def __init__(self,
model_dir=None,
n_classes=2,
weight_column=None,
label_vocabulary=None,
optimizer='Ftrl',
config=None,
loss_reduction=losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE):
"""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.keras.optimizers.*` object, or callable that
creates the optimizer to use for training. If not specified, will use
`Ftrl` as the default optimizer.
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_OVER_BATCH_SIZE`.
Returns:
A `BaselineClassifier` estimator.
Raises:
ValueError: If `n_classes` < 2.
"""
head = head_utils.binary_or_multi_class_head(
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_v2(features=features,
labels=labels,
mode=mode,
head=head,
optimizer=optimizer,
weight_column=weight_column,
config=config,
loss_reduction=loss_reduction)
super(BaselineClassifierV2, 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,
warm_start_from=None,
loss_reduction=losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE,
batch_norm=False,
):
"""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. Can also
be a string (one of 'Adagrad', 'Adam', 'Ftrl', 'RMSProp', 'SGD'), or
callable. 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.
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_OVER_BATCH_SIZE`.
batch_norm: Whether to use batch normalization after each hidden layer.
"""
head = head_utils.binary_or_multi_class_head(
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 _dnn_model_fn_v2."""
return _dnn_model_fn_v2(
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,
batch_norm=batch_norm)
super(DNNClassifierV2, self).__init__(
model_fn=_model_fn,
model_dir=model_dir,
config=config,
warm_start_from=warm_start_from)
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_OVER_BATCH_SIZE,
batch_norm=False,
linear_sparse_combiner='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. Can also be a string (one of 'Adagrad',
'Adam', 'Ftrl', 'RMSProp', 'SGD'), or callable. 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. Can also be a string (one of 'Adagrad',
'Adam', 'Ftrl', 'RMSProp', 'SGD'), or callable. 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_OVER_BATCH_SIZE`.
batch_norm: Whether to use batch normalization after each hidden layer.
linear_sparse_combiner: A string specifying how to reduce the linear model
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`.
Raises:
ValueError: If both linear_feature_columns and dnn_features_columns are
empty at the same time.
"""
self._feature_columns = _validate_feature_columns(
linear_feature_columns=linear_feature_columns,
dnn_feature_columns=dnn_feature_columns)
head = head_utils.binary_or_multi_class_head(
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,
dnn_activation_fn=dnn_activation_fn,
dnn_dropout=dnn_dropout,
input_layer_partitioner=input_layer_partitioner,
config=config,
batch_norm=batch_norm,
linear_sparse_combiner=linear_sparse_combiner)
super(DNNLinearCombinedClassifierV2,
self).__init__(model_fn=_model_fn,
model_dir=model_dir,
config=config,
warm_start_from=warm_start_from)
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_utils.ReductionV2.SUM_OVER_BATCH_SIZE,
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` or
`tf.estimator.experimental.LinearSDCA` 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_OVER_BATCH_SIZE`.
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.
"""
_validate_linear_sdca_optimizer_for_linear_classifier(
feature_columns=feature_columns,
n_classes=n_classes,
optimizer=optimizer,
sparse_combiner=sparse_combiner)
head = head_utils.binary_or_multi_class_head(
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(LinearClassifierV2, self).__init__(
model_fn=_model_fn,
model_dir=model_dir,
config=config,
warm_start_from=warm_start_from)
