lale.lib.sklearn.svr module

class lale.lib.sklearn.svr.SVR(*, kernel='rbf', degree=3, gamma='scale', coef0=0.0, tol=0.001, C=1.0, epsilon=0.1, shrinking=True, cache_size=200.0, verbose=False, max_iter=-1)

Bases: PlannedIndividualOp

Support Vector Classification from scikit-learn.

This documentation is auto-generated from JSON schemas.

Parameters

• kernel (union type, default 'rbf') –

  Specifies the kernel type to be used in the algorithm.

  • ’precomputed’, not for optimizer

  • or ‘linear’, ‘poly’, ‘rbf’, or ‘sigmoid’

  • or callable, not for optimizer

  See also constraint-1.

• degree (integer, >=0, >=2 for optimizer, <=5 for optimizer, default 3) – Degree of the polynomial kernel function (‘poly’).

• gamma (union type, default 'scale') –

  Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.

  • ’scale’ or ‘auto’

  • or float, >0.0, >=3.0517578125e-05 for optimizer, <=8 for optimizer, loguniform distribution

• coef0 (float, >=-1 for optimizer, <=1 for optimizer, not for optimizer, default 0.0) – Independent term in kernel function.

• tol (float, >0.0, <=0.01 for optimizer, default 0.001) – Tolerance for stopping criteria.

• C (float, >0.0, >=0.03125 for optimizer, <=32768 for optimizer, loguniform distribution, default 1.0) – Penalty parameter C of the error term.

• epsilon (float, >=0.0, >=1e-05 for optimizer, <=10000.0 for optimizer, not for optimizer, default 0.1) – Epsilon in the epsilon-SVR model. It specifies the epsilon-tube within which no penalty is associated in the training loss function with points predicted within a distance epsilon from the actual value.

• shrinking (boolean, default True) – Whether to use the shrinking heuristic.

• cache_size (float, >=0, <=1000 for optimizer, not for optimizer, default 200.0) – Specify the size of the kernel cache (in MB).

• verbose (boolean, not for optimizer, default False) – Enable verbose output.

• max_iter (integer, >=1 for optimizer, <=1000 for optimizer, not for optimizer, default -1) – Hard limit on iterations within solver, or -1 for no limit.

Notes

constraint-1 : union type

Sparse precomputed kernels are not supported.

• negated type of ‘X/isSparse’

• or kernel : negated type of ‘precomputed’

fit(X, y=None, **fit_params)

Train the operator.

Note: The fit method is not available until this operator is trainable.

Once this method is available, it will have the following signature:

Parameters

• X (array) –

  The outer array is over samples aka rows.

  • items : array of items : float

    The inner array is over features aka columns.

• y (array of items : float) –

predict(X, **predict_params)

Make predictions.

Note: The predict method is not available until this operator is trained.

Once this method is available, it will have the following signature:

Parameters

X (array, optional) –

The outer array is over samples aka rows.

• items : array of items : float

  The inner array is over features aka columns.

Returns

result – The predicted classes.

Return type

array of items : float