chy168

// k-mean
import org.apache.spark.mllib.clustering.{KMeans, KMeansModel}
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint

case class Data(userId: String, videoId: String, isKid: String)

val raw_data = sc.textFile("/Users/zzchen/Downloads/locked_video_up5.csv").map { line => 
    val f = line.split(",")
    Data(f(0),f(1).split("=")(1),f(5))

chy168

jupyter:
  image: jupyter/datascience-notebook
  environment:
    - PASSWORD=${PASSWORD}


nginx:  
  image: nginx
  links: 
    - jupyter

chy168

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: testing
  labels:
    component: db
spec:
  template:
    metadata:
      labels:

chy168

## Pre-install package
https://github.com/jonmosco/kube-ps1