Class: GeneralizedLinearRegressionSummary

eclairjs/ml/regression.GeneralizedLinearRegressionSummary

:: Experimental :: Summary of GeneralizedLinearRegression model and predictions.

Constructor

new GeneralizedLinearRegressionSummary(dataset, origModel)

Parameters:
Name Type Description
dataset Dataset to be summarized.
origModel Model to be summarized. This is copied to create an internal model which cannot be modified from outside.
Source:

Methods

aic() → {Promise.<number>}

Akaike Information Criterion (AIC) for the fitted model.
Source:
Returns:
Type
Promise.<number>

degreesOfFreedom() → {Promise.<number>}

Degrees of freedom.
Source:
Returns:
Type
Promise.<number>

deviance() → {Promise.<number>}

The deviance for the fitted model.
Source:
Returns:
Type
Promise.<number>

dispersion() → {Promise.<number>}

The dispersion of the fitted model.
Source:
Returns:
Type
Promise.<number>

nullDeviance() → {Promise.<number>}

The deviance for the null model.
Source:
Returns:
Type
Promise.<number>

predictionCol() → {Promise.<string>}

Field in "predictions" which gives the predicted value of each instance.
Source:
Returns:
Type
Promise.<string>

predictions() → {module:eclairjs/sql.Dataset}

Predictions output by the model's `transform` method.
Source:
Returns:
Type
module:eclairjs/sql.Dataset

rank() → {Promise.<number>}

The numeric rank of the fitted linear model.
Source:
Returns:
Type
Promise.<number>

residualDegreeOfFreedom() → {Promise.<number>}

The residual degrees of freedom.
Source:
Returns:
Type
Promise.<number>

residualDegreeOfFreedomNull() → {Promise.<number>}

The residual degrees of freedom for the null model.
Source:
Returns:
Type
Promise.<number>

residuals(residualsTypeopt) → {module:eclairjs/sql.Dataset}

Get the residuals of the fitted model by type.
Parameters:
Name Type Attributes Description
residualsType string <optional>
 The type of residuals which should be returned. Supported options: deviance, pearson, working and response.
Source:
Returns:
Type
module:eclairjs/sql.Dataset