Question

您好我在Python中有一个kNN实现，我得到一些语法错误，如下所示。该代码稍后在帖子中给出。

Traceback (most recent call last):
  File "C:\Users\user\Desktop\knn test\knn.py", line 76, in <module>
     main()
   File "C:\Users\user\Desktop\knn test\knn.py", line 63, in main
    print ("Train set: ") + repr(len(trainingSet))
 TypeError: unsupported operand type(s) for +: 'NoneType' and 'str'

我正在运行Python 3.任何人都可以告诉我在代码中编辑什么，以便我得到正确的输出？

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.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('C:/Users/user/Desktop/knn test/text.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()

Answer 1

检查你的print语句，试图用字符串连接print语句。

您的打印声明应为：

print("Train set: " + repr(len(trainingSet)))
print("Test set: " + repr(len(testSet)))

Answer 2

您的打印声明不正确。如果您希望连接字符串以进行打印，则表明您没有正确执行此操作。

以一个打印语句为例：

print ("Train set: ") + repr(len(trainingSet))

首先，您无需占用repr长度的trainingSet。 repr给出了对象的字符串表示。在您的情况下，您正在呼叫len(trainingSet)。所以你实际上得到了一个整数。从技术上讲，你可以在这上面调用repr，但实际上没有必要为你想要显示你的结构长度而想要实现的目标。

其次，您没有正确地将此设置为您的打印语句，您应该将len(trainingSet)放入打印功能并使用字符串格式。所以，你想要这个：

print ("Train set: {}".format(len(trainingSet)))

Python TypeError：+的不支持的操作数类型：'NoneType'和'str'

2 个答案: