agedi.api._display
==================

.. py:module:: agedi.api._display

.. autoapi-nested-parse::

   Rich UI / console display utilities.



Functions
---------

.. autoapisummary::

   agedi.api._display._fmt_target
   agedi.api._display._extract_data_info
   agedi.api._display._check_head_dimensions
   agedi.api._display._render_config_tree
   agedi.api._display._extract_diffusion_display_info
   agedi.api._display._get_device_info
   agedi.api._display._print_training_config
   agedi.api._display._print_log_path
   agedi.api._display._print_loaded_model_info
   agedi.api._display._print_sampling_config


Module Contents
---------------

.. py:function:: _fmt_target(target: str) -> str

   Return the short class name from a dotted ``_target_`` string.


.. py:function:: _extract_data_info(data: Sequence[Atoms]) -> Dict

   Extract summary information from a list of ASE Atoms objects.

   :param data: List of ASE :class:`~ase.Atoms` objects to inspect.
   :type data: Sequence[Atoms]

   :returns: A dictionary with the following keys:

             * ``"cell"`` – flattened 9-element list of the (shared) unit-cell
               matrix, or ``None`` if cells differ between structures.
             * ``"symbols"`` – list of unique chemical symbols present in the data.
             * ``"n_training_data"`` – total number of structures.
   :rtype: dict


.. py:function:: _check_head_dimensions(diffusion_cfg: dict) -> list

   Validate that head input dimensions match feature_size + conditioning output dims.

   :param diffusion_cfg: The ``diffusion`` sub-dict from ``hparams.yaml``.
   :type diffusion_cfg: dict

   :returns: Warning messages for any dimension mismatches, empty if all match.
   :rtype: list of str


.. py:function:: _render_config_tree(data, tree: rich.tree.Tree) -> None

   Recursively populate a Rich :class:`~rich.tree.Tree` with config key/values.

   * Dicts: each key becomes a leaf (scalar) or sub-branch (dict/list).
     The ``_target_`` key is skipped — callers show it as the branch label.
   * Lists: each item becomes a sub-branch labelled by its ``_target_`` class
     name (or a numeric index for plain scalars).
   * Scalars and ``None``: shown as ``key  value``; ``None`` is omitted.


.. py:function:: _extract_diffusion_display_info(diffusion_cfg: dict) -> dict

   Extract human-readable display values from a nested Hydra diffusion config.

   :param diffusion_cfg: The ``diffusion`` sub-dict from ``hparams.yaml``, as returned by
                         :meth:`~agedi.diffusion.agedi.Agedi.get_hparams`.
   :type diffusion_cfg: dict

   :returns: Flat dict with display-friendly keys: ``model``, ``feature_size``,
             ``n_blocks``, ``cutoff``, ``noisers``, ``conditionings``, ``lr``,
             ``lr_factor``, ``lr_patience``, ``weight_decay``.
   :rtype: dict


.. py:function:: _get_device_info() -> str

   Return a human-readable string describing the available compute device.


.. py:function:: _print_training_config(hparams: dict) -> None

   Print a Rich-formatted training configuration panel.

   :param hparams: The hparams dict as saved to ``hparams.yaml``.  Must contain a
                   ``"diffusion"`` key with the nested Hydra config.  Metadata keys
                   (``n_train``, ``n_val``, ``batch_size``, etc.) are read directly.
   :type hparams: dict


.. py:function:: _print_log_path(trainer: Trainer) -> None

   Print the resolved log directory for this training run.


.. py:function:: _print_loaded_model_info(params: dict, checkpoint_path: pathlib.Path, device) -> None

   Print a Rich-formatted summary of a loaded diffusion model.


.. py:function:: _print_sampling_config(n_samples: int, steps: int, eps: float, batch_size: int, formula=None, n_atoms=None, template=None, cell=None, confinement=None, property=None, force_field_guidance: float = 0.0) -> None

   Print a Rich-formatted sampling configuration panel.