tfm.uplift.metrics.loss_metric.LossMetric

Computes a loss sliced by treatment group.

tfm.uplift.metrics.loss_metric.LossMetric(
    loss_fn: (Callable[[tf.Tensor, tf.Tensor], tf.Tensor] | tf_keras.metrics.Metric),
    from_logits: bool = True,
    slice_by_treatment: bool = True,
    name: str = 'loss',
    dtype: tf.DType = tf.float32,
    **loss_fn_kwargs
)

Example standalone usage:

sliced_loss = LossMetric(tf_keras.losses.mean_squared_error)
y_true = tf.constant([0, 0, 2, 2])
y_pred = types.TwoTowerTrainingOutputs(
    true_logits=tf.constant([1, 2, 3, 4])
    is_treatment=tf.constant([True, False, True, False]),
)
sliced_loss(y_true=y_true, y_pred=y_pred)
{
    "loss": 2.5
    "loss/control": 4.0
    "loss/treatment": 1.0
}

Example usage with the model.compile() API:

model.compile(
    optimizer="sgd",
    loss=TrueLogitsLoss(tf_keras.losses.mean_squared_error),
    metrics=[LossMetric(tf_keras.losses.mean_squared_error)]
)

loss_fn The loss function or Keras metric to apply with call signature __call__(y_true: tf,Tensor, y_pred: tf.Tensor, **loss_fn_kwargs). Note that the loss_fn_kwargs will not be passed to the __call__ method if loss_fn is a Keras metric.
from_logits When y_pred is of type TwoTowerTrainingOutputs, specifies whether the true logits or true predictions should be used to compute the loss (defaults to using the true logits). Othwerwise, this argument will be ignored if y_pred is of type tf.Tensor.
slice_by_treatment Specifies whether the loss should be sliced by the treatment indicator tensor. If True, loss_fn will be wrapped in a TreatmentSlicedMetric to report the loss values sliced by the treatment group.
name Optional name for the instance. If loss_fn is a Keras metric then its name will be used instead.
dtype Optional data type for the instance. If loss_fn is a Keras metric then its dtype will be used instead.
**loss_fn_kwargs The keyword arguments that are passed on to loss_fn. These arguments will be ignored if loss_fn is a Keras metric.

Methods

call

call(
    inputs, *args, **kwargs
)

This is where the layer's logic lives.

The call() method may not create state (except in its first invocation, wrapping the creation of variables or other resources in tf.init_scope()). It is recommended to create state, including tf.Variable instances and nested Layer instances, in __init__(), or in the build() method that is called automatically before call() executes for the first time.

Args
inputs Input tensor, or dict/list/tuple of input tensors. The first positional inputs argument is subject to special rules:

  • inputs must be explicitly passed. A layer cannot have zero arguments, and inputs cannot be provided via the default value of a keyword argument.
  • NumPy array or Python scalar values in inputs get cast as tensors.
  • TF-Keras mask metadata is only collected from inputs.
  • Layers are built (build(input_shape) method) using shape info from inputs only.
  • input_spec compatibility is only checked against inputs.
  • Mixed precision input casting is only applied to inputs. If a layer has tensor arguments in *args or **kwargs, their casting behavior in mixed precision should be handled manually.
  • The SavedModel input specification is generated using inputs only.
  • Integration with various ecosystem packages like TFMOT, TFLite, TF.js, etc is only supported for inputs and not for tensors in positional and keyword arguments.
*args Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above.
**kwargs Additional keyword arguments. May contain tensors, although this is not recommended, for the reasons above. The following optional keyword arguments are reserved:
  • training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference.
  • mask: Boolean input mask. If the layer's call() method takes a mask argument, its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a TF-Keras layer with masking support).

    • Returns
    A tensor or list/tuple of tensors.

    merge_state

    merge_state(
    metrics
)

    Merges the state from one or more metrics.

    This method can be used by distributed systems to merge the state computed by different metric instances. Typically the state will be stored in the form of the metric's weights. For example, a tf.keras.metrics.Mean metric contains a list of two weight values: a total and a count. If there were two instances of a tf.keras.metrics.Accuracy that each independently aggregated partial state for an overall accuracy calculation, these two metric's states could be combined as follows:

    m1 = tf.keras.metrics.Accuracy()
_ = m1.update_state([[1], [2]], [[0], [2]])
     
    m2 = tf.keras.metrics.Accuracy()
_ = m2.update_state([[3], [4]], [[3], [4]])
     
    m2.merge_state([m1])
m2.result().numpy()
0.75

    Args
    metrics an iterable of metrics. The metrics must have compatible state.

    Raises
    ValueError If the provided iterable does not contain metrics matching the metric's required specifications.

    reset_state

    View source

    reset_state()

    Resets all of the metric state variables.

    This function is called between epochs/steps, when a metric is evaluated during training.

    result

    View source

    result() -> (tf.Tensor | dict[str, tf.Tensor])

    Computes and returns the scalar metric value tensor or a dict of scalars.

    Result computation is an idempotent operation that simply calculates the metric value using the state variables.

    Returns
    A scalar tensor, or a dictionary of scalar tensors.

    update_state

    View source

    update_state(
    y_true: tf.Tensor,
    y_pred: (types.TwoTowerTrainingOutputs | tf.Tensor | np.ndarray),
    sample_weight: (tf.Tensor | None) = None
)

    Updates the overall, control and treatment losses.

    Args
    y_true A tf.Tensor with the targets.
    y_pred Model outputs. If of type TwoTowerTrainingOutputs, the treatment indicator tensor is used to slice the true logits or true predictions into control and treatment losses.
    sample_weight Optional sample weight to compute weighted losses. If given, the sample weight will also be sliced by the treatment indicator tensor to compute the weighted control and treatment losses.

    Raises
    TypeError if y_pred is not of type TwoTowerTrainingOutputs.