lkrsnik/STARK
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Modified README.md + Added licence

Browse Source
This commit is contained in:
Luka 2019-12-20 08:35:08 +01:00
parent e90374b643
commit 7b641382d6
15 changed files with 4228 additions and 269 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -4,5 +4,5 @@ internal_saves/
__pycache__/
results/
data/
config.ini
config2.ini
configs/

202
LICENSE.txt Normal file
View File

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

37
README.md
View File

@ -1,4 +1,6 @@
# dependency parsetree
# STARK: a tool for statisical analysis of dependency-parsed corpora
STARK is a python-based command-line tool for extraction of dependency trees from parsed corpora based on various user-defined criteria. It is primarily aimed at processing corpora based on the [Universal Dependencies](https://universaldependencies.org/) annotation scheme, but it also takes any other corpus in the [CONLL-U](https://universaldependencies.org/format.html) format as input.
## Linux installation and execution
### Installation
Install python 3 on your sistem.
@ -24,8 +26,37 @@ python3 dependency-parsetree.py --config_file=<PATH TO .ini file>
Example:
```bash
python3 dependency-parsetree.py --config_file=official_config.ini
python3 dependency-parsetree.py --config_file=config.ini
```
## Parameter settings
The type of trees to be extracted can be defined through several parameters in the `config.ini` configuration file.
[![alt text](https://gitea.cjvt.si/lkrsnik/dependency_parsing/raw/branch/master/Clarin-SI-logo.png)](http://www.clarin.si/info/about/)
- `input`: location of the input file or directory (parsed corpus in .conllu)
- `output`: location of the output file (extraction results)
- `internal_saves`: location of the folder with files for optimization during processing
- `cpu_cores`: number of CPU cores to be used during processing
- `tree_size`: number of nodes in the tree (integer or range)
- `tree_type`: extraction of all possible subtrees or full subtrees only (values *all* or *complete*)
- `dependency_type`: extraction of labeled or unlabeled trees (values *labeled* or *unlabeled*)
- `node_order`: extraction of trees by taking surface word order into account (values *free* or *fixed*)
- `node_type`: type of nodes under investigation (values *form*, *lemma*, *upos*, *xpos*, *feats* or *deprel*)
- `label_whitelist`: predefined list of dependency labels allowed in the extracted tree
- `root_whitelist`: predefined characteristics of the root node
- `query`: predefined tree structure based on the modified Turku NLP [query language](http://bionlp.utu.fi/searchexpressions-new.html).
- `print_root`: print root node information in the output file (values *yes* or *no*)
- `nodes_number`: print the number of nodes in the tree in the output file (values *yes* or *no*)
- `association_measures`: calculate the strength of association between nodes by MI, MI3, t-test, logDice, Dice and simple-LL scores (values *yes* or *no*)
- `frequency_threshold`: minimum frequency of occurrences of the tree in the corpus
- `lines_threshold`: maximum number of trees in the output
## Output
The tool returns the resulting list of all relevant trees in the form of a tab-separated `.tsv` file with information on the tree structure, its frequency and other relevant information in relation to specific parameter settings. The tool does not support any data visualization, however, the output structure of the tree is directly trasnferable to the [Dep_Search](http://bionlp-www.utu.fi/dep_search/) concordancing service giving access to specific examples in many corpora.
## Credits
This program was developed by Luka Krsnik in collaboration with Kaja Dobrovoljc and Marko Robnik Šikonja and with financial support from [CLARIN.SI](https://www.clarin.si/).
[![alt text](https://gitea.cjvt.si/lkrsnik/dependency_parsing/raw/branch/master/logos/CLARIN.png)](http://www.clarin.si/info/about/)
[![alt text](https://gitea.cjvt.si/lkrsnik/dependency_parsing/raw/branch/master/logos/CJVT.png)](https://www.cjvt.si/en/)
[![alt text](https://gitea.cjvt.si/lkrsnik/dependency_parsing/raw/branch/master/logos/FRI.png)](https://www.fri.uni-lj.si/en/about)
[![alt text](https://gitea.cjvt.si/lkrsnik/dependency_parsing/raw/branch/master/logos/FF.png)](http://www.ff.uni-lj.si/an/aboutFaculty/about_faculty)

140
Result.py
View File

@ -1,140 +0,0 @@
import copy
import string
from generic import create_output_string_form, create_output_string_deprel, create_output_string_lemma, \
create_output_string_upos, create_output_string_xpos, create_output_string_feats, generate_key
class Result(object):
def __init__(self, node, architecture_order, create_output_strings):
# self.array = [[create_output_string(node) for create_output_string in create_output_strings]]
# if create_output_string_lemma in create_output_strings:
# key_array = [[create_output_string(node) if create_output_string != create_output_string_lemma else 'L=' + create_output_string(node) for create_output_string in create_output_strings]]
# else:
# key_array = self.array
# if len(self.array[0]) > 1:
# self.key = '&'.join(key_array[0])
# else:
# # output_string = create_output_strings[0](node)
# self.key = key_array[0][0]
self.array, self.key = generate_key(node, create_output_strings)
self.key_free = self.key
# self.array = [[output_string]]
self.order_key = str(architecture_order)
self.order = [architecture_order]
self.deprel = node.deprel.get_value()
# order with original numbers in sentences
# self.order = str([architecture_order])
# order with numbers from 0 to n of n-gram
self.root = ''
self.final_order = ''
self.separators = []
def __repr__(self):
return self.key
def add(self, string, architecture_order, separator, is_left):
if is_left:
self.array = [string] + self.array
self.order = [architecture_order] + self.order
# self.order = [architecture_order] + self.order
self.separators = [separator] + self.separators
self.key = string + ' ' + separator + ' ' + self.key
self.order_key = architecture_order + ' ' + separator + ' ' + self.order_key
else:
self.array += [string]
self.order += [architecture_order]
# self.order += [architecture_order]
self.separators += [separator]
self.key += ' ' + separator + ' ' + string
self.order_key += ' ' + separator + ' ' + architecture_order
def add_separator(self, separator, left=True):
self_copy = copy.copy(self)
if left:
self_copy.separators += [separator]
self_copy.key += separator
self_copy.order_key += separator
else:
self_copy.separators = [separator] + self_copy.separators
self_copy.key = separator + self_copy.key
self_copy.order_key = separator + self_copy.order_key
return self_copy
# def merge_results2(self):
def merge_results(self, right_t, separator, left=True):
left_tree = copy.copy(self)
right_tree = copy.copy(right_t)
if separator:
if left:
# merged_results.append(left_part + right_part + separator)
left_tree.key = left_tree.key + right_tree.key + separator
left_tree.order_key = left_tree.order_key + right_tree.order_key + separator
left_tree.array = left_tree.array + right_tree.array
left_tree.order = left_tree.order + right_tree.order
# left_tree.order = str([architecture_order])
left_tree.separators = left_tree.separators + right_tree.separators + [separator]
else:
# merged_results.append(left_part + separator + right_part)
left_tree.key = left_tree.key + separator + right_tree.key
left_tree.order_key = left_tree.order_key + separator + right_tree.order_key
left_tree.array = left_tree.array + right_tree.array
left_tree.order = left_tree.order + right_tree.order
# left_tree.order = str([architecture_order])
left_tree.separators = left_tree.separators + [separator] + right_tree.separators
else:
# merged_results.append(left_part + right_part)
left_tree.key = left_tree.key + right_tree.key
left_tree.order_key = left_tree.order_key + right_tree.order_key
left_tree.array = left_tree.array + right_tree.array
left_tree.order = left_tree.order + right_tree.order
# left_tree.order = str([architecture_order])
left_tree.separators = left_tree.separators + right_tree.separators
return left_tree
def extend_answer(self, other_answer, separator):
self.array.extend(other_answer.array)
self.order.extend(other_answer.order)
self.key += separator + other_answer.key
self.order_key += separator + other_answer.order_key
self.separators.extend(separator)
def put_in_bracelets(self, inplace=False):
if inplace:
self.key = ('(' + self.key + ')')
self.order_key = ('(' + self.order_key + ')')
return
result = copy.copy(self)
result.key = ('(' + result.key + ')')
result.order_key = ('(' + result.order_key + ')')
return result
def finalize_result(self):
result = copy.copy(self)
result.key = result.key[1:-1]
result.set_root()
# create order letters
order_letters = [''] * len(result.order)
for i in range(len(result.order)):
ind = result.order.index(min(result.order))
result.order[ind] = 10000
order_letters[ind] = string.ascii_uppercase[i]
result.order = ''.join(order_letters)
# result.order_key = result.order_key[1:-1]
# TODO When tree is finalized create relative word order (alphabet)!
return result
def set_root(self):
if len(self.array[0]) > 1:
self.root = '&'.join(self.array[0])
else:
# output_string = create_output_strings[0](node)
self.root = self.array[0][0]

14
ResultNode.py
View File

@ -1,3 +1,17 @@
# Copyright 2019 CJVT
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from generic import generate_key, generate_name

14
ResultTree.py
View File

@ -1,3 +1,17 @@
# Copyright 2019 CJVT
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import copy
import string

3
Tree.py
View File

@ -1,7 +1,6 @@
import sys
from copy import copy
from Result import Result
from ResultNode import ResultNode
from ResultTree import ResultTree
from Value import Value
@ -270,7 +269,7 @@ class Tree(object):
# TODO add order rearagement (TO KEY)
complete_answers[i].extend(new_complete_answers[i])
# if create_output_string_form(self) == 'Dogodek':
# if create_output_string_lemma(self) == 'drama':
# print('HERE!@@!')
# if create_output_string_form(self) == 'vpiti':
# print('HERE!@@!')

14
Value.py
View File

@ -1,3 +1,17 @@
# Copyright 2019 CJVT
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
class Value(object):
def __init__(self, value):
self.value = value

0
official_config.ini → config.ini
View File

284
dependency-parsetree.py
View File

@ -1,4 +1,18 @@
#!/usr/bin/env python
# Copyright 2019 CJVT
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import argparse
import configparser
import copy
@ -11,6 +25,16 @@ import string
import time
import timeit
from multiprocessing import Pool
import gzip
def save_zipped_pickle(obj, filename, protocol=-1):
with gzip.open(filename, 'wb') as f:
pickle.dump(obj, f, protocol)
def load_zipped_pickle(filename):
with gzip.open(filename, 'rb') as f:
loaded_object = pickle.load(f)
return loaded_object
import pyconll
@ -123,6 +147,8 @@ def decode_query(orig_query, dependency_type, feats_detailed_list):
def create_trees(config):
internal_saves = config.get('settings', 'internal_saves')
input_path = config.get('settings', 'input')
# internal_saves = filters['internal_saves']
# input_path = filters['input']
hash_object = hashlib.sha1(input_path.encode('utf-8'))
hex_dig = hash_object.hexdigest()
trees_read_outputfile = os.path.join(internal_saves, hex_dig)
@ -183,14 +209,16 @@ def create_trees(config):
raise Exception('No root element in sentence!')
all_trees.append(root)
with open(trees_read_outputfile, 'wb') as output:
pickle.dump((all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict), output)
save_zipped_pickle((all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict), trees_read_outputfile, protocol=2)
# with open(trees_read_outputfile, 'wb') as output:
#
# pickle.dump((all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict), output)
else:
print('Reading trees:')
print('Completed')
with open(trees_read_outputfile, 'rb') as pkl_file:
(all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict) = pickle.load(pkl_file)
all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict = load_zipped_pickle(trees_read_outputfile)
# with open(trees_read_outputfile, 'rb') as pkl_file:
# (all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict) = pickle.load(pkl_file)
return all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size, feats_detailed_dict
@ -333,123 +361,8 @@ def create_ngrams_query_trees(n, trees):
# tree['children'] = [{}]
return trees
def main():
parser = argparse.ArgumentParser()
## Required parameters
parser.add_argument("--config_file",
default=None,
type=str,
required=True,
help="The input config file.")
args = parser.parse_args()
config = configparser.ConfigParser()
config.read(args.config_file)
# a = args.config_file
# config.read('config.ini')
# create queries
tree_size = 0
# 261 - 9 grams
# 647 - 10 grams
# 1622 - 11 grams
# 4126 - 12 grams
# 10598 - 13 grams
(all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size,
feats_detailed_list) = create_trees(config)
# if config.getint('settings', 'tree_size') == 2:
# tree_size = 2
# query_tree = [{"children": [{}]}]
# elif config.getint('settings', 'tree_size') == 3:
# tree_size = 3
# query_tree = [{"children": [{}, {}]}, {"children": [{"children": [{}]}]}]
# elif config.getint('settings', 'tree_size') == 4:
# tree_size = 4
# query_tree = [{"children": [{}, {}, {}]}, {"children": [{"children": [{}, {}]}]}, {"children": [{"children": [{}]}, {}]}, {"children": [{"children": [{"children": [{}]}]}]}]
# elif config.getint('settings', 'tree_size') == 5:
# tree_size = 5
# query_tree = [{"children": [{}, {}, {}, {}]}, {"children": [{"children": [{}]}, {}, {}]}, {"children": [{"children": [{}, {}]}, {}]}, {"children": [{"children": [{}]}, {"children": [{}]}]},
# {"children": [{"children": [{"children": [{}]}]}, {}]}, {"children": [{"children": [{"children": [{}]}, {}]}]}, {"children": [{"children": [{"children": [{}, {}]}]}]},
# {"children": [{"children": [{"children": [{"children": [{}]}]}]}]}, {'children': [{'children': [{}, {}, {}]}]}]
tree_size_range = config.get('settings', 'tree_size', fallback='0').split('-')
tree_size_range = [int(r) for r in tree_size_range]
if tree_size_range[0] > 1:
if len(tree_size_range) == 1:
query_tree = create_ngrams_query_trees(tree_size_range[0], [{}])
elif len(tree_size_range) == 2:
query_tree = []
for i in range(tree_size_range[0], tree_size_range[1] + 1):
query_tree.extend(create_ngrams_query_trees(i, [{}]))
else:
query_tree = [decode_query('(' + config.get('settings', 'query') + ')', '', feats_detailed_list)]
# order_independent_queries(query_tree)
# set filters
node_types = config.get('settings', 'node_type').split('+')
create_output_string_functs = []
for node_type in node_types:
assert node_type in ['deprel', 'lemma', 'upos', 'xpos', 'form', 'feats'], '"node_type" is not set up correctly'
cpu_cores = config.getint('settings', 'cpu_cores')
if node_type == 'deprel':
create_output_string_funct = create_output_string_deprel
elif node_type == 'lemma':
create_output_string_funct = create_output_string_lemma
elif node_type == 'upos':
create_output_string_funct = create_output_string_upos
elif node_type == 'xpos':
create_output_string_funct = create_output_string_xpos
elif node_type == 'feats':
create_output_string_funct = create_output_string_feats
else:
create_output_string_funct = create_output_string_form
create_output_string_functs.append(create_output_string_funct)
result_dict = {}
unigrams_dict = {}
filters = {}
filters['node_order'] = config.get('settings', 'node_order') == 'fixed'
# filters['caching'] = config.getboolean('settings', 'caching')
filters['dependency_type'] = config.get('settings', 'dependency_type') == 'labeled'
if config.has_option('settings', 'label_whitelist'):
filters['label_whitelist'] = config.get('settings', 'label_whitelist').split('|')
else:
filters['label_whitelist'] = []
if config.has_option('settings', 'root_whitelist'):
# test
filters['root_whitelist'] = []
for option in config.get('settings', 'root_whitelist'). split('|'):
attribute_dict = {}
for attribute in option.split('&'):
value = attribute.split('=')
# assert value[0] in ['deprel', 'lemma', 'upos', 'xpos', 'form',
# 'feats'], '"root_whitelist" is not set up correctly'
attribute_dict[value[0]] = value[1]
filters['root_whitelist'].append(attribute_dict)
# filters['root_whitelist'] = [{'upos': 'NOUN', 'Case': 'Nom'}, {'upos': 'ADJ', 'Degree': 'Sup'}]
else:
filters['root_whitelist'] = []
filters['complete_tree_type'] = config.get('settings', 'tree_type') == 'complete'
filters['association_measures'] = config.getboolean('settings', 'association_measures')
filters['nodes_number'] = config.getboolean('settings', 'nodes_number')
filters['frequency_threshold'] = config.getfloat('settings', 'frequency_threshold', fallback=0)
filters['lines_threshold'] = config.getint('settings', 'lines_threshold', fallback=0)
filters['print_root'] = config.getboolean('settings', 'print_root')
# for tree in all_trees[2:]:
# for tree in all_trees[1205:]:
def count_trees(cpu_cores, all_trees, query_tree, create_output_string_functs, filters, unigrams_dict, result_dict):
with Pool(cpu_cores) as p:
start_exe_time = time.time()
# 1.25 s (16 cores)
# chunked_trees = list(chunkify(all_trees, cpu_cores))
# if cpu_cores > 1:
@ -531,8 +444,133 @@ def main():
else:
result_dict[key] = {'object': r, 'number': 1}
print("Execution time:")
print("--- %s seconds ---" % (time.time() - start_exe_time))
def read_filters(config, feats_detailed_list):
tree_size_range = config.get('settings', 'tree_size', fallback='0').split('-')
tree_size_range = [int(r) for r in tree_size_range]
if tree_size_range[0] > 1:
if len(tree_size_range) == 1:
query_tree = create_ngrams_query_trees(tree_size_range[0], [{}])
elif len(tree_size_range) == 2:
query_tree = []
for i in range(tree_size_range[0], tree_size_range[1] + 1):
query_tree.extend(create_ngrams_query_trees(i, [{}]))
else:
query_tree = [decode_query('(' + config.get('settings', 'query') + ')', '', feats_detailed_list)]
# order_independent_queries(query_tree)
# set filters
node_types = config.get('settings', 'node_type').split('+')
create_output_string_functs = []
for node_type in node_types:
assert node_type in ['deprel', 'lemma', 'upos', 'xpos', 'form', 'feats'], '"node_type" is not set up correctly'
cpu_cores = config.getint('settings', 'cpu_cores')
if node_type == 'deprel':
create_output_string_funct = create_output_string_deprel
elif node_type == 'lemma':
create_output_string_funct = create_output_string_lemma
elif node_type == 'upos':
create_output_string_funct = create_output_string_upos
elif node_type == 'xpos':
create_output_string_funct = create_output_string_xpos
elif node_type == 'feats':
create_output_string_funct = create_output_string_feats
else:
create_output_string_funct = create_output_string_form
create_output_string_functs.append(create_output_string_funct)
result_dict = {}
unigrams_dict = {}
filters = {}
filters['internal_saves'] = config.get('settings', 'internal_saves')
filters['input'] = config.get('settings', 'input')
filters['node_order'] = config.get('settings', 'node_order') == 'fixed'
# filters['caching'] = config.getboolean('settings', 'caching')
filters['dependency_type'] = config.get('settings', 'dependency_type') == 'labeled'
if config.has_option('settings', 'label_whitelist'):
filters['label_whitelist'] = config.get('settings', 'label_whitelist').split('|')
else:
filters['label_whitelist'] = []
if config.has_option('settings', 'root_whitelist'):
# test
filters['root_whitelist'] = []
for option in config.get('settings', 'root_whitelist').split('|'):
attribute_dict = {}
for attribute in option.split('&'):
value = attribute.split('=')
# assert value[0] in ['deprel', 'lemma', 'upos', 'xpos', 'form',
# 'feats'], '"root_whitelist" is not set up correctly'
attribute_dict[value[0]] = value[1]
filters['root_whitelist'].append(attribute_dict)
# filters['root_whitelist'] = [{'upos': 'NOUN', 'Case': 'Nom'}, {'upos': 'ADJ', 'Degree': 'Sup'}]
else:
filters['root_whitelist'] = []
filters['complete_tree_type'] = config.get('settings', 'tree_type') == 'complete'
filters['association_measures'] = config.getboolean('settings', 'association_measures')
filters['nodes_number'] = config.getboolean('settings', 'nodes_number')
filters['frequency_threshold'] = config.getfloat('settings', 'frequency_threshold', fallback=0)
filters['lines_threshold'] = config.getint('settings', 'lines_threshold', fallback=0)
filters['print_root'] = config.getboolean('settings', 'print_root')
return filters, query_tree, create_output_string_functs, cpu_cores, unigrams_dict, result_dict, tree_size_range, node_types
def main():
parser = argparse.ArgumentParser()
## Required parameters
parser.add_argument("--config_file",
default=None,
type=str,
required=True,
help="The input config file.")
args = parser.parse_args()
config = configparser.ConfigParser()
config.read(args.config_file)
# a = args.config_file
# config.read('config.ini')
# create queries
# 261 - 9 grams
# 647 - 10 grams
# 1622 - 11 grams
# 4126 - 12 grams
# 10598 - 13 grams
(all_trees, form_dict, lemma_dict, upos_dict, xpos_dict, deprel_dict, corpus_size,
feats_detailed_list) = create_trees(config)
filters, query_tree, create_output_string_functs, cpu_cores, unigrams_dict, result_dict, tree_size_range, node_types = read_filters(config, feats_detailed_list)
# if config.getint('settings', 'tree_size') == 2:
# tree_size = 2
# query_tree = [{"children": [{}]}]
# elif config.getint('settings', 'tree_size') == 3:
# tree_size = 3
# query_tree = [{"children": [{}, {}]}, {"children": [{"children": [{}]}]}]
# elif config.getint('settings', 'tree_size') == 4:
# tree_size = 4
# query_tree = [{"children": [{}, {}, {}]}, {"children": [{"children": [{}, {}]}]}, {"children": [{"children": [{}]}, {}]}, {"children": [{"children": [{"children": [{}]}]}]}]
# elif config.getint('settings', 'tree_size') == 5:
# tree_size = 5
# query_tree = [{"children": [{}, {}, {}, {}]}, {"children": [{"children": [{}]}, {}, {}]}, {"children": [{"children": [{}, {}]}, {}]}, {"children": [{"children": [{}]}, {"children": [{}]}]},
# {"children": [{"children": [{"children": [{}]}]}, {}]}, {"children": [{"children": [{"children": [{}]}, {}]}]}, {"children": [{"children": [{"children": [{}, {}]}]}]},
# {"children": [{"children": [{"children": [{"children": [{}]}]}]}]}, {'children': [{'children': [{}, {}, {}]}]}]
# for tree in all_trees[2:]:
# for tree in all_trees[1205:]:
start_exe_time = time.time()
count_trees(cpu_cores, all_trees, query_tree, create_output_string_functs, filters, unigrams_dict, result_dict)
print("Execution time:")
print("--- %s seconds ---" % (time.time() - start_exe_time))
# test 1 layer queries
# # tree.r_children = []
# # tree.children[1].children = []

14
generic.py
View File

@ -1,3 +1,17 @@
# Copyright 2019 CJVT
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import math
import sys

BIN
logos/CJVT.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 76 KiB

0
Clarin-SI-logo.png → logos/CLARIN.png
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 28 KiB

After

Width:  |  Height:  |  Size: 28 KiB

3773
logos/FF.svg Normal file
View File

File diff suppressed because it is too large Load Diff
Side by Side

After

Width:  |  Height:  |  Size: 314 KiB

BIN
logos/FRI.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 128 KiB