Given an input dataset, we use SMACdown to find the best parameters for creating an ensemble from that dataset.

The script uses as inputs, beside the identifier of the dataset, the evaluation metric we maximize (defaulting to average_phi), the objective field and a string used as a prefix when naming intermediate resources created by the workflow. You can select the metric to optimize (see below).

Classification metrics:

• average_recall

• average_phi

• accuracy

• average_precision

• average_f_measure

Regression metrics:

• r_squared

• mean_absolute_error

• mean_squared_erro

This workflow will generate a big number of auxiliary resources when executed. To instruct the script to delete all of them before finishing set the delete-resources execution input parameter to true.

This routine implements K-means clustering using the Pham-Dimov-Nguyen algorithm for choosing the best K.

"Selection of K in K-means clustering", Proc. IMechE, Part C: J. Mechanical Engineering Science, v.219

(best-cluster ...)

(best-cluster dataset cluster-args k)

Inputs: dataset: (string) Dataset ID for the dataset to be clustered cluster-args: (map) cluster function arguments * k: (number) number of clusters

Output: (cluster) Created cluster for K

This function is used by (best-k-means ...) to do a K-means clustering of the dataset using the WhizzML cluster function with the specified K.

This routine implements K-means clustering using the Pham-Dimov-Nguyen algorithm for choosing the best K.

'Selection of K in K-means clustering' Proc. IMechE, Part C: J. Mechanical Engineering Science, v.219

Inputs: dataset: (string) Dataset ID for the dataset to be clustered cluster-args: (map) cluster arguments for the cluster search operation k-min: (number) minimum value of k k-max: (number) maximum value of k bestcluster-args: (map) cluster arguments for the final best cluster operation clean: (boolean) Delete all but the optimal cluster * logf: (boolean) Enable logging

Output: (batchcentroid) Batchcentroid for best K-means clustering

This routine uses the Pham-Dimov-Nguyen algorithm to create a WhizzML batchcentroid object and WhizzML dataset annotated with the best K-means clustering of the supplied dataset.

The clusters-args and bestcluster-args parameters are maps that one can use to optionally specify all the parameters for the cluster function except the dataset, k, and name parameters. (See the 'Clusters Arguments' table in the BigML 'Clusters' documentation for details.) cluster-args is used in the search phase for the best K. bestcluster-args allows one to specify different args for the final stage of clustering with the best K. In particular, one might do clustering on samples of the dataset during the search phase to save time and other resources, then do the best clustering on the full dataset.

If bestcluster-args matches cluster-args, the result for the best K generated with cluster-args during the search phase is returned by (best-k-means ....). If bestcluster-args differs from cluster-args, the dataset is re-clustered with the best K and that is returned by (best-k-means ....).