diff options
author | Yanbo Liang <ybliang8@gmail.com> | 2016-04-15 08:23:51 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2016-04-15 08:23:51 -0700 |
commit | 83af297ac42546580983f91079f74e3a4cf25050 (patch) | |
tree | abaa00d9f381bcd4fa4adae7a2bc79b54ad325b4 /R/pkg/inst/tests/testthat/test_mllib.R | |
parent | 06b9d623e8f58d7bd450a50d938f83b4b3472a32 (diff) | |
download | spark-83af297ac42546580983f91079f74e3a4cf25050.tar.gz spark-83af297ac42546580983f91079f74e3a4cf25050.tar.bz2 spark-83af297ac42546580983f91079f74e3a4cf25050.zip |
[SPARK-13925][ML][SPARKR] Expose R-like summary statistics in SparkR::glm for more family and link functions
## What changes were proposed in this pull request?
Expose R-like summary statistics in SparkR::glm for more family and link functions.
Note: Not all values in R [summary.glm](http://stat.ethz.ch/R-manual/R-patched/library/stats/html/summary.glm.html) are exposed, we only provide the most commonly used statistics in this PR. More statistics can be added in the followup work.
## How was this patch tested?
Unit tests.
SparkR Output:
```
Deviance Residuals:
(Note: These are approximate quantiles with relative error <= 0.01)
Min 1Q Median 3Q Max
-0.95096 -0.16585 -0.00232 0.17410 0.72918
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.6765 0.23536 7.1231 4.4561e-11
Sepal_Length 0.34988 0.046301 7.5566 4.1873e-12
Species_versicolor -0.98339 0.072075 -13.644 0
Species_virginica -1.0075 0.093306 -10.798 0
(Dispersion parameter for gaussian family taken to be 0.08351462)
Null deviance: 28.307 on 149 degrees of freedom
Residual deviance: 12.193 on 146 degrees of freedom
AIC: 59.22
Number of Fisher Scoring iterations: 1
```
R output:
```
Deviance Residuals:
Min 1Q Median 3Q Max
-0.95096 -0.16522 0.00171 0.18416 0.72918
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.67650 0.23536 7.123 4.46e-11 ***
Sepal.Length 0.34988 0.04630 7.557 4.19e-12 ***
Speciesversicolor -0.98339 0.07207 -13.644 < 2e-16 ***
Speciesvirginica -1.00751 0.09331 -10.798 < 2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for gaussian family taken to be 0.08351462)
Null deviance: 28.307 on 149 degrees of freedom
Residual deviance: 12.193 on 146 degrees of freedom
AIC: 59.217
Number of Fisher Scoring iterations: 2
```
cc mengxr
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #12393 from yanboliang/spark-13925.
Diffstat (limited to 'R/pkg/inst/tests/testthat/test_mllib.R')
-rw-r--r-- | R/pkg/inst/tests/testthat/test_mllib.R | 49 |
1 files changed, 49 insertions, 0 deletions
diff --git a/R/pkg/inst/tests/testthat/test_mllib.R b/R/pkg/inst/tests/testthat/test_mllib.R index a9dbd2bdc4..47bbf7e5bd 100644 --- a/R/pkg/inst/tests/testthat/test_mllib.R +++ b/R/pkg/inst/tests/testthat/test_mllib.R @@ -77,6 +77,55 @@ test_that("glm and predict", { expect_equal(length(predict(lm(y ~ x))), 15) }) +test_that("glm summary", { + # gaussian family + training <- suppressWarnings(createDataFrame(sqlContext, iris)) + stats <- summary(glm(Sepal_Width ~ Sepal_Length + Species, data = training)) + + rStats <- summary(glm(Sepal.Width ~ Sepal.Length + Species, data = iris)) + + coefs <- unlist(stats$coefficients) + rCoefs <- unlist(rStats$coefficients) + expect_true(all(abs(rCoefs - coefs) < 1e-4)) + expect_true(all( + rownames(stats$coefficients) == + c("(Intercept)", "Sepal_Length", "Species_versicolor", "Species_virginica"))) + expect_equal(stats$dispersion, rStats$dispersion) + expect_equal(stats$null.deviance, rStats$null.deviance) + expect_equal(stats$deviance, rStats$deviance) + expect_equal(stats$df.null, rStats$df.null) + expect_equal(stats$df.residual, rStats$df.residual) + expect_equal(stats$aic, rStats$aic) + + # binomial family + df <- suppressWarnings(createDataFrame(sqlContext, iris)) + training <- df[df$Species %in% c("versicolor", "virginica"), ] + stats <- summary(glm(Species ~ Sepal_Length + Sepal_Width, data = training, + family = binomial(link = "logit"))) + + rTraining <- iris[iris$Species %in% c("versicolor", "virginica"), ] + rStats <- summary(glm(Species ~ Sepal.Length + Sepal.Width, data = rTraining, + family = binomial(link = "logit"))) + + coefs <- unlist(stats$coefficients) + rCoefs <- unlist(rStats$coefficients) + expect_true(all(abs(rCoefs - coefs) < 1e-4)) + expect_true(all( + rownames(stats$coefficients) == + c("(Intercept)", "Sepal_Length", "Sepal_Width"))) + expect_equal(stats$dispersion, rStats$dispersion) + expect_equal(stats$null.deviance, rStats$null.deviance) + expect_equal(stats$deviance, rStats$deviance) + expect_equal(stats$df.null, rStats$df.null) + expect_equal(stats$df.residual, rStats$df.residual) + expect_equal(stats$aic, rStats$aic) + + # Test summary works on base GLM models + baseModel <- stats::glm(Sepal.Width ~ Sepal.Length + Species, data = iris) + baseSummary <- summary(baseModel) + expect_true(abs(baseSummary$deviance - 12.19313) < 1e-4) +}) + test_that("kmeans", { newIris <- iris newIris$Species <- NULL |