def create_name_for_xgbmodel(run_cfg: Dict[str, Any],
outer_split_num: int,
model: XGBModel,
inner_split_num: int,
prefix_location='logs/',
suffix='.pkl') -> str:
if run_cfg['analysis_type'] == AnalysisType.FLATTEN_CORRS:
model_str_representation = run_cfg['analysis_type'].value
for key in [
'colsample_bylevel', 'colsample_bynode', 'colsample_bytree',
'gamma', 'learning_rate', 'max_depth', 'min_child_weight',
'n_estimators', 'subsample'
]:
model_str_representation += key[-3:] + '_' + str(
model.get_params()[key])
return prefix_location + '_'.join([
run_cfg['target_var'], run_cfg['dataset_type'].value,
str(outer_split_num),
str(inner_split_num), model_str_representation,
str(run_cfg['num_nodes']), run_cfg['param_conn_type'].value
]) + suffix
def to_mls(xgboost_model: xgboost.XGBModel, **kwargs):
params = xgboost_model.get_params()
def standardize_types(v):
if isinstance(v, np.ndarray):
return [normalize_float(x) for x in v.tolist()]
elif isinstance(v, float):
return normalize_float(v)
elif callable(v):
return str(v) # TODO
return v
def deep_get_params(params):
if isinstance(params, (list, tuple)):
return [deep_get_params(x) for x in params]
elif isinstance(params, dict):
return {k: deep_get_params(v) for k, v in params.items()}
else:
v = standardize_types(params)
try:
p = v.get_params()
t = type(v).__module__ + "." + type(v).__name__
return {"@value": {"type": t, "params": deep_get_params(p)}}
except AttributeError:
try:
json.dumps(v)
return v
except TypeError as e:
raise NotImplementedError(
"can't convert sklearn model of type {} to mls: {}".format(
type(xgboost_model), e
)
)
params = deep_get_params(params)
model_hash = xgboost_model.__hash__()
model_class = "{}.{}".format(
type(xgboost_model).__module__, type(xgboost_model).__name__
)
algo = Algorithm(_id=model_class)
implementation = Implementation(
_id=generate_unique_id("http://www.w3.org/ns/mls#Implementation"),
parameters=[
HyperParameter(key, model_hash=model_hash) for key in params.keys()
],
implements=algo,
version=xgboost.__version__,
)
input_values = [
HyperParameterSetting(
value=val,
specified_by=HyperParameter(key, model_hash=model_hash),
model_hash=model_hash,
)
for key, val in params.items()
if val is not None
]
output_values = []
if EVALUATION_MEASURE_KEY in kwargs:
eval_measure = kwargs[EVALUATION_MEASURE_KEY]
output_values.append(evaluation_measure(eval_measure[0], eval_measure[1]))
model = Run(model_hash, implementation, input_values, output_values, algo)
return RunSchema().dumps(model)