Github user wangmiao1981 commented on a diff in the pull request:
https://github.com/apache/spark/pull/16148#discussion_r90934508
--- Diff: examples/src/main/r/ml/ml.R ---
@@ -0,0 +1,64 @@
+#
+# 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.
+#
+
+# To run this example use
+# ./bin/spark-submit examples/src/main/r/ml.R
+
+# Load SparkR library into your R session
+library(SparkR)
+
+# Initialize SparkSession
+sparkR.session(appName = "SparkR-ML-example")
+
+############################ model read/write
##############################################
+# $example on:read_write$
+irisDF <- suppressWarnings(createDataFrame(iris))
+# Fit a generalized linear model of family "gaussian" with spark.glm
+gaussianDF <- irisDF
+gaussianTestDF <- irisDF
+gaussianGLM <- spark.glm(gaussianDF, Sepal_Length ~ Sepal_Width + Species,
family = "gaussian")
+
+# Save and then load a fitted MLlib model
+modelPath <- tempfile(pattern = "ml", fileext = ".tmp")
+write.ml(gaussianGLM, modelPath)
+gaussianGLM2 <- read.ml(modelPath)
+
+# Check model summary
+summary(gaussianGLM2)
+
+# Check model prediction
+gaussianPredictions <- predict(gaussianGLM2, gaussianTestDF)
+showDF(gaussianPredictions)
+
+unlink(modelPath)
+# $example off:read_write$
+############################ fit models with spark.lapply
#####################################
+
+# Perform distributed training of multiple models with spark.lapply
+families <- c("gaussian", "poisson")
+train <- function(family) {
+ model <- glm(Sepal.Length ~ Sepal.Width + Species, iris, family = family)
+ summary(model)
+}
+model.summaries <- spark.lapply(families, train)
+
+# Print the summary of each model
+print(model.summaries)
+
+
--- End diff --
Extra blank line
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
