From 8d5bb5283c3cc9180ef34b05be4a715d83073b1e Mon Sep 17 00:00:00 2001 From: Eric Liang Date: Tue, 28 Jul 2015 14:16:57 -0700 Subject: [SPARK-9391] [ML] Support minus, dot, and intercept operators in SparkR RFormula Adds '.', '-', and intercept parsing to RFormula. Also splits RFormulaParser into a separate file. Umbrella design doc here: https://docs.google.com/document/d/10NZNSEurN2EdWM31uFYsgayIPfCFHiuIu3pCWrUmP_c/edit?usp=sharing mengxr Author: Eric Liang Closes #7707 from ericl/string-features-2 and squashes the following commits: 8588625 [Eric Liang] exclude complex types for . 8106ffe [Eric Liang] comments a9350bb [Eric Liang] s/var/val 9c50d4d [Eric Liang] Merge branch 'string-features' into string-features-2 581afb2 [Eric Liang] Merge branch 'master' into string-features 08ae539 [Eric Liang] Merge branch 'string-features' into string-features-2 f99131a [Eric Liang] comments cecec43 [Eric Liang] Merge branch 'string-features' into string-features-2 0bf3c26 [Eric Liang] update docs 4592df2 [Eric Liang] intercept supports 7412a2e [Eric Liang] Fri Jul 24 14:56:51 PDT 2015 3cf848e [Eric Liang] fix the parser 0556c2b [Eric Liang] Merge branch 'string-features' into string-features-2 c302a2c [Eric Liang] fix tests 9d1ac82 [Eric Liang] Merge remote-tracking branch 'upstream/master' into string-features e713da3 [Eric Liang] comments cd231a9 [Eric Liang] Wed Jul 22 17:18:44 PDT 2015 4d79193 [Eric Liang] revert to seq + distinct 169a085 [Eric Liang] tweak functional test a230a47 [Eric Liang] Merge branch 'master' into string-features 72bd6f3 [Eric Liang] fix merge d841cec [Eric Liang] Merge branch 'master' into string-features 5b2c4a2 [Eric Liang] Mon Jul 20 18:45:33 PDT 2015 b01c7c5 [Eric Liang] add test 8a637db [Eric Liang] encoder wip a1d03f4 [Eric Liang] refactor into estimator --- R/pkg/R/mllib.R | 2 +- R/pkg/inst/tests/test_mllib.R | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'R/pkg') diff --git a/R/pkg/R/mllib.R b/R/pkg/R/mllib.R index 258e354081..6a8bacaa55 100644 --- a/R/pkg/R/mllib.R +++ b/R/pkg/R/mllib.R @@ -27,7 +27,7 @@ setClass("PipelineModel", representation(model = "jobj")) #' Fits a generalized linear model, similarly to R's glm(). Also see the glmnet package. #' #' @param formula A symbolic description of the model to be fitted. Currently only a few formula -#' operators are supported, including '~' and '+'. +#' operators are supported, including '~', '+', '-', and '.'. #' @param data DataFrame for training #' @param family Error distribution. "gaussian" -> linear regression, "binomial" -> logistic reg. #' @param lambda Regularization parameter diff --git a/R/pkg/inst/tests/test_mllib.R b/R/pkg/inst/tests/test_mllib.R index 29152a1168..3bef693247 100644 --- a/R/pkg/inst/tests/test_mllib.R +++ b/R/pkg/inst/tests/test_mllib.R @@ -40,3 +40,11 @@ test_that("predictions match with native glm", { rVals <- predict(glm(Sepal.Width ~ Sepal.Length + Species, data = iris), iris) expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals) }) + +test_that("dot minus and intercept vs native glm", { + training <- createDataFrame(sqlContext, iris) + model <- glm(Sepal_Width ~ . - Species + 0, data = training) + vals <- collect(select(predict(model, training), "prediction")) + rVals <- predict(glm(Sepal.Width ~ . - Species + 0, data = iris), iris) + expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals) +}) -- cgit v1.2.3