深度学习基础系列（四）之 用 python 实现 KNN 算法

获得数据，将数据集分离成 测试集 和 训练集

计算每个测试实例与训练集之间的 euclideanDistance，从训练集中抽离出euclideanDistance 最短的 k 个实例成新的数据集

根据选出的 k 个实例集的结果按照标记进行分类，判断测试实例

计算算法的精确度

import csv
import random
import math
import operator
# 获得数据
# prepare data
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):
# 将数据集中的字符串类型转换成浮点类型
# change the type into float in order to sort in a more simple way
dataset[x][y] = float(dataset[x][y])
if random.random() < split:
trainingSet.append(dataset[x])
else:
testSet.append(dataset[x])

# 计算 instance1 和 instance2 的 euclidean
# calculate euclidean distance between two instance
def euclideanDistance(instance1, instance2, length):
distance = 0
for x in range(length):
distance += pow((instance1[x]-instance2[x]), 2)
return math.sqrt(distance)

# 获得 测试实例 与 训练集离得最近的 k 个点
def getNeighbors(trainingSet, testInstance, k):
distances = []
length = len(testInstance)-1
for x in range(len(trainingSet)):
dist = euclideanDistance(testInstance, trainingSet[x], length) # length is 4
distances.append((trainingSet[x], dist))
distances.sort(key=operator.itemgetter(1))
neighbors = []
for x in range(k):
neighbors.append(distances[x][0])
return neighbors

# 获得模型的判断结果
def getResponse(neighbors):
classVotes = {}
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]

# 获得精确度
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 = 0.80
loadDataset('irisdata.txt', split, trainingSet, testSet)
print('Train set: ' + str(len(trainingSet)))
print('Test    set: ' + str(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=' + str(result) + ', actual=' + str(testSet[x][-1]))
accuracy = getAccuracy(testSet, predictions)
print('Accuracy: ' + repr(accuracy) + '%')

if __name__ == '__main__':
main()