loki2.mil.prampt_generate.blca_metastasis_prampt
================================================

.. py:module:: loki2.mil.prampt_generate.blca_metastasis_prampt

.. autoapi-nested-parse::

   Generate PRAMPT data for BLCA metastasis analysis.

   This script loads cell embeddings from .pt files, samples a subset of cells,
   and saves the merged embeddings as a parquet file for MIL training.







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

.. py:function:: setup_dummy_modules() -> None

   Sets up dummy modules for 'loki2' and its submodules.

   This is required to simulate the module structure that the torch model
   expects when unpickling objects that reference e.g. 'loki2.data.dataclass.cell_graph'.


.. py:function:: load_tensor(file_path: Union[str, pathlib.Path]) -> Any

   Load torch object from .pt file with dummy loki2 module support.

   Sets up dummy loki2 modules before loading to handle unpickling of
   objects that reference loki2.data.dataclass.cell_graph classes.

   :param file_path: Path to the .pt file to load.

   :returns: Loaded torch object (typically containing cell embeddings and positions).


.. py:data:: directory_path
   :value: './data/TCGA/BLCA'


.. py:data:: meta_path
   :value: './data/loki2_MIL/data/downsamples/blca_metastasis/BLCA_META.txt'


.. py:data:: sample_ratio
   :value: 0.1


.. py:data:: meta_df

.. py:data:: patient_embeddings

.. py:data:: patient_id

.. py:data:: records
   :value: []


.. py:data:: combined_df

.. py:data:: merged_df