Knn算法解决海伦约会问题代码

以下是使用Python实现KNN算法解决海伦约会问题的代码，代码中使用了sklearn库来实现KNN算法。

from sklearn.neighbors import KNeighborsClassifier
import numpy as np

# 读取数据集
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = np.zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

# 数据归一化
def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m, 1))
    normDataSet = normDataSet/np.tile(ranges, (m, 1))
    return normDataSet, ranges, minVals

# 测试集比例
hoRatio = 0.10

# 读取数据集
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')

# 数据归一化
normMat, ranges, minVals = autoNorm(datingDataMat)

# 数据集划分
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
numTrainVecs = m - numTestVecs
trainMat = normMat[numTestVecs:m,:]
trainLabels = datingLabels[numTestVecs:m]
testMat = normMat[0:numTestVecs,:]
testLabels = datingLabels[0:numTestVecs]

# 训练模型
k = 3
clf = KNeighborsClassifier(n_neighbors=k)
clf.fit(trainMat, trainLabels)

# 预测结果
accuracy = clf.score(testMat, testLabels)
print("预测准确率为：%.2f%%" % (accuracy*100))

其中，数据集文件`datingTestSet2.txt`需要自行下载，也可以使用其他数据集进行测试。