Parameters:
N:int
The total number of elements in the data set.
N_iter:int (default 10)
Re-shuffle and split iteration count.
Test_size:float (default 0.1), int, or None
If it is a float type of data, this number should be between 0-1.0, representing the percentage of the test set. If it is an int type, represents the number of test sets. If none, the value is automatically set to the complement of the train set size
train_size:float, int, or none (default is None)
If the data for the float type should be between 0 and 1, and the percentage of the dataset in the train set split is the int type, represents the number of samples for the train set. If none, the value is automatically set to the complement of the test set size
Random_state:int or Randomstate
Pseudo-random number generator state for random sampling.
Example
rs = cross_validation. Shufflesplit (4, n_iter=3, test_size=.25, random_state=0)
Shufflesplit () function in Python