yankov

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

yankov

/* Given a list of numbers 0 to 10,000, return all those whose digits sum up to 20
 * Digits cannot repeat. Search space should be reduced.
 */

def get20s(): Seq[Seq[Int]] = {
  val ns = for {
    i <- 0 to 6
    j <- 1 to 7
    k <- 2 to 8
    if i + j + k == 11

yankov

%matplotlib inline
import md5, struct
import seaborn as sns
import matplotlib.pyplot as plt
import mmh3

def md5hash(i):
    return md5.new(str(i)).digest()[12:16]

def mm(i):

yankov

from scipy import sparse


class OneHotEncoder():
    """
    OneHotEncoder takes data matrix with categorical columns and
    converts it to a sparse binary matrix doing one-of-k encoding.

    Parts of code borrowed from Paul Duan (www.paulduan.com)
    Licence: MIT (https://github.com/pyduan/amazonaccess/blob/master/MIT-LICENSE)

yankov

# Avazu CTR prediction
# SGD Logistic regression + hashing trick.

import pandas as pd
import numpy as np
from datetime import datetime, date, time
from sklearn.linear_model import SGDClassifier
from sklearn.feature_extraction import FeatureHasher
from sklearn.preprocessing import LabelEncoder

yankov

# Avazu CTR prediction
# SGD Logistic regression + one hot encoder. Score: 0.414
import pandas as pd
import numpy as np
from datetime import datetime, date, time
from OneHotEncoderPartial import OneHotEncoder
from sklearn.linear_model import SGDClassifier

cols = ["C1","banner_pos","site_category", "device_type","device_conn_type","C14","C15","C16","C17","C18","C19","C20","C21", "hour"]

yankov

  val poolConfiguration = new PoolConfiguration(
    maxIdle = 1000,
    maxObjects = 5,
    maxQueueSize = 5,
    validationInterval = 1000
  )

  val factory = new PostgreSQLConnectionFactory(configuration)
  val pool = new SingleThreadedAsyncObjectPool[PostgreSQLConnection](factory, poolConfiguration)

yankov

import com.datastax.driver.core._

val cluster = Cluster.builder.addContactPoint("127.0.0.1").build
val session = cluster.connect

// http://www.datastax.com/documentation/developer/java-driver/1.0/webhelp/index.html#java-driver/quick_start/qsSimpleClientAddSession_t.html
session.execute("CREATE KEYSPACE simplex WITH replication " + 
      "= {'class':'SimpleStrategy', 'replication_factor':3};");
      
session.execute(

yankov

val topic = "urls"
val props = new Properties()
props.put("broker.list", "0:localhost:9092")
props.put("serializer.class", "kafka.serializer.StringEncoder")
val config = new ProducerConfig(props)
val producer = new Producer[String, String](config)

val data = new ProducerData[String, String](topic, href)
producer.send(data)
     

yankov

package week7

class Pouring(capacity: Vector[Int]) {
  // States

  type State = Vector[Int]
  val initialState = capacity map (x => 0)

  // Moves