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(line.rstrip().casefold())

kylebgorman

#!/usr/bin/env python

import fileinput

import nltk


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

kylebgorman

#!/usr/bin/env python
# What's the nearest word (in Levenshtein distance) to "covfefe"?

import string

# Available from: https://github.com/kylebgorman/EditTransducer
import edit_transducer

# You probably have this file if you're on Linux or Mac OS X.
with open("/usr/share/dict/words") as source:

kylebgorman

# On Linux:
sudo ldconfig
# On Mac OS X:
sudo update_dyld_shared_cache

kylebgorman

#!/usr/bin/env python
"""Checks that PyTorch can reach CUDA."""

import sys

import torch


if __name__ == "__main__":
    if not torch.cuda.is_available():

kylebgorman

"""Log-odds computations."""


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


ctypedef int64_t int64

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
#
# Constructs resources for Zodiac cipher 408:
#
#   * Plaintext and ciphertext FARs
#   * Unweighted "key" FSTs and "channel" (hypothesis space) FSTs
#   * A textual symbol table for plaintext and ciphertext
#
# Requires: Pynini and OpenFst with the FAR extension.