Used this to cut up every word in a CSV to count any common places where I made purchases. Such as a certain gas station or how many times at an ATM.

word_parse.rb

require 'csv'

class String
  def titleize
    split(/(\W)/).map(&:capitalize).join
  end
end

def separate_word(word)
  word.gsub(/[0-9\-\/\\\*\#()&'.]/,"").titleize.split(" ")
end

def sort_word_limits(word, min, length)
  word.select { |k,v| v >= min && k.length >= length }.sort_by { |k,v| v }.reverse
end

def word_size(word)
  word.keys.map { |n| n.length }.max
end

file_name       = ARGV[0]
inputfile       = CSV.open(file_name).readlines.flatten.map { |row| separate_word(row)}
min_word_length = 4
min_count       = 15
word_count      = {}

inputfile.each do |items|
  items.each { |item| word_count.has_key?(item) ? word_count[item] += 1 : word_count[item] = 1 }
end

big_word    = word_size(word_count)
final_count = sort_word_limits(word_count, min_count, min_word_length)

final_count.each { |k,v| print k.rjust(big_word) + " " + v.to_s; puts}

######### Example Input from CSV########
# Tremors Riverside Ca
# Shell Oil 61635192007 Cabazon Ca
# 2995 Iowa Ave. Stater 114Riverside Ca 3319
# ATM Withdrawal - 01/19 3060046 5797 North Victglobal Cashighland Ca 3319
# Non-Wells Fargo ATM Transaction Fee
# UCR Bookstore Riverside Ca
# Circle Bar Santamonica Ca
# ATM Withdrawal - 01/25 Scad4057 *Corona-01 B Of A Corona Ca 3319
# 1294 Universityarco Payporiverside Ca 3319
# Non-Wells Fargo ATM Transaction Fee
# Exxonmobil34 07865660 Riversid Ca
# 2650 N Main St L And L Mariverside Ca 3319