【转+修正】在Windows和Rstudio下本地安装SparkR

            ?#（附一个例子）

?# Set the system environment variables

Sys.setenv(SPARK_HOME = "C:/Apache/spark-1.6.1")

.libPaths(c(file.path(Sys.getenv("SPARK_HOME"), "R", "lib"), .libPaths()))

            R的library地址可通过如下方式进行查看：

.libPaths()

默认情况下会将新的lib库安装在第一个地址中（默认地址）
        

            #load the Sparkr library

library(SparkR)

# Create a spark context and a SQL context

sc <- sparkR.init(master = "local")

sqlContext <- sparkRSQL.init(sc)

#create a sparkR DataFrame

DF <- createDataFrame(sqlContext, faithful)

head(DF)

# 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)

# 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()

# 另一个例子 wordcount--------------

# 来源 http://www.cnblogs.com/hseagle/p/3998853.html
sc <- sparkR.init(master="local", "RwordCount")

lines <- textFile(sc, "README.md")

                
                    ——————“textFile”函数从sparkR1.4之后就无法使用了，之后的sparkR必须通过SqlContext来加载数据，如下所示：
                
                
people <- read.df(sqlContext,
"./examples/src/main/resources/people.json", "json"
)
除此之外还支持csv、parquet、hive数据等等。

            
words <- flatMap(lines,

                 function(line) {

                   strsplit(line, "")[[1]]

                 })

wordCount <- lapply(words, function(word) { list(word, 1L) })

counts <- reduceByKey(wordCount, "+", 2L)

output <- collect(counts)

for (wordcount in output) {

  cat(wordcount[[1]], ": ", wordcount[[2]], "\n")

}