amundra2016

AWSTemplateFormatVersion: '2010-09-09'
Description: 'Broker cloudformation template'
Parameters:
  KeyName:
    Description: 'For SSH access'
    Type: 'AWS::EC2::KeyPair::KeyName'
  MinimumInstances:
    Description: Minimum number of instances for autoscaling group
    Type: Number
    AllowedValues:

amundra2016

AWSTemplateFormatVersion: '2010-09-09'
Description: 'Zookeeper cloudformation template'
Parameters:
  MinimumInstances:
    Description: Minimum number of instances for autoscaling group
    Type: Number
    AllowedValues:
      - 3
      - 5
  InstanceType:

jsmouret

package pb

import (
	"fmt"
	"reflect"

	st "github.com/golang/protobuf/ptypes/struct"
)

// ToStruct converts a map[string]interface{} to a ptypes.Struct

Nikolay-Lysenko

from time import sleep
from io import StringIO

import psycopg2


def upsert_df_into_postgres(df, target_table, primary_keys, conn_string,
                            n_trials=5, quoting=None, null_repr=None):
    """
    Uploads data from `df` to `target_table`

MLnick

Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /___/ .__/\_,_/_/ /_/\_\   version 2.0.0
      /_/

Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_77)
Type in expressions to have them evaluated.
Type :help for more information.

thoolihan

sudo yum -y install epel-release
sudo yum -y install gcc gcc-c++ python-pip python-devel atlas atlas-devel gcc-gfortran openssl-devel libffi-devel
# use pip or pip3 as you prefer for python or python3
pip install --upgrade virtualenv
virtualenv --system-site-packages ~/venvs/tensorflow
source ~/venvs/tensorflow/bin/activate
pip install --upgrade numpy scipy wheel cryptography #optional
pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.10.0rc0-cp35-cp35m-linux_x86_64.whl
# or below if you want gpu, support, but cuda and cudnn are required, see docs for more install instructions
pip install --upgrade https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.10.0rc0-cp35-cp35m-linux_x86_64.whl

elliotchance

next_xid = 1
active_xids = set()
records = []

def new_transaction():
    global next_xid
    next_xid += 1
    active_xids.add(next_xid)
    return Transaction(next_xid)

MLnick

class HyperLogLogStoreUDAF extends UserDefinedAggregateFunction {

  override def inputSchema = new StructType()
    .add("stringInput", BinaryType)

  override def update(buffer: MutableAggregationBuffer, input: Row) = {
    // This input Row only has a single column storing the input value in String (or other Binary data).
    // We only update the buffer when the input value is not null.
    if (!input.isNullAt(0)) {
      if (buffer.isNullAt(0)) {

debasishg

General Background and Overview

1. Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
2. Models and Issues in Data Stream Systems
3. Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
4. Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
5. [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep=rep1&t

MLnick

import spark.streaming.{Seconds, StreamingContext}
import spark.storage.StorageLevel
import spark.streaming.examples.twitter.TwitterInputDStream
import com.twitter.algebird._
import spark.streaming.StreamingContext._
import spark.SparkContext._

/**
 * Example of using CountMinSketch monoid from Twitter's Algebird together with Spark Streaming's
 * TwitterInputDStream