afe.apis.statistic
==================

.. py:module:: afe.apis.statistic

.. autoapi-nested-parse::

   Analysis of statistics on tensors.



Attributes
----------

.. autoapisummary::

   afe.apis.statistic.Metric


Functions
---------

.. autoapisummary::

   afe.apis.statistic.equality
   afe.apis.statistic.mean_float
   afe.apis.statistic.threshold_test_counter
   afe.apis.statistic.tensor_set_statistics
   afe.apis.statistic.mean
   afe.apis.statistic.mean_text


Module Contents
---------------

.. py:data:: Metric

.. py:function:: equality(x: afe.apis.compilation_job_base.Tensor, y: afe.apis.compilation_job_base.Tensor) -> float

   Equality as a distance metric.

   Return 0 if the tensors are equal, 1 otherwise.


.. py:function:: mean_float(x: afe.apis.compilation_job_base.Tensor, y: afe.apis.compilation_job_base.Tensor) -> float

   Mean value of difference between input values and ground truth values.


.. py:function:: threshold_test_counter(metric: Metric, threshold: float) -> afe.driver.statistic.Statistic[Tuple[afe.apis.compilation_job_base.Tensor, afe.apis.compilation_job_base.Tensor], str]

   Create a Statistic over a stream of (x, y) pairs
   that counts the number of times metric(x, y) < threshold is satisfied.

   :param metric: Distance metric
   :param threshold: Threshold to compare against
   :return: Statistic that captures the data


.. py:function:: tensor_set_statistics(statistics: List[afe.driver.statistic.Statistic[Tuple[Any, Any], str]]) -> afe.driver.statistic.Statistic[Tuple[List[Any], List[Any]], str]

   Apply an independent Statistic to each tensor in a stream of pairs of
   fixed-length lists.

   This is intended for evaluating models that have multiple outputs and a
   ground truth value corresponding to each output.  Each Statistic would
   be applied to one of the outputs and ground truth values.

   :param statistics: Statistic to apply to each pair of values
   :return: Composed statistic that applies the statistics to list items


.. py:function:: mean(metric: Metric) -> afe.driver.statistic.Statistic[Tuple[List[afe.apis.compilation_job_base.Tensor], afe.apis.compilation_job_base.Tensor], float]

   Create a statistic that takes input pairs (i, g)
   and computes the arithmetic mean of metric(i, g) over all given inputs.

   :param metric: Mean metric.
   :return: Statistic that captures the data


.. py:function:: mean_text(metric: Metric) -> afe.driver.statistic.Statistic[Tuple[List[afe.apis.compilation_job_base.Tensor], afe.apis.compilation_job_base.Tensor], str]

   Create a statistic that takes input pairs (i, g)
   and computes the arithmetic mean of metric(i, g) over all given inputs and formats the results as text message.

   :param metric: Mean metric.
   :return: Statistic that captures the data