turicreate.SArray.random_split — Turi Create API 6.4.1 documentation (original) (raw)
SArray. random_split(fraction, seed=None)¶
Randomly split the rows of an SArray into two SArrays. The first SArray contains M rows, sampled uniformly (without replacement) from the original SArray. M is approximately the fraction times the original number of rows. The second SArray contains the remaining rows of the original SArray.
| Parameters: | fraction : float Approximate fraction of the rows to fetch for the first returned SArray. Must be between 0 and 1. seed : int, optional Seed for the random number generator used to split. |
|---|---|
| Returns: | out : tuple [SArray] Two new SArrays. |
Examples
Suppose we have an SArray with 1,024 rows and we want to randomly split it into training and testing datasets with about a 90%/10% split.
sa = turicreate.SArray(range(1024)) sa_train, sa_test = sa.random_split(.9, seed=5) print(len(sa_train), len(sa_test)) 922 102