Changeforest

--------------------------

**New features:**

- `changeforest` now uses random forests from [`biosphere`](https://github.com/mlondschien/biosphere). This should be faster than `smartcore` used previously and supports parallelization.

--------------------------

**New features:**

- Implemented trait `Display` for `BinarySegmentationResult`. In Python `str(result)` now prints a pretty display (77).

**Other changes:**

- The `TwoStepSearch` algorithm now only uses valid guesses from `split_candidates` (76).

**Bug fixes:**

- (R only) The R6 class `Control` now gets correctly exported (79).

--------------------------

**Bug fixes:**

- (Python only) Parameters will now be correctly passed to `changeforest` via `Control` even if they have the incorrect data type.
- Fixed a bug where SBS would panic in cases with very small minimal segments lengths due to rounding.
- Fixed a bug in model selection which resulted in a higher type I error.

--------------------------

**New feature**:

- The `TwoStepSearch` now uses three initial guesses, the 0.25, 0.5 and 0.75 quantiles of the segment, for the first step. The the best split corresponding to the highest maximal gain from the three guesses is used in the second step. The permutation test used for model selection has also been adjusted to be consistent.

This increases estimation performance for classifier based methods, especially if used with standard binary segmentation, i.e. for `changeforest_bs` and `changeknn_bs`.

------------------

Added license file for compatibility with conda-forge.

------------------

Initial release of `changeforest`.