org.apache.spark.ml.regression

Class LinearRegressionSummary

java.lang.Object

org.apache.spark.ml.regression.LinearRegressionSummary

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

LinearRegressionTrainingSummary

public class LinearRegressionSummary
extends java.lang.Object
implements scala.Serializable

:: Experimental :: Linear regression results evaluated on a dataset.

param: predictions predictions output by the model's transform method. param: predictionCol Field in "predictions" which gives the predicted value of the label at each instance. param: labelCol Field in "predictions" which gives the true label of each instance. param: featuresCol Field in "predictions" which gives the features of each instance as a vector.

See Also:

Serialized Form

Method Summary

Methods

Modifier and Type	Method and Description
double[]	coefficientStandardErrors() Standard error of estimated coefficients and intercept.
double[]	devianceResiduals() The weighted residuals, the usual residuals rescaled by the square root of the instance weights.
double	explainedVariance() Returns the explained variance regression score.
java.lang.String	featuresCol()
java.lang.String	labelCol()
double	meanAbsoluteError() Returns the mean absolute error, which is a risk function corresponding to the expected value of the absolute error loss or l1-norm loss.
double	meanSquaredError() Returns the mean squared error, which is a risk function corresponding to the expected value of the squared error loss or quadratic loss.
LinearRegressionModel	model() Deprecated. The model field is deprecated and will be removed in 2.1.0. Since 2.0.0.
long	numInstances() Number of instances in DataFrame predictions
java.lang.String	predictionCol()
Dataset<Row>	predictions()
double[]	pValues() Two-sided p-value of estimated coefficients and intercept.
double	r2() Returns R^2^, the coefficient of determination.
Dataset<Row>	residuals() Residuals (label - predicted value)
double	rootMeanSquaredError() Returns the root mean squared error, which is defined as the square root of the mean squared error.
double[]	tValues() T-statistic of estimated coefficients and intercept.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

predictions

public Dataset<Row> predictions()

predictionCol

public java.lang.String predictionCol()

labelCol

public java.lang.String labelCol()

featuresCol

public java.lang.String featuresCol()

model

public LinearRegressionModel model()

Deprecated. The model field is deprecated and will be removed in 2.1.0. Since 2.0.0.

explainedVariance

public double explainedVariance()

Returns the explained variance regression score. explainedVariance = 1 - variance(y - \hat{y}) / variance(y) Reference: http://en.wikipedia.org/wiki/Explained_variation

Note: This ignores instance weights (setting all to 1.0) from LinearRegression.weightCol. This will change in later Spark versions.

Returns:

(undocumented)

meanAbsoluteError

public double meanAbsoluteError()

Returns the mean absolute error, which is a risk function corresponding to the expected value of the absolute error loss or l1-norm loss.

Note: This ignores instance weights (setting all to 1.0) from LinearRegression.weightCol. This will change in later Spark versions.

Returns:

(undocumented)

meanSquaredError

public double meanSquaredError()

Returns the mean squared error, which is a risk function corresponding to the expected value of the squared error loss or quadratic loss.

Note: This ignores instance weights (setting all to 1.0) from LinearRegression.weightCol. This will change in later Spark versions.

Returns:

(undocumented)

rootMeanSquaredError

public double rootMeanSquaredError()

Returns the root mean squared error, which is defined as the square root of the mean squared error.

Note: This ignores instance weights (setting all to 1.0) from LinearRegression.weightCol. This will change in later Spark versions.

Returns:

(undocumented)

r2

public double r2()

Returns R^2^, the coefficient of determination. Reference: http://en.wikipedia.org/wiki/Coefficient_of_determination

Note: This ignores instance weights (setting all to 1.0) from LinearRegression.weightCol. This will change in later Spark versions.

Returns:

(undocumented)

residuals

public Dataset<Row> residuals()

Residuals (label - predicted value)

numInstances

public long numInstances()

Number of instances in DataFrame predictions

devianceResiduals

public double[] devianceResiduals()

The weighted residuals, the usual residuals rescaled by the square root of the instance weights.

Returns:

(undocumented)

coefficientStandardErrors

public double[] coefficientStandardErrors()

Standard error of estimated coefficients and intercept. This value is only available when using the "normal" solver.

If LinearRegression.fitIntercept is set to true, then the last element returned corresponds to the intercept.

Returns:

(undocumented)

See Also:

LinearRegression.solver

tValues

public double[] tValues()

T-statistic of estimated coefficients and intercept. This value is only available when using the "normal" solver.

If LinearRegression.fitIntercept is set to true, then the last element returned corresponds to the intercept.

Returns:

(undocumented)

See Also:

LinearRegression.solver

pValues

public double[] pValues()

Two-sided p-value of estimated coefficients and intercept. This value is only available when using the "normal" solver.

If LinearRegression.fitIntercept is set to true, then the last element returned corresponds to the intercept.

Returns:

(undocumented)

See Also:

LinearRegression.solver