# osprey configuration file.
#---------------------------
# usage:
#  osprey worker config.yaml

estimator:
    # The model/estimator to be fit.
    eval: |
        Pipeline([
                ('tica', tICA()),
                ('cluster', MiniBatchKMeans()),
                ('msm', MarkovStateModel(lag_time=100, n_timescales=5, verbose=True)),
        ])

    # for eval, a python package containing the estimator definitions
    eval_scope: msmbuilder


strategy:
    name: random

search_space:
  cluster__n_clusters:
    min: 50
    max: 5000
    type: int

  tica__lag_time:
    min: 1
    max: 200
    type: int

  tica__commute_mapping:
    choices:
      - True
      - False
    type: enum

  tica__n_components:
    min: 1
    max: 20
    type: int


cv:
  name: shufflesplit
  params:
    n_splits: 5
    test_size: 0.4

dataset_loader:
  # specification of the dataset on which to train the models.
  name: numpy
  params:
    filenames: /work/je714/cross-validations/ef-hand/sctrajs/*


trials:
  uri: sqlite:////work/je714/cross-validations/ef-hand/osprey-trials.db