说明：  kNN的思想:计算待分类的数据点与训练集所有样本点，取距离最近的k个样本；统计这k个样本的类别数量；根据多数表决方案，取数量最多的那一类作为待测样本的类别。距离度量可采用Euclidean distance，Manhattan distance和cosine。
(kNN The idea is simple: the training set and calculated data points to be classified all sample points taken the nearest k samples the number of statistical categories that k samples according to the majority voting scheme up to take the kind of quantity as to be test samples category. Distance metrics can be used Euclidean distance, Manhattan distance and cosine.)