#coding=utf-8
import math
#定義鳶尾花的數(shù)據(jù)類
class Iris:
 data=[]
 label=[]
 pass
#定義一個讀取鶯尾花數(shù)據(jù)集的函數(shù)
def load_dataset(filename="Iris_train.txt"):
 f=open(filename)
 line=f.readline().strip()
 propty=line.split(',')#屬性名
 dataset=[]#保存每一個樣本的數(shù)據(jù)信息
 label=[]#保存樣本的標(biāo)簽
 while line:
 line=f.readline().strip()
 if(not line):
 break
 temp=line.split(',')
 content=[]
 for i in temp[0:-1]:
 content.append(float(i))
 dataset.append(content)
 label.append(temp[-1])
 total=Iris()
 total.data=dataset
 total.label=label
 return total#返回數(shù)據(jù)集
 
#定義一個Knn分類器類
class KnnClassifier:
 def __init__(self,k,type="Euler"):#初始化的時候定義正整數(shù)K和距離計算方式
 self.k=k
 self.type=type
 self.dataloaded=False
 def load_traindata(self,traindata):#加載數(shù)據(jù)集
 self.data=traindata.data
 self.label=traindata.label
 self.label_set=set(traindata.label)
 self.dataloaded=True#是否加載數(shù)據(jù)集的標(biāo)記
 
 def Euler_dist(self,x,y):# 歐拉距離計算方法，x、y都是向量
 sum=0
 for i,j in zip(x,y):
 sum+=math.sqrt((i-j)**2)
 return sum
 def Manhattan_dist(self,x,y):#曼哈頓距離計算方法，x、y都是向量
 sum=0
 for i,j in zip(x,y):
 sum+=abs(i-j)
 return sum
 def predict(self,temp):#預(yù)測函數(shù)，讀入一個預(yù)測樣本的數(shù)據(jù)，temp是一個向量
 if(not self.dataloaded):#判斷是否有訓(xùn)練數(shù)據(jù)
 print "No train_data load in"
 return
 distance_and_label=[]
 if(self.type=="Euler"):#判斷距離計算方式，歐拉距離或者曼哈頓距離
 for i,j in zip(self.data,self.label):
 dist=self.Euler_dist(temp,i)
 distance_and_label.append([dist,j])
 else:
 if(self.type=="Manhattan"):
 for i,j in zip(self.data,self.label):
 dist=self.Manhattan_dist(temp,i)
 distance_and_label.append([dist,j])
 else:
 print "type choice error"
 #獲取K個最鄰近的樣本的距離和類別標(biāo)簽
 neighborhood=sorted(distance_and_label,cmp=lambda x,y : cmp(x[0],y[0]))[0:self.k]
 neighborhood_class=[]
 for i in neighborhood:
 neighborhood_class.append(i[1])
 class_set=set(neighborhood_class)
 neighborhood_class_count=[]
 print "In k nearest neighborhoods:"
 #統(tǒng)計該K個最鄰近點中各個類別的個數(shù)
 for i in class_set:
 a=neighborhood_class.count(i)
 neighborhood_class_count.append([i,a])
 print "class: ",i," count: ",a
 result=sorted(neighborhood_class_count,cmp=lambda x,y : cmp(x[1],y[1]))[-1][0]
 print "result: ",result
 return result#返回預(yù)測的類別
 
if __name__ == '__main__':
 traindata=load_dataset()#training data
 testdata=load_dataset("Iris_test.txt")#testing data
 #新建一個Knn分類器的K為20，默認(rèn)為歐拉距離計算方式
 kc=KnnClassifier(20)
 kc.load_traindata(traindata)
 predict_result=[]
 #預(yù)測測試集testdata中所有待預(yù)測樣本的結(jié)果
 for i,j in zip(testdata.data,testdata.label):
 predict_result.append([i,kc.predict(i),j])
 correct_count=0
 #將預(yù)測結(jié)果和正確結(jié)果進(jìn)行比對，計算該次預(yù)測的準(zhǔn)確率
 for i in predict_result:
 if(i[1]==i[2]):
 correct_count+=1
 ratio=float(correct_count)/len(predict_result)
 print "correct predicting ratio",ratio

In k nearest neighborhoods:
class: Iris-setosa count: 20
result: Iris-setosa
In k nearest neighborhoods:
class: Iris-setosa count: 20
result: Iris-setosa
In k nearest neighborhoods:
class: Iris-setosa count: 20
result: Iris-setosa
In k nearest neighborhoods:
class: Iris-setosa count: 20
result: Iris-setosa
In k nearest neighborhoods:
class: Iris-setosa count: 20
result: Iris-setosa
In k nearest neighborhoods:
class: Iris-versicolor count: 20
result: Iris-versicolor
In k nearest neighborhoods:
class: Iris-versicolor count: 20
result: Iris-versicolor
In k nearest neighborhoods:
class: Iris-versicolor count: 20
result: Iris-versicolor
In k nearest neighborhoods:
class: Iris-versicolor count: 20
result: Iris-versicolor
In k nearest neighborhoods:
class: Iris-versicolor count: 20
result: Iris-versicolor
In k nearest neighborhoods:
class: Iris-setosa count: 18
class: Iris-versicolor count: 2
result: Iris-setosa
correct predicting ratio 0.909090909091