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;

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)

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

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

corneliouzbett

sc = spark.sparkContext

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

# The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
# root

corneliouzbett

 // Create the dataframe
 val df = Seq("Red", "Green", "Blue").map(Tuple1.apply).toDF("color")
 df.createOrReplaceTempView("data")
 val df4 = sql(""" select *, case when color = 'green' then 1 else 0 end as Green_ind from data """)
 df4.show()




   df4:org.apache.spark.sql.DataFrame = [color: string, Green_ind: integer]

corneliouzbett

<?xml version="1.0" encoding="utf-8"?>
<resources>
    <color name="colorPrimary">#008577</color>
    <color name="colorPrimaryDark">#00574B</color>
    <color name="colorAccent">#FBC02D</color>
</resources>

corneliouzbett

version: '3'
services:
  postgres:
    image: postgres:9.6
    environment:
      - POSTGRES_USER=airflow
      - POSTGRES_PASSWORD=airflow
      - POSTGRES_DB=airflow
    ports:
      - "5432:5432"

corneliouzbett

def shared_locations(self):
        """
        A dictionary of shared locations whose keys are in the set 'prefix',
        'purelib', 'platlib', 'scripts', 'headers', 'data' and 'namespace'.
        The corresponding value is the absolute path of that category for
        this distribution, and takes into account any paths selected by the
        user at installation time (e.g. via command-line arguments). In the
        case of the 'namespace' key, this would be a list of absolute paths
        for the roots of namespace packages in this distribution.

corneliouzbett

public class Scheduler {
   @Scheduled(fixedDelay = 1000, initialDelay = 3000)
   public void fixedDelaySch() {
      SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
      Date now = new Date();
      String strDate = sdf.format(now);
      System.out.println("Fixed Delay scheduler:: " + strDate);
   }
}