KNN算法的实现

1 Iris Plants Database介绍：

150个实例

特征值（4种）： 
萼片长度，萼片宽度，花瓣长度，花瓣宽度 
(sepal length, sepal width, petal length and petal width）

类别（3类）： 
Iris setosa, Iris versicolor, Iris virginica.

2. KNN实现（利用sklearn机器学习库）:

from sklearn import neighborsfrom sklearn import datasets# get knn algorithmknn = neighbors.KNeighborsClassifier()# get iris datasetsiris = datasets.load_iris()print(iris)# use knn build the modelknn.fit(iris.data,iris.target)# use the model to predictpredictedLabel = knn.predict([[0.1,0.2,0.3,0.4]])print(predictedLabel)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16

3.KNN实现（不用sklearn机器学习库）

iris.data.txt

5.1,3.5,1.4,0.2,Iris-setosa4.9,3.0,1.4,0.2,Iris-setosa4.7,3.2,1.3,0.2,Iris-setosa4.6,3.1,1.5,0.2,Iris-setosa5.0,3.6,1.4,0.2,Iris-setosa5.4,3.9,1.7,0.4,Iris-setosa4.6,3.4,1.4,0.3,Iris-setosa5.0,3.4,1.5,0.2,Iris-setosa4.4,2.9,1.4,0.2,Iris-setosa4.9,3.1,1.5,0.1,Iris-setosa5.4,3.7,1.5,0.2,Iris-setosa4.8,3.4,1.6,0.2,Iris-setosa4.8,3.0,1.4,0.1,Iris-setosa4.3,3.0,1.1,0.1,Iris-setosa5.8,4.0,1.2,0.2,Iris-setosa5.7,4.4,1.5,0.4,Iris-setosa5.4,3.9,1.3,0.4,Iris-setosa5.1,3.5,1.4,0.3,Iris-setosa5.7,3.8,1.7,0.3,Iris-setosa5.1,3.8,1.5,0.3,Iris-setosa5.4,3.4,1.7,0.2,Iris-setosa5.1,3.7,1.5,0.4,Iris-setosa4.6,3.6,1.0,0.2,Iris-setosa5.1,3.3,1.7,0.5,Iris-setosa4.8,3.4,1.9,0.2,Iris-setosa5.0,3.0,1.6,0.2,Iris-setosa5.0,3.4,1.6,0.4,Iris-setosa5.2,3.5,1.5,0.2,Iris-setosa5.2,3.4,1.4,0.2,Iris-setosa4.7,3.2,1.6,0.2,Iris-setosa4.8,3.1,1.6,0.2,Iris-setosa5.4,3.4,1.5,0.4,Iris-setosa5.2,4.1,1.5,0.1,Iris-setosa5.5,4.2,1.4,0.2,Iris-setosa4.9,3.1,1.5,0.1,Iris-setosa5.0,3.2,1.2,0.2,Iris-setosa5.5,3.5,1.3,0.2,Iris-setosa4.9,3.1,1.5,0.1,Iris-setosa4.4,3.0,1.3,0.2,Iris-setosa5.1,3.4,1.5,0.2,Iris-setosa5.0,3.5,1.3,0.3,Iris-setosa4.5,2.3,1.3,0.3,Iris-setosa4.4,3.2,1.3,0.2,Iris-setosa5.0,3.5,1.6,0.6,Iris-setosa5.1,3.8,1.9,0.4,Iris-setosa4.8,3.0,1.4,0.3,Iris-setosa5.1,3.8,1.6,0.2,Iris-setosa4.6,3.2,1.4,0.2,Iris-setosa5.3,3.7,1.5,0.2,Iris-setosa5.0,3.3,1.4,0.2,Iris-setosa7.0,3.2,4.7,1.4,Iris-versicolor6.4,3.2,4.5,1.5,Iris-versicolor6.9,3.1,4.9,1.5,Iris-versicolor5.5,2.3,4.0,1.3,Iris-versicolor6.5,2.8,4.6,1.5,Iris-versicolor5.7,2.8,4.5,1.3,Iris-versicolor6.3,3.3,4.7,1.6,Iris-versicolor4.9,2.4,3.3,1.0,Iris-versicolor6.6,2.9,4.6,1.3,Iris-versicolor5.2,2.7,3.9,1.4,Iris-versicolor5.0,2.0,3.5,1.0,Iris-versicolor5.9,3.0,4.2,1.5,Iris-versicolor6.0,2.2,4.0,1.0,Iris-versicolor6.1,2.9,4.7,1.4,Iris-versicolor5.6,2.9,3.6,1.3,Iris-versicolor6.7,3.1,4.4,1.4,Iris-versicolor5.6,3.0,4.5,1.5,Iris-versicolor5.8,2.7,4.1,1.0,Iris-versicolor6.2,2.2,4.5,1.5,Iris-versicolor5.6,2.5,3.9,1.1,Iris-versicolor5.9,3.2,4.8,1.8,Iris-versicolor6.1,2.8,4.0,1.3,Iris-versicolor6.3,2.5,4.9,1.5,Iris-versicolor6.1,2.8,4.7,1.2,Iris-versicolor6.4,2.9,4.3,1.3,Iris-versicolor6.6,3.0,4.4,1.4,Iris-versicolor6.8,2.8,4.8,1.4,Iris-versicolor6.7,3.0,5.0,1.7,Iris-versicolor6.0,2.9,4.5,1.5,Iris-versicolor5.7,2.6,3.5,1.0,Iris-versicolor5.5,2.4,3.8,1.1,Iris-versicolor5.5,2.4,3.7,1.0,Iris-versicolor5.8,2.7,3.9,1.2,Iris-versicolor6.0,2.7,5.1,1.6,Iris-versicolor5.4,3.0,4.5,1.5,Iris-versicolor6.0,3.4,4.5,1.6,Iris-versicolor6.7,3.1,4.7,1.5,Iris-versicolor6.3,2.3,4.4,1.3,Iris-versicolor5.6,3.0,4.1,1.3,Iris-versicolor5.5,2.5,4.0,1.3,Iris-versicolor5.5,2.6,4.4,1.2,Iris-versicolor6.1,3.0,4.6,1.4,Iris-versicolor5.8,2.6,4.0,1.2,Iris-versicolor5.0,2.3,3.3,1.0,Iris-versicolor5.6,2.7,4.2,1.3,Iris-versicolor5.7,3.0,4.2,1.2,Iris-versicolor5.7,2.9,4.2,1.3,Iris-versicolor6.2,2.9,4.3,1.3,Iris-versicolor5.1,2.5,3.0,1.1,Iris-versicolor5.7,2.8,4.1,1.3,Iris-versicolor6.3,3.3,6.0,2.5,Iris-virginica5.8,2.7,5.1,1.9,Iris-virginica7.1,3.0,5.9,2.1,Iris-virginica6.3,2.9,5.6,1.8,Iris-virginica6.5,3.0,5.8,2.2,Iris-virginica7.6,3.0,6.6,2.1,Iris-virginica4.9,2.5,4.5,1.7,Iris-virginica7.3,2.9,6.3,1.8,Iris-virginica6.7,2.5,5.8,1.8,Iris-virginica7.2,3.6,6.1,2.5,Iris-virginica6.5,3.2,5.1,2.0,Iris-virginica6.4,2.7,5.3,1.9,Iris-virginica6.8,3.0,5.5,2.1,Iris-virginica5.7,2.5,5.0,2.0,Iris-virginica5.8,2.8,5.1,2.4,Iris-virginica6.4,3.2,5.3,2.3,Iris-virginica6.5,3.0,5.5,1.8,Iris-virginica7.7,3.8,6.7,2.2,Iris-virginica7.7,2.6,6.9,2.3,Iris-virginica6.0,2.2,5.0,1.5,Iris-virginica6.9,3.2,5.7,2.3,Iris-virginica5.6,2.8,4.9,2.0,Iris-virginica7.7,2.8,6.7,2.0,Iris-virginica6.3,2.7,4.9,1.8,Iris-virginica6.7,3.3,5.7,2.1,Iris-virginica7.2,3.2,6.0,1.8,Iris-virginica6.2,2.8,4.8,1.8,Iris-virginica6.1,3.0,4.9,1.8,Iris-virginica6.4,2.8,5.6,2.1,Iris-virginica7.2,3.0,5.8,1.6,Iris-virginica7.4,2.8,6.1,1.9,Iris-virginica7.9,3.8,6.4,2.0,Iris-virginica6.4,2.8,5.6,2.2,Iris-virginica6.3,2.8,5.1,1.5,Iris-virginica6.1,2.6,5.6,1.4,Iris-virginica7.7,3.0,6.1,2.3,Iris-virginica6.3,3.4,5.6,2.4,Iris-virginica6.4,3.1,5.5,1.8,Iris-virginica6.0,3.0,4.8,1.8,Iris-virginica6.9,3.1,5.4,2.1,Iris-virginica6.7,3.1,5.6,2.4,Iris-virginica6.9,3.1,5.1,2.3,Iris-virginica5.8,2.7,5.1,1.9,Iris-virginica6.8,3.2,5.9,2.3,Iris-virginica6.7,3.3,5.7,2.5,Iris-virginica6.7,3.0,5.2,2.3,Iris-virginica6.3,2.5,5.0,1.9,Iris-virginica6.5,3.0,5.2,2.0,Iris-virginica6.2,3.4,5.4,2.3,Iris-virginica5.9,3.0,5.1,1.8,Iris-virginica

程序代码：

# Example of knn implemented in Pythonimport csvimport randomimport mathimport operatordef loadDataset(filename, split, trainingSet=[] , testSet=[]):    with open(filename, 'r') as csvfile:        lines = csv.reader(csvfile)        dataset = list(lines)# print("dataset: "+str(dataset))# print("type of dataset[0][0]: "+str(type(dataset[0][0])))# print("length of dataset: "+str(len(dataset)))        for x in range(len(dataset)):            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])def euclideanDistance(instance1, instance2, length):    distance = 0    for x in range(length):        distance += pow((instance1[x] - instance2[x]), 2)    return math.sqrt(distance)def getNeighbors(trainingSet, testInstance, k):    distances = []# print("testInstance: "+str(len(testInstance)))    length = len(testInstance)-1# print("trainingSet: "+str(len(trainingSet)))    for x in range(len(trainingSet)):        dist = euclideanDistance(testInstance, trainingSet[x], length)        distances.append((trainingSet[x], dist))    distances.sort(key=operator.itemgetter(1))    neighbors = []    for x in range(k):        neighbors.append(distances[x][0])    return neighborsdef getResponse(neighbors):    classVotes = {}    for x in range(len(neighbors)):# print("neighbors[x][-1]:"+str(neighbors[x][-1]))        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]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))) * 100.0def main():    # prepare data    trainingSet=[]    testSet=[]    split = 0.67    loadDataset(r'D:\eclipse\mars\project\DeepLearningBasicsMachineLearning\Datasets\iris.data.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)):        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) + '%')main()