ScikitLearners.py 文件源码

def predictKFoldKNN(X, y, K=10, kfold=10, selectKBest=0):
    """
    Classifies the data using K-nearest neighbors and k-fold CV
    :param X: The list of feature vectors
    :type X: list
    :param y: The list of labels corresponding to the feature vectors
    :type y: list
    :param K: The number of nearest neighbors to consider in classification
    :type K: int
    :param kfold: The number of folds in the CV
    :type kfold: int
    :param selectKBest: The number of best features to select
    :type selectKBest: int
    :return: An array of predicted classes
    """
    try:
        # Prepare data 
        X, y = numpy.array(X), numpy.array(y)
        # Define classifier
        clf = neighbors.KNeighborsClassifier(n_neighbors=K)
        # 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