Github user shivaram commented on a diff in the pull request: https://github.com/apache/spark/pull/14082#discussion_r70122361 --- Diff: examples/src/main/r/RSparkSQLExample.R --- @@ -0,0 +1,198 @@ +# +# 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(SparkR) + +# $example on:init_session$ +sparkR.session() +# $example off:init_session$ + + +# $example on:create_DataFrames$ +df <- read.json("examples/src/main/resources/people.json") + +# Displays the content of the DataFrame +head(df) + +# Another method to print the first few rows and optionally truncate the printing of long values +head(df) +# $example off:create_DataFrames$ + + +# $example on:dataframe_operations$ +# Create the DataFrame +df <- read.json("examples/src/main/resources/people.json") + +# Show the content of the DataFrame +head(df) +## age name +## null Michael +## 30 Andy +## 19 Justin + +# Print the schema in a tree format +printSchema(df) +## root +## |-- age: long (nullable = true) +## |-- name: string (nullable = true) + +# Select only the "name" column +head(select(df, "name")) +## name +## Michael +## Andy +## Justin + +# Select everybody, but increment the age by 1 +head(select(df, df$name, df$age + 1)) +## name (age + 1) +## Michael null +## Andy 31 +## Justin 20 + +# Select people older than 21 +head(where(df, df$age > 21)) +## age name +## 30 Andy + +# Count people by age +head(count(groupBy(df, "age"))) +## age count +## null 1 +## 19 1 +## 30 1 +# $example off:dataframe_operations$ + + +# Create a DataFrame from json file +path <- file.path(Sys.getenv("SPARK_HOME"), "examples/src/main/resources/people.json") +peopleDF <- read.json(path) +# Register this DataFrame as a table. +createOrReplaceTempView(peopleDF, "table") +# $example on:sql_query$ +df <- sql("SELECT * FROM table") +# $example off:sql_query$ + + +# $example on:source_parquet$ +df <- read.df("examples/src/main/resources/users.parquet") +write.df(select(df, "name", "favorite_color"), "namesAndFavColors.parquet") +# $example off:source_parquet$ + + +# $example on:source_json$ +df <- read.df("examples/src/main/resources/people.json", "json") +write.df(select(df, "name", "age"), "namesAndAges.parquet", "parquet") --- End diff -- I have slight preference to be more verbose and write this as `write.df(..., source = "parquet")`
--- 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