FIt SNE Versions Save

Fixed bugs that prevented v1.2.0 from compiling on Windows.

Several changes to default FIt-SNE settings to make it more suitable for embedding large datasets. See this recent paper by Dmitry Kobak and Philipp Berens for more details.

Major changes to default values: -Learning rate increased from the fixed value of 200 to max(200, N/early_exag_coeff). -Iteration number decreased from 1000 to 750. -Initialization is set to PCA (computed via fast SVD implementations like ARPACK).

Minor changes: -Late exaggeration start is set to the end of early exaggeration (if late exaggeration coefficient is provided). -Limiting max step size to 5 (solves problem encountered when learning rate set too high and attractive forces cause a small number of points to overshoot)

• Decreasing the degree of freedom (df) of the t-distribution reveals fine structure that is not visible in standard t-SNE. This PR adds a df parameter for that purpose. Preprint will be forthcoming.
• Added documentation to Python and R wrappers
• Added License
• Binary checks if the wrapper version matches the binary version

First stable release (i.e. future changes will be integrated into releases and the versioning will follow the semantic versioning guidelines).

Also, including a binary for Windows users. Mac/Linux can compile with a single command, as described in the README.