ScikitLearners.py 文件源码

def predictKFoldSVMSSK(X, y, kfold=10, subseqLength=3, selectKBest=0):
    """Classifies the data using Support vector machines with the SSK kernel and k-fold CV
    :param X: The list of text documents containing traces
    :type X: list
    :param y: The labels of documents in 'X'
    :type y: list
    :param kfold: The number of folds
    :type kfold: int (default: 10)
    :param subseqLength: Length of subsequence used by the SSK
    :type subseqLength: int (default: 3)
    :param selectKBest: The number of best features to select
    :type selectKBest: int
    :return: An array of predicted classes 
    """
    try:
        predicted = []
        # Retrieve Gram Matrix from string kernel
        if verboseON():
            prettyPrint("Generating Gram Matrix from documents", "debug")
        X_gram = string_kernel(X, X)
        y = numpy.array(y)
        # Define classifier
        clf = svm.SVC(kernel="precomputed")
        X_gram_new = SelectKBest(chi2, k=selectKBest).fit_transform(X_gram, y) if selectKBest > 0 else X_gram
        prettyPrint("Performing %s-fold CV on the %s best features" % (kfold, selectKBest))
        predicted = cross_val_predict(clf, X_gram_new, y, cv=kfold).tolist()
    except Exception as e:
        prettyPrintError(e)
        return []

    return predicted