add_verbs.py
10.4 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
#-*- coding:utf-8 -*-
#Copyright (c) 2012, Bartłomiej Nitoń
#All rights reserved.
#Redistribution and use in source and binary forms, with or without modification, are permitted provided
#that the following conditions are met:
# Redistributions of source code must retain the above copyright notice, this list of conditions and
# the following disclaimer.
# Redistributions in binary form must reproduce the above copyright notice, this list of conditions
# and the following disclaimer in the documentation and/or other materials provided with the distribution.
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED
# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
# PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
# ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
import codecs
import re
from django.core.management.base import BaseCommand
from lxml import etree
from dictionary.models import Entry, Lemma, Lemma_Status, POS, Vocabulary
VERBS_IN_DICT = 600
POLANSKI_PATH = 'data/dictionary.xml'
B_PATH = 'data/B_frames/B_cz_frames.txt'
PATH_300M = 'data/susp-1.1-verbs-300M-counts.txt'
NEW_VERBS_PATH = 'data/new_verbs_140213.txt'
NWALENTY_PATH = 'data/checked-nwalenty.txt'
# dodawanie nowych haseł, skryptami:
# add_verbs
# load_frequency
# !!! po wprowadzeniu haseł sprawdzić czy nie ma niedodanych multirelacji postaci \).*\( !!!!!!!!
ADJS_RELATIONS_PATH = 'data/nverbs/relations/merged_adjs+verb-freq.txt'
NOUNS_RELATIONS_PATH = 'data/nverbs/relations/nouns+verb-freq.txt'
class Command(BaseCommand):
args = 'none'
help = """
Add verbs from given freqency list. Script checks if verb
is not already included in Slowal tool database.
"""
def handle(self, **options):
#add_verbs_intersec_freq()
#get_new_verbs()
#add_verbs(NEW_VERBS_PATH, 'data/added_verbs_20140701_pol_i_tajny.txt')
#add_verbs(PATH_300M, 'data/added_verbs_20140701.txt')
verbs = add_verbs('data/new+plwn-chosen.txt',
'data/added_verbs_20150701.txt')
add_relations_by_verb_entries(verbs, ADJS_RELATIONS_PATH, 'adj')
add_relations_by_verb_entries(verbs, NOUNS_RELATIONS_PATH, 'noun')
def add_verbs(verbs_path, added_path):
added_verbs = []
added_file = codecs.open(added_path, 'wt', 'utf-8')
dict_basename = 'clarin'
dict = 18
new_last_dict = 18
verbs_per_dict = VERBS_IN_DICT
min_freq = 0
with codecs.open(verbs_path, 'rt', 'utf8') as infile:
if dict == 0:
new_voc = Vocabulary(name=dict_basename)
new_voc.save()
else:
new_voc = Vocabulary(name=dict_basename+str(dict))
new_voc.save()
initial_status = Lemma_Status.objects.order_by('priority')[0]
for line in infile:
line = line.strip()
if line.startswith('*'):
continue
print line
line_ls = line.split()
word = line_ls[0].strip()
freq = int(line_ls[1].strip())
lemmas = Lemma.objects.filter(entry = word)
if lemmas.count() == 0 and freq >= min_freq:
if verbs_per_dict == 0:
verbs_per_dict = VERBS_IN_DICT
dict += 1
if dict > new_last_dict:
break
else:
new_voc = Vocabulary(name=dict_basename+str(dict))
new_voc.save()
entry_obj = get_verb_entry(word)
new_lemma = Lemma(entry_obj=entry_obj,
entry=word, vocabulary=new_voc,
status=initial_status, old=False)
new_lemma.save()
verbs_per_dict -= 1
added_file.write('%s\t%s\t%d\n' % (dict_basename+str(dict), word, freq))
added_verbs.append(word)
added_file.close()
return added_verbs
def get_verb_entry(verb):
try:
entry = Entry.objects.get(name=verb, pos__tag='verb')
except Entry.DoesNotExist:
try:
entry = Entry.objects.get(name=verb, pos__tag='unk')
verb_pos = POS.objects.get(tag='verb')
entry.pos = verb_pos
entry.save()
except Entry.DoesNotExist:
verb_pos = POS.objects.get(tag='verb')
entry = Entry(name=verb, pos=verb_pos)
entry.save()
return entry
def add_relations_by_verb_entries(entries, relations_path, pos_tag):
print 'Adding relations!'
pos = POS.objects.get(tag=pos_tag)
try:
freq_file = codecs.open(relations_path, "rt", 'utf-8')
for line in freq_file:
line_ls = line.split()
verb = line_ls[3].lstrip('(').strip()
try:
nverb = line_ls[0].strip()
if verb in entries:
verb_obj = Lemma.objects.get(old=False, entry=verb, entry_obj__pos__tag='verb')
nverb_obj = Lemma.objects.get(old=False, entry=nverb, entry_obj__pos=pos)
nverb_entry = nverb_obj.entry_obj
verb_entry = verb_obj.entry_obj
verb_entry.rel_entries.add(nverb_entry)
nverb_entry.rel_entries.add(verb_entry)
print line
except Lemma.DoesNotExist:
pass
finally:
freq_file.close()
def get_polanski_verbs(inpath):
verbs = []
tree = etree.parse(inpath)
words = tree.xpath("//*[local-name() = 'orth']")
for word in words:
verb = word.text.replace(u'się', '').strip()
if verb not in verbs:
verbs.append(verb)
print verb
return verbs
def get_B_verbs(inpath):
verbs = []
try:
f = codecs.open(inpath, "rt", 'utf-8')
for line in f:
line_pattern = re.compile(ur"^([^\d]+)[\d]+(.*)$")
m = line_pattern.match(line)
if not m:
print '!!!!!!!!!!!!!!!!match error!!!!!!!!!!!!!!!!!!!!!!!'
if m:
lemma_str = m.group(1).strip()
lemma_ls = lemma_str.split()
line = line.strip()
if not lemma_ls[0] in verbs:
verbs.append(lemma_ls[0])
finally:
f.close()
return verbs
def load_B_lemmas(inpath, voc_name):
print 'Loading %s dict.' % (voc_name)
try:
f = codecs.open(inpath, "rt", 'utf-8')
voc_obj, xx = Vocabulary.objects.get_or_create(name=voc_name)
initial_status = Lemma_Status.objects.get(status=u'do obróbki')
for line in f:
line_ls = line.split()
entry = line_ls[1].strip()
try:
Lemma.objects.get(old=False, entry=entry)
except Lemma.DoesNotExist:
lemma_obj, created = Lemma.objects.get_or_create(old=False,
entry=entry,
vocabulary=voc_obj,
status=initial_status)
if created:
voc_obj.lemmas.add(lemma_obj)
finally:
f.close()
def compare_to_300M(pol_verbs, b_verbs, path_300M, outpath, nwalenty_path):
try:
pol_verbs_to_check = []
file_300M = codecs.open(path_300M, "rt", 'utf-8')
outfile = codecs.open(outpath, 'wt', 'utf-8')
nwalenty_file = codecs.open(nwalenty_path, 'wt', 'utf-8')
for line in file_300M:
print line.strip()
if line.strip().startswith('*'):
continue
line_ls = line.split()
entry = line_ls[0].strip()
if entry in pol_verbs and not entry in b_verbs:
pol_verbs_to_check.append(entry)
if Lemma.objects.filter(old=False, entry=entry).exists():
continue
if entry in b_verbs or entry in pol_verbs:
outfile.write(line)
else:
nwalenty_file.write(line)
finally:
file_300M.close()
outfile.close()
def get_new_verbs():
pol_verbs = get_polanski_verbs(POLANSKI_PATH)
b_verbs = get_B_verbs(B_PATH)
compare_to_300M(pol_verbs, b_verbs, PATH_300M, NEW_VERBS_PATH, NWALENTY_PATH)
def add_verbs_intersec_freq():
verbs_path = 'data/polanski_verbs_freq_list.txt'
added_path = 'data/added_verbs_clarin6.txt'
added_file = codecs.open(added_path, 'wt', 'utf-8')
dict_basename = 'clarin'
dict = 6
new_last_dict = 10
verbs_per_dict = VERBS_IN_DICT
with codecs.open(verbs_path,'rt', 'utf8') as infile:
new_voc = Vocabulary(name=dict_basename+str(dict))
new_voc.save()
initial_status = Lemma_Status.objects.order_by('priority')[0]
for line in infile:
line = line.strip()
ngram_pattern = re.compile(ur'^[\s]*([\d]+)[\s]*([^\s]+).*$')
m = ngram_pattern.match(line)
if m:
freq = int(m.group(1).strip())
word = m.group(2).strip()
lemmas = Lemma.objects.filter(entry = word)
if lemmas.count() == 0:
if verbs_per_dict == 0:
verbs_per_dict = VERBS_IN_DICT
dict += 1
if dict > new_last_dict:
break
else:
new_voc = Vocabulary(name=dict_basename+str(dict))
new_voc.save()
new_lemma = Lemma(entry=word, vocabulary=new_voc,
status=initial_status, old=False)
new_lemma.save()
verbs_per_dict -= 1
added_file.write(dict_basename+str(dict) + ' ' + word +
' ' + str(freq) + '\n')
added_file.close()