class AnalyzeJobConf(Bean):
job_name = StringField()
dataset_name = StringField()
sample_conf = BeanField(SampleConf)
path = StringField()
temporary_dataset = BooleanField()
label_col = StringField()
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 DatasetStats(Bean):
label_col = StringField()
file_path = StringField()
has_header = BooleanField()
n_rows = IntegerField()
n_cols = IntegerField()
features = ListBeanField(Feature)
feature_summary = BeanField(FeatureTypeStats)
create_datetime = IntegerField()
@property
def features_names(self):
return [f.name for f in self.features]
class SampleConf(Bean):
sample_strategy = StringField()
percentage = IntegerField()
n_rows = IntegerField()
class Strategy:
RandomRows = "random_rows"
Percentage = "percentage"
WholeData = "whole_data"
class TrainJobConf(Bean):
framework = StringField()
name = StringField()
model_name = StringField()
searcher = StringField()
max_trails = IntegerField()
search_space = StringField()
class SearchSpace:
Complex = "complex"
Basic = "basic"
Minimal = "minimal"
class Searcher:
RandomSearcher = 'random_searcher'
EvolutionSearcher = 'evolution_searcher'
MCTSSearcher = 'MCTS_searcher'
EnasSearcher = 'Enas_searcher'
class ExperimentConf(Bean):
dataset_name = StringField()
dataset_has_header = BooleanField()
dataset_default_headers = ListObjectField()
train_mode = StringField()
engine = StringField()
label_col = StringField()
pos_label = ObjectField()
task_type = StringField() # calc in frontend
partition_strategy = StringField()
cross_validation = BeanField(CrossValidation)
train_validation_holdout = BeanField(TrainValidationHoldout)
datetime_series_col = StringField()
partition_col = StringField()
# feature_series_name = StringField()
file_path = StringField()
test_file_path = StringField()
class PartitionStrategy:
CrossValidation = 'cross_validation'
TrainValidationHoldout = 'train_validation_holdout'
Manual = 'manual'
class FeatureMissing(Bean):
value = IntegerField()
percentage = FloatField()
status = StringField()
class Status:
TooHigh = 'too_high'
@staticmethod
def calc_status(percentage):
if percentage > 70:
return FeatureMissing.Status.TooHigh
else:
return FeatureNormalStatus
class FeatureUnique(Bean):
value = IntegerField()
percentage = FloatField()
status = StringField()
class Status:
ID_ness = 'ID-ness'
Stable = 'stable'
@staticmethod
def calc_status(n_uniques, percentage):
if n_uniques == 1:
return FeatureUnique.Status.Stable
else:
if percentage > 90:
return FeatureUnique.Status.ID_ness
else:
return FeatureNormalStatus
class FeatureCorrelation(Bean):
value = FloatField()
status = StringField()
class Status:
TooHigh = 'too_high'
TooLow = 'too_low'
@staticmethod
def calc_status(correlation, is_target_col):
_c = abs(correlation)
if _c > 0.5:
if is_target_col is True:
return FeatureNormalStatus
else:
return FeatureCorrelation.Status.TooHigh
elif _c < 0.01:
return FeatureCorrelation.Status.TooLow
else:
return FeatureNormalStatus
class RespPreviewDataset(Bean):
headers = ListObjectField()
rows = ListObjectField()
count = IntegerField()
file_path = StringField()
class FeatureMode(Bean):
value = StringField()
count = IntegerField()
percentage = FloatField()
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 ModelFeature(Bean):
name = StringField()
type = StringField()
data_type = StringField()
class TrainTrial(Bean):
trial_no = IntegerField()
status = StringField()
extension = DictField()