import org.apache.spark.sql.SparkSession

val spark = SparkSession
  .builder()
  .appName("Spark SQL basic example")
  .config("spark.some.config.option", "some-value")
  .getOrCreate()

// For implicit conversions like converting RDDs to DataFrames
import spark.implicits._

val df = spark.read.json("examples/src/main/resources/people.json")

// Displays the content of the DataFrame to stdout
df.show()
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

// This import is needed to use the $-notation
import spark.implicits._
// Print the schema in a tree format
df.printSchema()
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)

// Select only the "name" column
df.select("name").show()
// +-------+
// |   name|
// +-------+
// |Michael|
// |   Andy|
// | Justin|
// +-------+

// Select everybody, but increment the age by 1
df.select($"name", $"age" + 1).show()
// +-------+---------+
// |   name|(age + 1)|
// +-------+---------+
// |Michael|     null|
// |   Andy|       31|
// | Justin|       20|
// +-------+---------+

// Select people older than 21
df.filter($"age" > 21).show()
// +---+----+
// |age|name|
// +---+----+
// | 30|Andy|
// +---+----+

// Count people by age
df.groupBy("age").count().show()
// +----+-----+
// | age|count|
// +----+-----+
// |  19|    1|
// |null|    1|
// |  30|    1|
// +----+-----+

// Register the DataFrame as a SQL temporary view
df.createOrReplaceTempView("people")

val sqlDF = spark.sql("SELECT * FROM people")
sqlDF.show()
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

// Register the DataFrame as a global temporary view
df.createGlobalTempView("people")

// Global temporary view is tied to a system preserved database `global_temp`
spark.sql("SELECT * FROM global_temp.people").show()
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

// Global temporary view is cross-session
spark.newSession().sql("SELECT * FROM global_temp.people").show()
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

// Note: Case classes in Scala 2.10 can support only up to 22 fields. To work around this limit,
// you can use custom classes that implement the Product interface
case class Person(name: String, age: Long)

// Encoders are created for case classes
val caseClassDS = Seq(Person("Andy", 32)).toDS()
caseClassDS.show()
// +----+---+
// |name|age|
// +----+---+
// |Andy| 32|
// +----+---+

// Encoders for most common types are automatically provided by importing spark.implicits._
val primitiveDS = Seq(1, 2, 3).toDS()
primitiveDS.map(_ + 1).collect() // Returns: Array(2, 3, 4)

// DataFrames can be converted to a Dataset by providing a class. Mapping will be done by name
val path = "examples/src/main/resources/people.json"
val peopleDS = spark.read.json(path).as[Person]
peopleDS.show()
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

// For implicit conversions from RDDs to DataFrames
import spark.implicits._

// Create an RDD of Person objects from a text file, convert it to a Dataframe
val peopleDF = spark.sparkContext
  .textFile("examples/src/main/resources/people.txt")
  .map(_.split(","))
  .map(attributes => Person(attributes(0), attributes(1).trim.toInt))
  .toDF()
// Register the DataFrame as a temporary view
peopleDF.createOrReplaceTempView("people")

// SQL statements can be run by using the sql methods provided by Spark
val teenagersDF = spark.sql("SELECT name, age FROM people WHERE age BETWEEN 13 AND 19")

// The columns of a row in the result can be accessed by field index
teenagersDF.map(teenager => "Name: " + teenager(0)).show()
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

// or by field name
teenagersDF.map(teenager => "Name: " + teenager.getAs[String]("name")).show()
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

// No pre-defined encoders for Dataset[Map[K,V]], define explicitly
implicit val mapEncoder = org.apache.spark.sql.Encoders.kryo[Map[String, Any]]
// Primitive types and case classes can be also defined as
// implicit val stringIntMapEncoder: Encoder[Map[String, Any]] = ExpressionEncoder()

// row.getValuesMap[T] retrieves multiple columns at once into a Map[String, T]
teenagersDF.map(teenager => teenager.getValuesMap[Any](List("name", "age"))).collect()
// Array(Map("name" -> "Justin", "age" -> 19))

import org.apache.spark.sql.types._

// Create an RDD
val peopleRDD = spark.sparkContext.textFile("examples/src/main/resources/people.txt")

// The schema is encoded in a string
val schemaString = "name age"

// Generate the schema based on the string of schema
val fields = schemaString.split(" ")
  .map(fieldName => StructField(fieldName, StringType, nullable = true))
val schema = StructType(fields)

// Convert records of the RDD (people) to Rows
val rowRDD = peopleRDD
  .map(_.split(","))
  .map(attributes => Row(attributes(0), attributes(1).trim))

// Apply the schema to the RDD
val peopleDF = spark.createDataFrame(rowRDD, schema)

// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")

// SQL can be run over a temporary view created using DataFrames
val 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
results.map(attributes => "Name: " + attributes(0)).show()
// +-------------+
// |        value|
// +-------------+
// |Name: Michael|
// |   Name: Andy|
// | Name: Justin|
// +-------------+

import org.apache.spark.sql.expressions.MutableAggregationBuffer
import org.apache.spark.sql.expressions.UserDefinedAggregateFunction
import org.apache.spark.sql.types._
import org.apache.spark.sql.Row
import org.apache.spark.sql.SparkSession

object MyAverage extends UserDefinedAggregateFunction {
  // Data types of input arguments of this aggregate function
  def inputSchema: StructType = StructType(StructField("inputColumn", LongType) :: Nil)
  // Data types of values in the aggregation buffer
  def bufferSchema: StructType = {
    StructType(StructField("sum", LongType) :: StructField("count", LongType) :: Nil)
  }
  // The data type of the returned value
  def dataType: DataType = DoubleType
  // Whether this function always returns the same output on the identical input
  def deterministic: Boolean = true
  // Initializes the given aggregation buffer. The buffer itself is a `Row` that in addition to
  // standard methods like retrieving a value at an index (e.g., get(), getBoolean()), provides
  // the opportunity to update its values. Note that arrays and maps inside the buffer are still
  // immutable.
  def initialize(buffer: MutableAggregationBuffer): Unit = {
    buffer(0) = 0L
    buffer(1) = 0L
  }
  // Updates the given aggregation buffer `buffer` with new input data from `input`
  def update(buffer: MutableAggregationBuffer, input: Row): Unit = {
    if (!input.isNullAt(0)) {
      buffer(0) = buffer.getLong(0) + input.getLong(0)
      buffer(1) = buffer.getLong(1) + 1
    }
  }
  // Merges two aggregation buffers and stores the updated buffer values back to `buffer1`
  def merge(buffer1: MutableAggregationBuffer, buffer2: Row): Unit = {
    buffer1(0) = buffer1.getLong(0) + buffer2.getLong(0)
    buffer1(1) = buffer1.getLong(1) + buffer2.getLong(1)
  }
  // Calculates the final result
  def evaluate(buffer: Row): Double = buffer.getLong(0).toDouble / buffer.getLong(1)
}

// Register the function to access it
spark.udf.register("myAverage", MyAverage)

val df = spark.read.json("examples/src/main/resources/employees.json")
df.createOrReplaceTempView("employees")
df.show()
// +-------+------+
// |   name|salary|
// +-------+------+
// |Michael|  3000|
// |   Andy|  4500|
// | Justin|  3500|
// |  Berta|  4000|
// +-------+------+

val result = spark.sql("SELECT myAverage(salary) as average_salary FROM employees")
result.show()
// +--------------+
// |average_salary|
// +--------------+
// |        3750.0|
// +--------------+

import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.Encoder
import org.apache.spark.sql.Encoders
import org.apache.spark.sql.SparkSession

case class Employee(name: String, salary: Long)
case class Average(var sum: Long, var count: Long)

object MyAverage extends Aggregator[Employee, Average, Double] {
  // A zero value for this aggregation. Should satisfy the property that any b + zero = b
  def zero: Average = Average(0L, 0L)
  // Combine two values to produce a new value. For performance, the function may modify `buffer`
  // and return it instead of constructing a new object
  def reduce(buffer: Average, employee: Employee): Average = {
    buffer.sum += employee.salary
    buffer.count += 1
    buffer
  }
  // Merge two intermediate values
  def merge(b1: Average, b2: Average): Average = {
    b1.sum += b2.sum
    b1.count += b2.count
    b1
  }
  // Transform the output of the reduction
  def finish(reduction: Average): Double = reduction.sum.toDouble / reduction.count
  // Specifies the Encoder for the intermediate value type
  def bufferEncoder: Encoder[Average] = Encoders.product
  // Specifies the Encoder for the final output value type
  def outputEncoder: Encoder[Double] = Encoders.scalaDouble
}

val ds = spark.read.json("examples/src/main/resources/employees.json").as[Employee]
ds.show()
// +-------+------+
// |   name|salary|
// +-------+------+
// |Michael|  3000|
// |   Andy|  4500|
// | Justin|  3500|
// |  Berta|  4000|
// +-------+------+

// Convert the function to a `TypedColumn` and give it a name
val averageSalary = MyAverage.toColumn.name("average_salary")
val result = ds.select(averageSalary)
result.show()
// +--------------+
// |average_salary|
// +--------------+
// |        3750.0|
// +--------------+

val usersDF = spark.read.load("examples/src/main/resources/users.parquet")
usersDF.select("name", "favorite_color").write.save("namesAndFavColors.parquet")

val peopleDF = spark.read.format("json").load("examples/src/main/resources/people.json")
peopleDF.select("name", "age").write.format("parquet").save("namesAndAges.parquet")

val sqlDF = spark.sql("SELECT * FROM parquet.`examples/src/main/resources/users.parquet`")

peopleDF.write.bucketBy(42, "name").sortBy("age").saveAsTable("people_bucketed")

usersDF.write.partitionBy("favorite_color").format("parquet").save("namesPartByColor.parquet")

peopleDF
  .write
  .partitionBy("favorite_color")
  .bucketBy(42, "name")
  .saveAsTable("people_partitioned_bucketed")

// Encoders for most common types are automatically provided by importing spark.implicits._
import spark.implicits._

val peopleDF = spark.read.json("examples/src/main/resources/people.json")

// DataFrames can be saved as Parquet files, maintaining the schema information
peopleDF.write.parquet("people.parquet")

// Read in the parquet file created above
// Parquet files are self-describing so the schema is preserved
// The result of loading a Parquet file is also a DataFrame
val parquetFileDF = spark.read.parquet("people.parquet")

// Parquet files can also be used to create a temporary view and then used in SQL statements
parquetFileDF.createOrReplaceTempView("parquetFile")
val namesDF = spark.sql("SELECT name FROM parquetFile WHERE age BETWEEN 13 AND 19")
namesDF.map(attributes => "Name: " + attributes(0)).show()
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

// This is used to implicitly convert an RDD to a DataFrame.
import spark.implicits._

// Create a simple DataFrame, store into a partition directory
val squaresDF = spark.sparkContext.makeRDD(1 to 5).map(i => (i, i * i)).toDF("value", "square")
squaresDF.write.parquet("data/test_table/key=1")

// Create another DataFrame in a new partition directory,
// adding a new column and dropping an existing column
val cubesDF = spark.sparkContext.makeRDD(6 to 10).map(i => (i, i * i * i)).toDF("value", "cube")
cubesDF.write.parquet("data/test_table/key=2")

// Read the partitioned table
val mergedDF = spark.read.option("mergeSchema", "true").parquet("data/test_table")
mergedDF.printSchema()

// The final schema consists of all 3 columns in the Parquet files together
// with the partitioning column appeared in the partition directory paths
// root
//  |-- value: int (nullable = true)
//  |-- square: int (nullable = true)
//  |-- cube: int (nullable = true)
//  |-- key: int (nullable = true)

// Primitive types (Int, String, etc) and Product types (case classes) encoders are
// supported by importing this when creating a Dataset.
import spark.implicits._

// A JSON dataset is pointed to by path.
// The path can be either a single text file or a directory storing text files
val path = "examples/src/main/resources/people.json"
val peopleDF = spark.read.json(path)

// The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
// root
//  |-- age: long (nullable = true)
//  |-- name: string (nullable = true)

// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")

// SQL statements can be run by using the sql methods provided by spark
val teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
// +------+
// |  name|
// +------+
// |Justin|
// +------+

// Alternatively, a DataFrame can be created for a JSON dataset represented by
// a Dataset[String] storing one JSON object per string
val otherPeopleDataset = spark.createDataset(
  """{"name":"Yin","address":{"city":"Columbus","state":"Ohio"}}""" :: Nil)
val otherPeople = spark.read.json(otherPeopleDataset)
otherPeople.show()
// +---------------+----+
// |        address|name|
// +---------------+----+
// |[Columbus,Ohio]| Yin|
// +---------------+----+

import java.io.File

import org.apache.spark.sql.Row
import org.apache.spark.sql.SparkSession

case class Record(key: Int, value: String)

// warehouseLocation points to the default location for managed databases and tables
val warehouseLocation = new File("spark-warehouse").getAbsolutePath

val spark = SparkSession
  .builder()
  .appName("Spark Hive Example")
  .config("spark.sql.warehouse.dir", warehouseLocation)
  .enableHiveSupport()
  .getOrCreate()

import spark.implicits._
import spark.sql

sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive")
sql("LOAD DATA LOCAL INPATH ‘examples/src/main/resources/kv1.txt‘ INTO TABLE src")

// Queries are expressed in HiveQL
sql("SELECT * FROM src").show()
// +---+-------+
// |key|  value|
// +---+-------+
// |238|val_238|
// | 86| val_86|
// |311|val_311|
// ...

// Aggregation queries are also supported.
sql("SELECT COUNT(*) FROM src").show()
// +--------+
// |count(1)|
// +--------+
// |    500 |
// +--------+

// The results of SQL queries are themselves DataFrames and support all normal functions.
val sqlDF = sql("SELECT key, value FROM src WHERE key < 10 ORDER BY key")

// The items in DataFrames are of type Row, which allows you to access each column by ordinal.
val stringsDS = sqlDF.map {
  case Row(key: Int, value: String) => s"Key: $key, Value: $value"
}
stringsDS.show()
// +--------------------+
// |               value|
// +--------------------+
// |Key: 0, Value: val_0|
// |Key: 0, Value: val_0|
// |Key: 0, Value: val_0|
// ...

// You can also use DataFrames to create temporary views within a SparkSession.
val recordsDF = spark.createDataFrame((1 to 100).map(i => Record(i, s"val_$i")))
recordsDF.createOrReplaceTempView("records")

// Queries can then join DataFrame data with data stored in Hive.
sql("SELECT * FROM records r JOIN src s ON r.key = s.key").show()
// +---+------+---+------+
// |key| value|key| value|
// +---+------+---+------+
// |  2| val_2|  2| val_2|
// |  4| val_4|  4| val_4|
// |  5| val_5|  5| val_5|
// ...

// Note: JDBC loading and saving can be achieved via either the load/save or jdbc methods
// Loading data from a JDBC source
val jdbcDF = spark.read
  .format("jdbc")
  .option("url", "jdbc:postgresql:dbserver")
  .option("dbtable", "schema.tablename")
  .option("user", "username")
  .option("password", "password")
  .load()

val connectionProperties = new Properties()
connectionProperties.put("user", "username")
connectionProperties.put("password", "password")
val jdbcDF2 = spark.read
  .jdbc("jdbc:postgresql:dbserver", "schema.tablename", connectionProperties)

// Saving data to a JDBC source
jdbcDF.write
  .format("jdbc")
  .option("url", "jdbc:postgresql:dbserver")
  .option("dbtable", "schema.tablename")
  .option("user", "username")
  .option("password", "password")
  .save()

jdbcDF2.write
  .jdbc("jdbc:postgresql:dbserver", "schema.tablename", connectionProperties)

// Specifying create table column data types on write
jdbcDF.write
  .option("createTableColumnTypes", "name CHAR(64), comments VARCHAR(1024)")
  .jdbc("jdbc:postgresql:dbserver", "schema.tablename", connectionProperties)