Include a n_splits option in AutoMLSearch

[guilhermeparreira]

trafficstars

• As a user, I wish I could use EvalML to predict my time series, allowing me to change the default n_splits options in class evalml.automl.AutoMLSearch.

Nowadays this option does not exist. I am currently working with a small time series length.

I can not use n_splits in any of these functions:

delays = 14
problem_config = {
        'forecast_horizon':35,
        'gap':0,
        'max_delay': delays, # it uses 14 periods behind to predict
        'time_index':'Date',
        'verbose':False,
        'njobs':-1,
      }
automl = AutoMLSearch(
          X_train,
          y_train,
          problem_type="time series regression",
          max_batches=1,
          problem_configuration=problem_config,
          allowed_model_families=[
              "xgboost",
              "random_forest",
              "linear_model",
              "extra_trees",
              "decision_tree",
          ],
      )
automl.search()

Thanks in advance!