# 時系列ユーティリティ

このページには、時系列ベースのモデルに使用できるすべてのユーティリティ関数とクラスがリストされます。

これらのほとんどは、時系列モデルのコードを研究している場合、または分散出力クラスのコレクションに追加したい場合にのみ役立ちます。

## Distributional Output[[transformers.time_series_utils.NormalOutput]]

Normal distribution output class.

A mock value for a dotted path (e.g. `torch.float32`): attribute access chains,
calls behave as pass-through decorators, `repr` is the dotted path, and using it
as a base class substitutes a plain-`type` base (PEP 560 `__mro_entries__`), so
real subclasses keep a normal metaclass and `inspect.signature` reads their real
`__init__` instead of a mock's.

Student-T distribution output class.

A mock value for a dotted path (e.g. `torch.float32`): attribute access chains,
calls behave as pass-through decorators, `repr` is the dotted path, and using it
as a base class substitutes a plain-`type` base (PEP 560 `__mro_entries__`), so
real subclasses keep a normal metaclass and `inspect.signature` reads their real
`__init__` instead of a mock's.

Negative Binomial distribution output class.

A mock value for a dotted path (e.g. `torch.float32`): attribute access chains,
calls behave as pass-through decorators, `repr` is the dotted path, and using it
as a base class substitutes a plain-`type` base (PEP 560 `__mro_entries__`), so
real subclasses keep a normal metaclass and `inspect.signature` reads their real
`__init__` instead of a mock's.