.. _metrics_H2OMultinomialGLMMetrics:

H2OMultinomialGLMMetrics Class
------------------------------

The class makes available all multinomial metrics supported by GLM algorithm.

**Getter Methods**

getAIC()
  **Returns:** The AIC for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getAUC()
  **Returns:** The average AUC for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getConfusionMatrix()
  **Returns:** The ConfusionMatrix object for this scoring run.

  *Type:* ``DataFrame``

getCustomMetricName()
  **Returns:** Name of custom metric.

  *Scala type:* ``String``, *Python type:* ``string``, *R type:* ``character``

getCustomMetricValue()
  **Returns:** Value of custom metric.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getDataFrameSerializer()
  **Returns:** A full name of a serializer used for serialization and deserialization of Spark DataFrames to a JSON value within NullableDataFrameParam.

  *Scala type:* ``String``, *Python type:* ``string``, *R type:* ``character``

getDescription()
  **Returns:** Optional description for this scoring run (to note out-of-bag, sampled data, etc.).

  *Scala type:* ``String``, *Python type:* ``string``, *R type:* ``character``

getHitRatioTable()
  **Returns:** The hit ratio table for this scoring run.

  *Type:* ``DataFrame``

getLoglikelihood()
  **Returns:** The logarithmic likelihood for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getLogloss()
  **Returns:** The logarithmic loss for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getMeanPerClassError()
  **Returns:** The mean misclassification error per class.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getMSE()
  **Returns:** The Mean Squared Error of the prediction for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getMultinomialAUCTable()
  **Returns:** The multinomial AUC values.

  *Type:* ``DataFrame``

getMultinomialPRAUCTable()
  **Returns:** The multinomial PR AUC values.

  *Type:* ``DataFrame``

getNobs()
  **Returns:** Number of observations.

  *Scala type:* ``Long``, *Python type:* ``int``, *R type:* ``integer``

getNullDegreesOfFreedom()
  **Returns:** null DOF.

  *Scala type:* ``Long``, *Python type:* ``int``, *R type:* ``integer``

getNullDeviance()
  **Returns:** null deviance.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getPRAUC()
  **Returns:** The average precision-recall AUC for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getR2()
  **Returns:** The R^2 for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getResidualDegreesOfFreedom()
  **Returns:** residual DOF.

  *Scala type:* ``Long``, *Python type:* ``int``, *R type:* ``integer``

getResidualDeviance()
  **Returns:** residual deviance.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getRMSE()
  **Returns:** The Root Mean Squared Error of the prediction for this scoring run.

  *Scala type:* ``Double``, *Python type:* ``float``, *R type:* ``numeric``

getScoringTime()
  **Returns:** The time in mS since the epoch for the start of this scoring run.

  *Scala type:* ``Long``, *Python type:* ``int``, *R type:* ``integer``