diff --git a/mindinsight/lineagemgr/common/utils.py b/mindinsight/lineagemgr/common/utils.py index 21cae5ea..52624864 100644 --- a/mindinsight/lineagemgr/common/utils.py +++ b/mindinsight/lineagemgr/common/utils.py @@ -13,15 +13,13 @@ # limitations under the License. # ============================================================================ """Lineage utils.""" -import os import re from mindinsight.datavisual.data_transform.summary_watcher import SummaryWatcher -from mindinsight.lineagemgr.common.exceptions.exceptions import LineageParamTypeError -from mindinsight.lineagemgr.common.log import logger as log def enum_to_list(enum): + """Enum to list.""" return [enum_ele.value for enum_ele in enum] @@ -29,28 +27,3 @@ def get_timestamp(filename): """Get timestamp from filename.""" timestamp = int(re.search(SummaryWatcher().SUMMARY_FILENAME_REGEX, filename)[1]) return timestamp - - -def make_directory(path): - """Make directory.""" - if path is None or not isinstance(path, str) or not path.strip(): - log.error("Invalid input path: %r.", path) - raise LineageParamTypeError("Invalid path type") - - # convert relative path to abs path - path = os.path.realpath(path) - log.debug("The abs path is %r", path) - - # check path exist and its write permissions] - if os.path.exists(path): - real_path = path - else: - # All exceptions need to be caught because create directory maybe have some limit(permissions) - log.debug("The directory(%s) doesn't exist, will create it", path) - try: - os.makedirs(path, exist_ok=True) - real_path = path - except PermissionError as err: - log.error("No write permission on the directory(%r), error = %r", path, err) - raise LineageParamTypeError("No write permission on the directory.") - return real_path diff --git a/mindinsight/lineagemgr/common/validator/model_parameter.py b/mindinsight/lineagemgr/common/validator/model_parameter.py index cebbacf0..aff90909 100644 --- a/mindinsight/lineagemgr/common/validator/model_parameter.py +++ b/mindinsight/lineagemgr/common/validator/model_parameter.py @@ -15,37 +15,13 @@ """Define schema of model lineage input parameters.""" from marshmallow import Schema, fields, ValidationError, pre_load, validates -from mindinsight.lineagemgr.common.exceptions.error_code import LineageErrorMsg, \ - LineageErrors -from mindinsight.lineagemgr.common.exceptions.exceptions import \ - LineageParamTypeError, LineageParamValueError -from mindinsight.lineagemgr.common.log import logger +from mindinsight.lineagemgr.common.exceptions.error_code import LineageErrorMsg, LineageErrors +from mindinsight.lineagemgr.common.exceptions.exceptions import LineageParamTypeError, LineageParamValueError from mindinsight.lineagemgr.common.utils import enum_to_list from mindinsight.lineagemgr.querier.querier import LineageType from mindinsight.lineagemgr.querier.query_model import FIELD_MAPPING from mindinsight.utils.exceptions import MindInsightException -try: - from mindspore.dataset.engine import Dataset -except (ImportError, ModuleNotFoundError): - logger.error('MindSpore Not Found!') - - - -class EvalParameter(Schema): - """Define the parameter schema for Evaluation job.""" - valid_dataset = fields.Function(allow_none=True) - metrics = fields.Dict(allow_none=True) - - @pre_load - def check_valid_dataset(self, data, **kwargs): - valid_dataset = data.get("valid_dataset") - if valid_dataset and not isinstance(valid_dataset, Dataset): - raise ValidationError({'valid_dataset': [ - "Parameter valid_dataset must be an instance of " - "mindspore.dataengine.datasets.Dataset"]}) - return data - class SearchModelConditionParameter(Schema): """Define the search model condition parameter schema.""" diff --git a/mindinsight/lineagemgr/common/validator/validate.py b/mindinsight/lineagemgr/common/validator/validate.py index 9d4a4242..712e6814 100644 --- a/mindinsight/lineagemgr/common/validator/validate.py +++ b/mindinsight/lineagemgr/common/validator/validate.py @@ -13,34 +13,12 @@ # limitations under the License. # ============================================================================ """Validate the parameters.""" -import re -from marshmallow import ValidationError - from mindinsight.lineagemgr.common.exceptions.error_code import LineageErrors, LineageErrorMsg from mindinsight.lineagemgr.common.exceptions.exceptions import LineageParamTypeError, LineageParamValueError from mindinsight.lineagemgr.common.log import logger as log -from mindinsight.lineagemgr.common.validator.validate_path import safe_normalize_path from mindinsight.lineagemgr.querier.query_model import FIELD_MAPPING from mindinsight.utils.exceptions import MindInsightException, ParamValueError - -# Named string regular expression -_name_re = r"^\w+[0-9a-zA-Z\_\.]*$" - -TRAIN_RUN_CONTEXT_ERROR_MAPPING = { - 'optimizer': LineageErrors.PARAM_OPTIMIZER_ERROR, - 'loss_fn': LineageErrors.PARAM_LOSS_FN_ERROR, - 'net_outputs': LineageErrors.PARAM_NET_OUTPUTS_ERROR, - 'train_network': LineageErrors.PARAM_TRAIN_NETWORK_ERROR, - 'train_dataset': LineageErrors.PARAM_DATASET_ERROR, - 'epoch_num': LineageErrors.PARAM_EPOCH_NUM_ERROR, - 'batch_num': LineageErrors.PARAM_BATCH_NUM_ERROR, - 'parallel_mode': LineageErrors.PARAM_TRAIN_PARALLEL_ERROR, - 'device_number': LineageErrors.PARAM_DEVICE_NUMBER_ERROR, - 'list_callback': LineageErrors.PARAM_CALLBACK_LIST_ERROR, - 'train_dataset_size': LineageErrors.PARAM_DATASET_SIZE_ERROR, -} - SEARCH_MODEL_ERROR_MAPPING = { 'summary_dir': LineageErrors.LINEAGE_PARAM_SUMMARY_DIR_ERROR, 'loss_function': LineageErrors.LINEAGE_PARAM_LOSS_FUNCTION_ERROR, @@ -64,19 +42,6 @@ SEARCH_MODEL_ERROR_MAPPING = { 'lineage_type': LineageErrors.LINEAGE_PARAM_LINEAGE_TYPE_ERROR } - -TRAIN_RUN_CONTEXT_ERROR_MSG_MAPPING = { - 'optimizer': LineageErrorMsg.PARAM_OPTIMIZER_ERROR.value, - 'loss_fn': LineageErrorMsg.PARAM_LOSS_FN_ERROR.value, - 'net_outputs': LineageErrorMsg.PARAM_NET_OUTPUTS_ERROR.value, - 'train_network': LineageErrorMsg.PARAM_TRAIN_NETWORK_ERROR.value, - 'epoch_num': LineageErrorMsg.PARAM_EPOCH_NUM_ERROR.value, - 'batch_num': LineageErrorMsg.PARAM_BATCH_NUM_ERROR.value, - 'parallel_mode': LineageErrorMsg.PARAM_TRAIN_PARALLEL_ERROR.value, - 'device_number': LineageErrorMsg.PARAM_DEVICE_NUMBER_ERROR.value, - 'list_callback': LineageErrorMsg.PARAM_CALLBACK_LIST_ERROR.value -} - SEARCH_MODEL_ERROR_MSG_MAPPING = { 'summary_dir': LineageErrorMsg.LINEAGE_PARAM_SUMMARY_DIR_ERROR.value, 'loss_function': LineageErrorMsg.LINEAGE_LOSS_FUNCTION_ERROR.value, @@ -101,84 +66,6 @@ SEARCH_MODEL_ERROR_MSG_MAPPING = { } -EVAL_RUN_CONTEXT_ERROR_MAPPING = { - 'valid_dataset': LineageErrors.PARAM_DATASET_ERROR, - 'metrics': LineageErrors.PARAM_EVAL_METRICS_ERROR -} - -EVAL_RUN_CONTEXT_ERROR_MSG_MAPPING = { - 'metrics': LineageErrorMsg.PARAM_EVAL_METRICS_ERROR.value, -} - - -def validate_int_params(int_param, param_name): - """ - Verify the parameter which type is integer valid or not. - - Args: - int_param (int): parameter that is integer, - including epoch, dataset_batch_size, step_num - param_name (str): the name of parameter, - including epoch, dataset_batch_size, step_num - - Raises: - MindInsightException: If the parameters are invalid. - """ - if not isinstance(int_param, int) or int_param <= 0 or int_param > pow(2, 63) - 1: - if param_name == 'step_num': - log.error('Invalid step_num. The step number should be a positive integer.') - raise MindInsightException(error=LineageErrors.PARAM_STEP_NUM_ERROR, - message=LineageErrorMsg.PARAM_STEP_NUM_ERROR.value) - - if param_name == 'dataset_batch_size': - log.error('Invalid dataset_batch_size. ' - 'The batch size should be a positive integer.') - raise MindInsightException(error=LineageErrors.PARAM_BATCH_SIZE_ERROR, - message=LineageErrorMsg.PARAM_BATCH_SIZE_ERROR.value) - - -def validate_file_path(file_path, allow_empty=False): - """ - Verify that the file_path is valid. - - Args: - file_path (str): Input file path. - allow_empty (bool): Whether file_path can be empty. - - Raises: - MindInsightException: If the parameters are invalid. - """ - try: - if allow_empty and not file_path: - return file_path - return safe_normalize_path(file_path, raise_key='dataset_path', safe_prefixes=None) - except ValidationError as error: - log.error(str(error)) - raise MindInsightException(error=LineageErrors.PARAM_FILE_PATH_ERROR, - message=str(error)) - - -def validate_eval_run_context(schema, data): - """ - Validate mindspore evaluation job run_context data according to schema. - - Args: - schema (Schema): data schema. - data (dict): data to check schema. - - Raises: - MindInsightException: If the parameters are invalid. - """ - errors = schema().validate(data) - for error_key, error_msg in errors.items(): - if error_key in EVAL_RUN_CONTEXT_ERROR_MAPPING.keys(): - error_code = EVAL_RUN_CONTEXT_ERROR_MAPPING.get(error_key) - if EVAL_RUN_CONTEXT_ERROR_MSG_MAPPING.get(error_key): - error_msg = EVAL_RUN_CONTEXT_ERROR_MSG_MAPPING.get(error_key) - log.error(error_msg) - raise MindInsightException(error=error_code, message=error_msg) - - def validate_search_model_condition(schema, data): """ Validate search model condition. @@ -203,25 +90,6 @@ def validate_search_model_condition(schema, data): raise MindInsightException(error=error_code, message=error_msg) -def validate_raise_exception(raise_exception): - """ - Validate raise_exception. - - Args: - raise_exception (bool): decide raise exception or not, - if True, raise exception; else, catch exception and continue. - - Raises: - MindInsightException: If the parameters are invalid. - """ - if not isinstance(raise_exception, bool): - log.error("Invalid raise_exception. It should be True or False.") - raise MindInsightException( - error=LineageErrors.PARAM_RAISE_EXCEPTION_ERROR, - message=LineageErrorMsg.PARAM_RAISE_EXCEPTION_ERROR.value - ) - - def validate_condition(search_condition): """ Verify the param in search_condition is valid or not. @@ -276,44 +144,6 @@ def validate_condition(search_condition): raise LineageParamValueError(err_msg) -def validate_user_defined_info(user_defined_info): - """ - Validate user defined info， delete the item if its key is in lineage. - - Args: - user_defined_info (dict): The user defined info. - - Raises: - LineageParamTypeError: If the type of parameters is invalid. - LineageParamValueError: If user defined keys have been defined in lineage. - - """ - if not isinstance(user_defined_info, dict): - log.error("Invalid user defined info. It should be a dict.") - raise LineageParamTypeError("Invalid user defined info. It should be dict.") - for key, value in user_defined_info.items(): - if not isinstance(key, str): - error_msg = "Dict key type {} is not supported in user defined info." \ - "Only str is permitted now.".format(type(key)) - log.error(error_msg) - raise LineageParamTypeError(error_msg) - if not isinstance(value, (int, str, float)): - error_msg = "Dict value type {} is not supported in user defined info." \ - "Only str, int and float are permitted now.".format(type(value)) - log.error(error_msg) - raise LineageParamTypeError(error_msg) - - field_map = set(FIELD_MAPPING.keys()) - user_defined_keys = set(user_defined_info.keys()) - insertion = list(field_map & user_defined_keys) - - if insertion: - for key in insertion: - user_defined_info.pop(key) - raise LineageParamValueError("There are some keys have defined in lineage. " - "Duplicated key(s): %s. " % insertion) - - def validate_train_id(relative_path): """ Check if train_id is valid. @@ -385,27 +215,3 @@ def validate_added_info(added_info: dict): raise LineageParamValueError("'remark' must be str.") # length of remark should be in [0, 128]. validate_range("length of remark", len(value), min_value=0, max_value=128) - - -def validate_str_by_regular(target, reg=None, flag=re.ASCII): - """ - Validate string by given regular. - - Args: - target: target string. - reg: pattern. - flag: pattern mode. - - Raises: - LineageParamValueError, if string not match given pattern. - - Returns: - bool, if target matches pattern, return True. - - """ - if reg is None: - reg = _name_re - if re.match(reg, target, flag) is None: - raise LineageParamValueError("'{}' is illegal, it should be match " - "regular'{}' by flags'{}'".format(target, reg, flag)) - return True diff --git a/mindinsight/lineagemgr/summary/_summary_adapter.py b/mindinsight/lineagemgr/summary/_summary_adapter.py index f045b0b6..83c61e1b 100644 --- a/mindinsight/lineagemgr/summary/_summary_adapter.py +++ b/mindinsight/lineagemgr/summary/_summary_adapter.py @@ -14,6 +14,7 @@ # ============================================================================ """The converter between proto format event of lineage and dict.""" + def organize_graph(graph_message): """ Convert a dataset graph to its dict format. diff --git a/tests/st/func/lineagemgr/collection/model/__init__.py b/tests/st/func/lineagemgr/collection/model/__init__.py index 47b43a6e..c5deecaa 100644 --- a/tests/st/func/lineagemgr/collection/model/__init__.py +++ b/tests/st/func/lineagemgr/collection/model/__init__.py @@ -12,3 +12,4 @@ # See the License for the specific language governing permissions and # limitations under the License. # ============================================================================ +"""Lineage collection.""" diff --git a/tests/st/func/lineagemgr/collection/model/test_model_lineage.py b/tests/st/func/lineagemgr/collection/model/test_model_lineage.py index 857add95..93338745 100644 --- a/tests/st/func/lineagemgr/collection/model/test_model_lineage.py +++ b/tests/st/func/lineagemgr/collection/model/test_model_lineage.py @@ -28,8 +28,6 @@ from unittest import TestCase, mock import numpy as np import pytest from mindinsight.lineagemgr.model import filter_summary_lineage -from mindinsight.lineagemgr.common.exceptions.error_code import LineageErrors -from mindinsight.utils.exceptions import MindInsightException from mindspore.application.model_zoo.resnet import ResNet from mindspore.common.tensor import Tensor @@ -213,14 +211,12 @@ class TestModelLineage(TestCase): @pytest.mark.platform_x86_ascend_training @pytest.mark.platform_x86_cpu @pytest.mark.env_single - @mock.patch('tests.utils.lineage_writer.model_lineage.validate_eval_run_context') - @mock.patch.object(AnalyzeObject, 'get_file_size', return_value=64) - def test_raise_exception_record_trainlineage(self, *args): + @mock.patch.object(AnalyzeObject, 'get_file_size') + def test_raise_exception_record_trainlineage(self, mock_analyze): """Test exception when error happened after recording training infos.""" + mock_analyze.return_value = 64 if os.path.exists(SUMMARY_DIR_3): shutil.rmtree(SUMMARY_DIR_3) - args[1].side_effect = MindInsightException(error=LineageErrors.PARAM_RUN_CONTEXT_ERROR, - message="RunContext error.") train_callback = TrainLineage(SUMMARY_DIR_3, True) train_callback.begin(RunContext(self.run_context)) full_file_name = train_callback.lineage_summary.lineage_log_path diff --git a/tests/utils/lineage_writer/model_lineage.py b/tests/utils/lineage_writer/model_lineage.py index 1d6b6047..6dba0441 100644 --- a/tests/utils/lineage_writer/model_lineage.py +++ b/tests/utils/lineage_writer/model_lineage.py @@ -19,17 +19,13 @@ import os import numpy as np from mindinsight.lineagemgr.common.exceptions.error_code import LineageErrorMsg, LineageErrors from mindinsight.lineagemgr.common.log import logger as log -from mindinsight.lineagemgr.common.utils import make_directory -from mindinsight.lineagemgr.common.validator.model_parameter import EvalParameter -from mindinsight.lineagemgr.common.validator.validate import (validate_eval_run_context, validate_file_path, - validate_int_params, - validate_raise_exception, - validate_user_defined_info) from mindinsight.utils.exceptions import MindInsightException from ._summary_record import LineageSummary from .base import Metadata -from .utils import try_except, LineageParamRunContextError, LineageGetModelFileError, LineageLogError +from .utils import try_except, LineageParamRunContextError, LineageGetModelFileError, LineageLogError, \ + validate_int_params, validate_file_path, validate_raise_exception, \ + validate_user_defined_info, make_directory try: from mindspore.common.tensor import Tensor @@ -308,7 +304,6 @@ class EvalLineage(Callback): raise LineageParamRunContextError(error_msg) run_context_args = run_context.original_args() - validate_eval_run_context(EvalParameter, run_context_args) valid_dataset = run_context_args.get('valid_dataset') diff --git a/tests/utils/lineage_writer/utils.py b/tests/utils/lineage_writer/utils.py index 7acd8a9e..8fea4739 100644 --- a/tests/utils/lineage_writer/utils.py +++ b/tests/utils/lineage_writer/utils.py @@ -13,9 +13,16 @@ # limitations under the License. # ============================================================================ """Lineage writer utils.""" +import os from functools import wraps +from marshmallow import ValidationError + from mindinsight.lineagemgr.common.exceptions.error_code import LineageErrors, LineageErrorMsg +from mindinsight.lineagemgr.common.exceptions.exceptions import LineageParamTypeError, LineageParamValueError +from mindinsight.lineagemgr.common.log import logger as log +from mindinsight.lineagemgr.common.validator.validate_path import safe_normalize_path +from mindinsight.lineagemgr.querier.query_model import FIELD_MAPPING from mindinsight.utils.exceptions import MindInsightException @@ -81,3 +88,141 @@ def try_except(logger): return wrapper return try_except_decorate + + +def validate_int_params(int_param, param_name): + """ + Verify the parameter which type is integer valid or not. + + Args: + int_param (int): parameter that is integer, + including epoch, dataset_batch_size, step_num + param_name (str): the name of parameter, + including epoch, dataset_batch_size, step_num + + Raises: + MindInsightException: If the parameters are invalid. + """ + if not isinstance(int_param, int) or int_param <= 0 or int_param > pow(2, 63) - 1: + if param_name == 'step_num': + log.error('Invalid step_num. The step number should be a positive integer.') + raise MindInsightException(error=LineageErrors.PARAM_STEP_NUM_ERROR, + message=LineageErrorMsg.PARAM_STEP_NUM_ERROR.value) + + if param_name == 'dataset_batch_size': + log.error('Invalid dataset_batch_size. ' + 'The batch size should be a positive integer.') + raise MindInsightException(error=LineageErrors.PARAM_BATCH_SIZE_ERROR, + message=LineageErrorMsg.PARAM_BATCH_SIZE_ERROR.value) + + +def validate_file_path(file_path, allow_empty=False): + """ + Verify that the file_path is valid. + + Args: + file_path (str): Input file path. + allow_empty (bool): Whether file_path can be empty. + + Raises: + MindInsightException: If the parameters are invalid. + """ + try: + if allow_empty and not file_path: + return file_path + return safe_normalize_path(file_path, raise_key='dataset_path', safe_prefixes=None) + except ValidationError as error: + log.error(str(error)) + raise MindInsightException(error=LineageErrors.PARAM_FILE_PATH_ERROR, + message=str(error)) + + +EVAL_RUN_CONTEXT_ERROR_MSG_MAPPING = { + 'metrics': LineageErrorMsg.PARAM_EVAL_METRICS_ERROR.value, +} +EVAL_RUN_CONTEXT_ERROR_MAPPING = { + 'valid_dataset': LineageErrors.PARAM_DATASET_ERROR, + 'metrics': LineageErrors.PARAM_EVAL_METRICS_ERROR +} + + +def validate_raise_exception(raise_exception): + """ + Validate raise_exception. + + Args: + raise_exception (bool): decide raise exception or not, + if True, raise exception; else, catch exception and continue. + + Raises: + MindInsightException: If the parameters are invalid. + """ + if not isinstance(raise_exception, bool): + log.error("Invalid raise_exception. It should be True or False.") + raise MindInsightException( + error=LineageErrors.PARAM_RAISE_EXCEPTION_ERROR, + message=LineageErrorMsg.PARAM_RAISE_EXCEPTION_ERROR.value + ) + + +def validate_user_defined_info(user_defined_info): + """ + Validate user defined info， delete the item if its key is in lineage. + + Args: + user_defined_info (dict): The user defined info. + + Raises: + LineageParamTypeError: If the type of parameters is invalid. + LineageParamValueError: If user defined keys have been defined in lineage. + + """ + if not isinstance(user_defined_info, dict): + log.error("Invalid user defined info. It should be a dict.") + raise LineageParamTypeError("Invalid user defined info. It should be dict.") + for key, value in user_defined_info.items(): + if not isinstance(key, str): + error_msg = "Dict key type {} is not supported in user defined info." \ + "Only str is permitted now.".format(type(key)) + log.error(error_msg) + raise LineageParamTypeError(error_msg) + if not isinstance(value, (int, str, float)): + error_msg = "Dict value type {} is not supported in user defined info." \ + "Only str, int and float are permitted now.".format(type(value)) + log.error(error_msg) + raise LineageParamTypeError(error_msg) + + field_map = set(FIELD_MAPPING.keys()) + user_defined_keys = set(user_defined_info.keys()) + insertion = list(field_map & user_defined_keys) + + if insertion: + for key in insertion: + user_defined_info.pop(key) + raise LineageParamValueError("There are some keys have defined in lineage. " + "Duplicated key(s): %s. " % insertion) + + +def make_directory(path): + """Make directory.""" + if path is None or not isinstance(path, str) or not path.strip(): + log.error("Invalid input path: %r.", path) + raise LineageParamTypeError("Invalid path type") + + # convert relative path to abs path + path = os.path.realpath(path) + log.debug("The abs path is %r", path) + + # check path exist and its write permissions] + if os.path.exists(path): + real_path = path + else: + # All exceptions need to be caught because create directory maybe have some limit(permissions) + log.debug("The directory(%s) doesn't exist, will create it", path) + try: + os.makedirs(path, exist_ok=True) + real_path = path + except PermissionError as err: + log.error("No write permission on the directory(%r), error = %r", path, err) + raise LineageParamTypeError("No write permission on the directory.") + return real_path