kylebgorman

"""Log-odds computations."""


from libc.math cimport log, sqrt
from libc.stdint cimport int64_t


ctypedef int64_t int64

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

syn on
set hlsearch
set ruler
" tab stuff
set expandtab
set tabstop=4
" scrolling
set scrolloff=5
" backspace over everythign
set backspace=indent,eol,start

kylebgorman

"""English function words.

Sets of English function words, based on

    E.O. Selkirk. 1984. Phonology and syntax: The relationship between
    sound and structure. Cambridge: MIT Press. (p. 352f.)

The categories are of my own creation.
"""

kylebgorman

#!/usr/bin/env python
"""LNRE calculator.

This script computes a number of statistics characterizing LNRE data:

* N: corpus size
* V: vocabulary size
* V(1): the number of _hapax legomena_ (symbols occuring once)
* V(2): the number of _dis legomena_ (symbols occurring twice)
* V/N: vocabulary growth rate

kylebgorman

<epsilon>	0
<SOH>	1
<STX>	2
<ETX>	3
<EOT>	4
<ENQ>	5
<ACK>	6
<BEL>	7
<BS>	8
<HT>	9

kylebgorman

#!/usr/bin/env python

import fileinput

import nltk


if __name__ == "__main__":
    for line in fileinput.input():
        print(" ".join(nltk.word_tokenize(line)))

kylebgorman

# Copyright (c) 2013-2022 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:
#

kylebgorman

#!/usr/bin/env Rscript
# WALS131A.R
# Kyle Gorman <kylebgorman@gmail.com>
# 
# Tests the hypothesis that vigesimal (base-20) number systems are more common
# at tropical latitudes. Thanks to Richard Sproat for suggesting this
# hypothesis.
# 
# The data is read directly from WALS (#131A):
# 

kylebgorman

# autoloess.R: compute loess metaparameters automatically
# Kyle Gorman <gormanky@ohsu.edu>

aicc.loess <- function(fit) {
    # compute AIC_C for a LOESS fit, from:
    # 
    # Hurvich, C.M., Simonoff, J.S., and Tsai, C. L. 1998. Smoothing 
    # parameter selection in nonparametric regression using an improved 
    # Akaike Information Criterion. Journal of the Royal Statistical 
    # Society B 60: 271–293.