prep_freq_list.py
2.64 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
#-*- 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.
"""Script for getting prepositions usage frequency list."""
from django.core.management.base import BaseCommand
from dictionary.models import *
class Command(BaseCommand):
'SloVal command for getting preposition frequency list.'
help = 'Get prepositions frequency use list.'
def handle(self, **options):
prep_freq_ls()
def prep_freq_ls():
'Get prepositions frequency list.'
print 'Be patient, it can take a while.'
prep_ls = []
for prep in Atribute_Model.objects.get(atr_model_name='PRZYIMEK').atribute_values.all():
prep_ls.append({'prep' : prep.value,
'count': 0})
lemmas = Lemma.objects.filter(old=False, status__status=u'sprawdzone')
for lemma in lemmas.all():
for frame in lemma.frames.all():
for position in frame.positions.all():
for arg in position.arguments.all():
for attr in arg.atributes.filter(Q(type='PRZYIMEK') | Q(type='PRZYIMEK1')):
prep = (item for item in prep_ls if item['prep'] == attr.atribute_value.value).next()
prep['count'] += 1
prep_ls.sort(key=lambda x:x['count'])
prep_ls.reverse()
for prep in prep_ls:
print smart_str(prep['prep']) + ': ' + str(prep['count'])