diff --git a/clustering/KMeans.java b/clustering/KMeans.java
new file mode 100644
index 0000000..69d8f17
--- /dev/null
+++ b/clustering/KMeans.java
@@ -0,0 +1,112 @@
+package clustering;
+import java.util.ArrayList;
+import java.util.List;
+import helperClasses.DataPoint;
+import helperClasses.Serialization;
+
+public class KMeans {
+	static int K = 3;
+	public List<Double> means = new ArrayList<Double>();
+	public List<List<DataPoint>> clusters = new ArrayList<List<DataPoint>>();
+	
+	public void importClusterData(){
+		ArrayList<List<DataPoint>> c = null;
+		Serialization S = new Serialization();
+		clusters = S.clustDeserialize(c, "kMeansClusterData.ser");
+	}
+	
+	public double getClusterMean(int current){
+		double sum = 0, mean=clusters.get(current).get(0).x;
+		for(int i=1; i<clusters.get(current).size(); i++)
+			sum = sum + clusters.get(current).get(i).x;
+		mean = sum / (clusters.get(current).size()-1);
+		return mean;
+	}
+	
+	public List<List<DataPoint>> reviseClusters(){
+		for(int i=0; i<K; i++){
+			for(int j=1; j<clusters.get(i).size(); j++){
+				int current = i;
+				int closest = searchClosestCluster(clusters.get(current).get(j));
+				if(closest == current){
+					continue;
+				}
+				else{
+					DataPoint toBeTransferred = clusters.get(current).remove(j);
+					clusters.get(current).get(0).x = getClusterMean(current);
+					updateCluster(toBeTransferred, closest);
+				}
+			}
+		}
+		
+		return clusters;
+	}
+	
+	public void updateCluster(DataPoint newData, int closest){
+		//Initial means for 3 clusters. Not really useful after the first execution. Change the mean values by uncommenting.
+		/*means.add(3.0);
+		means.add(4.0);
+		means.add(6.0);
+		for(int i=0; i<K; i++){
+			clusters.add(new ArrayList<DataPoint>());
+		}
+		for(int i=0; i<K; i++){
+			clusters.get(i).add(new DataPoint(means.get(i)));
+		}*/
+
+		clusters.get(closest).add(newData);
+		clusters.get(closest).get(0).x = getClusterMean(closest);
+		
+		clusters = reviseClusters();
+		
+		Serialization S = new Serialization();
+		S.clustSerialize(clusters, "kMeansClusterData.ser");
+	}
+	
+	public void dispayClusterData(){
+		ArrayList<List<DataPoint>> c = null;
+		Serialization S = new Serialization();
+		c = S.clustDeserialize(c, "kMeansClusterData.ser");
+		System.out.println("Clusters : ");
+		for(int i=0; i<K; i++){
+			System.out.print("[");
+			for(int j=1; j<c.get(i).size(); j++){
+				System.out.print(c.get(i).get(j).x+", ");
+			}
+			System.out.println("]\tMean = "+c.get(i).get(0).x);
+		}
+	}
+	
+	public int searchClosestCluster(DataPoint input){
+		double min = Math.abs(input.x - clusters.get(0).get(0).x);
+		int closest = 0;
+		for(int i=1; i<K; i++){
+			if(Math.abs(input.x - clusters.get(i).get(0).x) < min){
+				min = Math.abs(input.x - clusters.get(i).get(0).x);
+				closest = i;
+				continue;
+			}
+		}
+		
+		return closest;
+	}
+	
+	
+	public static void main(String[] args) {
+		// TODO Auto-generated method stub
+		KMeans sol = new KMeans();
+		sol.importClusterData();
+	    
+		int closest=-1;
+		DataPoint input = new DataPoint(25);
+		closest = sol.searchClosestCluster(input);
+		
+		System.out.println("Closest : "+closest);
+		System.out.println("\n\n\t***********Updated Cluster Data************\t");
+		sol.updateCluster(input, closest);
+		sol.dispayClusterData();
+		
+		
+	}
+
+}
\ No newline at end of file
diff --git a/clustering/info b/clustering/info
new file mode 100644
index 0000000..29ba171
--- /dev/null
+++ b/clustering/info
@@ -0,0 +1,2 @@
+It is a package that contains modules that are used to implement clustering algorithms.
+You will find the respective ".ser" files in the main(outermost) folder.
diff --git a/kMeansClusterData.ser b/kMeansClusterData.ser
new file mode 100644
index 0000000..06916c2
Binary files /dev/null and b/kMeansClusterData.ser differ
diff --git a/knnTrainingData.ser b/knnTrainingData.ser
new file mode 100644
index 0000000..41229ce
Binary files /dev/null and b/knnTrainingData.ser differ
diff --git a/linRegTrainingData.ser b/linRegTrainingData.ser
new file mode 100644
index 0000000..3ace5e5
Binary files /dev/null and b/linRegTrainingData.ser differ
diff --git a/logRegTrainingData.ser b/logRegTrainingData.ser
new file mode 100644
index 0000000..db44225
Binary files /dev/null and b/logRegTrainingData.ser differ
diff --git a/nbcTrainingData.ser b/nbcTrainingData.ser
new file mode 100644
index 0000000..39cc18b
Binary files /dev/null and b/nbcTrainingData.ser differ
diff --git a/notebooks/Shared/BYOD_POC.py b/notebooks/Shared/BYOD_POC.py
new file mode 100644
index 0000000..e10357d
--- /dev/null
+++ b/notebooks/Shared/BYOD_POC.py
@@ -0,0 +1,17 @@
+# Databricks notebook source
+from pyspark import SparkContext
+from pyspark import SQLContext
+from pyspark.sql.functions import *
+target_query="SELECT * from databse_name.byod_dbfs_table"
+sparkContext = SparkContext.getOrCreate()
+sqlContext = SQLContext(sparkContext)
+dataframe = sqlContext.sql(target_query)
+dataframe.repartition(1).write.format('com.databricks.spark.csv').options(delimiter=",").save("s3n://amgen-edl-acux-aaaa123-bkt/BYOD/", header="true", mode="overwrite")
+
+# COMMAND ----------
+
+print "test2"
+
+# COMMAND ----------
+
+print "test3"
\ No newline at end of file