def datingClassTest():
"""
对约会网站进行数据测试
"""
# 从文件中加载数据
datingDataMat, datingLabels = file2matrix(
'../../../Data/KNN/dating/dating.txt')
draw(datingDataMat, datingLabels)
# 归一化数据
normMat, ranges, minVals = autoNorm0(datingDataMat)
# m 表示数据的行数，即矩阵的第一维
m = normMat.shape[0]
# 测试数据集范围,训练数据集比例=1-hoRatio
hoRatio = 0.1
numTestVecs = int(m * hoRatio)
print('numTestVecs=', numTestVecs)
errorCount = 0.0
for i in range(numTestVecs):
# 对数据测试
classifierResult = classify_knn.classify0(normMat[i, :],
normMat[numTestVecs:m, :],
datingLabels[numTestVecs:m],
3)
print("the classifier came back with: %d, the real answer is: %d" %
(classifierResult, datingLabels[i]))
if (classifierResult != datingLabels[i]): errorCount += 1.0
print("the total error rate is: %f" % (errorCount / float(numTestVecs)))
print(errorCount)
def handwritingClassTest():
# 导入训练数据
hwLabels = []
trainingFileList = listdir('../../../Data/KNN/handwriting/trainingDigits')
m = len(trainingFileList)
trainingMat = np.zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
# 将 32*32的矩阵->1*1024的矩阵
trainingMat[i, :] = img2vector(
'../../../Data/KNN/handwriting/trainingDigits/%s' % fileNameStr)
# 导入测试数据
testFileList = listdir('../../../Data/KNN/handwriting/testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector(
'../../../Data/KNN/handwriting/testDigits/%s' % fileNameStr)
classifierResult = classify_knn.classify0(vectorUnderTest, trainingMat,
hwLabels, 3)
print("the classifier came back with: %d, the real answer is: %d" %
(classifierResult, classNumStr))
if (classifierResult != classNumStr): errorCount += 1.0
print("\nthe total number of errors is: %d" % errorCount)
print("\nthe total error rate is: %f" % (errorCount / float(mTest)))
def testMovies():
"""
给定一个新坐标，判断是哪一类数据
"""
group, labels = createDataSet()
print(str(group))
print(str(labels))
print(classify_knn.classify0([18, 90], group, labels, 3))
print(classify_knn.classify1([18, 90], group, labels, 3))
def testPoints():
"""
给定一个新坐标，判断是哪一类数据
"""
group, labels = createDataSet()
print(str(group))
print(str(labels))
print(classify_knn.classify0([0.1, 0.1], group, labels, 3))
print(classify_knn.classify1([0.1, 0.1], group, labels, 3))
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = 10
ffMiles = 10000
iceCream = 0.5
datingDataMat, datingLabels = file2matrix(
'../../../Data/KNN/dating/dating.txt')
normMat, ranges, minVals = autoNorm0(datingDataMat)
inArr = np.array([ffMiles, percentTats, iceCream])
classifierResult = classify_knn.classify0((inArr - minVals) / ranges,
normMat, datingLabels, 3)
print("You will probably like this person: ",
resultList[classifierResult - 1])