load_initial_nverb_frames.py
10.2 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
#-*- coding:utf-8 -*-
#Copyright (c) 2014, 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 itertools
from operator import itemgetter
from django.core.management.base import BaseCommand
#from dictionary.common_func import arg_data_to_arg, args_to_position, \
# positions_to_frame
from dictionary.models import Argument, Argument_Model, Frame_Opinion, \
Frame_Opinion_Value, Lemma, positions_to_frame, \
get_or_create_position
NOUNS_ADDED_PATH = 'data/nverbs/nouns/added-merged_nouns_val.txt'
NOUNS_ERROR_PATH = 'data/nverbs/nouns/error-merged_nouns_val.txt'
NOUNS_FRAMES_PATH = 'data/nverbs/nouns/merged_nouns_val-poss.txt'
ADJS_ADDED_PATH = 'data/nverbs/adjs/added-merged_adjs_val.txt'
ADJS_ERROR_PATH = 'data/nverbs/adjs/error-merged_adjs_val.txt'
ADJS_FRAMES_PATH = 'data/nverbs/adjs/merged_adjs_val-P1.txt'
class Command(BaseCommand):
args = 'none'
help = """
Adds initial nverb frames.
"""
def handle(self, **options):
#add_initial_frames(NOUNS_FRAMES_PATH, NOUNS_ADDED_PATH, NOUNS_ERROR_PATH, 'noun')
add_initial_frames(ADJS_FRAMES_PATH, ADJS_ADDED_PATH, ADJS_ERROR_PATH, 'adj')
def add_initial_frames(frames_path, added_path, error_path, pos_tag):
try:
added_file = codecs.open(added_path, "wt", 'utf-8')
error_file = codecs.open(error_path, "wt", 'utf-8')
frames_file = codecs.open(frames_path, "rt", 'utf-8')
for line in frames_file:
line = line.strip()
pred_val = ''
if line.startswith('%'):
continue
lemma, frames_str, pred_val = get_frames_info(line)
try:
lemma_obj = Lemma.objects.get(entry_obj__name=lemma, old=False,
status__status=u'do obróbki',
entry_obj__pos__tag=pos_tag)
#lemma_obj.frames.clear()
print lemma_obj
try:
parse_and_add_frames(lemma_obj, frames_str, pred_val)
added_file.write(u'%s\n' % line)
except:
error_file.write(u'%s\n' % line)
except Lemma.DoesNotExist:
pass
finally:
added_file.close()
error_file.close()
frames_file.close()
def add_initial_frames_by_entries(entries, frames_path, added_path, error_path, pos_tag):
print 'Adding initial frames!'
try:
added_file = codecs.open(added_path, "wt", 'utf-8')
error_file = codecs.open(error_path, "wt", 'utf-8')
frames_file = codecs.open(frames_path, "rt", 'utf-8')
for line in frames_file:
line = line.strip()
pred_val = ''
if line.startswith('%'):
continue
lemma, frames_str, pred_val = get_frames_info(line)
if lemma in entries:
try:
lemma_obj = Lemma.objects.get(entry_obj__name=lemma, old=False,
status__status=u'do obróbki',
entry_obj__pos__tag=pos_tag)
print lemma_obj
try:
parse_and_add_frames(lemma_obj, frames_str, pred_val)
added_file.write(u'%s\n' % line)
except:
error_file.write(u'%s\n' % line)
except Lemma.DoesNotExist:
pass
finally:
added_file.close()
error_file.close()
frames_file.close()
def get_frames_info(line):
predicativity_val = ''
line_parts = line.split('\t')
lemma = line_parts[0].strip()
frames_str = line_parts[1].strip()
if len(line_parts) == 3 and line_parts[2] == 'PRED':
predicativity_val = 'pred'
return lemma, frames_str, predicativity_val
def parse_and_add_frames(lemma_obj, frames_str, predicativity_val):
poss_ls = []
valence_ls = [arg.strip() for arg in frames_str.split('+')]
for pos_arg in valence_ls:
pos_arg = pos_arg.strip()
possible_args = pos_arg.split('/')
possible_args = coordinate_arguments(possible_args)
poss_ls.append(possible_args)
confs = itertools.product(*poss_ls)
for frame_args in list(confs):
frame_args = list(set(frame_args)) #--> tutaj byl fuckup i tworzyly sie dziwne pozycje majace ten sam argument kilkukrotnie, moze ta linijka pomoze
frame_obj, frame_opinion_obj = create_frame(frame_args, predicativity_val)
lemma_obj.frames.add(frame_obj)
lemma_obj.frame_opinions.add(frame_opinion_obj)
def coordinate_arguments(arguments):
coordinated_args = []
for arg in arguments:
arg_type, attributes = arg_from_text_rep(arg)
case, preposition = get_arg_case_and_preposition(arg)
coordinated_arg = next((arg for arg in coordinated_args if (arg['case'] == case and
arg['preposition'] == preposition)), None)
if coordinated_arg and case:
coordinated_arg['argument'] += ';%s' % arg
else:
coordinated_arg = {'argument': arg,
'case': case,
'preposition': preposition}
coordinated_args.append(coordinated_arg)
if arg_type == 'ncp':
additional_arg = u'np(%s)' % case
coordinated_arg['argument'] += ';%s' % additional_arg
elif arg_type == 'prepncp':
additional_arg = u'prepnp(%s,%s)' % (preposition, case)
coordinated_arg['argument'] += ';%s' % additional_arg
return [arg['argument'] for arg in coordinated_args]
def arg_from_text_rep(argument):
attributes = []
arg_parts = argument.split('(')
arg_type = arg_parts[0]
if len(arg_parts) > 1:
attributes = arg_parts[1].rstrip(')').replace("'", "").split(',')
return arg_type, attributes
def get_arg_case_and_preposition(argument):
case = ''
preposition = ''
argument = arg_conversion(argument)
arg_type, attributes = arg_from_text_rep(argument)
argument_model = Argument_Model.objects.get(arg_model_name=arg_type)
attribute_models = argument_model.atribute_models.order_by('priority')
for attr_model, attr_text_rep in zip(attribute_models, attributes):
if attr_model.atr_model_name == u'PRZYPADEK':
case = attr_text_rep
elif attr_model.atr_model_name == u'PRZYIMEK':
preposition = attr_text_rep
return case, preposition
def arg_conversion(arg_text_rep):
arg_text_rep = arg_text_rep.replace('!', '').replace('*', '').replace('?', '')
if arg_text_rep == 'advp':
arg_text_rep = u'xp(_)'
elif arg_text_rep.startswith('comprepnp'):
arg_text_rep = arg_text_rep.replace("'", "").replace(',gen', '')
return arg_text_rep
def create_frame(frame_args, predicativity_val):
positions_objs, frame_opinion_value = get_positions(frame_args)
frame_obj = positions_to_frame(positions_objs,
reflex='',
negativity='',
predicativity=predicativity_val,
aspect='')
frame_opinion_obj, xx = Frame_Opinion.objects.get_or_create(frame=frame_obj,
value=frame_opinion_value)
return frame_obj, frame_opinion_obj
def get_positions(args_strs):
poss_objs = []
frame_opinions = []
for poss_args_str in args_strs:
frame_opinions.append(possible_frame_opinion(poss_args_str))
poss_objs.append(create_position(poss_args_str))
frame_opinion = sorted(frame_opinions, key=itemgetter('priority'), reverse=False)[0]
frame_opinion_value = Frame_Opinion_Value.objects.get(value=frame_opinion['opinion'])
return poss_objs, frame_opinion_value
def possible_frame_opinion(arg_str):
opinion = {'opinion': 'pewny',
'priority': '4'}
if '!' in arg_str:
opinion = {'opinion': u'zły',
'priority': '1'}
elif '?' in arg_str:
opinion = {'opinion': u'wątpliwy',
'priority': '2'}
elif '*' in arg_str:
opinion = {'opinion': u'archaiczny',
'priority': '3'}
return opinion
def create_position(args_str):
arg_objs = []
for arg_text_rep in args_str.split(';'):
arg_text_rep = arg_conversion(arg_text_rep)
# try:
arg_obj = Argument.objects.get(text_rep=arg_text_rep)
# except Argument.DoesNotExist: # TODO wylaczac przy wstepnym wrzucaniu hasel
# arg_type, attributes = arg_from_text_rep(arg_text_rep)
# arg_obj = arg_data_to_arg(arg_type, attributes)
arg_objs.append(arg_obj)
pos_obj = get_or_create_position(categories=[], arguments=arg_objs)
return pos_obj