DaalKMeansModel train

---

train(self, frame, observation_columns, column_scalings=None, k=2, max_iterations=100, label_column='predicted_cluster')

[ALPHA] Creates DAAL KMeans Model from train frame.

Parameters:

frame : Frame

A frame to train the model on.

observation_columns : list

Columns containing the observations.

column_scalings : list (default=None)

Optional column scalings for each of the observation columns. The scaling value is multiplied by the corresponding value in the observation column.

k : int32 (default=2)

Desired number of clusters. Default is 2.

max_iterations : int32 (default=100)

Number of iterations for which the algorithm should run. Default is 20.

label_column : unicode (default=predicted_cluster)

Optional name of output column with index of cluster each observation belongs to.

Returns:

: dict

dictionary

A dictionary with trained KMeans model with the following keys:

‘centroids’ : dictionary with ‘Cluster:id’ as the key and the corresponding centroid as the value ‘assignments’ : Frame with cluster assignments.

Creating a DAAL KMeans Model using the observation columns. The algorithm chooses random observations as the initial cluster centers.

Examples

See here for examples.