def _persist_to_file(data,
expert_type="best_model",
partition_label=None,
partition_hash=None,
path=""):
"""Returns unpickled file or json metadata from directory.
Parameters
----------
expert_type : string
options for json format
['partition','model_reprs','logical_partition','physical_partition',
'frequency','horizon','best_model_hash','best_model_name','best_model_repr']
anything else is pickled (e.g. 'best_model', 'cv_data', 'cv_results')
partition_label : dict
Model's metadata used to generate hash for .pkl file.
e.g. {'country':'Canada', 'city':'Vancouver', 'series':'Number of citizens'}
partition_hash : string
Partition's hash generated with `generate_partition_hash` function
path : str
Path to the directory, where files are to be stored,
by default '' resulting in current working directory behaviour
"""
if partition_hash is None:
if partition_label is not None:
partition_hash = generate_partition_hash(partition_label)
else:
raise ValueError(
"Either one of `partition_label` or `partition_hash` must be set."
)
elif partition_label is not None:
raise ValueError(
"Only one of `partition_label` or `partition_hash` must be set. You set both"
)
file_path = Path(path, f"{partition_hash}.{expert_type}")
if not file_path.parent.exists():
file_path.parent.mkdir(parents=True)
if expert_type in [
"partition",
"model_reprs",
"logical_partition",
"physical_partition",
"frequency",
"horizon",
"best_model_hash",
"best_model_name",
"best_model_repr",
]:
with open(file_path, "w") as json_file:
json.dump(data, json_file)
else:
with open(file_path, "wb") as pickle_file:
pickle.dump(data, pickle_file)
def __init__(
self,
best_model,
cv_results,
cv_data,
model_reprs,
partition,
X_train,
y_train,
frequency,
horizon,
country_code_column,
):
self.best_model = best_model
self.cv_results = cv_results
self.cv_data = cv_data
self.model_reprs = model_reprs
self.partition = partition
self.X_train = X_train
self.y_train = y_train
self.frequency = frequency
self.horizon = horizon
self.country_code_column = country_code_column
self.best_model_hash = generate_estimator_hash(best_model)
self.best_model_cv_data = self.cv_data.rename({self.best_model_hash: "best_model"}, axis=1)[
["split", "y_true", "best_model"]
]
self.best_model_name = get_estimator_name(best_model).replace("model__", "")
self.best_model_cv_results = self.cv_results[self.cv_results["rank_test_score"] == 1].iloc[0]
self.best_model_repr = self.model_reprs[self.best_model_hash]
self.partition_hash = generate_partition_hash(self.partition)
self._persist_attrs = sorted(set(self.__dict__.keys()).difference(["self"]))
self._df_plot = None