seenimohamed

JavaRDD<String> uniqueRDD = SparkUtils.getInstance().getSparkContext()
					.parallelize(Arrays.asList(Preprocessor.getInstance().getVocabulary()));

Map<Long, String> vocabMap = uniqueRDD.zipWithIndex().mapToPair(f -> f.swap()).collectAsMap();

JavaPairRDD<Long, Integer> dataPair = tfidf.select("tf").toJavaRDD().flatMapToPair( r -> {
	SparseVector vec = r.getAs(0);
	List<Tuple2<Long, Integer>> results = new ArrayList<>();
	for(int i : vec.indices()) {
		results.add(new Tuple2<Long, Integer>((long)i, (int) vec.apply(i)));

seenimohamed

	public static void main(String[] args) {
		int i = 10;
		while(--i > 0) {
			System.out.println(i);
			i = i%4;
		}
		
		while(i>0) {
			System.out.println(i);
			i--;

seenimohamed

Installing java in ubuntu 
Commands : 
sudo apt-get update
sudo apt-get install default-jre
sudo apt-get install default-jdk

https://www.digitalocean.com/community/tutorials/how-to-install-java-with-apt-get-on-ubuntu-16-04

seenimohamed

ls <options>

-l -> detailed view
S -> sort in decending order
r -> reverse


ls -lS  -> decending order
ls -lSr -> ascending order

seenimohamed

//to compile a java class
javac 

//to include jars in classpath
java -cp 

//to run jar
java -jar jarfile.jar

//to give args

seenimohamed

	private String getPredictedModule(List<Result> result) {
		Collector<Result, ?, Map<String, Double>> summarizeByModules = 
				Collectors.groupingBy(Result::getModule, Collectors.summingDouble(Result::getConfidence));
		Map<String, Double> finalMap = new LinkedHashMap<>();
		
	        result.stream().collect(summarizeByModules)
			.entrySet().stream().sorted(Map.Entry.<String, Double>comparingByValue()
                        .reversed()).forEachOrdered(e -> finalMap.put(e.getKey(), e.getValue()));
		return finalMap.keySet().stream().findFirst().get();
	}

seenimohamed

//to get key for single max value from map
Integer max=mapGroup.entrySet().stream().max(Map.Entry.comparingByValue()).get().getKey();

//to get keys for for getting all equivalent maximums
private List<Integer> testStreamMap(Map<Integer, Long> mapGroup) {
    if(mapGroup.isEmpty())
        return Collections.emptyList();
    long max = mapGroup.values().stream().max(Comparator.naturalOrder()).get();
    return mapGroup.entrySet().stream()
        .filter(e -> e.getValue() == max)

seenimohamed

public static CSVRecord convertToCSVRecord(String query, char delimiter) {
		try {
			Reader in = new StringReader(query);
			CSVParser parser = CSVFormat.newFormat(delimiter).parse(in);
			List<CSVRecord> recorder = parser.getRecords();
			return recorder.get(0);  //returning first element
		} catch (IOException e) {
			e.printStackTrace();
		}
		return null;

seenimohamed

from six.moves import urllib
import requests

def url_is_alive(url):
    """
    Checks that a given URL is reachable.
    :param url: A URL
    :rtype: bool
    """
    request = urllib.request.Request(url)

seenimohamed

#!/bin/sh

# Usage : move all mp4 files with removing extension

# Command to run : 
# ./move_all_files_with_diff_name.sh <source_folder> <destination_folder> 

# Command structure
# find . -name "*.mp4" 
# normal find command