使用knn算法进行水果分类给出代码和数据集

以下是使用KNN算法进行水果分类的Python代码，数据集可以自行收集或者使用公开数据集。

import csv
import random
import math
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][0])
    return neighbors

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]

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
    loadDataset('<your dataset file>', split, trainingSet, testSet)
    print('Train set: ' + repr(len(trainingSet)))
    print('Test set: ' + repr(len(testSet)))
    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()

数据集应该包含以下内容：

| 颜色 | 直径 | 重量 | 类型 |
| --- | --- | --- | --- |
| 绿 | 3 | 176 | 苹果 |
| 黄 | 3 | 170 | 苹果 |
| 红 | 1 | 70 | 葡萄 |
| 红 | 1.5 | 92 | 葡萄 |
| 黄 | 3.5 | 180 | 苹果 |
| 绿 | 3.2 | 150 | 苹果 |
| ... | ... | ... | ... |

请将数据保存为CSV格式。在代码中指定数据集文件的路径，例如`loadDataset('fruits.csv', split, trainingSet, testSet)`。