机器学习sklearn之knn拟合iris数据集的实现

knn拟合sklearn中的iris数据集

class sklearn.neighbors.KNeighborsClassifier(n_neighbors=5, weights=’uniform’, algorithm=’auto’, leaf_size=30, p=2, metric=’minkowski’, metric_params=None, n_jobs=1, **kwargs) 

1. n_neighbors：选取几个邻居

2. weights：邻居的权重是平均呢，还是越重话语权越大呢

3. algorithm：后面再展开

       ‘ball_tree’ will use BallTree 
       ‘kd_tree’ will use KDTree 
       ‘brute’ will use a brute-force search. 
       ‘auto‘默认选项，是看哪个好用那个 
   

4. leaf_size：只有ball_tree和kd_tree才有必要

5. p与metric：距离表示，p=1是manhattan_distance，p=2是euclidean_distance。

   from sklearn import neighbors
   from sklearn import datasets
   #导出k近邻算法，并导出数据集
   knn=neighbors.KNeighborsClassifier()
   
   iris=datasets.load_iris()
   #在数据集中找到iris
   #print(iris)
   
   knn.fit(iris.data,iris.target)
   #对数据集进行拟合
   
   predictedlabel =knn.predict([[0.1,0.2,0.3,0.4]])
   print(predictedlabel)#对数据进行预测
   
   
   import csv
   import random
   import math
   import operator
    
   #导入数据，并分为训练集和测试集
   def loadDataset(filename, split, trainingSet = [], testSet = []):
       with open(filename, 'rt') as csvfile:
           lines = csv.reader(csvfile)
           dataset = list(lines)
           for x in range(len(dataset)-1):
               for y in range(4):
                   dataset[x][y] = float(dataset[x][y])
               if random.random() < split:
                   trainingSet.append(dataset[x])
               else:
                   testSet.append(dataset[x])
   #求欧拉距离
   def euclideanDistance(instance1, instance2, length):
       distance = 0
       for x in range(length):
           distance += pow((instance1[x]-instance2[x]), 2)
       return math.sqrt(distance)
   #计算最近邻(K个数据集)，testInstance是实例
   def getNeighbors(trainingSet, testInstance, k):
       distances = []
       length = len(testInstance)-1
       for x in range(len(trainingSet)):
           #testinstance
           dist = euclideanDistance(testInstance, trainingSet[x], length)
           distances.append((trainingSet[x], dist))#distance是一个多个元组的list
           #distances.append(dist)
       distances.sort(key=operator.itemgetter(1))#按照dist排序
       neighbors = []
       for x in range(k):
           neighbors.append(distances[x][0])#要的是数据集
           return neighbors
   #投票法找出最近邻的结果哪种最多
   def getResponse(neighbors):
       classVotes = {}#key--花名字 value--个数
       for x in range(len(neighbors)):
           response = neighbors[x][-1]
           if response in classVotes:
               classVotes[response] += 1
           else:
               classVotes[response] = 1
       sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True)
       return sortedVotes[0][0]
   #求出精确性
   def getAccuracy(testSet, predictions):
       correct = 0
       for x in range(len(testSet)):
           if testSet[x][-1] == predictions[x]:
               correct += 1
       return (correct/float(len(testSet)))*100.0
   def main():
       #prepare data
       trainingSet = []
       testSet = []
       split = 0.8
       loadDataset('irisdata.txt', split, trainingSet, testSet)
       print('Train set: '+ repr(len(trainingSet)))
       print('Test set: ' + repr(len(testSet)))
       #generate predictions
       predictions = []
       k = 3
       for x in range(len(testSet)):
           # trainingsettrainingSet[x]
           neighbors = getNeighbors(trainingSet, testSet[x], k)
           result = getResponse(neighbors)
           predictions.append(result)
           print ('>predicted=' + repr(result) + ', actual=' + repr(testSet[x][-1]))
       accuracy = getAccuracy(testSet, predictions)
       print('Accuracy: ' + repr(accuracy) + '%')
    
   if __name__ == '__main__':
       main()