column representing
      weights. It is used to down weight or boost examples during training. It
      will be multiplied by the loss of the example.
    label_vocabulary: A list of strings represents possible label values. If it
      is not given, that means labels are already encoded as integer within
      [0, n_classes). If given, labels must be string type and have any value in
      `label_vocabulary`. Also there will be errors if vocabulary is not
      provided and labels are string.
    name: name of the head. If provided, summary and metrics keys will be
      suffixed by `"/" + name`.

  Returns:
    An instance of `_Head` for multi class classification.

  Raises:
    ValueError: if `n_classes`, `metric_class_ids` or `label_keys` is invalid.
  """
  return head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint:disable=protected-access
      n_classes=n_classes,
      weight_column=weight_column,
      label_vocabulary=label_vocabulary,
      name=name)

  def __init__(self,
               feature_columns,
               model_dir=None,
               n_classes=2,
               weight_column=None,
               label_vocabulary=None,
               optimizer='Ftrl',
               config=None,
               partitioner=None,
               warm_start_from=None,
               loss_reduction=losses.Reduction.SUM,
               sparse_combiner='sum'):
    """Construct a `LinearClassifier` estimator object.

    Args:
      feature_columns: An iterable containing all the feature columns used by
        the model. All items in the set should be instances of classes derived
        from `FeatureColumn`.
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator
        to continue training a previously saved model.
      n_classes: number of label classes. Default is binary classification.
        Note that class labels are integers representing the class index (i.e.
        values from 0 to n_classes-1). For arbitrary label values (e.g. string
        labels), convert to class indices first.
      weight_column: A string or a `_NumericColumn` created by
        `tf.feature_column.numeric_column` defining feature column representing
        weights. It is used to down weight or boost examples during training. It
        will be multiplied by the loss of the example. If it is a string, it is
        used as a key to fetch weight tensor from the `features`. If it is a
        `_NumericColumn`, raw tensor is fetched by key `weight_column.key`,
        then weight_column.normalizer_fn is applied on it to get weight tensor.
      label_vocabulary: A list of strings represents possible label values. If
        given, labels must be string type and have any value in
        `label_vocabulary`. If it is not given, that means labels are
        already encoded as integer or float within [0, 1] for `n_classes=2` and
        encoded as integer values in {0, 1,..., n_classes-1} for `n_classes`>2 .
        Also there will be errors if vocabulary is not provided and labels are
        string.
      optimizer: An instance of `tf.Optimizer` used to train the model. Can also
        be a string (one of 'Adagrad', 'Adam', 'Ftrl', 'RMSProp', 'SGD'), or
        callable. Defaults to FTRL optimizer.
      config: `RunConfig` object to configure the runtime settings.
      partitioner: Optional. Partitioner for input layer.
      warm_start_from: A string filepath to a checkpoint to warm-start from, or
        a `WarmStartSettings` object to fully configure warm-starting.  If the
        string filepath is provided instead of a `WarmStartSettings`, then all
        weights and biases are warm-started, and it is assumed that vocabularies
        and Tensor names are unchanged.
      loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how
        to reduce training loss over batch. Defaults to `SUM`.
      sparse_combiner: A string specifying how to reduce if a categorical column
        is multivalent.  One of "mean", "sqrtn", and "sum" -- these are
        effectively different ways to do example-level normalization, which can
        be useful for bag-of-words features. for more details, see
        `tf.feature_column.linear_model`.

    Returns:
      A `LinearClassifier` estimator.

    Raises:
      ValueError: if n_classes < 2.
    """
    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes, weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)

    def _model_fn(features, labels, mode, config):
      """Call the defined shared _linear_model_fn."""
      return _linear_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          feature_columns=tuple(feature_columns or []),
          optimizer=optimizer,
          partitioner=partitioner,
          config=config,
          sparse_combiner=sparse_combiner)

    super(LinearClassifier, self).__init__(
        model_fn=_model_fn,
        model_dir=model_dir,
        config=config,
        warm_start_from=warm_start_from)

def multi_class_head(n_classes,
                     weight_column=None,
                     label_vocabulary=None,
                     loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
                     loss_fn=None,
                     name=None):
  """Creates a `_Head` for multi class classification.

  Uses `sparse_softmax_cross_entropy` loss.

  The head expects `logits` with shape `[D0, D1, ... DN, n_classes]`.
  In many applications, the shape is `[batch_size, n_classes]`.

  `labels` must be a dense `Tensor` with shape matching `logits`, namely
  `[D0, D1, ... DN, 1]`. If `label_vocabulary` given, `labels` must be a string
  `Tensor` with values from the vocabulary. If `label_vocabulary` is not given,
  `labels` must be an integer `Tensor` with values specifying the class index.

  If `weight_column` is specified, weights must be of shape
  `[D0, D1, ... DN]`, or `[D0, D1, ... DN, 1]`.

  The loss is the weighted sum over the input dimensions. Namely, if the input
  labels have shape `[batch_size, 1]`, the loss is the weighted sum over
  `batch_size`.

  Also supports custom `loss_fn`. `loss_fn` takes `(labels, logits)` or
  `(labels, logits, features)` as arguments and returns unreduced loss with
  shape `[D0, D1, ... DN, 1]`. `loss_fn` must support integer `labels` with
  shape `[D0, D1, ... DN, 1]`. Namely, the head applies `label_vocabulary` to
  the input labels before passing them to `loss_fn`.

  The head can be used with a canned estimator. Example:

  ```python
  my_head = tf.contrib.estimator.multi_class_head(n_classes=3)
  my_estimator = tf.contrib.estimator.DNNEstimator(
      head=my_head,
      hidden_units=...,
      feature_columns=...)
  ```

  It can also be used with a custom `model_fn`. Example:

  ```python
  def _my_model_fn(features, labels, mode):
    my_head = tf.contrib.estimator.multi_class_head(n_classes=3)
    logits = tf.keras.Model(...)(features)

    return my_head.create_estimator_spec(
        features=features,
        mode=mode,
        labels=labels,
        optimizer=tf.AdagradOptimizer(learning_rate=0.1),
        logits=logits)

  my_estimator = tf.estimator.Estimator(model_fn=_my_model_fn)
  ```

  Args:
    n_classes: Number of classes, must be greater than 2 (for 2 classes, use
      `binary_classification_head`).
    weight_column: A string or a `_NumericColumn` created by
      `tf.feature_column.numeric_column` defining feature column representing
      weights. It is used to down weight or boost examples during training. It
      will be multiplied by the loss of the example.
    label_vocabulary: A list or tuple of strings representing possible label
      values. If it is not given, that means labels are already encoded as an
      integer within [0, n_classes). If given, labels must be of string type and
      have any value in `label_vocabulary`. Note that errors will be raised if
      `label_vocabulary` is not provided but labels are strings.
    loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
      reduce training loss over batch. Defaults to `SUM_OVER_BATCH_SIZE`, namely
      weighted sum of losses divided by batch size. See `tf.losses.Reduction`.
    loss_fn: Optional loss function.
    name: name of the head. If provided, summary and metrics keys will be
      suffixed by `"/" + name`. Also used as `name_scope` when creating ops.

  Returns:
    An instance of `_Head` for multi class classification.

  Raises:
    ValueError: if `n_classes`, `label_vocabulary` or `loss_reduction` is
      invalid.
  """
  return head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint:disable=protected-access
      n_classes=n_classes,
      weight_column=weight_column,
      label_vocabulary=label_vocabulary,
      loss_reduction=loss_reduction,
      loss_fn=loss_fn,
      name=name)

  def __init__(self,
               model_dir=None,
               linear_feature_columns=None,
               linear_optimizer='Ftrl',
               dnn_feature_columns=None,
               dnn_optimizer='Adagrad',
               dnn_hidden_units=None,
               dnn_activation_fn=nn.relu,
               dnn_dropout=None,
               n_classes=2,
               weight_column=None,
               label_vocabulary=None,
               input_layer_partitioner=None,
               config=None,
               warm_start_from=None,
               loss_reduction=losses.Reduction.SUM):
    """Initializes a DNNLinearCombinedClassifier instance.

    Args:
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator
        to continue training a previously saved model.
      linear_feature_columns: An iterable containing all the feature columns
        used by linear part of the model. All items in the set must be
        instances of classes derived from `FeatureColumn`.
      linear_optimizer: An instance of `tf.Optimizer` used to apply gradients to
        the linear part of the model. Defaults to FTRL optimizer.
      dnn_feature_columns: An iterable containing all the feature columns used
        by deep part of the model. All items in the set must be instances of
        classes derived from `FeatureColumn`.
      dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
        the deep part of the model. Defaults to Adagrad optimizer.
      dnn_hidden_units: List of hidden units per layer. All layers are fully
        connected.
      dnn_activation_fn: Activation function applied to each layer. If None,
        will use `tf.nn.relu`.
      dnn_dropout: When not None, the probability we will drop out
        a given coordinate.
      n_classes: Number of label classes. Defaults to 2, namely binary
        classification. Must be > 1.
      weight_column: A string or a `_NumericColumn` created by
        `tf.feature_column.numeric_column` defining feature column representing
        weights. It is used to down weight or boost examples during training. It
        will be multiplied by the loss of the example. If it is a string, it is
        used as a key to fetch weight tensor from the `features`. If it is a
        `_NumericColumn`, raw tensor is fetched by key `weight_column.key`,
        then weight_column.normalizer_fn is applied on it to get weight tensor.
      label_vocabulary: A list of strings represents possible label values. If
        given, labels must be string type and have any value in
        `label_vocabulary`. If it is not given, that means labels are
        already encoded as integer or float within [0, 1] for `n_classes=2` and
        encoded as integer values in {0, 1,..., n_classes-1} for `n_classes`>2 .
        Also there will be errors if vocabulary is not provided and labels are
        string.
      input_layer_partitioner: Partitioner for input layer. Defaults to
        `min_max_variable_partitioner` with `min_slice_size` 64 << 20.
      config: RunConfig object to configure the runtime settings.
      warm_start_from: A string filepath to a checkpoint to warm-start from, or
        a `WarmStartSettings` object to fully configure warm-starting.  If the
        string filepath is provided instead of a `WarmStartSettings`, then all
        weights are warm-started, and it is assumed that vocabularies and Tensor
        names are unchanged.
      loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how
        to reduce training loss over batch. Defaults to `SUM`.

    Raises:
      ValueError: If both linear_feature_columns and dnn_features_columns are
        empty at the same time.
    """
    linear_feature_columns = linear_feature_columns or []
    dnn_feature_columns = dnn_feature_columns or []
    self._feature_columns = (
        list(linear_feature_columns) + list(dnn_feature_columns))
    if not self._feature_columns:
      raise ValueError('Either linear_feature_columns or dnn_feature_columns '
                       'must be defined.')
    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes,
          weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)

    def _model_fn(features, labels, mode, config):
      """Call the _dnn_linear_combined_model_fn."""
      return _dnn_linear_combined_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          linear_feature_columns=linear_feature_columns,
          linear_optimizer=linear_optimizer,
          dnn_feature_columns=dnn_feature_columns,
          dnn_optimizer=dnn_optimizer,
          dnn_hidden_units=dnn_hidden_units,
#.........这里部分代码省略.........

  def __init__(self,
               sequence_feature_columns,
               context_feature_columns=None,
               num_units=None,
               cell_type=USE_DEFAULT,
               rnn_cell_fn=None,
               model_dir=None,
               n_classes=2,
               weight_column=None,
               label_vocabulary=None,
               optimizer='Adagrad',
               loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
               input_layer_partitioner=None,
               config=None):
    """Initializes a `RNNClassifier` instance.

    Args:
      sequence_feature_columns: An iterable containing the `FeatureColumn`s
        that represent sequential input. All items in the set should either be
        sequence columns (e.g. `sequence_numeric_column`) or constructed from
        one (e.g. `embedding_column` with `sequence_categorical_column_*` as
        input).
      context_feature_columns: An iterable containing the `FeatureColumn`s
        for contextual input. The data represented by these columns will be
        replicated and given to the RNN at each timestep. These columns must be
        instances of classes derived from `_DenseColumn` such as
        `numeric_column`, not the sequential variants.
      num_units: Iterable of integer number of hidden units per RNN layer. If
        set, `cell_type` must also be specified and `rnn_cell_fn` must be
        `None`.
      cell_type: A subclass of `tf.nn.rnn_cell.RNNCell` or a string specifying
        the cell type. Supported strings are: `'basic_rnn'`, `'lstm'`, and
        `'gru'`. If set, `num_units` must also be specified and `rnn_cell_fn`
        must be `None`.
      rnn_cell_fn: A function with one argument, a `tf.estimator.ModeKeys`, and
        returns an object of type `tf.nn.rnn_cell.RNNCell` that will be used to
        construct the RNN. If set, `num_units` and `cell_type` cannot be set.
        This is for advanced users who need additional customization beyond
        `num_units` and `cell_type`. Note that `tf.nn.rnn_cell.MultiRNNCell` is
        needed for stacked RNNs.
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator to
        continue training a previously saved model.
      n_classes: Number of label classes. Defaults to 2, namely binary
        classification. Must be > 1.
      weight_column: A string or a `_NumericColumn` created by
        `tf.feature_column.numeric_column` defining feature column representing
        weights. It is used to down weight or boost examples during training. It
        will be multiplied by the loss of the example. If it is a string, it is
        used as a key to fetch weight tensor from the `features`. If it is a
        `_NumericColumn`, raw tensor is fetched by key `weight_column.key`,
        then weight_column.normalizer_fn is applied on it to get weight tensor.
      label_vocabulary: A list of strings represents possible label values. If
        given, labels must be string type and have any value in
        `label_vocabulary`. If it is not given, that means labels are
        already encoded as integer or float within [0, 1] for `n_classes=2` and
        encoded as integer values in {0, 1,..., n_classes-1} for `n_classes`>2 .
        Also there will be errors if vocabulary is not provided and labels are
        string.
      optimizer: An instance of `tf.Optimizer` or string specifying optimizer
        type. Defaults to Adagrad optimizer.
      loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how
        to reduce training loss over batch. Defaults to `SUM_OVER_BATCH_SIZE`.
      input_layer_partitioner: Optional. Partitioner for input layer. Defaults
        to `min_max_variable_partitioner` with `min_slice_size` 64 << 20.
      config: `RunConfig` object to configure the runtime settings.

    Raises:
      ValueError: If `num_units`, `cell_type`, and `rnn_cell_fn` are not
        compatible.
    """
    rnn_cell_fn = _assert_rnn_cell_fn(rnn_cell_fn, num_units, cell_type)

    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes,
          weight_column=weight_column,
          label_vocabulary=label_vocabulary,
          loss_reduction=loss_reduction)

    def _model_fn(features, labels, mode, config):
      return _rnn_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          rnn_cell_fn=rnn_cell_fn,
          sequence_feature_columns=tuple(sequence_feature_columns or []),
          context_feature_columns=tuple(context_feature_columns or []),
          optimizer=optimizer,
          input_layer_partitioner=input_layer_partitioner,
          config=config)
    super(RNNClassifier, self).__init__(
        model_fn=_model_fn, model_dir=model_dir, config=config)

  def __init__(self,
               feature_columns,
               model_dir=None,
               n_classes=2,
               weight_column=None,
               label_vocabulary=None,
               optimizer='Ftrl',
               config=None,
               partitioner=None,
               warm_start_from=None):
    """Construct a `LinearClassifier` estimator object.

    Args:
      feature_columns: An iterable containing all the feature columns used by
        the model. All items in the set should be instances of classes derived
        from `FeatureColumn`.
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator
        to continue training a previously saved model.
      n_classes: number of label classes. Default is binary classification.
        Note that class labels are integers representing the class index (i.e.
        values from 0 to n_classes-1). For arbitrary label values (e.g. string
        labels), convert to class indices first.
      weight_column: A string or a `_NumericColumn` created by
        `tf.feature_column.numeric_column` defining feature column representing
        weights. It is used to down weight or boost examples during training. It
        will be multiplied by the loss of the example. If it is a string, it is
        used as a key to fetch weight tensor from the `features`. If it is a
        `_NumericColumn`, raw tensor is fetched by key `weight_column.key`,
        then weight_column.normalizer_fn is applied on it to get weight tensor.
      label_vocabulary: A list of strings represents possible label values. If
        given, labels must be string type and have any value in
        `label_vocabulary`. If it is not given, that means labels are
        already encoded as integer or float within [0, 1] for `n_classes=2` and
        encoded as integer values in {0, 1,..., n_classes-1} for `n_classes`>2 .
        Also there will be errors if vocabulary is not provided and labels are
        string.
      optimizer: An instance of `tf.Optimizer` used to train the model. Defaults
        to FTRL optimizer.
      config: `RunConfig` object to configure the runtime settings.
      partitioner: Optional. Partitioner for input layer.
      warm_start_from: A string filepath to a checkpoint to warm-start from, or
        a `WarmStartSettings` object to fully configure warm-starting.  If the
        string filepath is provided instead of a `WarmStartSettings`, then all
        weights and biases are warm-started, and it is assumed that vocabularies
        and Tensor names are unchanged.

    Returns:
      A `LinearClassifier` estimator.

    Raises:
      ValueError: if n_classes < 2.
    """
    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_column=weight_column,
          label_vocabulary=label_vocabulary)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes, weight_column=weight_column,
          label_vocabulary=label_vocabulary)

    def _model_fn(features, labels, mode, config):
      """Call the defined shared _linear_model_fn and possibly warm-start."""
      estimator_spec = _linear_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          feature_columns=tuple(feature_columns or []),
          optimizer=optimizer,
          partitioner=partitioner,
          config=config)
      # pylint: disable=protected-access
      warm_start_settings = warm_starting_util._get_default_warm_start_settings(
          warm_start_from)
      if warm_start_settings:
        warm_starting_util._warm_start(warm_start_settings)
      # pylint: enable=protected-access

      return estimator_spec

    super(LinearClassifier, self).__init__(
        model_fn=_model_fn,
        model_dir=model_dir,
        config=config)

  def __init__(self,
               hidden_units,
               feature_columns,
               model_dir=None,
               n_classes=2,
               weight_column=None,
               label_vocabulary=None,
               optimizer='Adagrad',
               activation_fn=nn.relu,
               dropout=None,
               input_layer_partitioner=None,
               config=None):
    """Initializes a `DNNClassifier` instance.

    Args:
      hidden_units: Iterable of number hidden units per layer. All layers are
        fully connected. Ex. `[64, 32]` means first layer has 64 nodes and
        second one has 32.
      feature_columns: An iterable containing all the feature columns used by
        the model. All items in the set should be instances of classes derived
        from `_FeatureColumn`.
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator to
        continue training a previously saved model.
      n_classes: Number of label classes. Defaults to 2, namely binary
        classification. Must be > 1.
      weight_column: A string or a `_NumericColumn` created by
        `tf.feature_column.numeric_column` defining feature column representing
        weights. It is used to down weight or boost examples during training. It
        will be multiplied by the loss of the example. If it is a string, it is
        used as a key to fetch weight tensor from the `features`. If it is a
        `_NumericColumn`, raw tensor is fetched by key `weight_column.key`,
        then weight_column.normalizer_fn is applied on it to get weight tensor.
      label_vocabulary: A list of strings represents possible label values. If
        given, labels must be string type and have any value in
        `label_vocabulary`. If it is not given, that means labels are
        already encoded as integer or float within [0, 1] for `n_classes=2` and
        encoded as integer values in {0, 1,..., n_classes-1} for `n_classes`>2 .
        Also there will be errors if vocabulary is not provided and labels are
        string.
      optimizer: An instance of `tf.Optimizer` used to train the model. Defaults
        to Adagrad optimizer.
      activation_fn: Activation function applied to each layer. If `None`, will
        use `tf.nn.relu`.
      dropout: When not `None`, the probability we will drop out a given
        coordinate.
      input_layer_partitioner: Optional. Partitioner for input layer. Defaults
        to `min_max_variable_partitioner` with `min_slice_size` 64 << 20.
      config: `RunConfig` object to configure the runtime settings.
    """
    if n_classes == 2:
      head = head_lib._binary_logistic_head_with_sigmoid_cross_entropy_loss(  # pylint: disable=protected-access
          weight_column=weight_column,
          label_vocabulary=label_vocabulary)
    else:
      head = head_lib._multi_class_head_with_softmax_cross_entropy_loss(  # pylint: disable=protected-access
          n_classes, weight_column=weight_column,
          label_vocabulary=label_vocabulary)
    def _model_fn(features, labels, mode, config):
      return _dnn_model_fn(
          features=features,
          labels=labels,
          mode=mode,
          head=head,
          hidden_units=hidden_units,
          feature_columns=tuple(feature_columns or []),
          optimizer=optimizer,
          activation_fn=activation_fn,
          dropout=dropout,
          input_layer_partitioner=input_layer_partitioner,
          config=config)
    super(DNNClassifier, self).__init__(
        model_fn=_model_fn, model_dir=model_dir, config=config)

  def __init__(self,
               model_dir=None,
               linear_feature_columns=None,
               linear_optimizer='Ftrl',
               dnn_feature_columns=None,
               dnn_optimizer='Adagrad',
               dnn_hidden_units=None,
               dnn_activation_fn=nn.relu,
               dnn_dropout=None,
               n_classes=2,
               input_layer_partitioner=None,
               config=None):
    """Initializes a DNNLinearCombinedClassifier instance.

    Args:
      model_dir: Directory to save model parameters, graph and etc. This can
        also be used to load checkpoints from the directory into a estimator
        to continue training a previously saved model.
      lin