python - 实现 KNN 算法时出现错误

Question

刚接触stackoverflow和编程，我来自统计背景，下面是KNN算法的实现。出现错误类型错误:不支持的操作数类型 -:“str”和“str”。

这些是我遇到的其他错误。预先感谢您的答复。

File "knn.py", line 78, in main()

File "knn.py", line 71, in main neighbors = getNeighbors(trainingSet, testSet[x], k)

File "knn.py", line 33, in getNeighbors dist = euclideanDistance(testInstance, trainingSet[x], length)

File "knn.py", line 26, in euclideanDistance distance += pow((instance1[x] - instance2[x]), 2)

import csv
import random
import math
import pandas
import numpy

def loadDataset(filename, split, trainingSet=[] , testSet=[]):

    filename = 'data1.csv'
    raw_data = open(filename, 'rt')
    reader = csv.reader(raw_data, delimiter=',', quoting=csv.QUOTE_NONE)
    dataset = list(reader)


    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.iteritems(), 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():
# prepare data
    trainingSet=[]
    testSet=[]
    split = 0.67
    loadDataset('data1.csv', 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()

Answer 1

瓦姆西，

我注意到你正在使用 numpy 和 pandas。在进行调试的同时，我确实想推荐一个更棒的软件包，sci-kit learn。

他们已经内置了 KNN 的实现:http://scikit-learn.org/stable/modules/neighbors.html

编辑:我相信第 26 行存在转换问题。看来您正在尝试减去 2 个字符串。我认为如果您正在使用整数数据，这可能会解决您的问题

def euclideanDistance(instance1, instance2, length):
     distance = 0
     for x in range(length):
         distance += pow((int(instance1[x]) - int(instance2[x])), 2)
     return math.sqrt(distance)

如果您正在使用 float 据，则以下内容可行:

distance += pow((float(instance1[x]) - float(instance2[x])), 2)