wjohnson

#Get the data here http://grouplens.org/datasets/movielens/
movielens = sc.textFile("../in/ml-100k/u.data")

movielens.first() #u'196\t242\t3\t881250949'
movielens.count() #100000

#Clean up the data by splitting it
#Movielens readme says the data is split by tabs and
#is user product rating timestamp
clean_data = movielens.map(lambda x:x.split('\t'))

wjohnson

#http://archive.ics.uci.edu/ml/datasets/Bank+Marketing
data <- read.csv("~/in/bank/bank-full.csv",header=T,
         sep=";")

####Decision Tree####
library(rpart)
library(rpart.plot)

rp <- rpart(y~., data = data)
rpart.plot(rp)

wjohnson

{
  "type" : "record",
  "name" : "TrainingExample",
  "namespace" : "com.linkedin.metronome.avro.generated",
  "fields" : [ {
    "name" : "uid",
    "type" : [ "null", "string", "long", "int" ],
    "doc" : "a unique id for the training event",
    "default" : null
  }, {

wjohnson

# Reusable Functions
def azuread_auth(tenant_id: str, client_id: str, client_secret: str, resource_url: str):
    """
    Authenticates Service Principal to the provided Resource URL, and returns the OAuth Access Token
    """
    url = f"https://login.microsoftonline.com/{tenant_id}/oauth2/token"
    payload= f'grant_type=client_credentials&client_id={client_id}&client_secret={client_secret}&resource={resource_url}'
    headers = {
    'Content-Type': 'application/x-www-form-urlencoded'
    }