Remove old unused files

This commit is contained in:
Ines Montani 2017-01-11 18:58:38 +01:00
parent 8e962de39f
commit 3a9c6a9563
2 changed files with 0 additions and 163 deletions

View File

@ -1,81 +0,0 @@
# -*- coding: utf-8 -*-
"""Sphinx doctest is just too hard. Manually paste doctest examples here"""
import pytest
#@pytest.mark.models
#def test_1():
# import spacy.en
# from spacy.parts_of_speech import ADV
# # Load the pipeline, and call it with some text.
# nlp = spacy.en.English()
# tokens = nlp(u"Give it back, he pleaded abjectly, its mine.",
# tag=True, parse=False)
# o = u''.join(tok.string.upper() if tok.pos == ADV else tok.string for tok in tokens)
# assert u"Give it BACK, he pleaded ABJECTLY, its mine."
#
# o = nlp.vocab[u'back'].prob
# assert o == -7.033305644989014
# o = nlp.vocab[u'not'].prob
# assert o == -5.332601070404053
# o = nlp.vocab[u'quietly'].prob
# assert o == -11.994928359985352
#
#
#@pytest.mark.m
#def test2():
# import spacy.en
# from spacy.parts_of_speech import ADV
# nlp = spacy.en.English()
# # Find log probability of Nth most frequent word
# probs = [lex.prob for lex in nlp.vocab]
# probs.sort()
# is_adverb = lambda tok: tok.pos == ADV and tok.prob < probs[-1000]
# tokens = nlp(u"Give it back, he pleaded abjectly, its mine.")
# o = u''.join(tok.string.upper() if is_adverb(tok) else tok.string for tok in tokens)
# o == u'Give it back, he pleaded ABJECTLY, its mine.'
#
#@pytest.mark.models
#def test3():
# import spacy.en
# from spacy.parts_of_speech import ADV
# nlp = spacy.en.English()
# # Find log probability of Nth most frequent word
# probs = [lex.prob for lex in nlp.vocab]
# probs.sort()
# is_adverb = lambda tok: tok.pos == ADV and tok.prob < probs[-1000]
# tokens = nlp(u"Give it back, he pleaded abjectly, its mine.")
# o = u''.join(tok.string.upper() if is_adverb(tok) else tok.string for tok in tokens)
# assert o == u'Give it back, he pleaded ABJECTLY, its mine.'
#
# pleaded = tokens[7]
# assert pleaded.repvec.shape == (300,)
# o = pleaded.repvec[:5]
# assert sum(o) != 0
# from numpy import dot
# from numpy.linalg import norm
#
# cosine = lambda v1, v2: dot(v1, v2) / (norm(v1) * norm(v2))
# words = [w for w in nlp.vocab if w.is_lower and w.has_repvec]
# words.sort(key=lambda w: cosine(w.repvec, pleaded.repvec))
# words.reverse()
# o = [w.orth_ for w in words[0:20]]
# assert o == [u'pleaded', u'pled', u'plead', u'confessed', u'interceded',
# u'pleads', u'testified', u'conspired', u'motioned', u'demurred',
# u'countersued', u'remonstrated', u'begged', u'apologised',
# u'consented', u'acquiesced', u'petitioned', u'quarreled',
# u'appealed', u'pleading']
# o = [w.orth_ for w in words[50:60]]
# assert o == [u'martialed', u'counselled', u'bragged',
# u'backtracked', u'caucused', u'refiled', u'dueled', u'mused',
# u'dissented', u'yearned']
# o = [w.orth_ for w in words[100:110]]
# assert o == [u'acquits', u'cabled', u'ducked', u'sentenced',
# u'gaoled', u'perjured', u'absconded', u'bargained', u'overstayed',
# u'clerked']
#
# #o = [w.orth_ for w in words[1000:1010]]
# #assert o == [u'scorned', u'baled', u'righted', u'requested', u'swindled',
# # u'posited', u'firebombed', u'slimed', u'deferred', u'sagged']
# #o = [w.orth_ for w in words[50000:50010]]
# #assert o == [u'fb', u'ford', u'systems', u'puck', u'anglers', u'ik', u'tabloid',
# # u'dirty', u'rims', u'artists']

View File

@ -1,82 +0,0 @@
#!/bin/sed -f
# Sed script to produce Penn Treebank tokenization on arbitrary raw text.
# Yeah, sure.
# expected input: raw text with ONE SENTENCE TOKEN PER LINE
# by Robert MacIntyre, University of Pennsylvania, late 1995.
# If this wasn't such a trivial program, I'd include all that stuff about
# no warrantee, free use, etc. from the GNU General Public License. If you
# want to be picky, assume that all of its terms apply. Okay?
# attempt to get correct directional quotes
s=^"=`` =g
s=\([ ([{<]\)"=\1 `` =g
# close quotes handled at end
s=\.\.\.= ... =g
s=[,;:@#$%&]= & =g
# Assume sentence tokenization has been done first, so split FINAL periods
# only.
s=\([^.]\)\([.]\)\([])}>"']*\)[ ]*$=\1 \2\3 =g
# however, we may as well split ALL question marks and exclamation points,
# since they shouldn't have the abbrev.-marker ambiguity problem
s=[?!]= & =g
# parentheses, brackets, etc.
s=[][(){}<>]= & =g
# Some taggers, such as Adwait Ratnaparkhi's MXPOST, use the parsed-file
# version of these symbols.
# UNCOMMENT THE FOLLOWING 6 LINES if you're using MXPOST.
# s/(/-LRB-/g
# s/)/-RRB-/g
# s/\[/-LSB-/g
# s/\]/-RSB-/g
# s/{/-LCB-/g
# s/}/-RCB-/g
s=--= -- =g
# NOTE THAT SPLIT WORDS ARE NOT MARKED. Obviously this isn't great, since
# you might someday want to know how the words originally fit together --
# but it's too late to make a better system now, given the millions of
# words we've already done "wrong".
# First off, add a space to the beginning and end of each line, to reduce
# necessary number of regexps.
s=$= =
s=^= =
s="= '' =g
# possessive or close-single-quote
s=\([^']\)' =\1 ' =g
# as in it's, I'm, we'd
s='\([sSmMdD]\) = '\1 =g
s='ll = 'll =g
s='re = 're =g
s='ve = 've =g
s=n't = n't =g
s='LL = 'LL =g
s='RE = 'RE =g
s='VE = 'VE =g
s=N'T = N'T =g
s= \([Cc]\)annot = \1an not =g
s= \([Dd]\)'ye = \1' ye =g
s= \([Gg]\)imme = \1im me =g
s= \([Gg]\)onna = \1on na =g
s= \([Gg]\)otta = \1ot ta =g
s= \([Ll]\)emme = \1em me =g
s= \([Mm]\)ore'n = \1ore 'n =g
s= '\([Tt]\)is = '\1 is =g
s= '\([Tt]\)was = '\1 was =g
s= \([Ww]\)anna = \1an na =g
# s= \([Ww]\)haddya = \1ha dd ya =g
# s= \([Ww]\)hatcha = \1ha t cha =g
# clean out extra spaces
s= *= =g
s=^ *==g