鸢尾[yuān wěi]（学名：Iris tectorum Maxim. ）iris数据集，统计学常用数据集
from sklearn import neighbors
from sklearn import datasets
knn = neighbors.KNeighborsClassifier()
iris = datasets.load_iris()
print(iris)
knn.fit(iris.data, iris.target)
predictedLabel = knn.predict([[0.1,0.2,0.3,0.4]])
print(predictedLabel)
自己编程实现KNN算法（根据网上代码修改，已添加权重，即便这样，还是有90%的情况，算法确实不怎么好）
--key，需要说明的是，数据点有可能是重复的，即dist为0，这样就不能作为权重了，但同时也可以break（找到完全匹配）
import csv
import math
import random
import operator
def loadDataset(filename, split, trainingSet=[], testSet=[]):
with open(filename, 'r') 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])
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 = []
length = len(testInstance) - 1
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])
return neighbors
def getResponse(neighbors):
classVotes = {}
for x in range(len(neighbors)):
species = neighbors[x][0][-1]
dist = neighbors[x][1]
if dist == 0:
return species
if species in classVotes:
classVotes[species] += 1 / dist
else:
classVotes[species] = 1 / dist
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))) * 100.0
def main():
trainingSet = []
testSet = []
split = 0.67 # 2/3训练集，1/3测试集
loadDataset(r'D:\OneDrive\data\[Python]\iris.txt', split, trainingSet, testSet)
print('Train set: ' + repr(len(trainingSet)))
print('Test set: ' + repr(len(testSet)))
predictions = []
k = 7
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]))
print ('predictions: ' + repr(predictions))
accuracy = getAccuracy(testSet, predictions)
print('Accuracy: ' + repr(accuracy) + '%')
if __name__ == '__main__':
main()
iris数据sample（这是从R中取的，去掉第一列，空格从长到短批量替换为英文逗号）:5.1,3.5,1.4,0.2,setosa
