Skip to content

Instantly share code, notes, and snippets.

@Pragith
Created June 26, 2015 19:19
Show Gist options
  • Save Pragith/a1e8c09268725f38641d to your computer and use it in GitHub Desktop.
Save Pragith/a1e8c09268725f38641d to your computer and use it in GitHub Desktop.
SparkR Example 2
#
# 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.
#
Sys.setenv(SPARK_HOME="/home/pragith/spark")
Sys.setenv('SPARKR_SUBMIT_ARGS'='"--packages" "com.databricks:spark-csv_2.10:1.0.3" "sparkr-shell"')
library(SparkR)
# Initialize SparkContext and SQLContext
sc <- sparkR.init(appName="SparkR-DataFrame-example")
sqlContext <- sparkRSQL.init(sc)
# Create a simple local data.frame
localDF <- data.frame(name=c("John", "Smith", "Sarah"), age=c(19, 23, 18))
# Convert local data frame to a SparkR DataFrame
df <- createDataFrame(sqlContext, localDF)
# Print its schema
printSchema(df)
# root
# |-- name: string (nullable = true)
# |-- age: double (nullable = true)
# Create a DataFrame from a JSON file
path <- file.path(Sys.getenv("SPARK_HOME"), "examples/src/main/resources/people.json")
peopleDF <- jsonFile(sqlContext, path)
printSchema(peopleDF)
showDF(peopleDF)
# Register this DataFrame as a table.
registerTempTable(peopleDF, "people")
# SQL statements can be run by using the sql methods provided by sqlContext
teenagers <- sql(sqlContext, "SELECT name FROM people WHERE age >= 13 AND age <= 19")
# Call collect to get a local data.frame
teenagersLocalDF <- collect(teenagers)
# Print the teenagers in our dataset
print(teenagersLocalDF)
# Stop the SparkContext now
sparkR.stop()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment