diff options
author | sethah <seth.hendrickson16@gmail.com> | 2016-05-13 09:01:20 +0200 |
---|---|---|
committer | Nick Pentreath <nick.pentreath@gmail.com> | 2016-05-13 09:01:20 +0200 |
commit | 5b849766ab080c91864ed06ebbfd82ad978d5e4c (patch) | |
tree | 7ce287278bbeb2e0771300784aba26cb98d13aa4 /mllib/src/main/scala | |
parent | 87d69a01f027aa18718827f94f921b4a1eaa78a5 (diff) | |
download | spark-5b849766ab080c91864ed06ebbfd82ad978d5e4c.tar.gz spark-5b849766ab080c91864ed06ebbfd82ad978d5e4c.tar.bz2 spark-5b849766ab080c91864ed06ebbfd82ad978d5e4c.zip |
[SPARK-15181][ML][PYSPARK] Python API for GLR summaries.
## What changes were proposed in this pull request?
This patch adds a python API for generalized linear regression summaries (training and test). This helps provide feature parity for Python GLMs.
## How was this patch tested?
Added a unit test to `pyspark.ml.tests`
Author: sethah <seth.hendrickson16@gmail.com>
Closes #12961 from sethah/GLR_summary.
Diffstat (limited to 'mllib/src/main/scala')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala index c294ef31f9..05fffa0d97 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala @@ -848,7 +848,7 @@ class GeneralizedLinearRegressionSummary private[regression] ( import GeneralizedLinearRegression._ /** - * Field in "predictions" which gives the prediction value of each instance. + * 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. */ @Since("2.0.0") @@ -870,7 +870,7 @@ class GeneralizedLinearRegressionSummary private[regression] ( protected val model: GeneralizedLinearRegressionModel = origModel.copy(ParamMap.empty).setPredictionCol(predictionCol) - /** predictions output by the model's `transform` method */ + /** Predictions output by the model's `transform` method. */ @Since("2.0.0") @transient val predictions: DataFrame = model.transform(dataset) private[regression] lazy val family: Family = Family.fromName(model.getFamily) @@ -880,10 +880,10 @@ class GeneralizedLinearRegressionSummary private[regression] ( family.defaultLink } - /** Number of instances in DataFrame predictions */ + /** Number of instances in DataFrame predictions. */ private[regression] lazy val numInstances: Long = predictions.count() - /** The numeric rank of the fitted linear model */ + /** The numeric rank of the fitted linear model. */ @Since("2.0.0") lazy val rank: Long = if (model.getFitIntercept) { model.coefficients.size + 1 @@ -891,17 +891,17 @@ class GeneralizedLinearRegressionSummary private[regression] ( model.coefficients.size } - /** Degrees of freedom */ + /** Degrees of freedom. */ @Since("2.0.0") lazy val degreesOfFreedom: Long = { numInstances - rank } - /** The residual degrees of freedom */ + /** The residual degrees of freedom. */ @Since("2.0.0") lazy val residualDegreeOfFreedom: Long = degreesOfFreedom - /** The residual degrees of freedom for the null model */ + /** The residual degrees of freedom for the null model. */ @Since("2.0.0") lazy val residualDegreeOfFreedomNull: Long = if (model.getFitIntercept) { numInstances - 1 @@ -944,7 +944,7 @@ class GeneralizedLinearRegressionSummary private[regression] ( } /** - * Get the default residuals(deviance residuals) of the fitted model. + * Get the default residuals (deviance residuals) of the fitted model. */ @Since("2.0.0") def residuals(): DataFrame = devianceResiduals @@ -1000,7 +1000,7 @@ class GeneralizedLinearRegressionSummary private[regression] ( /** * 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 + * 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. */ @Since("2.0.0") |