mayonesa

from __future__ import division

#given the mean of a set of data and
#get a single additional number. Given the number of observations in the
#existing data, the old mean and the new value

def mean(oldmean, n, x):
    return (oldmean * n + x) / (n + 1)

mayonesa

#Compute the likelihood of observing a sequence of die rolls
#Likelihood is the probability of getting the specific set of rolls 
#in the given order
#Given a multi-sided die whose labels and probabilities are 
#given by a Python dictionary called dist and a sequence (list, tuple, string) 
#of rolls called data, complete the function likelihood
  
def likelihood(dist,data):
    return reduce(lambda acc, x: acc * dist[x], data, 1)
    

mayonesa

from decimal import Decimal, getcontext

from vector import Vector

getcontext().prec = 30


class Line(object):

    __NO_NONZERO_ELTS_FOUND_MSG = 'No nonzero elements found'

mayonesa

log_factorial <- function (n) {
  # Return the log of factorial(n) for any integer n > 0
  if (n <= 1)
    return (0)
  return (log(n) + log_factorial(n - 1))
}

sum_log_factorial <- function (n) {
  # Return the sum of log_factorial(i) for i in 1..n
  sum <- 0

mayonesa

---
title: 'Project 2: Modeling and Evaluation'
subtitle: '<p>CSE6242 - Data and Visual Analytics</p><p>Due: Friday, April 21, 2017
  at 11:59 PM UTC-12:00 on T-Square</p>'
output:
  pdf_document: default
  html_document: default
---

# Data

mayonesa

# AC4: Visualize Vehicular Accident Non-motorist Mortalities per State
# inspirational reference: https://blog.dominodatalab.com/geographic-visualization-with-rs-ggmaps/

# infrastructure
install.packages("ggmap", type = "source")
library(ggmap)
setwd("~/Google Drive/gatech/dva/ac4") # **** Needs to accomodate particular workstation ****
vas <- read.csv("vehicle-accidents.csv")

# only continental states

mayonesa

# Activity: Time Series Analysis

library(zoo)  # basic time series package
library(xts)  # eXtensible Time Series package

data_dir <- "data"
label_dir <- "labeled_windows"

load_ts <- function(csv_filename) {
    # Load and return time series data from a CSV file.

mayonesa

#!/usr/bin/Rscript

# 2. Log Gamma (Loop)
log_gamma_loop = function(n) {
  acc = 0
  if (n > 1) {
    for (i in 1:(n-1)) {
      acc = acc + log(i)
    }
  } else if (n < 1) acc = -Inf # emulating log(<=0) return

mayonesa

# tidyverse (includes ggplot2)
install.packages("tidyverse")
library(tidyverse)

# midwest data
data("midwest")

# 1. Professional Education by State

# aggregate all counties up to their states (Interpretation A @300)

mayonesa

# hw3.R Logistic Regression

# 0. Data Preprocessing

# b
train <- read.csv("mnist_train.csv", header = F)
test <- read.csv("mnist_test.csv", header = F)

# c, d, e
class.indx <- 785