Scikit-Learn

auto: 
It let choose the solver automatically 
based on the type of data
. 

svd: 
In order to calculate the Ridge 
coefficients, this parameter uses a Singular 
Value Decomposition of X.
 

cholesky:
This parameter uses the 
standard 
scipy.linalg.solve()
function to 
get a closed-form solution.
 

Sparse_cg: 
It uses the conjugate gradient 
solver which is more appropriate than 
‘cholesky’ for large-scale data.
 

lsqr:
It is the fastest and uses the 
dedicated regularized least-squares routine 
scipy.sparse.linalg.lsqr. 
 

sag: 
It uses iterative process and a 
Stochastic Average Gradient descent.
 

---

Scikit-Learn
39 

saga:
It also uses iterative process and an 
improved Stochastic Average Gradient 
descent.
 
random_state: 
int, RandomState instance 
or None,
 
optional, default = none
 
This parameter represents the seed of the pseudo 
random number generated which is used while 
shuffling the data. Following are the options: 

int:
In this case, 
random_state
is the 
seed used by random number generator. 

RandomState instance:
In this case, 
random_state
is the random number 
generator.

None:
In this case, the random number 
generator is the RandonState instance used 
by np.random.
Attributes 
Followings table consist the attributes used by 
Ridge
module: