http://spark.apache.org/docs/latest/sql-getting-started.html
建立spark
import org.apache.spark.sql.SparkSession;
SparkSession spark = SparkSession
.builder()
.appName("Java Spark SQL basic example")
.config("spark.some.config.option", "some-value")
.getOrCreate();
列简单计算 + 强制类型转换
df.select(col("name"), col("age").plus(1)).show();
Dataset<Row> covData = spark.read()
.jdbc(dbUrl, TABLE, connectionProperties)
.select("sta, "dev", "r", "ts")
.withColumn("tm", col("ts").divide(60))
.cast(DataTypes.IntegerType));
类实例 转 dataset
Encoder<Person> personEncoder = Encoders.bean(Person.class);
Dataset<Person> javaBeanDS = spark.createDataset(
Collections.singletonList(person),
personEncoder
);
javaRDD 转 dataset
Dataset<Row> devData = spark.createDataFrame(covDataRdd, SingleInspectResult.class)
简单map操作+javaRDD转Dataset
JavaRDD<Person> peopleRDD = spark.read()
.textFile("examples/src/main/resources/people.txt")
.javaRDD()
.map(line -> {
String[] parts = line.split(",");
Person person = new Person();
person.setName(parts[0]);
person.setAge(Integer.parseInt(parts[1].trim()));
return person;
});
Dataset<Row> peopleDF = spark.createDataFrame(peopleRDD, Person.class);
map复杂MapFunction<Row,String>操作(入Row出String) ,类型加索引 和 类型加名字 两种方式
Dataset<Row> teenagersDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19");
// The columns of a row in the result can be accessed by field index
Encoder<String> stringEncoder = Encoders.STRING();
Dataset<String> teenagerNamesByIndexDF = teenagersDF.map(
(MapFunction<Row, String>) row -> "Name: " + row.getString(0),
stringEncoder);
// or by field name
Dataset<String> teenagerNamesByFieldDF = teenagersDF.map(
(MapFunction<Row, String>) row -> "Name: " + row.<String>getAs("name"),
stringEncoder);
简单操作示例(解析文本数据集)
1,创建RDD
2,创建structType
3,应用structType到RDD上
import java.util.ArrayList;
import java.util.List;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
// Create an RDD
JavaRDD<String> peopleRDD = spark.sparkContext()
.textFile("examples/src/main/resources/people.txt", 1)
.toJavaRDD();
// The schema is encoded in a string
String schemaString = "name age";
// Generate the schema based on the string of schema
List<StructField> fields = new ArrayList<>();
for (String fieldName : schemaString.split(" ")) {
StructField field = DataTypes.createStructField(fieldName, DataTypes.StringType, true);
fields.add(field);
}
StructType schema = DataTypes.createStructType(fields);
// Convert records of the RDD (people) to Rows
JavaRDD<Row> rowRDD = peopleRDD.map((Function<String, Row>) record -> {
String[] attributes = record.split(",");
return RowFactory.create(attributes[0], attributes[1].trim());
});
// Apply the schema to the RDD
Dataset<Row> peopleDataFrame = spark.createDataFrame(rowRDD, schema);
// Creates a temporary view using the DataFrame
peopleDataFrame.createOrReplaceTempView("people");
// SQL can be run over a temporary view created using DataFrames
Dataset<Row> results = spark.sql("SELECT name FROM people");
// The results of SQL queries are DataFrames and support all the normal RDD operations
// The columns of a row in the result can be accessed by field index or by field name
Dataset<String> namesDS = results.map(
(MapFunction<Row, String>) row -> "Name: " + row.getString(0),
Encoders.STRING());
namesDS.show();
// +-------------+
// | value|
// +-------------+
// |Name: Michael|
// | Name: Andy|
// | Name: Justin|
// +-------------+