danared

def main(args: Array[String]): Unit = {
    // Set up configurations
    val sc = getSparkContext()
    val sqlContext = SQLContext.getOrCreate(sc)

    val readConfig = ReadConfig(Map("uri" -> "mongodb://127.0.0.1/movies.movie_ratings?readPreference=primaryPreferred"))
    val writeConfig = WriteConfig(Map("uri" -> "mongodb://127.0.0.1/movies.user_recommendations"))

    val userId = 0

danared

  /**
   * Gets or creates the Spark Context
   */
  def getSparkContext(): SparkContext = {
    val conf = new SparkConf()
      .setMaster("local[*]")
      .setAppName("MovieRatings")

    val sc = SparkContext.getOrCreate(conf)
    sc.setCheckpointDir("/tmp/checkpoint/")

danared

package example

import org.apache.log4j.{Level, Logger}
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.recommendation.ALS
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}

import com.mongodb.spark.MongoSpark

danared

number_of_documents = 100

load_data(collection, number_of_documents)

winner = [ d for d in collection.aggregate([{'$sample': {'size': 1 }}])][0]

print "AND THE WINNER IS ..... " + winner['name']

danared

number_of_documents = 100

load_data(collection, number_of_documents )

query = {'i': random.randint(0, 10 )  }

docs = [x for x in collection.find(query)]

winner = random.sample(docs, 1)[0]

danared

def load_data(collection, n=100):
    #fixed number of marks
    max_i = 10
    for j,d in load_data_file(n):
        d['i'] = random.randint(0, max_i)
        collection.insert( d )

danared

def load_data(collection, n=100):
    #let's skip some elements
    skiplist = [10, 12, 231 , 2 , 4]
    for i,d in load_data_file(n):
        d['i'] = i
        if i in skiplist:
            continue
        collection.insert( d )

load_data(collection, 100)

danared

number_of_documents = collection.count()

danared

mc = MongoClient()
db = mc.simplerandom
collection = db.names

number_of_documents = 100

load_data(collection, number_of_documents )

query = {'i': random.randint(0, number_of_documents )  }

danared

def load_data(collection, n=100):
    #for each element we will insert the `i` value
    for i in xrange(n):
        name = ''.join(random.sample( string.letters, 20))
        collection.insert( {'name': name, 'i': i})