GeneralizedLinearRegressionTrainingSummary¶

class pyspark.ml.regression.GeneralizedLinearRegressionTrainingSummary(java_obj=None)[source]¶

Generalized linear regression training results.

New in version 2.0.0.

Methods

residuals([residualsType])

Get the residuals of the fitted model by type.

Attributes

`aic`	Akaike’s “An Information Criterion”(AIC) for the fitted model.
`coefficientStandardErrors`	Standard error of estimated coefficients and intercept.
`degreesOfFreedom`	Degrees of freedom.
`deviance`	The deviance for the fitted model.
`dispersion`	The dispersion of the fitted model.
`nullDeviance`	The deviance for the null model.
`numInstances`	Number of instances in DataFrame predictions.
`numIterations`	Number of training iterations.
`pValues`	Two-sided p-value of estimated coefficients and intercept.
`predictionCol`	Field in `predictions` which gives the predicted value of each instance.
`predictions`	Predictions output by the model’s transform method.
`rank`	The numeric rank of the fitted linear model.
`residualDegreeOfFreedom`	The residual degrees of freedom.
`residualDegreeOfFreedomNull`	The residual degrees of freedom for the null model.
`solver`	The numeric solver used for training.
`tValues`	T-statistic of estimated coefficients and intercept.

Methods Documentation

residuals(residualsType='deviance')¶

Get the residuals of the fitted model by type.

New in version 2.0.0.

Parameters

residualsTypestr, optional: The type of residuals which should be returned. Supported options: deviance (default), pearson, working, and response.

Attributes Documentation

aic¶: Akaike’s “An Information Criterion”(AIC) for the fitted model.

New in version 2.0.0.

coefficientStandardErrors¶

Standard error of estimated coefficients and intercept.

If GeneralizedLinearRegression.fitIntercept is set to True, then the last element returned corresponds to the intercept.

New in version 2.0.0.

dispersion¶: The dispersion of the fitted model. It is taken as 1.0 for the “binomial” and “poisson” families, and otherwise estimated by the residual Pearson’s Chi-Squared statistic (which is defined as sum of the squares of the Pearson residuals) divided by the residual degrees of freedom.

New in version 2.0.0.

numInstances¶: Number of instances in DataFrame predictions.

New in version 2.2.0.

pValues¶

Two-sided p-value of estimated coefficients and intercept.

If GeneralizedLinearRegression.fitIntercept is set to True, then the last element returned corresponds to the intercept.

New in version 2.0.0.

predictionCol¶: Field in predictions which gives the predicted value of each instance. This is set to a new column name if the original model’s predictionCol is not set.

New in version 2.0.0.

predictions¶: Predictions output by the model’s transform method.

New in version 2.0.0.

rank¶: The numeric rank of the fitted linear model.

New in version 2.0.0.

residualDegreeOfFreedom¶: The residual degrees of freedom.

New in version 2.0.0.

residualDegreeOfFreedomNull¶: The residual degrees of freedom for the null model.

New in version 2.0.0.

tValues¶

T-statistic of estimated coefficients and intercept.

If GeneralizedLinearRegression.fitIntercept is set to True, then the last element returned corresponds to the intercept.

New in version 2.0.0.