Adding tests for cross validation

Need to add tests for cross validation on time series and tables. Metrics should be measured, and monitor how models will predict on synthetic data.

Example:
generate synthetic dataset with linear dependence, e.g. time series `1, 2, 3, 4, ..., 50` - create pipeline `lagged -> linear` - run cross-validation on 2 folds with 2 validation blocks and check that the algorithm predicts everything with small (almost zero) error and with the correct length