Implementation:Scikit learn Scikit learn SVC

Knowledge Sources	Scikit_learn Scikit-learn Docs
Domains	Machine Learning, Support Vector Machines
Last Updated	2026-02-08 15:00 GMT

Overview

Concrete tool for C-Support Vector Classification and other SVM variants provided by scikit-learn.

Description

SVC implements C-Support Vector Classification based on libsvm. The module also includes NuSVC (Nu-Support Vector Classification), SVR (Support Vector Regression), NuSVR (Nu-Support Vector Regression), OneClassSVM (unsupervised outlier detection), LinearSVC (linear SVM using liblinear), and LinearSVR (linear SVR using liblinear). SVC supports multiple kernel functions (linear, polynomial, RBF, sigmoid, precomputed) and handles multiclass classification via a one-vs-one scheme.

Usage

Use SVC for classification tasks where you need a powerful, flexible classifier with kernel support. It works well for small to medium datasets. For large datasets, prefer LinearSVC or SGDClassifier. Use probability=True to enable predict_proba, though this adds computational cost.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/svm/_classes.py

Signature

class SVC(BaseSVC):
    def __init__(
        self,
        *,
        C=1.0,
        kernel="rbf",
        degree=3,
        gamma="scale",
        coef0=0.0,
        shrinking=True,
        probability=False,
        tol=1e-3,
        cache_size=200,
        class_weight=None,
        verbose=False,
        max_iter=-1,
        decision_function_shape="ovr",
        break_ties=False,
        random_state=None,
    ):

Import

from sklearn.svm import SVC

I/O Contract

Inputs

Name	Type	Required	Description
C	float	No	Regularization parameter (default=1.0)
kernel	str or callable	No	Kernel type: 'linear', 'poly', 'rbf', 'sigmoid', 'precomputed' (default='rbf')
degree	int	No	Degree of polynomial kernel (default=3)
gamma	str or float	No	Kernel coefficient: 'scale', 'auto', or float (default='scale')
coef0	float	No	Independent term in kernel function (default=0.0)
shrinking	bool	No	Whether to use the shrinking heuristic (default=True)
probability	bool	No	Whether to enable probability estimates (default=False)
tol	float	No	Tolerance for stopping criterion (default=1e-3)
cache_size	float	No	Kernel cache size in MB (default=200)
class_weight	dict or str or None	No	Class weights; 'balanced' or dict mapping class to weight
verbose	bool	No	Enable verbose output (default=False)
max_iter	int	No	Maximum iterations; -1 for no limit (default=-1)
decision_function_shape	str	No	Decision function shape: 'ovr' or 'ovo' (default='ovr')
break_ties	bool	No	Whether to break ties using decision function values (default=False)
random_state	int, RandomState, or None	No	Random state for probability estimation

Outputs

Name	Type	Description
class_weight_	ndarray of shape (n_classes,)	Multipliers of parameter C for each class
classes_	ndarray of shape (n_classes,)	Unique class labels
coef_	ndarray of shape (n_classes * (n_classes - 1) / 2, n_features)	Weights (linear kernel only)
dual_coef_	ndarray of shape (n_classes - 1, n_SV)	Dual coefficients of support vectors
fit_status_	int	0 if correctly fitted, 1 otherwise
intercept_	ndarray	Constants in decision function
support_	ndarray	Indices of support vectors
support_vectors_	ndarray of shape (n_SV, n_features)	Support vectors
n_support_	ndarray of shape (n_classes,)	Number of support vectors per class
n_features_in_	int	Number of features seen during fit
n_iter_	ndarray	Number of iterations run by the optimization routine

Usage Examples

Basic Usage

from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

clf = SVC(kernel="rbf", C=1.0, gamma="scale")
clf.fit(X_train, y_train)
print(f"Accuracy: {clf.score(X_test, y_test):.3f}")
print(f"Number of support vectors: {clf.n_support_}")

Related Pages

• Principle:Scikit_learn_Scikit_learn_Support_Vector_Machines