GraphDataSet Class Reference

Inheritance diagram for GraphDataSet:

Collaboration diagram for GraphDataSet:

Public Member Functions
	__init__ (self, root, n_files=None, samples=None, features=[], edge_features=[], global_features=[], normalize=None, **kwargs)
	processed_file_names (self)
	process (self)

Public Attributes
	root = Path(root)
	Root path.
	normalize = normalize
	Normalize.
	n_files = n_files
	Number of files.
	node_features = features
	Node features.
	edge_features = edge_features
	Edge features.
	global_features = global_features
	Global features.
	samples = samples
	Samples.
	data = True)
	Data and Slices.
	slices = torch.load(self.processed_paths[0])
	Data and Slices.
	x
	delete attributes
	y
	delete attributes
	avail_samples
	delete attributes

Detailed Description

Dataset handler for converting Belle II data to PyTorch geometric InMemoryDataset.

The ROOT format expects the tree in every file to be named ``Tree``,
and all node features to have the format ``feat_FEATNAME``.

.. note:: This expects the files under root to have the structure ``root/**/<file_name>.root``
    where the root path is different for train and val.
    The ``**/`` is to handle subdirectories, e.g. ``sub00``.

Args:
    root (str): Path to ROOT files.
    n_files (int): Load only ``n_files`` files.
    samples (int): Load only ``samples`` events.
    features (list): List of node features names.
    edge_features (list): List of edge features names.
    global_features (list): List of global features names.
    normalize (bool): Whether to normalize input features.

Definition at line 258 of file geometric_datasets.py.

Constructor & Destructor Documentation

__init__()

__init__	(		self,
			root,
			n_files = None,
			samples = None,
			features = [],
			edge_features = [],
			global_features = [],
			normalize = None,
		**	kwargs )

Initialization.

Definition at line 279 of file geometric_datasets.py.

    ):
        """
        Initialization.
        """
        assert isinstance(
            features, list
        ), f'Argument "features" must be a list and not {type(features)}'
        assert len(features) > 0, "You need to use at least one node feature"
 
        
        self.root = Path(root)
 
        
        self.normalize = normalize
 
        
        self.n_files = n_files
        
        self.node_features = features
        
        self.edge_features = edge_features
        
        self.global_features = global_features
        
        self.samples = samples
 
        # Delete processed files, in case
        file_path = Path(self.root, "processed")
        files = list(file_path.glob("*.pt"))
        for f in files:
            f.unlink(missing_ok=True)
 
        # Needs to be called after having assigned all attributes
        super().__init__(root, None, None, None)
 
        
        self.data, self.slices = torch.load(self.processed_paths[0])
 

Member Function Documentation

process()

process

(

self

)

Processes the data to create graph objects and stores them in ``root/processed/processed_data.pt``
where the root path is different for train and val.

Called internally by PyTorch.

Definition at line 334 of file geometric_datasets.py.

    def process(self):
        """
        Processes the data to create graph objects and stores them in ``root/processed/processed_data.pt``
        where the root path is different for train and val.
 
        Called internally by PyTorch.
        """
        num_samples = _preload(self)
        data_list = [_process_graph(self, i) for i in range(num_samples)]
        data, slices = self.collate(data_list)
        torch.save((data, slices), self.processed_paths[0])
 
        
        del self.x, self.y, self.avail_samples, data_list, data, slices

processed_file_names()

processed_file_names

(

self

)

Name of processed file.

Definition at line 328 of file geometric_datasets.py.

    def processed_file_names(self):
        """
        Name of processed file.
        """
        return ["processed_data.pt"]
 

Member Data Documentation

avail_samples

avail_samples

delete attributes

Definition at line 347 of file geometric_datasets.py.

data

data = True)

Data and Slices.

Definition at line 325 of file geometric_datasets.py.

edge_features

edge_features = edge_features

Edge features.

Definition at line 309 of file geometric_datasets.py.

global_features

global_features = global_features

Global features.

Definition at line 311 of file geometric_datasets.py.

n_files

n_files = n_files

Number of files.

Definition at line 305 of file geometric_datasets.py.

node_features

node_features = features

Node features.

Definition at line 307 of file geometric_datasets.py.

normalize

normalize = normalize

Normalize.

Definition at line 302 of file geometric_datasets.py.

root

root = Path(root)

Root path.

Definition at line 299 of file geometric_datasets.py.

samples

samples = samples

Samples.

Definition at line 313 of file geometric_datasets.py.

slices

slices = torch.load(self.processed_paths[0])

Data and Slices.

Definition at line 325 of file geometric_datasets.py.

x

x

delete attributes

Definition at line 347 of file geometric_datasets.py.

y

y

delete attributes

Definition at line 347 of file geometric_datasets.py.

---

The documentation for this class was generated from the following file:

• analysis/scripts/grafei/model/geometric_datasets.py