Jeremy B. Merrill jeremybmerrill

## atlantacrime2012until2017.small.csv
offense_id,occur_date,UC2 Literal,neighborhood,npu
110171050,01/14/2012,LARCENY-NON VEHICLE,Sweet Auburn,M
110181057,08/22/2011,LARCENY-NON VEHICLE,Glenrose Heights,Z
112032439,07/22/2011,AUTO THEFT,Downtown,M
112152334,08/03/2011,AUTO THEFT,Perkerson,X
113491709,12/07/2011,LARCENY-FROM VEHICLE,Hills Park,D
120010023,01/01/2012,AGG ASSAULT,The Villages at Carver,Y
120010069,12/31/2011,LARCENY-FROM VEHICLE,Old Fourth Ward,M
120010072,12/31/2011,LARCENY-FROM VEHICLE,English Avenue,L
120010086,01/01/2012,LARCENY-FROM VEHICLE,Morningside/Lenox Park,F

## demo.html
<!DOCTYPE html>
<html>
<head>
  <title>How To Cause Trouble With Events' isTrusted Attribute</title>
  <meta charset="UTF-8">
  <script
        src="http://code.jquery.com/jquery-2.2.4.min.js"
        integrity="sha256-BbhdlvQf/xTY9gja0Dq3HiwQF8LaCRTXxZKRutelT44="
        crossorigin="anonymous"></script>
</head>

## airplanes.sql
create table flight_segments as
SELECT hexid,start_time,end_time,callsign,point,
   -- take a substring if the length reamining in the segment is greater than 5280 feet (1609.34 m)
   -- otherwise take the remainder
   ST_LineSubstring(geom, 1609.34*n/length,
   CASE
     WHEN 1609.34*(n+1) < length THEN 1609.34*(n+1)/length
     ELSE 1
   END) as geom
FROM

## code_tos.rb
require 'sinatra'
require 'csv'

$csv_read_path = "my_thing.uncoded.csv"
$csv_write_path = "my_thing.coded.csv"

$data = CSV.read($csv_read_path, {:headers => true})

def write_csv!
  CSV.open($csv_write_path, 'wb') do |csv|

## edc.rb
require 'tabula'
require 'fileutils'


folder_name = "EDC"
output_folder_name = "EDCcsvs"

#########################################################################
#########################################################################
FileUtils.mkdir_p(output_folder_name + "/")

## compstat.rb
require 'tabula'
require 'fileutils'


folder_name = "compstat"
output_folder_name = "compstat_csvs"

#########################################################################
#########################################################################
FileUtils.mkdir_p(output_folder_name + "/")

## tabula_basic.rb
require 'tabula'

pdf_file_path = "czechmaybe.pdf"
outfilename = "czechmaybe.csv"

out = open(outfilename, 'w')

extractor = Tabula::Extraction::ObjectExtractor.new(pdf_file_path, [5] ) #:all ) # 1..2643
extractor.extract.each do |pdf_page|
  pdf_page.spreadsheets.each do |spreadsheet|

## gender.rb
require 'csv'
require 'set'

class Gender
  def initialize(options={})
    countries = Set.new([:us, :uk])

    @threshold = options[:threshold] || 0.99

    @names_counts = {}

## count_scraper.rb
require 'upton'
require 'date'
require 'guess'

GLOBAL_VERBOSE = true

# - any lowercased pronoun is okay
# - capitalized pronouns are okay unless they're in a book title, which is a series of capitalized words;
#   that is, capitalized pronouns are okay if there are zero alphabetic characters between them and a sentence-final punct
FEMALE_REGEXES = [/ she[\.,\s!?\' ]/, / her[\.,\s!?\' ]/,

## astrazeneca.rb
require 'upton'

class AstraZenecaScraper < Upton::Scraper
  ROWS_PER_PAGE = 50

  def initialize(index_url_array, site_meta)
    @sleep_time_between_requests = 15
    @site_meta = site_meta
    @total_pages = @site_meta[:total_pages]
    @az_time_period_identifier = @site_meta[:az_time_period_identifier]