function?rate?=?KNN（Train_dataTrain_labelTest_dataTest_labelkDistance_mark）

%?K-Nearest-Neighbor?classifier（K-NN?classifier）
%%?參數表示
%Input:
%?Train_data?訓練數據集的數據列
%?Train_label?訓練數據集的類別列
%?Test_data?測試集的數據列
%?Test_label?測試集的類別列
%?k?近鄰個數
%?Distance_mark?:???[‘Euclidean‘?‘L2‘|?‘L1‘?|?‘Cos‘]??‘Cos‘?represents?Cosine?distance.

%?Output:
%?rate:Accuracy?of?K-NN?classifier

[n~]????=?size（Test_data）;?%?number?of?test?data?set
[train_num~]?=?size（Train_data）;?%?number?of?training?data?set


%?歸一化處理?正態分布?Normalize?each?feature?to?have?zero?mean?and?unit?variance.
%?M?=?mean（Train_data）;?%?mean?&?std?of?the?training?data?set
%?S?=?std（Train_data）;
%?Train_data?=?（Train_data?-?ones（train_num?1）?*?M）./（ones（train_num?1）?*?S）;?%?normalize?training?data?set
%?Test_data?=?（Test_data-ones（n1）*M）./（ones（n1）*S）;?%?normalize?data

U?=?unique（Train_label）;?%?class?labels
nclasses?=?length（U）;%number?of?classes
Result??=?zeros（n?1）;??%?存放測試樣本的預測類別
Count???=?zeros（nclasses1）;?%?存放K近鄰中每一類的個數
dist=zero