- Added retrain() function to allow for warm starts and restarts.
- Setting numit = 0 in train() now initializes the computation, but doesn’t do any iterations

- Fixed a bug where weights for regression with factorization were incorrectly included in the calculation.

Updated some of the internal linear algebra for 2-5x speedup

TRMF_summary now prints a weighted R2 for weighted data.

Fixed a bug in the component function which only returned the Xm component.

Fixed a bug in NormalizeMatrix which returns NA’s in some cases.

- Renamed TRMF_coefficients() to TRMF_columns() to make less confusing. TRMF_coefficients() will be deprecated future releases.