ScikitLearners.py 文件源码

def predictKFoldSVM(X, y, kernel="linear", C=1, selectKBest=0, kfold=10):
    """
    Classifies the data using Support vector machines and k-fold CV
    :param X: The matrix of feature vectors
    :type X: list
    :param y: The vector containing the labels corresponding to feature vectors
    :type y: list
    :param kernel: The kernel used to elevate data into higher dimensionalities
    :type kernel: str
    :param C: The penalty parameter of the error term
    :type C: int
    :param selectKBest: The number of best features to select
    :type selectKBest: int 
    :param kfold: The number of folds to use in K-fold CV
    :type kfold: int
    :return: A list of predicted labels across the k-folds
    """
    try:
        # Prepare data 
        X, y = numpy.array(X), numpy.array(y)
        # Define classifier
        clf = svm.SVC(kernel=kernel, C=C)
        # Select K Best features if enabled
        X_new = SelectKBest(chi2, k=selectKBest).fit_transform(X, y) if selectKBest > 0 else X
        predicted = cross_val_predict(clf, X_new, y, cv=kfold).tolist()
    except Exception as e:
        prettyPrintError(e)
        return []

    return predicted