Pypgx MLlib

Graph machine learning tools for use with PGX.

class pypgx.api.mllib.DeepWalkModel(java_deepwalk_model)

Bases: object

DeepWalk model object.

compute_similars(v, k)

Compute the top-k similar vertices for a given vertex.

Parameters

• v – id of the vertex or list of vetex ids for which to compute the similar vertices

• k – number of similars to return

destroy()

Destroy this model object.

export()

Return a ModelStore object which can be used to save the model.

Returns

ModelStore object

fit(graph)

Fit the model on a graph.

Parameters

graph – Graph to fit on

store(path, key, overwrite=False)

Store the model in a file.

Parameters

• path – Path where to store the model

• key – Encryption key

• overwrite – Whether or not to overwrite pre-existing file

property trained_vectors

Get the trained vertex vectors for the current DeepWalk model.

Returns

PgxFrame object with the trained vertex vectors

class pypgx.api.mllib.Pg2vecModel(java_pg2vec_model)

Bases: object

Pg2Vec model object.

compute_similars(graphlet_id, k)

Compute the top-k similar graphlets for a list of input graphlets.

Parameters

• graphlet_id – graphletIds or iterable of graphletIds

• k – number of similars to return

destroy()

Destroy this model object.

export()

Return a ModelStore object which can be used to save the model.

Returns

ModelStore object

fit(graph)

Fit the model on a graph.

Parameters

graph – Graph to fit on

infer_graphlet_vector(graph)

Parameters

graph – graphlet for which to infer a vector

infer_graphlet_vector_batched(graph)

Parameters

graph – graphlets (as a single graph but different graphlet-id) for which to infer vectors

store(path, key, overwrite=False)

Store the model in a file.

Parameters

• path – Path where to store the model

• key – Encryption key

• overwrite – Whether or not to overwrite pre-existing file

property trained_graphlet_vectors

Get the trained graphlet vectors for the current pg2vec model.

Returns

PgxFrame containing the trained graphlet vectors