corneliouzbett

spark = SparkSession.builder\
    .appName("Python Spark SQL basic example")\
    .config("spark.some.config.option", "")
    .getOrCreate()

corneliouzbett

from pyspark import SparkContext, SparkConf

if __name__ == "__main__":
    conf = SparkConf().setAppName("take").setMaster("local[*]")
    sc = SparkContext(conf = conf)
    
    inputWords = ["spark", "hadoop", "spark", "hive", "pig", "cassandra", "hadoop"]
    wordRdd = sc.parallelize(inputWords)
    
    words = wordRdd.take(3)

corneliouzbett

from pyspark import SparkContext, SparkConf

def display_words(words):
    for w, we in words.items():
        print("{} : {}".format(w, we))

if __name__ == "__main__":
    conf = SparkConf().setAppName("word count").setMaster("local[2]")
    sc = SparkContext(conf = conf)

dnetix

import org.json.JSONException;
import org.json.JSONObject;
import java.io.BufferedReader;
import java.io.DataOutputStream;
import java.io.FileNotFoundException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.Map;