zyocum

#!/usr/bin/env python3

"""Tokenize text naively based on unicode character properties"""

import json
import regex
import sys

from collections import namedtuple

zyocum

#!/usr/bin/env python3

"""Attempt to generate false etymologies from phonetically similar words"""

import csv
import json
import sys
import random

from itertools import groupby

zyocum

mbp-zyocu-4925:data-tools zyocum$ diff eng.en.fr.txt eng-forced.en.fr.txt 
76c76
< Prenez possession de votre hamburger moderniste au four à prévoir ensemble sur ayurveda: larCPbzs https://t.co/zbQLrcKASK
---
> Prenez possession de votre hamburger moderniste à l'heure d'attendre ensemble sur ayurveda: larCPbzs https://t.co/zbQLrcKASK
78c78
< RT @SixGodDrake: Je ne changerai pas pour n'importe qui, je ne me soucie pas de ce que les gens pensent, parce que je suis moi et fier de ça.
---
> RT @SixGodDrake: Je ne changerai pas pour n'importe qui, je m'en fiche de ce que les gens pensent, parce que je suis moi et fier de ça.
81c81

zyocum

#!/usr/bin/env python3
"""Generate 1-dimensional automata based on various rules"""

def ngrams(iterable, n=1):
    """Generate ngrams from an iterable"""
    return zip(*(iterable[i:] for i in range(n)))

def states(state, rule, left_pad='0', right_pad='0'):
    """Generate a stream of states from an initial state and a rule"""
    next_state = ''.join(rule[''.join(window)] for window in ngrams(state, 3))

zyocum

# Line 1: "The Cleveland Rams selected Graf in the 1942 NFL Draft, but he instead attended Harvard Business School. "
# Semantic graph: [selected/VBD
#                  nsubj:[Rams/NNPS det:The/DT nn:Cleveland/NNP]
#                  dobj:[Graf/NNP
#                        prep:[in/IN pobj:[Draft/NNP det:the/DT num:1942/CD nn:NFL/NNP]]]
#                  cc:but/CC
#                  conj:[attended/VBD
#                        nsubj:he/PRP
#                        advmod:instead/RB
#                        dobj:[School/NNP nn:Harvard/NNP nn:Business/NNP]]]