kylebgorman

# Z_r (or "averaging") transform functions, based on:
# 
# Kenneth W. Church and William A. Gale. 1991. A comparison of the enhanced 
# Good-Turing and deleted estimation methods for estimating probabilities of 
# English bigrams. Computer Speech and Language 5(1):19--54
#
# Kyle Gorman <kgorman@ling.upenn.edu>
# 
# Church and Gale do not say what is to be done about points at the edges. I 
# have chosen to average them with respect to only the inward facing frequency,

kylebgorman

#!/usr/bin/env python
# difflib_demo.py 
# Kyle Gorman <kgorman@ling.upenn.edu>

from difflib import SequenceMatcher

if __name__ == '__main__':

    from sys import argv
    for file in argv[1:]:

kylebgorman

#!/usr/bin/env python
# wagnerfischer.py: Dynamic programming Levensthein distance function 
# Kyle Gorman <gormanky@ohsu.edu>
# 
# Based on:
# 
# Robert A. Wagner and Michael J. Fischer (1974). The string-to-string 
# correction problem. Journal of the ACM 21(1):168-173.
#
# The thresholding function was inspired by BSD-licensed code from 

kylebgorman

#!/usr/bin/env python
# ProbDist.py: Two classes for probability distributions and sampling.
# Kyle Gorman <kgorman@ling.upenn.edu>

from math import fsum
from bisect import bisect
from random import random
from collections import defaultdict

class MLProbDist(object):

kylebgorman

#!/usr/bin/env python
# Knuth-Morris-Pratt demonstration
# Kyle Gorman <kgorman@ling.upenn.edu>
#
# A naive Python implementation of a function that returns the (first) index of
# a sequence in a supersequence is the following:

def subsequence(needle, haystack):
    """
    Naive subsequence indexer; None if not found

kylebgorman

File type = "ooTextFile"
Object class = "TextGrid"

xmin = 0
xmax = 3
tiers? <exists>
size = 1
item []:
    item [1]:
        class = "IntervalTier"

kylebgorman

/*
 *  Tolerance Principle calculator, based on:
 * 
 *  C. Yang (2005). On productivity. Language Variation Yearbook 5:333-370.
 *  
 *  Definition: 
 * 
 *  The number of data points consistent with a rule R is given by N, and the 
 *  number of exceptions to it by m. By Tolerance, R is productive iff:
 *  

kylebgorman

#!/usr/bin/env python
# point_bisect.py
# Kyle Gorman
# 
# I continually use these two patterns in Python for iterables that contain
# continuous values, sorted. Here they are in their full glory.

from bisect import bisect_left

kylebgorman

/* Copyright (c) 2012 Kyle Gorman
 * 
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to 
 * deal in the Software without restriction, including without limitation the 
 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or 
 * sell copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in

kylebgorman

/* Copyright (c) 2012 Kyle Gorman
 * 
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to 
 * deal in the Software without restriction, including without limitation the 
 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or 
 * sell copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in