class Feature(Bean): name = StringField() type = StringField() data_type = StringField() correlation = BeanField(bean_cls=FeatureCorrelation) missing = BeanField(bean_cls=FeatureMissing) unique = BeanField(bean_cls=FeatureUnique) extension = DictField()
class JobStep(Bean): type = StringField() status = StringField() took = FloatField() datetime = IntegerField() extension = DictField() class Status: Succeed = "succeed" Failed = "failed"
class Model(Bean): name = StringField() framework = StringField() dataset_name = StringField() model_file_size = IntegerField() no_experiment = IntegerField() inputs = ListBeanField(ModelFeature) task_type = StringField() performance = BeanField(Performance) model_path = StringField() status = StringField() pid = IntegerField() score = FloatField() progress = StringField() train_job_name = StringField() train_trail_no = IntegerField() trails = ListBeanField(TrainTrail) extension = DictField() create_datetime = DatetimeField() finish_datetime = DatetimeField() last_update_datetime = DatetimeField() def escaped_time(self): if self.status in [ModelStatusType.Succeed, ModelStatusType.Failed]: if self.finish_datetime is None: raise Exception( "Internal error, train finished but has no finish_datetime. " ) escaped = util.datetime_diff_human_format_by_minute( self.finish_datetime, self.create_datetime) else: escaped = util.datetime_diff_human_format_by_minute( util.get_now_datetime(), self.create_datetime) return escaped def escaped_time_by_seconds(self): if self.status in [ModelStatusType.Succeed, ModelStatusType.Failed]: if self.finish_datetime is None: raise Exception( f"Internal error, model name = {self.name} train finished but has no finish_datetime. " ) escaped = util.datetime_diff(self.finish_datetime, self.create_datetime) else: escaped = util.datetime_diff(util.get_now_datetime(), self.create_datetime) return escaped def default_metric(self): m = \ { 'multi_classification': "logloss", 'regression': "mae", 'binary_classification': "auc" } return m[self.task_type] def log_file_path(self): # exits begin from train start return util.relative_path(P.join(str(self.model_path), 'train.log')) def train_source_code_path(self): # exits begin from train start return util.relative_path(P.join(str(self.model_path), 'train.py')) def train_notebook_uri(self): # exits begin from train start train_notebook_path = P.join(str(self.model_path), 'train.ipynb') return util.relative_path(train_notebook_path)
class TrainTrail(Bean): trail_no = IntegerField() reward = FloatField() elapsed = FloatField() params = DictField()
class Performance(Bean): metrics = DictField() # RegressionTaskMetrics or ClassifyTaskMetrics confusion_matrix = BeanField(ConfusionMatrix) roc_curve = BeanField(ROCCurve)
class TrainTrial(Bean): trial_no = IntegerField() status = StringField() extension = DictField()