Table Of Contents

PowerIterationClusteringModel predict


predict(self, frame, source_column, destination_column, similarity_column, k=2, max_iterations=100, initialization_mode='random')

Predict the clusters to which the nodes belong to

Parameters:

frame : Frame

Frame storing the graph to be clustered

source_column : unicode

Name of the column containing the source node

destination_column : unicode

Name of the column containing the destination node

similarity_column : unicode

Name of the column containing the similarity

k : int32 (default=2)

Number of clusters to cluster the graph into. Default is 2

max_iterations : int32 (default=100)

Maximum number of iterations of the power iteration loop. Default is 100

initialization_mode : unicode (default=random)

Initialization mode of power iteration clustering. This can be either “random” to use a random vector as vertex properties, or “degree” to use normalized sum similarities. Default is “random”.

Returns:

: dict

A new frame with a column storing node id and a column with corresponding cluster assignment

Predict the cluster assignments for the nodes of the graph and create a new frame with a column storing node id and a column with corresponding cluster assignment

Examples

See here for examples.