DavidRdgz

    7.96 |                                                                                
         |                 ·         ·        ·       · ·· ··     ·                       
         |                         ··   ··   ·   · · ·       · ·· · ·                     
         |     ·                ·  ·· · ·  · ········· ······ ··· ·· ·                    
         |             ·   ··  ·  ··  ·· ····· ······················         ·           
    7.62 |              ·  ·  · ········································ ···  ·           
         |    ·  ·    ·  ·· ·····················∘·········∘············  ··  ··         ·
         |·        ·       ·· ·················∘·∘∘∘··∘·················· · ···         · 
         |  ·     ··     ···············∘·······∘·∘∘∘·○·∘··∘∘∘················· ·         
         |    ·  ·  ·  ··· ·············∘·∘∘∘∘∘··∘∘∘∘∘∘∘·∘∘··∘∘············· ·            

DavidRdgz

data = [7.650241800665554e-05,3.923801883327712e-05,3.0,3.0,3.0,7.283467537625357e-05,3.0,5.0,4.578335196970549e-05,8.864074492628704e-05,5.4930696397944266e-05,6.126587295338719e-05,6.870468675141216e-05,5.013033109090004e-05,1.5649705654594946e-05,6.665684055182832e-05,7.778241848184921e-05,6.152523259571738e-05,2.197341773568182e-05,6.514893533227304e-05,9.840354316222558e-05,2.0,5.118635504549967e-05,2.219241550856768e-05,8.707278988254699e-05,7.345254298994388e-05,1.038200304754831e-05,7.486178857899007e-05,4.400363543164666e-05,2.6109114103329375e-05,6.980217556269073e-05,6.497584542503085e-05,7.413016730642387e-05,8.622898038036913e-05,2.5108810275908995e-05,2.0,5.478937414861367e-05,3.416370076636977e-05,3.420693549749728e-05,5.289158824042955e-05,1.3250620985521934e-05,5.5149269115319916e-05,3.3351624592411055e-05,2.0,2.0,1.0,6.0963304813514516e-05,5.174888962660831e-05,3.234479792687862e-05,7.467867763461055e-05,4.008562585999516e-05,3.9392903445443475e-05,8.890909111618834e-05,3.979655341257482e-05

DavidRdgz

"""
A simple example of decluttering the settings for pandas so
that when developing the model and testing it, the dataframe
is a little cleaner and more readable.

"""

def pandas_defaults(defaults, pd):
    def decorator(f):
        def wrapper(*args, **kwargs):

DavidRdgz

package numpy

trait NumpyWriter[A] {
  def lessThan(list: List[A])(value: A): List[A]
  def greaterThan(list: List[A])(value: A): List[A]
  def multiply(list: List[A])(value: A): List[A]
  def add(list: List[A])(value: A): List[A]
  def subtract(list: List[A])(value: A): List[A]
}

DavidRdgz

import com.stripe.rainier.core.{Normal, Poisson}
import com.stripe.rainier.sampler.{RNG, ScalaRNG}
import org.apache.spark.{SparkConf, SparkContext}

object Driver {
  implicit val rng: RNG = ScalaRNG(1527608515939L)
  val DROP_BURN_IN = 100

  /*
   Refer to StackOverflow Q, about serializing methods/objects:

DavidRdgz

package com.stripe.rainier.core

import com.stripe.rainier.compute.{Evaluator, If, Real}

trait Discrete extends Distribution[Int] {
  self: Discrete =>
  val emptyEvaluator = new Evaluator(Map.empty)

  def logDensity(v: Real): Real

DavidRdgz

nb approximation to normal threshold

There's many ways to test if a negative binomial is approximately normal: e.g.

• visualize the qq plot
• normalize the nb sample and perform shapiro-wilkes test

Below is an image of the envelope where the negative binomial parameters create a distribution that is approximately normal.

DavidRdgz

/**
  * Bernoulli distribution with expectation `p`
  *
  * @param p The probability of success
  */
final case class Bernoulli(p: Real) extends Discrete {
  val generator: Generator[Int] =
    Generator.require(Set(p)) { (r, n) =>
      val u = r.standardUniform
      val l = n.toDouble(p)

DavidRdgz

from keras.models import Model
from keras.layers import Input, Dense, concatenate, dot
from numpy.random import randint
import numpy as np


def my_model(n=20):
    inputs = Input(shape=(n,))

    m1 = Dense(1)(inputs)

DavidRdgz

from keras.models import Model
from keras.layers import Input, Lambda, Dense
from keras.utils import to_categorical
from numpy.random import randint
import numpy as np


def belief_per_model(x):
    x1, x2, x3, x4 = x
    return x1 * .2 + x2 * .3 + x3 * .4 + x4 * .1