blob: 04347057178b1d62fcdc509d98ed638e6544e758 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
#
# 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)
# 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 SparkDataFrame
df <- createDataFrame(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 <- read.json(path)
printSchema(peopleDF)
# root
# |-- age: long (nullable = true)
# |-- name: string (nullable = true)
# Register this DataFrame as a table.
createOrReplaceTempView(peopleDF, "people")
# SQL statements can be run by using the sql methods provided by sqlContext
teenagers <- sql("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()
|