ampligraph.datasets.load_from_rdf(folder_name, file_name, rdf_format='nt', data_home=None, add_reciprocal_rels=False)

Load an RDF file

Loads an RDF knowledge graph using rdflib APIs. Multiple RDF serialization formats are supported (nt, ttl, rdf/xml, etc). The entire graph will be loaded in memory, and converted into an rdflib Graph object.


Large RDF graphs should be serialized to ntriples beforehand and loaded with load_from_ntriples() instead.


It is recommended to use ampligraph.evaluation.train_test_split_no_unseen() to split custom knowledge graphs into train, validation, and test sets. Using this function will lead to validation, test sets that do not include triples with entities that do not occur in the training set.

  • folder_name (str) – Base folder where the file is stored.
  • file_name (str) – File name.
  • rdf_format (str) – The RDF serialization format (nt, ttl, rdf/xml - see rdflib documentation).
  • data_home (str) – The path to the folder that contains the datasets.
  • add_reciprocal_rels (bool) – Flag which specifies whether to add reciprocal relations. For every <s, p, o> in the dataset this creates a corresponding triple with reciprocal relation <o, p_reciprocal, s>. (default: False).

triples – the actual triples of the file.

Return type:

ndarray , shape [n, 3]