Rob Coleman RobColeman

## NewFeatureComputers.scala
package com.chartboost.adrel.preprocessing.featureComputers

import com.chartboost.adrel.dataModels.EcpmPredictionRequest
import com.chartboost.adrel.util.JsonSaving
import org.apache.spark.mllib.linalg.{Vector => SparkVector, Vectors => SparkVectors}
import scala.util.hashing.MurmurHash3

/**
  * The meta-data for computing features.  In this format to easily save and load with models.
  *

## ApproximateDistribution.scala
package com.preact.platform.math.models

import java.lang.System._
import java.util
import com.tdunning.math.stats.{Centroid, TreeDigest}
import org.apache.commons.math3.distribution.NormalDistribution
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkContext, SparkConf}

import scala.collection.immutable.IndexedSeq

## TreeDigestHelper.scala
package com.preact.platform.math.models

import java.lang.System._
import java.nio.ByteBuffer

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkContext, SparkConf}
import org.apache.commons.math3.distribution.ExponentialDistribution
import org.apache.commons.math3.distribution.NormalDistribution
import com.tdunning.math.stats.TreeDigest

## TDigest.scala
import java.nio.ByteBuffer

import org.apache.spark.{SparkContext, SparkConf}
import org.apache.commons.math3.distribution.ExponentialDistribution
import scala.collection._
import scala.collection.generic.CanBuildFrom
import scala.util.Random

case class Centroid(var mean: Double, var count: Long) extends Ordered[Centroid] with Serializable {

## some_algorithms.py
# binary search
def binary_search(x, arr):
    """
    x is a integer,
    arr is an array of integers, in sorted order

    Binary search will tell you if x is contained in arr

    A binary search bisects the array, recursively, to search smaller and smaller
        sub-sections of the array until it either, finds the value or finds no more candidate

## count_nucleotides.py
def count_nucleotides_by_type(sequence):
  # use a dictionary to keep track of the counts of each nucleotide type in the sequence
  counts = {
    "A": 0,
    "C": 0,
    "G": 0,
    "T": 0,
    "length": 0
  }

## gist:2babd0fad3d7f01f3d7e
for x in "asdfasdfas2343asdf232dfasdf": print(x.isdigit())


def how_many_numbers_in_the_word(word):
  counter = 0
  for x in word:
    if x.isdigit():
      counter = counter + 1
  return counter

## index.html
<!DOCTYPE html>
<html lang="en">
	<head>
		<meta charset="utf-8">
		<title>Loading CSV Data with D3</title>
		<script type="text/javascript" src="http://d3js.org/d3.v3.js"></script>
	</head>
	<body>

		<p>Not much to see here; try looking in the console!</p>

## d3_course_dataset_meteorites
I have chosen the meteorites dataset from The Meteorite Society, hosted at http://visualizing.org/datasets/meteorite-landings .

It has a couple interesting things going for it.

- It's only about 3.1MB, not very big, but not to small in size.
- It's got a lot of different data-types, with intersting relationships to play with (variable-types)
  - Ratio (Mass, year)
  - Qualitative - Interval (lat, long)
  - Catagorical non-ordinal (class/type, namtype)
- It's already clean

## pdc_dtf.py
#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""Implements Partial Directed Coherence and Direct Transfer Function
using MVAR processes.

Reference
---------
Luiz A. Baccala and Koichi Sameshima. Partial directed coherence:
a new concept in neural structure determination.
	package com.chartboost.adrel.preprocessing.featureComputers

	import com.chartboost.adrel.dataModels.EcpmPredictionRequest
	import com.chartboost.adrel.util.JsonSaving
	import org.apache.spark.mllib.linalg.{Vector => SparkVector, Vectors => SparkVectors}
	import scala.util.hashing.MurmurHash3

	/**
	* The meta-data for computing features. In this format to easily save and load with models.
	*
	package com.preact.platform.math.models

	import java.lang.System._
	import java.util
	import com.tdunning.math.stats.{Centroid, TreeDigest}
	import org.apache.commons.math3.distribution.NormalDistribution
	import org.apache.spark.rdd.RDD
	import org.apache.spark.{SparkContext, SparkConf}

	import scala.collection.immutable.IndexedSeq
	package com.preact.platform.math.models

	import java.lang.System._
	import java.nio.ByteBuffer

	import org.apache.spark.rdd.RDD
	import org.apache.spark.{SparkContext, SparkConf}
	import org.apache.commons.math3.distribution.ExponentialDistribution
	import org.apache.commons.math3.distribution.NormalDistribution
	import com.tdunning.math.stats.TreeDigest
	# binary search
	def binary_search(x, arr):
	"""
	x is a integer,
	arr is an array of integers, in sorted order

	Binary search will tell you if x is contained in arr

	A binary search bisects the array, recursively, to search smaller and smaller
	sub-sections of the array until it either, finds the value or finds no more candidate
	def count_nucleotides_by_type(sequence):
	# use a dictionary to keep track of the counts of each nucleotide type in the sequence
	counts = {
	"A": 0,
	"C": 0,
	"G": 0,
	"T": 0,
	"length": 0
	}
	for x in "asdfasdfas2343asdf232dfasdf": print(x.isdigit())


	def how_many_numbers_in_the_word(word):
	counter = 0
	for x in word:
	if x.isdigit():
	counter = counter + 1
	return counter
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="utf-8">
	<title>Loading CSV Data with D3</title>
	<script type="text/javascript" src="http://d3js.org/d3.v3.js"></script>
	</head>
	<body>

	<p>Not much to see here; try looking in the console!</p>
	I have chosen the meteorites dataset from The Meteorite Society, hosted at http://visualizing.org/datasets/meteorite-landings .

	It has a couple interesting things going for it.

	- It's only about 3.1MB, not very big, but not to small in size.
	- It's got a lot of different data-types, with intersting relationships to play with (variable-types)
	- Ratio (Mass, year)
	- Qualitative - Interval (lat, long)
	- Catagorical non-ordinal (class/type, namtype)
	- It's already clean
	#!/usr/bin/env python
	# -- coding: utf-8 --

	"""Implements Partial Directed Coherence and Direct Transfer Function
	using MVAR processes.

	Reference
	---------
	Luiz A. Baccala and Koichi Sameshima. Partial directed coherence:
	a new concept in neural structure determination.