def testRegression(self):
"""Tests regression using matrix data as input."""
head_fn = head_lib._regression_head(
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
hparams = tensor_forest.ForestHParams(num_trees=5,
max_nodes=1000,
num_classes=1,
num_features=13,
regression=True,
split_after_samples=20)
regressor = random_forest.CoreTensorForestEstimator(hparams.fill(),
head=head_fn)
input_fn, predict_input_fn = _get_regression_input_fns()
regressor.train(input_fn=input_fn, steps=100)
res = regressor.evaluate(input_fn=input_fn, steps=10)
self.assertGreaterEqual(0.1, res['loss'])
predictions = list(regressor.predict(input_fn=predict_input_fn))
self.assertAllClose([[24.]],
[pred['predictions'] for pred in predictions],
atol=1)
def testRegression(self):
"""Tests regression using matrix data as input."""
head_fn = head_lib._regression_head(
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
hparams = tensor_forest.ForestHParams(
num_trees=5,
max_nodes=1000,
num_classes=1,
num_features=13,
regression=True,
split_after_samples=20)
regressor = random_forest.CoreTensorForestEstimator(
hparams.fill(), head=head_fn)
input_fn, predict_input_fn = _get_regression_input_fns()
regressor.train(input_fn=input_fn, steps=100)
res = regressor.evaluate(input_fn=input_fn, steps=10)
self.assertGreaterEqual(0.1, res['loss'])
predictions = list(regressor.predict(input_fn=predict_input_fn))
self.assertAllClose(
[[24.]], [pred['predictions'] for pred in predictions], atol=1)
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 poisson_regression_head(
weight_column=None,
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
compute_full_loss=True,
name=None):
"""Creates a `_Head` for poisson regression using `tf.nn.log_poisson_loss`.
The loss is the weighted sum over all input dimensions. Namely, if the input
labels have shape `[batch_size, label_dimension]`, the loss is the weighted
sum over both `batch_size` and `label_dimension`.
The head expects `logits` with shape `[D0, D1, ... DN, label_dimension]`.
In many applications, the shape is `[batch_size, label_dimension]`.
The `labels` shape must match `logits`, namely
`[D0, D1, ... DN, label_dimension]`. If `label_dimension=1`, shape
`[D0, D1, ... DN]` is also supported.
If `weight_column` is specified, weights must be of shape
`[D0, D1, ... DN]`, `[D0, D1, ... DN, 1]` or
`[D0, D1, ... DN, label_dimension]`.
This is implemented as a generalized linear model, see
https://en.wikipedia.org/wiki/Generalized_linear_model.
Args:
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_dimension: Number of regression labels per example. This is the size
of the last dimension of the labels `Tensor` (typically, this has shape
`[batch_size, label_dimension]`).
loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
reduce training loss over batch and label dimension. Defaults to
`SUM_OVER_BATCH_SIZE`, namely weighted sum of losses divided by
`batch size * label_dimension`. See `tf.losses.Reduction`.
compute_full_loss: Whether to include the constant `log(z!)` term in
computing the poisson loss. See `tf.nn.log_poisson_loss` for the full
documentation.
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 poisson regression.
Raises:
ValueError: If `label_dimension` or `loss_reduction` is invalid.
"""
def _poisson_loss(labels, logits):
return nn.log_poisson_loss(
targets=labels, log_input=logits, compute_full_loss=compute_full_loss)
return head_lib._regression_head( # pylint:disable=protected-access
weight_column=weight_column,
label_dimension=label_dimension,
loss_reduction=loss_reduction,
loss_fn=_poisson_loss,
inverse_link_fn=math_ops.exp,
name=name)
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 _create_regression_head(label_dimension, weight_column=None):
if label_dimension != 1:
raise ValueError('For now only 1 dimension regression is supported.'
'label_dimension given as {}'.format(label_dimension))
# pylint: disable=protected-access
return head_lib._regression_head(
label_dimension=label_dimension,
weight_column=weight_column,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)
def _create_regression_head(label_dimension, weight_column=None):
if label_dimension != 1:
raise ValueError('For now only 1 dimension regression is supported.'
'label_dimension given as {}'.format(label_dimension))
# pylint: disable=protected-access
return head_lib._regression_head(
label_dimension=label_dimension,
weight_column=weight_column,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)
def _model_fn(features, labels, mode, config):
"""Call the defined shared _dnn_model_fn."""
return _dnn_model_fn(
features=features,
labels=labels,
mode=mode,
head=head_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension, weight_column=weight_column,
loss_reduction=loss_reduction),
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)
def _model_fn(features, labels, mode, config):
"""Call the defined shared _dnn_model_fn."""
return _dnn_model_fn(
features=features,
labels=labels,
mode=mode,
head=head_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension, weight_column=weight_column,
loss_reduction=loss_reduction),
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)
def __init__(self,
model_dir=None,
label_dimension=1,
weight_column=None,
optimizer='Ftrl',
config=None,
loss_reduction=losses.Reduction.SUM):
"""Initializes a BaselineRegressor 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.
label_dimension: Number of regression targets per example. This is the
size of the last dimension of the labels and logits `Tensor` objects
(typically, these have shape `[batch_size, label_dimension]`).
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.
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 `BaselineRegressor` estimator.
"""
head = head_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension,
weight_column=weight_column,
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,
config=config)
super(BaselineRegressor, self).__init__(model_fn=_model_fn,
model_dir=model_dir,
config=config)
def __init__(self,
model_dir=None,
label_dimension=1,
weight_column=None,
optimizer='Ftrl',
config=None,
loss_reduction=losses.Reduction.SUM):
"""Initializes a BaselineRegressor 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.
label_dimension: Number of regression targets per example. This is the
size of the last dimension of the labels and logits `Tensor` objects
(typically, these have shape `[batch_size, label_dimension]`).
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.
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 `BaselineRegressor` estimator.
"""
head = head_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension,
weight_column=weight_column,
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,
config=config)
super(BaselineRegressor, self).__init__(
model_fn=_model_fn,
model_dir=model_dir,
config=config)
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_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension, weight_column=weight_column,
loss_reduction=loss_reduction),
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)
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_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension,
weight_column=weight_column,
loss_reduction=loss_reduction),
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)
def core_quantile_regression_head(
quantiles,
weight_column=None,
loss_reduction=core_losses.Reduction.SUM_OVER_NONZERO_WEIGHTS):
"""Core head for quantile regression problems."""
def loss_fn(labels, logits):
result = losses.per_example_quantile_regression_loss(
labels=labels,
predictions=logits,
weights=weight_column,
quantile=quantiles)
return result[0]
# pylint:disable=protected-access
head_fn = core_head_lib._regression_head(label_dimension=1,
loss_fn=loss_fn,
loss_reduction=loss_reduction,
weight_column=weight_column)
# pylint:enable=protected-access
return head_fn
def core_quantile_regression_head(
quantiles,
weight_column=None,
loss_reduction=core_losses.Reduction.SUM_OVER_NONZERO_WEIGHTS):
"""Core head for quantile regression problems."""
def loss_fn(labels, logits):
result = losses.per_example_quantile_regression_loss(
labels=labels,
predictions=logits,
weights=weight_column,
quantile=quantiles)
return result[0]
# pylint:disable=protected-access
head_fn = core_head_lib._regression_head(
label_dimension=1,
loss_fn=loss_fn,
loss_reduction=loss_reduction,
weight_column=weight_column)
# pylint:enable=protected-access
return head_fn
def __init__(self,
feature_columns,
model_dir=None,
label_dimension=1,
weight_column=None,
optimizer='Ftrl',
config=None,
partitioner=None,
warm_start_from=None,
loss_reduction=losses.Reduction.SUM,
sparse_combiner='sum'):
"""Initializes a `LinearRegressor` instance.
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.
label_dimension: Number of regression targets per example. This is the
size of the last dimension of the labels and logits `Tensor` objects
(typically, these have shape `[batch_size, label_dimension]`).
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.
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`.
"""
head = head_lib._regression_head( # pylint: disable=protected-access
label_dimension=label_dimension, weight_column=weight_column,
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(LinearRegressor, self).__init__(
model_fn=_model_fn,
model_dir=model_dir,
config=config,
warm_start_from=warm_start_from)
def logistic_regression_head(
weight_column=None,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
name=None):
"""Creates a `_Head` for logistic regression.
Uses `sigmoid_cross_entropy_with_logits` loss, which is the same as
`binary_classification_head`. The differences compared to
`binary_classification_head` are:
* Does not support `label_vocabulary`. Instead, labels must be float in the
range [0, 1].
* Does not calculate some metrics that do not make sense, such as AUC.
* In `PREDICT` mode, only returns logits and predictions
(`=tf.sigmoid(logits)`), whereas `binary_classification_head` also returns
probabilities, classes, and class_ids.
* Export output defaults to `RegressionOutput`, whereas
`binary_classification_head` defaults to `PredictOutput`.
The head expects `logits` with shape `[D0, D1, ... DN, 1]`.
In many applications, the shape is `[batch_size, 1]`.
The `labels` shape must match `logits`, namely
`[D0, D1, ... DN]` or `[D0, D1, ... DN, 1]`.
If `weight_column` is specified, weights must be of shape
`[D0, D1, ... DN]` or `[D0, D1, ... DN, 1]`.
This is implemented as a generalized linear model, see
https://en.wikipedia.org/wiki/Generalized_linear_model.
The head can be used with a canned estimator. Example:
```python
my_head = tf.contrib.estimator.logistic_regression_head()
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.logistic_regression_head()
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:
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.
loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
reduce training loss over batch and label dimension. Defaults to
`SUM_OVER_BATCH_SIZE`, namely weighted sum of losses divided by
`batch size * label_dimension`. See `tf.losses.Reduction`.
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 logistic regression.
Raises:
ValueError: If `loss_reduction` is invalid.
"""
def _logistic_loss(labels, logits):
labels = head_lib._assert_range( # pylint:disable=protected-access
labels, n_classes=2, message='Labels must be in range [0, 1]')
return nn.sigmoid_cross_entropy_with_logits(
labels=labels, logits=logits)
return head_lib._regression_head( # pylint:disable=protected-access
weight_column=weight_column,
label_dimension=1,
loss_reduction=loss_reduction,
loss_fn=_logistic_loss,
inverse_link_fn=math_ops.sigmoid,
name=name)
def regression_head(weight_column=None,
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
loss_fn=None,
inverse_link_fn=None,
name=None):
"""Creates a `_Head` for regression using the `mean_squared_error` loss.
The loss is the weighted sum over all input dimensions. Namely, if the input
labels have shape `[batch_size, label_dimension]`, the loss is the weighted
sum over both `batch_size` and `label_dimension`.
The head expects `logits` with shape `[D0, D1, ... DN, label_dimension]`.
In many applications, the shape is `[batch_size, label_dimension]`.
The `labels` shape must match `logits`, namely
`[D0, D1, ... DN, label_dimension]`. If `label_dimension=1`, shape
`[D0, D1, ... DN]` is also supported.
If `weight_column` is specified, weights must be of shape
`[D0, D1, ... DN]`, `[D0, D1, ... DN, 1]` or
`[D0, D1, ... DN, label_dimension]`.
Supports custom `loss_fn`. `loss_fn` takes `(labels, logits)` or
`(labels, logits, features)` as arguments and returns unreduced loss with
shape `[D0, D1, ... DN, label_dimension]`.
Also supports custom `inverse_link_fn`, also known as 'mean function'.
`inverse_link_fn` is only used in `PREDICT` mode. It takes `logits` as
argument and returns predicted values. This function is the inverse of the
link function defined in
https://en.wikipedia.org/wiki/Generalized_linear_model#Link_function
Namely, for poisson regression, set `inverse_link_fn=tf.exp`.
Args:
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_dimension: Number of regression labels per example. This is the size
of the last dimension of the labels `Tensor` (typically, this has shape
`[batch_size, label_dimension]`).
loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
reduce training loss over batch and label dimension. Defaults to
`SUM_OVER_BATCH_SIZE`, namely weighted sum of losses divided by
`batch size * label_dimension`. See `tf.losses.Reduction`.
loss_fn: Optional loss function. Defaults to `mean_squared_error`.
inverse_link_fn: Optional inverse link function, also known as 'mean
function'. Defaults to identity.
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 linear regression.
Raises:
ValueError: If `label_dimension` or `loss_reduction` is invalid.
"""
return head_lib._regression_head( # pylint:disable=protected-access
weight_column=weight_column,
label_dimension=label_dimension,
loss_reduction=loss_reduction,
loss_fn=loss_fn,
inverse_link_fn=inverse_link_fn,
name=name)
def regression_head(weight_column=None,
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
loss_fn=None,
inverse_link_fn=None,
name=None):
"""Creates a `_Head` for regression using the `mean_squared_error` loss.
The loss is the weighted sum over all input dimensions. Namely, if the input
labels have shape `[batch_size, label_dimension]`, the loss is the weighted
sum over both `batch_size` and `label_dimension`.
The head expects `logits` with shape `[D0, D1, ... DN, label_dimension]`.
In many applications, the shape is `[batch_size, label_dimension]`.
The `labels` shape must match `logits`, namely
`[D0, D1, ... DN, label_dimension]`. If `label_dimension=1`, shape
`[D0, D1, ... DN]` is also supported.
If `weight_column` is specified, weights must be of shape
`[D0, D1, ... DN]`, `[D0, D1, ... DN, 1]` or
`[D0, D1, ... DN, label_dimension]`.
Supports custom `loss_fn`. `loss_fn` takes `(labels, logits)` or
`(labels, logits, features)` as arguments and returns unreduced loss with
shape `[D0, D1, ... DN, label_dimension]`.
Also supports custom `inverse_link_fn`, also known as 'mean function'.
`inverse_link_fn` is only used in `PREDICT` mode. It takes `logits` as
argument and returns predicted values. This function is the inverse of the
link function defined in
https://en.wikipedia.org/wiki/Generalized_linear_model#Link_function
Namely, for poisson regression, set `inverse_link_fn=tf.exp`.
The head can be used with a canned estimator. Example:
```python
my_head = tf.contrib.estimator.regression_head()
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.regression_head()
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:
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_dimension: Number of regression labels per example. This is the size
of the last dimension of the labels `Tensor` (typically, this has shape
`[batch_size, label_dimension]`).
loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
reduce training loss over batch and label dimension. Defaults to
`SUM_OVER_BATCH_SIZE`, namely weighted sum of losses divided by
`batch size * label_dimension`. See `tf.losses.Reduction`.
loss_fn: Optional loss function. Defaults to `mean_squared_error`.
inverse_link_fn: Optional inverse link function, also known as 'mean
function'. Defaults to identity.
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 linear regression.
Raises:
ValueError: If `label_dimension` or `loss_reduction` is invalid.
"""
return head_lib._regression_head( # pylint:disable=protected-access
weight_column=weight_column,
label_dimension=label_dimension,
loss_reduction=loss_reduction,
loss_fn=loss_fn,
inverse_link_fn=inverse_link_fn,
name=name)
def logistic_regression_head(
weight_column=None,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
name=None):
"""Creates a `_Head` for logistic regression.
Uses `sigmoid_cross_entropy_with_logits` loss, which is the same as
`binary_classification_head`. The differences compared to
`binary_classification_head` are:
* Does not support `label_vocabulary`. Instead, labels must be float in the
range [0, 1].
* Does not calculate some metrics that do not make sense, such as AUC.
* In `PREDICT` mode, only returns logits and predictions
(`=tf.sigmoid(logits)`), whereas `binary_classification_head` also returns
probabilities, classes, and class_ids.
* Export output defaults to `RegressionOutput`, whereas
`binary_classification_head` defaults to `PredictOutput`.
The head expects `logits` with shape `[D0, D1, ... DN, 1]`.
In many applications, the shape is `[batch_size, 1]`.
The `labels` shape must match `logits`, namely
`[D0, D1, ... DN]` or `[D0, D1, ... DN, 1]`.
If `weight_column` is specified, weights must be of shape
`[D0, D1, ... DN]` or `[D0, D1, ... DN, 1]`.
This is implemented as a generalized linear model, see
https://en.wikipedia.org/wiki/Generalized_linear_model.
Args:
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.
loss_reduction: One of `tf.losses.Reduction` except `NONE`. Describes how to
reduce training loss over batch and label dimension. Defaults to
`SUM_OVER_BATCH_SIZE`, namely weighted sum of losses divided by
`batch size * label_dimension`. See `tf.losses.Reduction`.
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 logistic regression.
Raises:
ValueError: If `loss_reduction` is invalid.
"""
def _logistic_loss(labels, logits):
labels = head_lib._assert_range( # pylint:disable=protected-access
labels,
n_classes=2,
message='Labels must be in range [0, 1]')
return nn.sigmoid_cross_entropy_with_logits(labels=labels,
logits=logits)
return head_lib._regression_head( # pylint:disable=protected-access
weight_column=weight_column,
label_dimension=1,
loss_reduction=loss_reduction,
loss_fn=_logistic_loss,
inverse_link_fn=math_ops.sigmoid,
name=name)
