Pypairs

In order to increase reproduceability a fixed seed was added to cyclone() ensuring comperable results across subsequent calls on the same data. This affects the random shuffling within cyclone().

cyclone and sandbag are now even easier to call from the command line.

Easy as:
$ cyclone -i {mat.csv} -o {prediction.csv}

New feature:
* Multithreading now available for `pais.cyclone()`

Minor changes and fixes:
* `pais.sandbag()` now significally faster
* `pais.sandbag()` more stable in terms of memory access

Fixed wrong phase allocation for cell cycle prediction.
Cells where either G1 or G2M score is greater than 0.5 should be assigned to the greather of those two not of all