Developing Dataframe__java in the IDE using Java and Scala

The

Java version code is as follows:

Import org.apache.spark.SparkConf;
Import Org.apache.spark.SparkContext;
Import Org.apache.spark.sql.DataFrame;

Import Org.apache.spark.sql.SQLContext; /** * Use Java to combat dataframe Operations/public class Dataframeops {public static void main (string[) args) {//Create
                Sparkconf is used to read system configuration information and set the name of the current application sparkconf conf = new sparkconf (). Setmaster ("local")
        . Setappname ("Dataframeops");
        Create a Javasparkcontext object instance as the core cornerstone of the entire driver Sparkcontext sc = new Sparkcontext (conf);

        Create a SqlContext context object for SQL analysis SqlContext sqlcontext = new SqlContext (SC);
        To create a dataframe, you can simply think of dataframe as a table.

        Dataframe df = Sqlcontext.read (). JSON ("E://people.json");

        SELECT * FROM table Df.show ();

        Desc table Df.printschema ();

        Select name from table df.select (' name '). Show ();
        Select Name,age + 1 from tables; Df.select (Df.col ("name"), Df.col ("age").

        SELECT * FROM table where age > Df.filter (Df.col (' age '). GT (). Show ();
    Select COUNT (1) from table group by age Df.groupby (Df.col (' age '). Count (). Show (); }

}

Scala version;

Import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
Import Org.apache.spark.sql.SQLContext

Object Dataframeops {
  def main (args:array[string]): unit={
    val conf = new Sparkconf (). Setmaster ("local"). Setappname ("Dataframeops")
    val sc = new Sparkcontext (conf)

    val SqlContext = New SqlContext (SC)

    val df = SqlContext.read.json ("E://people.json")

    df.show ()
    Df.printschema (
    ) Df.select ("name"). Show ()
    Df.select (Df.col ("name"), Df.col (' age '). Show ()
    Df.filter (Df.col (" Age "). A. Show ()
    df.groupby (Df.col (' age ')). Count (). Show ()