SlightlyUnorthodox

# Title: US Exports to NATO Members as Percentage of GDP
# Author: Dax Gerts
# Date: February 6th, 2017
# Description: a quick analysis of proportion of US Exports attributed to NATO members 

# Load dependencies
library('openxlsx')
library('ggplot2')

# Get Census Data and parse as data frame

SlightlyUnorthodox

# The following are some uses for regular expressions in Python

# Import the regex library
import re

# Create a test string
test_string = "This is a test string with some numbers, '123456', and some letters, 'abcdef'."

# Now we have some uses

SlightlyUnorthodox

# Passphrase generation v1.0
# Author: Dax Gerts
# Date: 6 March 2016
# Description: example passphrase generation

from nltk.corpus import words
import numpy as np

# Prompt for passphrase length and store as in
pass_length = raw_input("How many words should your pass-phrase have? (enter #) ")

SlightlyUnorthodox

# Definition Retrieval v1.0
# Author: Dax Gerts
# Date: 6 March 2016
# Description: example definition lookup using WordNet in NLTK

# Uses Wordnets word lookup and definition
from nltk.corpus import wordnet as wn

# Prompt for a word to define
word = raw_input("Enter a word to define: ")

SlightlyUnorthodox

# Title: WordCount2
# Author: Dax Gerts
# Date: 13 November 2015
# Runtime: 47.213 seconds
# Results: 4,068,566,751,420 words

require(gtBase)

data = Read(ngrams2)

SlightlyUnorthodox

# Title: WordCount1
# Author: Dax Gerts
# Date: 13 November 2015
# Runtime: 8.947 seconds
# Results: 1,320,305,357,364 words

require(gtBase)

data = Read(ngrams1)

SlightlyUnorthodox

# Title: TupleCount2
# Author: Dax Gerts
# Date: 13 November 2015
# Runtime: 16.481 seconds
# Results: 37,582,158,107 tuples

require(gtBase)

data = Read(ngrams2)

SlightlyUnorthodox

# Title: TupleCount1
# Author: Dax Gerts
# Date: 13 November 2015
# Runtime: 8.218 seconds
# Results: 1,430,731,493 tuples

require(gtBase)

data = Read(ngrams1)

SlightlyUnorthodox

# Query: Zipf1
# Author: Dax Gerts
# Date: 11 November 2015 (UPDATED)
# Runtime: (1)-gram, 10,000, 100 years, approx 77 seconds
#          (2)-gram, 10,000, 100 years, approx 720 seconds

# Description: Prepare frequency table for Zipf analysis

require(gtBase)
require(gtStats)

SlightlyUnorthodox

# Query: Collocation2008
# Author: Dax Gerts
# Date: 4 November 2015
# Runtime Without Segmenter: approx. 12.83 minutes (with filter at > 0.000001, one in 100K) approx no convergence (with filter at > 0.0000001, one in 100K)
# Runtime With Segmenter:    approx. 12.85 minutes (with filter at > 0.000001, one in 100K) approx 14.03 minutes (with filter at > 0.0000001, one in 1M)

# Description: Attempts to identify English collocations in 2008 by comparing the relative frequency of natural occuring bigrams to independently calculated bigrams

library(gtBase)
library(methods)