1、从json文件创建dataFrame
val df: DataFrame = sqlContext.read.json("hdfs://master:9000/user/spark/data/people.json")
val people = df.registerTempTable("person")
val teenegers: DataFrame = sqlContext.sql("select name,age from person")
teenegers.map(x => "name:" + x(0)+ " " + "age:" + x(1)).collect().foreach(println)
2、从parquet文件创建dataFrame
val df: DataFrame = sqlContext.read.parquet("hdfs://master:9000/user/spark/data/namesAndAges.parquet")
val people = df.registerTempTable("person")
val teenegers: DataFrame = sqlContext.sql("select name,age from person")
teenegers.map(x => "name:" + x(0)+ " " + "age:" + x(1)).collect().foreach(println)
3、从普通RDD创建dataFrame_1
val people = sc.textFile("hdfs://master:9000/user/spark/data/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)).toDF
people.registerTempTable("people")
val teenagers = sqlContext.sql("select name,age from people")
teenagers.map(x => "name:" + x(0)+ " " + "age:" + x(1)).collect().foreach(println)
4、从普通RDD创建dataFrame_2
val people = sc.textFile("hdfs://master:9000/user/spark/data/people.txt")
val schemaString = "name age"
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.{StructType,StructField,StringType}
val schema = StructType(schemaString.split(" ").map(fieldName => StructField(fieldName,StringType,true)))
val rowRDD = people.map(_.split(",")).map(x => Row(x(0),x(1).trim))
val df: DataFrame = sqlContext.createDataFrame(rowRDD,schema)
df.registerTempTable("people")val teenagers = sqlContext.sql("select name,age from people")
teenagers.map(x => "name:" + x(0)+ " " + "age:" + x(1)).collect().foreach(println)
5、测试dataframe的read和save方法（注意load方法默认是加载parquet文件）
val df = sqlContext.read.load("hdfs://master:9000/user/spark/data/namesAndAges.parquet")
df.select("name").write.save("hdfs://master:9000/user/spark/data/name.parquet")
6、测试dataframe的read和save方法（可通过手动设置数据源和保存测mode）
val df =sqlContext.read.format("json").load("hdfs://master:9000/user/spark/ data/people.json")
df.select("age").write.format("parquet").mode(SaveMode.Append).save("hdfs://master:9000/user/spark/data/ages.parquet")
7、直接使用sql查询数据源
val df = sqlContext.sql("SELECT * FROM parquet.`hdfs://master:9000/user/spark/data/ages.parquet`")
df.map(x => "name:" + x(0)).foreach(println)
8、parquest文件的读写
val people = sc.textFile("hdfs://master:9000/user/spark/data/people.txt").toDF
people.write.mode(SaveMode.Overwrite).parquet("hdfs://master:9000/user/spark/data/people.parquet")
val parquetFile = sqlContext.read.parquet("hdfs://master:9000/user/spark/data/people.parquet")
parquetFile.registerTempTable("parquetFile")
val teenagers = sqlContext.sql("SELECT name FROM parquetFile")
teenagers.map(t => "Name: " + t(0)).collect().foreach(println)
9、Schema Merging
val df1 = sc.makeRDD(1 to 5).map(i => (i, i * 2)).toDF("single", "double")
df1.write.mode(SaveMode.Overwrite).parquet("hdfs://master:9000/user/spark/data/test_table/key=1")
df2 = sc.makeRDD(6 to 10).map(i => (i, i * 3)).toDF("single", "triple")
df2.write.mode(SaveMode.Overwrite).parquet("hdfs://master:9000/user/spark/data/test_table/key=2")
df3 = sqlContext.read.option("mergeSchema", "true").parquet("hdfs://master:9000/user/spark/data/test_table")
df3.printSchema()
df3.show()
10、hive metastore
val sqlContext = new HiveContext(sc)sqlContext.setConf("spark.sql.shuffle.partitions","5")
sqlContext.sql("use my_hive")
sqlContext.sql("create table if not exists sogouInfo (time STRING,id STRING,webAddr STRING,downFlow INT,upFlow INT,url STRING) row format delimited fields terminated by '\t'")
sqlContext.sql("LOAD DATA LOCAL INPATH '/root/testData/SogouQ1.txt' overwrite INTO TABLE sogouInfo")
sqlContext.sql("select " +"count(distinct id) as c " +"from sogouInfo " +"group by time order by c desc limit 10").collect().foreach(println)
11、df from jdbc eg:mysql
val sqlContext = new SQLContext(sc)
val jdbcDF = sqlContext.read.format("jdbc").options(Map("driver" -> "com.mysql.jdbc.Driver","url" -> "jdbc:mysql://192.168.0.65:3306/test?user=root&password=root","dbtable" -> "trade_total_info_copy")).load()
jdbcDF.registerTempTable("trade_total_info_copy")
sqlContext.sql("select * from trade_total_info_copy").foreach(println)
