2015-07-20 23:49:38 -04:00
|
|
|
#
|
|
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
|
|
# this work for additional information regarding copyright ownership.
|
|
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
|
|
# (the "License"); you may not use this file except in compliance with
|
|
|
|
# the License. You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
|
|
|
#
|
|
|
|
|
|
|
|
library(testthat)
|
|
|
|
|
|
|
|
context("MLlib functions")
|
|
|
|
|
|
|
|
# Tests for MLlib functions in SparkR
|
|
|
|
|
|
|
|
sc <- sparkR.init()
|
|
|
|
|
|
|
|
sqlContext <- sparkRSQL.init(sc)
|
|
|
|
|
|
|
|
test_that("glm and predict", {
|
|
|
|
training <- createDataFrame(sqlContext, iris)
|
|
|
|
test <- select(training, "Sepal_Length")
|
|
|
|
model <- glm(Sepal_Width ~ Sepal_Length, training, family = "gaussian")
|
|
|
|
prediction <- predict(model, test)
|
|
|
|
expect_equal(typeof(take(select(prediction, "prediction"), 1)$prediction), "double")
|
|
|
|
})
|
|
|
|
|
|
|
|
test_that("predictions match with native glm", {
|
|
|
|
training <- createDataFrame(sqlContext, iris)
|
2015-07-27 20:17:49 -04:00
|
|
|
model <- glm(Sepal_Width ~ Sepal_Length + Species, data = training)
|
2015-07-20 23:49:38 -04:00
|
|
|
vals <- collect(select(predict(model, training), "prediction"))
|
2015-07-27 20:17:49 -04:00
|
|
|
rVals <- predict(glm(Sepal.Width ~ Sepal.Length + Species, data = iris), iris)
|
|
|
|
expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
|
2015-07-20 23:49:38 -04:00
|
|
|
})
|
2015-07-28 17:16:57 -04:00
|
|
|
|
|
|
|
test_that("dot minus and intercept vs native glm", {
|
|
|
|
training <- createDataFrame(sqlContext, iris)
|
|
|
|
model <- glm(Sepal_Width ~ . - Species + 0, data = training)
|
|
|
|
vals <- collect(select(predict(model, training), "prediction"))
|
|
|
|
rVals <- predict(glm(Sepal.Width ~ . - Species + 0, data = iris), iris)
|
|
|
|
expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
|
|
|
|
})
|
2015-07-30 19:15:43 -04:00
|
|
|
|
2015-09-25 03:43:22 -04:00
|
|
|
test_that("feature interaction vs native glm", {
|
|
|
|
training <- createDataFrame(sqlContext, iris)
|
|
|
|
model <- glm(Sepal_Width ~ Species:Sepal_Length, data = training)
|
|
|
|
vals <- collect(select(predict(model, training), "prediction"))
|
|
|
|
rVals <- predict(glm(Sepal.Width ~ Species:Sepal.Length, data = iris), iris)
|
|
|
|
expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
|
|
|
|
})
|
|
|
|
|
2015-07-30 19:15:43 -04:00
|
|
|
test_that("summary coefficients match with native glm", {
|
|
|
|
training <- createDataFrame(sqlContext, iris)
|
2015-10-19 13:46:10 -04:00
|
|
|
stats <- summary(glm(Sepal_Width ~ Sepal_Length + Species, data = training, solver = "l-bfgs"))
|
2015-07-30 19:15:43 -04:00
|
|
|
coefs <- as.vector(stats$coefficients)
|
|
|
|
rCoefs <- as.vector(coef(glm(Sepal.Width ~ Sepal.Length + Species, data = iris)))
|
|
|
|
expect_true(all(abs(rCoefs - coefs) < 1e-6))
|
|
|
|
expect_true(all(
|
|
|
|
as.character(stats$features) ==
|
2015-09-25 03:43:22 -04:00
|
|
|
c("(Intercept)", "Sepal_Length", "Species_versicolor", "Species_virginica")))
|
2015-07-30 19:15:43 -04:00
|
|
|
})
|