Randomized Parameter Search¶
Randomized search on hyper parameters.
Documentation¶
Performs a randomized parameter search returning scores and best model found. Uses table as a “hypercube” of parameters to sample from. Not all parameter combinations are tested, but rather a fixed number of parameter settings is sampled from the specified distributions. All combinations of parameters from all columns have equal chance of beeing sampled. Use masked values for parameter/columns with different lengths.
Definition¶
Input ports¶
- in-model
- parameter space
- X
- Y
- cross-validation
Output ports¶
- results
- parameters
- out-model
Configuration¶
- Cross validation splits (cv)
Number of fold in the default K-Fold cross validation. Ignored when cross-validation port is given
- iterations (n_iter)
Number of randomized searches done
Implementation¶
- class node_paramsearch.ParameterSearch_Randomized[source]
