parent
4175c45ceb
commit
048825648a
@ -1,11 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<module type="PYTHON_MODULE" version="4">
|
||||
<component name="NewModuleRootManager">
|
||||
<content url="file://$MODULE_DIR$" />
|
||||
<orderEntry type="jdk" jdkName="Python 3.5.2 (~/miniconda3/bin/python)" jdkType="Python SDK" />
|
||||
<orderEntry type="sourceFolder" forTests="false" />
|
||||
</component>
|
||||
<component name="TestRunnerService">
|
||||
<option name="PROJECT_TEST_RUNNER" value="Unittests" />
|
||||
</component>
|
||||
</module>
|
@ -1,9 +0,0 @@
|
||||
<component name="ProjectDictionaryState">
|
||||
<dictionary name="luka">
|
||||
<words>
|
||||
<w>accentuations</w>
|
||||
<w>nonresonant</w>
|
||||
<w>overfitting</w>
|
||||
</words>
|
||||
</dictionary>
|
||||
</component>
|
@ -1,6 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="Encoding">
|
||||
<file url="PROJECT" charset="UTF-8" />
|
||||
</component>
|
||||
</project>
|
@ -1,22 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.5.2 (~/miniconda3/bin/python)" project-jdk-type="Python SDK" />
|
||||
<component name="SvnConfiguration">
|
||||
<configuration>$USER_HOME$/.subversion</configuration>
|
||||
</component>
|
||||
<component name="masterDetails">
|
||||
<states>
|
||||
<state key="ScopeChooserConfigurable.UI">
|
||||
<settings>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
</states>
|
||||
</component>
|
||||
</project>
|
@ -1,8 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectModuleManager">
|
||||
<modules>
|
||||
<module fileurl="file://$PROJECT_DIR$/.idea/accetuation.iml" filepath="$PROJECT_DIR$/.idea/accetuation.iml" />
|
||||
</modules>
|
||||
</component>
|
||||
</project>
|
@ -1,6 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="VcsDirectoryMappings">
|
||||
<mapping directory="$PROJECT_DIR$" vcs="Git" />
|
||||
</component>
|
||||
</project>
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,71 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import pickle
|
||||
import numpy as np
|
||||
from keras.models import load_model
|
||||
import sys
|
||||
|
||||
from prepare_data import *
|
||||
|
||||
# obtain data from parameters
|
||||
if len(sys.argv) < 3:
|
||||
print('Please provide arguments for this script to work. First argument should be location of file with unaccented words and morphological data '
|
||||
'and second the name of file where you would like to save file to. Example: python accentuate.py \'test_data/unaccented_dictionary\' '
|
||||
'\'test_data/accented_data\'')
|
||||
raise Exception
|
||||
read_location = sys.argv[1]
|
||||
write_location = sys.argv[2]
|
||||
|
||||
# get environment variables necessary for calculations
|
||||
pickle_input = open('preprocessed_data/environment.pkl', 'rb')
|
||||
environment = pickle.load(pickle_input)
|
||||
dictionary = environment['dictionary']
|
||||
max_word = environment['max_word']
|
||||
max_num_vowels = environment['max_num_vowels']
|
||||
vowels = environment['vowels']
|
||||
accented_vowels = environment['accented_vowels']
|
||||
feature_dictionary = environment['feature_dictionary']
|
||||
syllable_dictionary = environment['syllable_dictionary']
|
||||
|
||||
# load models
|
||||
data = Data('l', shuffle_all_inputs=False)
|
||||
letter_location_model, syllable_location_model, syllabled_letters_location_model = data.load_location_models(
|
||||
'cnn/word_accetuation/cnn_dictionary/v5_3/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllables/v3_3/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllabled_letters/v3_3/20_final_epoch.h5')
|
||||
|
||||
letter_location_co_model, syllable_location_co_model, syllabled_letters_location_co_model = data.load_location_models(
|
||||
'cnn/word_accetuation/cnn_dictionary/v5_2/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllables/v3_2/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllabled_letters/v3_2/20_final_epoch.h5')
|
||||
|
||||
letter_type_model, syllable_type_model, syllabled_letter_type_model = data.load_type_models(
|
||||
'cnn/accent_classification/letters/v3_1/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllables/v2_1/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllabled_letters/v2_1/20_final_epoch.h5')
|
||||
|
||||
letter_type_co_model, syllable_type_co_model, syllabled_letter_type_co_model = data.load_type_models(
|
||||
'cnn/accent_classification/letters/v3_0/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllables/v2_0/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllabled_letters/v2_0/20_final_epoch.h5')
|
||||
|
||||
# read from data
|
||||
content = data._read_content(read_location)
|
||||
|
||||
# format data for accentuate_word function it has to be like [['besedišči', '', 'Ncnpi', 'besedišči'], ]
|
||||
content = [[el[0], '', el[1][:-1], el[0]] for el in content[:-1]]
|
||||
|
||||
# use environment variables and models to accentuate words
|
||||
data = Data('l', shuffle_all_inputs=False)
|
||||
location_accented_words, accented_words = data.accentuate_word(content, letter_location_model, syllable_location_model, syllabled_letters_location_model,
|
||||
letter_location_co_model, syllable_location_co_model, syllabled_letters_location_co_model,
|
||||
letter_type_model, syllable_type_model, syllabled_letter_type_model,
|
||||
letter_type_co_model, syllable_type_co_model, syllabled_letter_type_co_model,
|
||||
dictionary, max_word, max_num_vowels, vowels, accented_vowels, feature_dictionary, syllable_dictionary)
|
||||
|
||||
# save accentuated words
|
||||
with open(write_location, 'w') as f:
|
||||
for i in range(len(location_accented_words)):
|
||||
f.write(location_accented_words[i] + ' ' + accented_words[i] + '\n')
|
||||
f.write('\n')
|
@ -0,0 +1,79 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, '../../../')
|
||||
from prepare_data import *
|
||||
|
||||
import pickle
|
||||
|
||||
# from keras import backend as Input
|
||||
np.random.seed(7)
|
||||
|
||||
# obtain data from parameters
|
||||
if len(sys.argv) < 3:
|
||||
print('Please provide arguments for this script to work. First argument should be location of file with unaccented words and morphological data, '
|
||||
'second the name of file where you would like to save results to and third location of ReLDI tagger. Example: python accentuate.py '
|
||||
'\'test_data/original_connected_text\' \'test_data/accented_connected_text\' \'../reldi_tagger\'')
|
||||
raise Exception
|
||||
read_location = sys.argv[1]
|
||||
write_location = sys.argv[2]
|
||||
reldi_location = sys.argv[3]
|
||||
|
||||
# get environment variables necessary for calculations
|
||||
pickle_input = open('preprocessed_data/environment.pkl', 'rb')
|
||||
environment = pickle.load(pickle_input)
|
||||
dictionary = environment['dictionary']
|
||||
max_word = environment['max_word']
|
||||
max_num_vowels = environment['max_num_vowels']
|
||||
vowels = environment['vowels']
|
||||
accented_vowels = environment['accented_vowels']
|
||||
feature_dictionary = environment['feature_dictionary']
|
||||
syllable_dictionary = environment['syllable_dictionary']
|
||||
|
||||
# get models
|
||||
data = Data('l', shuffle_all_inputs=False)
|
||||
letter_location_model, syllable_location_model, syllabled_letters_location_model = data.load_location_models(
|
||||
'cnn/word_accetuation/cnn_dictionary/v5_3/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllables/v3_3/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllabled_letters/v3_3/20_final_epoch.h5')
|
||||
|
||||
letter_location_co_model, syllable_location_co_model, syllabled_letters_location_co_model = data.load_location_models(
|
||||
'cnn/word_accetuation/cnn_dictionary/v5_2/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllables/v3_2/20_final_epoch.h5',
|
||||
'cnn/word_accetuation/syllabled_letters/v3_2/20_final_epoch.h5')
|
||||
|
||||
letter_type_model, syllable_type_model, syllabled_letter_type_model = data.load_type_models(
|
||||
'cnn/accent_classification/letters/v3_1/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllables/v2_1/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllabled_letters/v2_1/20_final_epoch.h5')
|
||||
|
||||
letter_type_co_model, syllable_type_co_model, syllabled_letter_type_co_model = data.load_type_models(
|
||||
'cnn/accent_classification/letters/v3_0/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllables/v2_0/20_final_epoch.h5',
|
||||
'cnn/accent_classification/syllabled_letters/v2_0/20_final_epoch.h5')
|
||||
|
||||
# get word tags
|
||||
tagged_words, original_text = data.tag_words(reldi_location, read_location)
|
||||
|
||||
# find accentuation locations
|
||||
predictions = data.get_ensemble_location_predictions(tagged_words, letter_location_model, syllable_location_model, syllabled_letters_location_model,
|
||||
letter_location_co_model, syllable_location_co_model, syllabled_letters_location_co_model,
|
||||
dictionary, max_word, max_num_vowels, vowels, accented_vowels, feature_dictionary,
|
||||
syllable_dictionary)
|
||||
|
||||
location_accented_text = data.create_connected_text_locations(tagged_words, original_text, predictions, vowels)
|
||||
|
||||
# accentuate text
|
||||
location_y = np.around(predictions)
|
||||
type_predictions = data.get_ensemble_type_predictions(tagged_words, location_y, letter_type_model, syllable_type_model, syllabled_letter_type_model,
|
||||
letter_type_co_model, syllable_type_co_model, syllabled_letter_type_co_model,
|
||||
dictionary, max_word, max_num_vowels, vowels, accented_vowels, feature_dictionary,
|
||||
syllable_dictionary)
|
||||
|
||||
accented_text = data.create_connected_text_accented(tagged_words, original_text, type_predictions, location_y, vowels, accented_vowels)
|
||||
|
||||
# save accentuated text
|
||||
with open(write_location, 'w') as f:
|
||||
f.write(accented_text)
|
@ -0,0 +1,74 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from __future__ import unicode_literals
|
||||
# text in Western (Windows 1252)
|
||||
|
||||
import pickle
|
||||
import numpy as np
|
||||
np.random.seed(7)
|
||||
|
||||
import sys
|
||||
from prepare_data import *
|
||||
|
||||
# preprocess data
|
||||
# data = Data('l', allow_shuffle_vector_generation=True, save_generated_data=False, shuffle_all_inputs=True)
|
||||
data = Data('l', save_generated_data=False, shuffle_all_inputs=True)
|
||||
data.generate_data('../../internal_representations/inputs/letters_word_accentuation_train',
|
||||
'../../internal_representations/inputs/letters_word_accentuation_test',
|
||||
'../../internal_representations/inputs/letters_word_accentuation_validate',
|
||||
content_location='../accetuation/data/',
|
||||
content_name='SlovarIJS_BESEDE_utf8.lex',
|
||||
inputs_location='../accetuation/cnn/internal_representations/inputs/',
|
||||
content_shuffle_vector='content_shuffle_vector',
|
||||
shuffle_vector='shuffle_vector')
|
||||
|
||||
# combine all data (if it is unwanted comment code below)
|
||||
data.x_train = np.concatenate((data.x_train, data.x_test, data.x_validate), axis=0)
|
||||
data.x_other_features_train = np.concatenate((data.x_other_features_train, data.x_other_features_test, data.x_other_features_validate), axis=0)
|
||||
data.y_train = np.concatenate((data.y_train, data.y_test, data.y_validate), axis=0)
|
||||
|
||||
# build neural network architecture
|
||||
nn_output_dim = 10
|
||||
batch_size = 16
|
||||
actual_epoch = 20
|
||||
num_fake_epoch = 20
|
||||
|
||||
conv_input_shape=(23, 36)
|
||||
othr_input = (140, )
|
||||
|
||||
conv_input = Input(shape=conv_input_shape, name='conv_input')
|
||||
x_conv = Conv1D(115, (3), padding='same', activation='relu')(conv_input)
|
||||
x_conv = Conv1D(46, (3), padding='same', activation='relu')(x_conv)
|
||||
x_conv = MaxPooling1D(pool_size=2)(x_conv)
|
||||
x_conv = Flatten()(x_conv)
|
||||
|
||||
othr_input = Input(shape=othr_input, name='othr_input')
|
||||
|
||||
x = concatenate([x_conv, othr_input])
|
||||
x = Dense(256, activation='relu')(x)
|
||||
x = Dropout(0.3)(x)
|
||||
x = Dense(256, activation='relu')(x)
|
||||
x = Dropout(0.3)(x)
|
||||
x = Dense(256, activation='relu')(x)
|
||||
x = Dropout(0.3)(x)
|
||||
x = Dense(nn_output_dim, activation='sigmoid')(x)
|
||||
|
||||
model = Model(inputs=[conv_input, othr_input], outputs=x)
|
||||
opt = optimizers.Adam(lr=1E-3, beta_1=0.9, beta_2=0.999, epsilon=1e-08)
|
||||
model.compile(loss='mean_squared_error', optimizer=opt, metrics=[actual_accuracy,])
|
||||
# model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])
|
||||
|
||||
|
||||
# start learning
|
||||
history = model.fit_generator(data.generator('train', batch_size, content_name='SlovarIJS_BESEDE_utf8.lex', content_location='../accetuation/data/'),
|
||||
data.x_train.shape[0]/(batch_size * num_fake_epoch),
|
||||
epochs=actual_epoch*num_fake_epoch,
|
||||
validation_data=data.generator('test', batch_size),
|
||||
validation_steps=data.x_test.shape[0]/(batch_size * num_fake_epoch))
|
||||
|
||||
|
||||
# save generated data
|
||||
name = 'test_data/20_epoch'
|
||||
model.save(name + '.h5')
|
||||
output = open(name + '_history.pkl', 'wb')
|
||||
pickle.dump(history.history, output)
|
||||
output.close()
|
Binary file not shown.
@ -0,0 +1,6 @@
|
||||
absolutístični absolutístični
|
||||
spoštljívejše spoštljívejše
|
||||
tresóče tresóče
|
||||
razneséna raznesěna
|
||||
žvížgih žvížgih
|
||||
|
@ -0,0 +1,6 @@
|
||||
absolutistični Afpmsay-n
|
||||
spoštljivejše Afcfsg
|
||||
tresoče Afpfsg
|
||||
raznesena Vmp--sfp
|
||||
žvižgih Ncmdl
|
||||
|
Loading…
Reference in new issue