Files
modelscope/tests/utils/test_ast.py

204 lines
8.5 KiB
Python
Raw Normal View History

# Copyright (c) Alibaba, Inc. and its affiliates.
import os
import shutil
import tempfile
import time
import unittest
from pathlib import Path
from modelscope.utils.ast_utils import (FILES_MTIME_KEY, INDEX_KEY, MD5_KEY,
MODELSCOPE_PATH_KEY, REQUIREMENT_KEY,
VERSION_KEY, AstScaning,
2023-01-11 10:43:56 +08:00
FilesAstScaning, generate_ast_template,
load_from_prebuilt, load_index)
p = Path(__file__)
MODELSCOPE_PATH = p.resolve().parents[2].joinpath('modelscope')
class AstScaningTest(unittest.TestCase):
def setUp(self):
print(('Testing %s.%s' % (type(self).__name__, self._testMethodName)))
self.tmp_dir = tempfile.TemporaryDirectory().name
self.test_file = os.path.join(self.tmp_dir, 'test.py')
if not os.path.exists(self.tmp_dir):
os.makedirs(self.tmp_dir)
def tearDown(self):
super().tearDown()
shutil.rmtree(self.tmp_dir)
def test_ast_scaning_class(self):
astScaner = AstScaning()
pipeline_file = os.path.join(MODELSCOPE_PATH, 'pipelines', 'nlp',
'text_generation_pipeline.py')
output = astScaner.generate_ast(pipeline_file)
self.assertTrue(output['imports'] is not None)
self.assertTrue(output['from_imports'] is not None)
self.assertTrue(output['decorators'] is not None)
imports, from_imports, decorators = output['imports'], output[
'from_imports'], output['decorators']
self.assertIsInstance(imports, dict)
self.assertIsInstance(from_imports, dict)
self.assertIsInstance(decorators, list)
[to #42322933] Refactor NLP and fix some user feedbacks 1. Abstract keys of dicts needed by nlp metric classes into the init method 2. Add Preprocessor.save_pretrained to save preprocessor information 3. Abstract the config saving function, which can lead to normally saving in the direct call of from_pretrained, and the modification of cfg one by one when training. 4. Remove SbertTokenizer and VecoTokenizer, use transformers' tokenizers instead 5. Use model/preprocessor's from_pretrained in all nlp pipeline classes. 6. Add model_kwargs and preprocessor_kwargs in all nlp pipeline classes 7. Add base classes for fill-mask and text-classification preprocessor, as a demo for later changes 8. Fix user feedback: Re-train the model in continue training scenario 9. Fix user feedback: Too many checkpoint saved 10. Simplify the nlp-trainer 11. Fix user feedback: Split the default trainer's __init__ method, which makes user easier to override 12. Add safe_get to Config class ---------------------------- Another refactor from version 36 ------------------------- 13. Name all nlp transformers' preprocessors from TaskNamePreprocessor to TaskNameTransformersPreprocessor, for example: TextClassificationPreprocessor -> TextClassificationTransformersPreprocessor 14. Add a base class per task for all nlp tasks' preprocessors which has at least two sub-preprocessors 15. Add output classes of nlp models 16. Refactor the logic for token-classification 17. Fix bug: checkpoint_hook does not support pytorch_model.pt 18. Fix bug: Pipeline name does not match with task name, so inference will not succeed after training NOTE: This is just a stop bleeding solution, the root cause is the uncertainty of the relationship between models and pipelines Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/10723513 * add save_pretrained to preprocessor * save preprocessor config in hook * refactor label-id mapping fetching logic * test ok on sentence-similarity * run on finetuning * fix bug * pre-commit passed * fix bug * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/preprocessors/nlp/nlp_base.py * add params to init * 1. support max ckpt num 2. support ignoring others but bin file in continue training 3. add arguments to some nlp metrics * Split trainer init impls to overridable methods * remove some obsolete tokenizers * unfinished * support input params in pipeline * fix bugs * fix ut bug * fix bug * fix ut bug * fix ut bug * fix ut bug * add base class for some preprocessors * Merge commit '379867739548f394d0fa349ba07afe04adf4c8b6' into feat/refactor_config * compatible with old code * fix ut bug * fix ut bugs * fix bug * add some comments * fix ut bug * add a requirement * fix pre-commit * Merge commit '0451b3d3cb2bebfef92ec2c227b2a3dd8d01dc6a' into feat/refactor_config * fixbug * Support function type in registry * fix ut bug * fix bug * Merge commit '5f719e542b963f0d35457e5359df879a5eb80b82' into feat/refactor_config # Conflicts: # modelscope/pipelines/nlp/multilingual_word_segmentation_pipeline.py # modelscope/pipelines/nlp/named_entity_recognition_pipeline.py # modelscope/pipelines/nlp/word_segmentation_pipeline.py # modelscope/utils/hub.py * remove obsolete file * rename init args * rename params * fix merge bug * add default preprocessor config for ner-model * move a method a util file * remove unused config * Fix a bug in pbar * bestckptsaver:change default ckpt numbers to 1 * 1. Add assert to max_epoch 2. split init_dist and get_device 3. change cmp func name * Fix bug * fix bug * fix bug * unfinished refactoring * unfinished * uw * uw * uw * uw * Merge branch 'feat/refactor_config' into feat/refactor_trainer # Conflicts: # modelscope/preprocessors/nlp/document_segmentation_preprocessor.py # modelscope/preprocessors/nlp/faq_question_answering_preprocessor.py # modelscope/preprocessors/nlp/relation_extraction_preprocessor.py # modelscope/preprocessors/nlp/text_generation_preprocessor.py * uw * uw * unify nlp task outputs * uw * uw * uw * uw * change the order of text cls pipeline * refactor t5 * refactor tg task preprocessor * fix * unfinished * temp * refactor code * unfinished * unfinished * unfinished * unfinished * uw * Merge branch 'feat/refactor_config' into feat/refactor_trainer * smoke test pass * ut testing * pre-commit passed * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/models/nlp/bert/document_segmentation.py # modelscope/pipelines/nlp/__init__.py # modelscope/pipelines/nlp/document_segmentation_pipeline.py * merge master * unifnished * Merge branch 'feat/fix_bug_pipeline_name' into feat/refactor_config * fix bug * fix ut bug * support ner batch inference * fix ut bug * fix bug * support batch inference on three nlp tasks * unfinished * fix bug * fix bug * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/models/base/base_model.py # modelscope/pipelines/nlp/conversational_text_to_sql_pipeline.py # modelscope/pipelines/nlp/dialog_intent_prediction_pipeline.py # modelscope/pipelines/nlp/dialog_modeling_pipeline.py # modelscope/pipelines/nlp/dialog_state_tracking_pipeline.py # modelscope/pipelines/nlp/document_segmentation_pipeline.py # modelscope/pipelines/nlp/faq_question_answering_pipeline.py # modelscope/pipelines/nlp/feature_extraction_pipeline.py # modelscope/pipelines/nlp/fill_mask_pipeline.py # modelscope/pipelines/nlp/information_extraction_pipeline.py # modelscope/pipelines/nlp/named_entity_recognition_pipeline.py # modelscope/pipelines/nlp/sentence_embedding_pipeline.py # modelscope/pipelines/nlp/summarization_pipeline.py # modelscope/pipelines/nlp/table_question_answering_pipeline.py # modelscope/pipelines/nlp/text2text_generation_pipeline.py # modelscope/pipelines/nlp/text_classification_pipeline.py # modelscope/pipelines/nlp/text_error_correction_pipeline.py # modelscope/pipelines/nlp/text_generation_pipeline.py # modelscope/pipelines/nlp/text_ranking_pipeline.py # modelscope/pipelines/nlp/token_classification_pipeline.py # modelscope/pipelines/nlp/word_segmentation_pipeline.py # modelscope/pipelines/nlp/zero_shot_classification_pipeline.py # modelscope/trainers/nlp_trainer.py * pre-commit passed * fix bug * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/preprocessors/__init__.py * fix bug * fix bug * fix bug * fix bug * fix bug * fixbug * pre-commit passed * fix bug * fixbug * fix bug * fix bug * fix bug * fix bug * self review done * fixbug * fix bug * fix bug * fix bugs * remove sub-token offset mapping * fix name bug * add some tests * 1. support batch inference of text-generation,text2text-generation,token-classification,text-classification 2. add corresponding UTs * add old logic back * tmp save * add tokenize by words logic back * move outputs file back * revert veco token-classification back * fix typo * Fix description * Merge commit '4dd99b8f6e4e7aefe047c68a1bedd95d3ec596d6' into feat/refactor_config * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/pipelines/builder.py
2022-11-30 23:52:17 +08:00
self.assertListEqual(
list(set(imports.keys()) - set(['torch', 'os'])), [])
self.assertEqual(len(from_imports.keys()), 10)
self.assertTrue(from_imports['modelscope.metainfo'] is not None)
self.assertEqual(from_imports['modelscope.metainfo'], ['Pipelines'])
[to #42322933] Refactor NLP and fix some user feedbacks 1. Abstract keys of dicts needed by nlp metric classes into the init method 2. Add Preprocessor.save_pretrained to save preprocessor information 3. Abstract the config saving function, which can lead to normally saving in the direct call of from_pretrained, and the modification of cfg one by one when training. 4. Remove SbertTokenizer and VecoTokenizer, use transformers' tokenizers instead 5. Use model/preprocessor's from_pretrained in all nlp pipeline classes. 6. Add model_kwargs and preprocessor_kwargs in all nlp pipeline classes 7. Add base classes for fill-mask and text-classification preprocessor, as a demo for later changes 8. Fix user feedback: Re-train the model in continue training scenario 9. Fix user feedback: Too many checkpoint saved 10. Simplify the nlp-trainer 11. Fix user feedback: Split the default trainer's __init__ method, which makes user easier to override 12. Add safe_get to Config class ---------------------------- Another refactor from version 36 ------------------------- 13. Name all nlp transformers' preprocessors from TaskNamePreprocessor to TaskNameTransformersPreprocessor, for example: TextClassificationPreprocessor -> TextClassificationTransformersPreprocessor 14. Add a base class per task for all nlp tasks' preprocessors which has at least two sub-preprocessors 15. Add output classes of nlp models 16. Refactor the logic for token-classification 17. Fix bug: checkpoint_hook does not support pytorch_model.pt 18. Fix bug: Pipeline name does not match with task name, so inference will not succeed after training NOTE: This is just a stop bleeding solution, the root cause is the uncertainty of the relationship between models and pipelines Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/10723513 * add save_pretrained to preprocessor * save preprocessor config in hook * refactor label-id mapping fetching logic * test ok on sentence-similarity * run on finetuning * fix bug * pre-commit passed * fix bug * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/preprocessors/nlp/nlp_base.py * add params to init * 1. support max ckpt num 2. support ignoring others but bin file in continue training 3. add arguments to some nlp metrics * Split trainer init impls to overridable methods * remove some obsolete tokenizers * unfinished * support input params in pipeline * fix bugs * fix ut bug * fix bug * fix ut bug * fix ut bug * fix ut bug * add base class for some preprocessors * Merge commit '379867739548f394d0fa349ba07afe04adf4c8b6' into feat/refactor_config * compatible with old code * fix ut bug * fix ut bugs * fix bug * add some comments * fix ut bug * add a requirement * fix pre-commit * Merge commit '0451b3d3cb2bebfef92ec2c227b2a3dd8d01dc6a' into feat/refactor_config * fixbug * Support function type in registry * fix ut bug * fix bug * Merge commit '5f719e542b963f0d35457e5359df879a5eb80b82' into feat/refactor_config # Conflicts: # modelscope/pipelines/nlp/multilingual_word_segmentation_pipeline.py # modelscope/pipelines/nlp/named_entity_recognition_pipeline.py # modelscope/pipelines/nlp/word_segmentation_pipeline.py # modelscope/utils/hub.py * remove obsolete file * rename init args * rename params * fix merge bug * add default preprocessor config for ner-model * move a method a util file * remove unused config * Fix a bug in pbar * bestckptsaver:change default ckpt numbers to 1 * 1. Add assert to max_epoch 2. split init_dist and get_device 3. change cmp func name * Fix bug * fix bug * fix bug * unfinished refactoring * unfinished * uw * uw * uw * uw * Merge branch 'feat/refactor_config' into feat/refactor_trainer # Conflicts: # modelscope/preprocessors/nlp/document_segmentation_preprocessor.py # modelscope/preprocessors/nlp/faq_question_answering_preprocessor.py # modelscope/preprocessors/nlp/relation_extraction_preprocessor.py # modelscope/preprocessors/nlp/text_generation_preprocessor.py * uw * uw * unify nlp task outputs * uw * uw * uw * uw * change the order of text cls pipeline * refactor t5 * refactor tg task preprocessor * fix * unfinished * temp * refactor code * unfinished * unfinished * unfinished * unfinished * uw * Merge branch 'feat/refactor_config' into feat/refactor_trainer * smoke test pass * ut testing * pre-commit passed * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/models/nlp/bert/document_segmentation.py # modelscope/pipelines/nlp/__init__.py # modelscope/pipelines/nlp/document_segmentation_pipeline.py * merge master * unifnished * Merge branch 'feat/fix_bug_pipeline_name' into feat/refactor_config * fix bug * fix ut bug * support ner batch inference * fix ut bug * fix bug * support batch inference on three nlp tasks * unfinished * fix bug * fix bug * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/models/base/base_model.py # modelscope/pipelines/nlp/conversational_text_to_sql_pipeline.py # modelscope/pipelines/nlp/dialog_intent_prediction_pipeline.py # modelscope/pipelines/nlp/dialog_modeling_pipeline.py # modelscope/pipelines/nlp/dialog_state_tracking_pipeline.py # modelscope/pipelines/nlp/document_segmentation_pipeline.py # modelscope/pipelines/nlp/faq_question_answering_pipeline.py # modelscope/pipelines/nlp/feature_extraction_pipeline.py # modelscope/pipelines/nlp/fill_mask_pipeline.py # modelscope/pipelines/nlp/information_extraction_pipeline.py # modelscope/pipelines/nlp/named_entity_recognition_pipeline.py # modelscope/pipelines/nlp/sentence_embedding_pipeline.py # modelscope/pipelines/nlp/summarization_pipeline.py # modelscope/pipelines/nlp/table_question_answering_pipeline.py # modelscope/pipelines/nlp/text2text_generation_pipeline.py # modelscope/pipelines/nlp/text_classification_pipeline.py # modelscope/pipelines/nlp/text_error_correction_pipeline.py # modelscope/pipelines/nlp/text_generation_pipeline.py # modelscope/pipelines/nlp/text_ranking_pipeline.py # modelscope/pipelines/nlp/token_classification_pipeline.py # modelscope/pipelines/nlp/word_segmentation_pipeline.py # modelscope/pipelines/nlp/zero_shot_classification_pipeline.py # modelscope/trainers/nlp_trainer.py * pre-commit passed * fix bug * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/preprocessors/__init__.py * fix bug * fix bug * fix bug * fix bug * fix bug * fixbug * pre-commit passed * fix bug * fixbug * fix bug * fix bug * fix bug * fix bug * self review done * fixbug * fix bug * fix bug * fix bugs * remove sub-token offset mapping * fix name bug * add some tests * 1. support batch inference of text-generation,text2text-generation,token-classification,text-classification 2. add corresponding UTs * add old logic back * tmp save * add tokenize by words logic back * move outputs file back * revert veco token-classification back * fix typo * Fix description * Merge commit '4dd99b8f6e4e7aefe047c68a1bedd95d3ec596d6' into feat/refactor_config * Merge branch 'master' into feat/refactor_config # Conflicts: # modelscope/pipelines/builder.py
2022-11-30 23:52:17 +08:00
self.assertEqual(
decorators,
[('PIPELINES', 'text-generation', 'text-generation'),
('PIPELINES', 'text2text-generation', 'translation_en_to_de'),
('PIPELINES', 'text2text-generation', 'translation_en_to_ro'),
('PIPELINES', 'text2text-generation', 'translation_en_to_fr'),
('PIPELINES', 'text2text-generation', 'text2text-generation')])
def test_files_scaning_method(self):
fileScaner = FilesAstScaning()
# case of pass in files directly
pipeline_file = os.path.join(MODELSCOPE_PATH, 'pipelines', 'nlp',
'text_generation_pipeline.py')
file_list = [pipeline_file]
output = fileScaner.get_files_scan_results(file_list)
self.assertTrue(output[INDEX_KEY] is not None)
self.assertTrue(output[REQUIREMENT_KEY] is not None)
index, requirements = output[INDEX_KEY], output[REQUIREMENT_KEY]
self.assertIsInstance(index, dict)
self.assertIsInstance(requirements, dict)
self.assertIsInstance(list(index.keys())[0], tuple)
index_0 = list(index.keys())[0]
self.assertIsInstance(index[index_0], dict)
self.assertTrue(index[index_0]['imports'] is not None)
self.assertIsInstance(index[index_0]['imports'], list)
self.assertTrue(index[index_0]['module'] is not None)
self.assertIsInstance(index[index_0]['module'], str)
index_0 = list(requirements.keys())[0]
self.assertIsInstance(requirements[index_0], list)
def test_file_mtime_md5_method(self):
fileScaner = FilesAstScaning()
# create first file
with open(self.test_file, 'w', encoding='utf-8') as f:
f.write('This is the new test!')
md5_1, mtime_1 = fileScaner.files_mtime_md5(self.tmp_dir, [])
md5_2, mtime_2 = fileScaner.files_mtime_md5(self.tmp_dir, [])
self.assertEqual(md5_1, md5_2)
self.assertEqual(mtime_1, mtime_2)
self.assertIsInstance(mtime_1, dict)
self.assertEqual(list(mtime_1.keys()), [self.test_file])
self.assertEqual(mtime_1[self.test_file], mtime_2[self.test_file])
time.sleep(2)
# case of revise
with open(self.test_file, 'w', encoding='utf-8') as f:
f.write('test again')
md5_3, mtime_3 = fileScaner.files_mtime_md5(self.tmp_dir, [])
self.assertNotEqual(md5_1, md5_3)
self.assertNotEqual(mtime_1[self.test_file], mtime_3[self.test_file])
# case of create
self.test_file_new = os.path.join(self.tmp_dir, 'test_1.py')
time.sleep(2)
with open(self.test_file_new, 'w', encoding='utf-8') as f:
f.write('test again')
md5_4, mtime_4 = fileScaner.files_mtime_md5(self.tmp_dir, [])
self.assertNotEqual(md5_1, md5_4)
self.assertNotEqual(md5_3, md5_4)
self.assertEqual(
set(mtime_4.keys()) - set([self.test_file, self.test_file_new]),
set())
def test_load_index_method(self):
# test full indexing case
output = load_index()
self.assertTrue(output[INDEX_KEY] is not None)
self.assertTrue(output[REQUIREMENT_KEY] is not None)
index, requirements = output[INDEX_KEY], output[REQUIREMENT_KEY]
self.assertIsInstance(index, dict)
self.assertIsInstance(requirements, dict)
self.assertIsInstance(list(index.keys())[0], tuple)
index_0 = list(index.keys())[0]
self.assertIsInstance(index[index_0], dict)
self.assertTrue(index[index_0]['imports'] is not None)
self.assertIsInstance(index[index_0]['imports'], list)
self.assertTrue(index[index_0]['module'] is not None)
self.assertIsInstance(index[index_0]['module'], str)
index_0 = list(requirements.keys())[0]
self.assertIsInstance(requirements[index_0], list)
self.assertIsInstance(output[MD5_KEY], str)
self.assertIsInstance(output[MODELSCOPE_PATH_KEY], str)
self.assertIsInstance(output[VERSION_KEY], str)
self.assertIsInstance(output[FILES_MTIME_KEY], dict)
2023-01-11 10:43:56 +08:00
# generate ast_template
file_path = os.path.join(self.tmp_dir, 'index_file.py')
index = generate_ast_template(file_path=file_path, force_rebuild=False)
self.assertTrue(os.path.exists(file_path))
self.assertEqual(output, index)
index_from_prebuilt = load_from_prebuilt(file_path)
self.assertEqual(index, index_from_prebuilt)
def test_update_load_index_method(self):
file_number = 20
file_list = []
for i in range(file_number):
filename = os.path.join(self.tmp_dir, f'test_{i}.py')
with open(filename, 'w', encoding='utf-8') as f:
f.write('import os')
file_list.append(filename)
index_file = 'ast_indexer_1'
start = time.time()
index = load_index(
file_list=file_list,
indexer_file_dir=self.tmp_dir,
indexer_file=index_file)
duration_1 = time.time() - start
self.assertEqual(len(index[FILES_MTIME_KEY]), file_number)
# no changing case, time should be less than original
start = time.time()
index = load_index(
file_list=file_list,
indexer_file_dir=self.tmp_dir,
indexer_file=index_file)
duration_2 = time.time() - start
self.assertGreater(duration_1, duration_2)
self.assertEqual(len(index[FILES_MTIME_KEY]), file_number)
# adding new file, time should be less than original
test_file_new_2 = os.path.join(self.tmp_dir, 'test_new.py')
with open(test_file_new_2, 'w', encoding='utf-8') as f:
f.write('import os')
file_list.append(test_file_new_2)
start = time.time()
index = load_index(
file_list=file_list,
indexer_file_dir=self.tmp_dir,
indexer_file=index_file)
duration_3 = time.time() - start
self.assertGreater(duration_1, duration_3)
self.assertEqual(len(index[FILES_MTIME_KEY]), file_number + 1)
# deleting one file, time should be less than original
file_list.pop()
start = time.time()
index = load_index(
file_list=file_list,
indexer_file_dir=self.tmp_dir,
indexer_file=index_file)
duration_4 = time.time() - start
self.assertGreater(duration_1, duration_4)
self.assertEqual(len(index[FILES_MTIME_KEY]), file_number)
if __name__ == '__main__':
unittest.main()