def main2():
'''
测试分类器
'''
group,labels = kNN.createDataSet()
result = kNN.classify0([0,0], group, labels, 3)
print result
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('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('testDigits/%s' % fileNameStr)
classifierResult = 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 local number of errors is :%d" % errorcount
print "\nThe total error rate is: %f " % (errorcount/float(mTest))
def handwritingClassTest(k=3):
hwLabels = []
trainingFileList = os.listdir('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)
trainingMat[i, :] = img2Vector('trainingDigits/%s' % fileNameStr)
testFileList = os.listdir('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('testDigits/%s' % fileNameStr)
classifierResult = kNN.classify0(vectorUnderTest, trainingMat,
hwLabels, k)
# print('the classifier came back with: %d, the real answer is: %d' % (classifierResult, classNumStr))
if classifierResult != classNumStr:
errorCount += 1.0
# print('the total number of error is: %d' % errorCount)
print('k = %d, and the total error rate is: %f' %
(k, errorCount / float(mTest)))
return errorCount / float(mTest)
def handWritingClassTest():
hwLables = []
#get the fileName list in the directory
trainingFileList = listdir('digits/trainingDigits')
trainingDatalength = len(trainingFileList)
#set the traning martrix
trainingMat = np.zeros((trainingDatalength,1024))
print trainingDatalength
for i in range(trainingDatalength):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split(".")[0]
# print (int)(fileStr.split('_')[0])
classNumStr = int(fileStr.split('_')[0])
print "%d:%d"%(i,classNumStr)
hwLables.append(classNumStr)
trainingMat[i,:] = img2Vector("digits/trainingDigits/%s"%fileNameStr)
print('hwLabels')
print hwLables
testFileList = listdir('digits/testDigits')
testDataLength = len(testFileList)
errorCount = 0.0
for i in range(testDataLength):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split(".")[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2Vector("digits/testDigits/%s"%fileNameStr)
classfiyResult = kNN.classify0(vectorUnderTest , trainingMat , hwLables , 3)
print "the clasifier came back with : %d ,the real answer is %d" %(classfiyResult,classNumStr)
if(classNumStr != classfiyResult): errorCount += 1.0
print 'the total error count is %d\n the error rate is %f' %(errorCount,errorCount/(float)(testDataLength))
def datingClassTest():
"""
约会网站测试
:return:
"""
# 设置测试数据比例
hoRatio = 0.1
# 从文件中加载数据
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
# 归一化数据
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
# m = 数据的行数 即第一维矩阵
m = normMat.shape[0]
# 设置测试的样本数量
numTestVecs = int(m * hoRatio)
print('numTestVecs = ', numTestVecs)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = 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 classifyImg(trainingdir,testdir):
trainingfiles=listdir(trainingdir)
filecount=len(trainingfiles)
trainMatrixData=zeros((filecount,1024))
label = []
for i in range(filecount):
fields = trainingfiles[i].split('_');
num = fields[0]
label.append(num)
filepath=trainingdir + '/' + trainingfiles[i]
trainMatrixData[i,:] = kNN.img2matrix(filepath)
testfiles=listdir(testdir)
filecount = len(testfiles)
errcount = 0.0
for i in range(filecount):
fields = testfiles[i].split('_');
num = fields[0]
filepath=testdir + '/' + testfiles[i]
testMatrix = kNN.img2matrix(filepath)
retval = kNN.classify0(testMatrix, trainMatrixData,label,3)
if (retval != num):
errcount += 1
print "error"
print "retval:%s,num:%s"%(retval,num)
print "rate:%f"%(errcount/float(filecount))
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits') # 获取目录文件
m = len(trainingFileList)
trainingMat = zeros(m, 1024)
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0]) # 从文件名解析分类数字
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits') # 获取测试目录文件
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('testDigits/%s' % fileNameStr)
classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
print '分类结果是：%d, 真是结果是：%d' % (classifierResult, classNumStr)
if (classifierResult != classNumStr):
errorCount += 1.0
print '分类错误的总数是：%d' % errorCount
print '总的错误率：%f' % (errorCount / float(mTest))
def handwritting_test():
hw_labels = []
training_file_list = os.listdir(TRAINING_DATA_DIR)
m = len(training_file_list)
training_mat = np.zeros((m, 1024))
#处理训练数据
for i in range(m):
filename = training_file_list[i]
file = filename.split('.')[0]
num_class = int(file.split('_')[0])
hw_labels.append(num_class)
training_mat[i, :] = img2vector(TRAINING_DATA_DIR + '/' + filename)
#处理测试数据
test_file_list = os.listdir(TEST_DATA_DIR)
error_count = 0
m_test = len(test_file_list)
#对每个测试集中的图像进行分类
for i in range(m_test):
filename = test_file_list[i]
file = filename.split('.')[0]
test_num_class = int(file.split('_')[0])
test_image_vec = img2vector(TEST_DATA_DIR + '/' + filename)
classifier_res = classify0(test_image_vec, training_mat, hw_labels, K)
print("the classifier came back with: %d,the real answer is: %d" %
(classifier_res, test_num_class))
if (classifier_res != test_num_class):
error_count += 1.0
print("\nthe total number of errors is: %d" % error_count)
print("\nthe total rate is:%f" % (error_count / float(m_test)))
def datingClassTest():
hoRatio = 0.50 #hold out 10%
datingDataMat, datingLabels = kNN.file2matrix(
'datingTestSet.txt') #load data setfrom file
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio) # 50% train set,50% test set
errorCount = 0.0
errorAns = m
for k in range(20):
errorCount = 0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normMat[i, :],
normMat[numTestVecs:m, :],
datingLabels[numTestVecs:m],
k + 1)
# print "the classifier came back with: %s, the real answer is: %s" % (classifierResult, datingLabels[i])
if (classifierResult != datingLabels[i]): errorCount += 1.0
print "when k is %d the total error rate is: %f" % (k + 1, (
errorCount / float(numTestVecs)))
print errorCount
if errorCount <= errorAns:
errorAns = errorCount
ans = k + 1
print "the best k is", ans
def hand_write_class_test(self):
hand_write_labels = []
train_file_list = listdir(
"/home/zhangzhiliang/Documents/my_git/DATA-SCIENTIST-/machine_learing_algorithm/"
"machine_learning_in_action/2_KNN/digits/trainingDigits")
train_num_of_digits = len(train_file_list)
train_data = np.zeros((train_num_of_digits, 1024))
for i in range(train_num_of_digits):
file_name_str = train_file_list[i]
file_str = file_name_str.split('.')[0]
class_digits_str = int(file_str.split('_')[0])
hand_write_labels.append(class_digits_str)
train_data[i, :] = self.img_to_vector(
'train_Digits {}'.format(file_name_str))
test_file_list = listdir(
"/home/zhangzhiliang/Documents/my_git/DATA-SCIENTIST-/machine_learing_algorithm/"
"machine_learning_in_action/2_KNN/digits/testDigits")
error_count = 0.0
test_num_of_digits = len(test_file_list)
for i in range(test_num_of_digits):
file_name_str = test_file_list[i]
file_str = file_name_str.split('.')[0]
class_digits_str = int(file_str.split('_')[0])
test_data = self.img_to_vector(
'test_Digits {}'.format(file_name_str))
result = kNN.classify0(test_data, train_data, hand_write_labels, 3)
print(
"the classifier came back with: {:d}, the real answer is: {:d}"
.format(result, class_digits_str))
if (result != class_digits_str):
error_count += 1.0
print("the total number of errors is {:d}".format(error_count))
print("the total number of error rate is : {:f}".format(
error_count / float(test_num_of_digits)))
def handwritingClassTest():
hwLabels = []
trainingFileList = os.listdir('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)
trainingMat = img2vector('trainingDigits/' + fileNameStr)
testFileList = os.listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(m):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits/' + fileNameStr)
classifierResult = kNN.classify0(vectorUnderTest, trainingMat,
hwLabels, 3)
print(
'the classifier came back with:{0},the real answer is:{1}'.format(
classifierResult, classNumStr))
if (classifierResult != classNumStr): errorCount += 1.0
print('the total number of errors is:{}'.format(errorCount))
print('the total erroe rate is:{:.2f}'.format(errorCount / float(mTest)))
def hand_writing_class_test():
hw_labels = []
training_file_list = listdir('trainingDigits')
m = len(training_file_list)
training_mat = zeros((m, 1024))
for i in range(m):
file_name_str = training_file_list[i]
file_str = file_name_str.split('.')[0]
class_num_str = int(file_str.split('_')[0])
hw_labels.append(class_num_str)
training_mat[i, :] = img2vector('trainingDigits/' + file_name_str)
test_file_list = listdir('testDigits')
error_count = 0.0
m_test = len(test_file_list)
for i in range(m_test):
file_name_str = test_file_list[i]
file_str = file_name_str.split('.')[0]
class_num_str = int(file_str.split('_')[0])
vector_under_test = img2vector('testDigits/' + file_name_str)
classifier_result = classify0(vector_under_test, training_mat, hw_labels, 3)
print 'the classifier came back with: %d, the real answer is: %d,' % (classifier_result, class_num_str)
if classifier_result != class_num_str:
error_count += 1
print "the total number of errors is: %d" % error_count
print "the total error rate is: %f" % (error_count/float(m_test))
def handwriting_test_class():
hw_labels = []
training_filter_list = os.listdir(digits_dir_0)
m = len(training_filter_list)
training_mat = numpy.zeros((m, 1024)) # 空间存储
for i in range(m):
filename = training_filter_list[i]
class_num = get_class_num_from_filename(filename)
hw_labels.append(class_num)
training_mat[i, :] = img2vector(os.path.join(digits_dir_0, filename))
test_file_list = os.listdir(digits_dir_1)
error_count = 0.0
m_test = len(test_file_list)
for i in range(m_test):
filename = test_file_list[i]
class_num = get_class_num_from_filename(filename)
vector_under_test = img2vector(os.path.join(digits_dir_1, filename))
classifier_result = classify0(vector_under_test,
training_mat,
hw_labels,
3)
print("the classifier came back with: %d, the real answer is: %d" % classifier_result, class_num)
if classifier_result != class_num:
error_count += 1.0
print("\nthe total number of errors is: %d" % error_count)
print("\nthe total error rate of is: %f" % (error_count/float(m_test)))
def handwriting_test_class():
hw_labels = []
training_filter_list = os.listdir(digits_dir_0)
m = len(training_filter_list)
training_mat = numpy.zeros((m, 1024)) # 空间存储
for i in range(m):
filename = training_filter_list[i]
class_num = get_class_num_from_filename(filename)
hw_labels.append(class_num)
training_mat[i, :] = img2vector(os.path.join(digits_dir_0, filename))
test_file_list = os.listdir(digits_dir_1)
error_count = 0.0
m_test = len(test_file_list)
for i in range(m_test):
filename = test_file_list[i]
class_num = get_class_num_from_filename(filename)
vector_under_test = img2vector(os.path.join(digits_dir_1, filename))
classifier_result = classify0(vector_under_test, training_mat,
hw_labels, 3)
print(
"the classifier came back with: %d, the real answer is: %d" %
classifier_result, class_num)
if classifier_result != class_num:
error_count += 1.0
print("\nthe total number of errors is: %d" % error_count)
print("\nthe total error rate of is: %f" % (error_count / float(m_test)))
def hwClassifyTest():
hwlabels = []
#listdir is an os function, get a list of filename in the dir
trainfilelist = listdir('trainingDigits')
m = len(trainfilelist)
traindata = zeros((m,1024))
for i in range(m):
filenamestr = trainfilelist[i]
#0_12.txt filestr=0_12; numclass=0;split by '.' and '_'
filestr = filenamestr.split('.')[0]
numclass = int(filestr.split('_')[0])
hwlabels.append(numclass)
traindata[i,:] = img2vector('trainingDigits/%s' % filenamestr)
testfilelist = listdir('testDigits')
errorcount = 0
mtest = len(testfilelist)
for i in range(10):#change the data of range(mtest)
filenamestr = testfilelist[i]
filestr = filenamestr.split('.')[0]
numclass = int(filestr.split('_')[0])
testvect = img2vector('testDigits/%s' % filenamestr)
result = kNN.classify0(testvect, traindata, hwlabels, 3)
print "handwriting classifier result: %d, the resl answer is: %d"\
% (result, numclass) #CARE the (..)
if (result != numclass): errorcount += 1.0
print "\nthe error rate is:%f " % (errorcount/float(mtest))#CARE the (..)
def handwriteringClassTest():
hwLabels = []
trainingFileList = os.listdir('digits/trainingDigits') #获取目录内容
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)
trainingMat[i, :] = imgtxt2vector('digits/trainingDigits/' +
fileNameStr)
testFileList = os.listdir('digits/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 = imgtxt2vector('digits/testDigits/' + fileNameStr)
classifierResult = kNN.classify0(vectorUnderTest, trainingMat,
hwLabels, 3)
print('the predicted answer is %d,the true answer is %d.' %
(classifierResult, classNumStr))
if classifierResult != classNumStr:
errorCount += 1
print('the total error rate is %f.' % (errorCount / mTest))
def hand_writing_class_test():
hwlabels = []
training_file_list = listdir('trainingDigits')
m = len(training_file_list)
training_mat = zeros((m, 1024))
for i in range(m):
file_name_str = training_file_list[i]
file_str = file_name_str.split('.')[0]
class_num_str = int(file_str.split('_')[0])
hwlabels.append(class_num_str)
training_mat[i, :] = img_to_vector('trainingDigits/%s' % file_name_str)
test_file_list = listdir('testDigits')
error_count = 0.0
m_test = len(test_file_list)
for i in range(m_test):
file_name_str = test_file_list[i]
file_str = file_name_str.split('.')[0]
class_num_str = int(file_str.split('_')[0])
vector_under_test = img_to_vector('testDigits/%s' % file_name_str)
classifier_result = kNN.classify0(vector_under_test, training_mat,
hwlabels, 3)
print("the classifier came back with: %d , the real answer is:%d" %
(classifier_result, class_num_str))
if (classifier_result != class_num_str):
error_count += 1.0
print("\nthe total number of error is :%d" % error_count)
print("\nthe total error rate is: %f" % (error_count / float(m_test)))
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('/home/jimlee/Documents/Git/kNN/HandwritingRecognitionSystem/trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2verctor('/home/jimlee/Documents/Git/kNN/HandwritingRecognitionSystem/trainingDigits/%s' % fileNameStr)
testFileList = listdir('/home/jimlee/Documents/Git/kNN/HandwritingRecognitionSystem/testDigits')
errorCount = 0.0
m_test = len(testFileList)
for i in range(m_test):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2verctor('/home/jimlee/Documents/Git/kNN/HandwritingRecognitionSystem/testDigits/%s' % fileNameStr)
classifierResult = 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(m_test))
def handwritingClassTest():
hwLabels = []
# 获取文件目录内容
trainingFileList = os.listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = np.zeros((m, 1024))
for i in range(m):
# 从文件中解析分类数字
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split(".")[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = os.listdir('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('testDigits/%s' % fileNameStr)
classifierResult = 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
print("\nthe total number of errors is: %d" % errorCount)
print("\nthe total error rate is: %f" % (errorCount / float(mTest)))
def testKNN2(self):
dataSet, labels = file2matrix('datingTestSet.txt')
normDataSet, ranges, minVals = kNN.autoNorm(dataSet)
testInput = numpy.array([51052, 4.680098, 0.625224])
testInput = (testInput-minVals) / ranges
c = kNN.classify0(testInput, normDataSet, labels, 3)
self.assertEqual(c, 1)
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('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('testDigits/%s' % fileNameStr)
classifierResult = 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 local number of errors is :%d" % errorcount
print "\nThe total error rate is: %f " % (errorcount / float(mTest))
def handwritingClassTest():
hwLabels = []
trainingFileList = os.listdir(
'resources/trainingDigits') #load the training set
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('resources/trainingDigits/%s' %
fileNameStr)
testFileList = os.listdir(
'resources/testDigits') #iterate through the test set
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('resources/testDigits/%s' % fileNameStr)
classifierResult = 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 handwritingClassTest():
hwLabels = []
trainingFileList = listdir('digits/trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('digits/trainingDigits/%s' %
fileNameStr)
testFileList = listdir('digits/txt') # testDigits
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
if fileNameStr != '.DS_Store':
# fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('digits/txt/%s' %
fileNameStr) # testDigits
classifierResult = 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 '\n the total number of errors is: %d' % errorCount
print '\n the total error rate is: %f' % (errorCount / float(mTest))
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir("trainingDigits")
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector("trainingDigits/%s" % fileNameStr)
testFileList = listdir("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("testDigits/%s" % fileNameStr)
classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
print("came back with %d, real is %d" %
(classifierResult, classNumStr))
if (classifierResult != classNumStr):
errorCount += 1.0
print("came back with %d, real is %d" %
(classifierResult, classNumStr),
end=" ")
print("file name : %s " % fileNameStr)
print("\n number of error : %d" % errorCount)
print("\n error rate : %f " % (errorCount / float(mTest)))
print("\n acc rate : %f" % (1.0 - (errorCount / float(mTest))))
def handWritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros(shape=(m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[
0] # take off the '.txt' from the filename
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('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('trainingDigits/%s' % fileNameStr)
classifierResult = kNN.classify0(vectorUnderTest, trainingMat,
hwLabels, 3)
print(
f"The classifier came back with: {classifierResult}, the real answer is {classNumStr}."
)
if (classifierResult != classNumStr): errorCount += 1
print(f"\nThe total number of errors is: {errorCount}.")
print(f"\nThe total error rate is: {errorCount / float(mTest)}.")
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('digits/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)
trainingMat[i, :] = img2vector('digits/trainingDigits/' + fileNameStr)
testFileList = listdir('digits/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('digits/testDigits/' + fileNameStr)
classifierResult = kNN.classify0(vectorUnderTest, trainingMat,
hwLabels, 3)
print('the classifier came back with: ' + str(classifierResult) +
', the real answer is: ' + str(classNumStr))
if classifierResult != classNumStr:
errorCount += 1.0
print('\nthe total number of error is: ' + str(errorCount) +
'\nthe total error rate is: ' + str(errorCount / float(mTest)))
def handwritingClassTest(height, width):
'''
the height and width of the image
'''
hwLabels = []
trainingFileList = listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m, int(height * width)))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNameStr = int(fileStr.split('_')[0])
hwLabels.append(classNameStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr, height, width)
testFileList = listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]
'''
the file name consists of 'class name'_'...'
'''
classNumStr = int(fileStr.split('_')[0])
vecUnderTest = img2vector('testDigits/%s' % fileNameStr, height, width)
classifierResult = kNN.classify0(vecUnderTest, trainingMat, hwLabels, 5)
print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)
if(classifierResult != classNumStr):
errorCount += 1
print "\nthe total number of errors is: %d" % errorCount
print "\nthe total error rate is: %f" % (errorCount/float(mTest))
def calcuteError(train_X, train_y, test_X, test_y):
testSize = len(test_X)
errorCount = 0.0
for i in range(testSize):
preLabel = kNN.classify0(test_X[i], train_X, train_y, 3)
if preLabel != test_y[i]:
errorCount += 1
print "error rate: %f" % (errorCount / testSize)
def classify0Test():
"""
测试第一个分类器
:return:
"""
group, labels = kNN.createDataSet()
print('group:', group)
print('labels:', labels)
print('result:', kNN.classify0([0.1, 0.1], group, labels, 3))
def calcErrorRate(features, lables, holdOutRatio):
testCount = int(features.shape[0]*holdOutRatio)
errorCount = 0.0
for i in range(testCount):
predictedLabel = kNN.classify0(features[i, :], features, labels, 3)
realLabel = labels[i]
print "predicted : " + predictedLabel + "\t\treal : " + realLabel
if predictedLabel != realLabel :
errorCount += 1.0
return errorCount/testCount
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input("percentage of time spent playing video games?"))
ffMiles = float(input("frequent flier miles earned per year?"))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat,classLabelVector = txtfile2matrix.file2matrix("C:/Users/jasper/iCloudDrive/newbie_programming/python/ml/chapter2/datingTestSet.txt",3)
datingLabels = txtfile2matrix.char2int(classLabelVector)
normMat, ranges, minVals = normalization.autoNorm(datingDataMat)
inArr = np.array([ffMiles, percentTats, iceCream,],dtype=float)
classifierResult = kNN.classify0((inArr - minVals)/ranges, normMat, datingLabels, 3)
print("You will probably like this person: %s" % (resultList[classifierResult - 1]))
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input("percent of time spent playing video games?"))
ffMiles = float(input("frequent flier miles earned per year?"))
iceCream = float(input("liters of ice Cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') # 数据加载
normDataSet, ranges, minVals = autoNorm(datingDataMat) # 归一化
inArr = np.array([ffMiles, percentTats, iceCream])
classifierResult = classify0((inArr - minVals) / ranges, normDataSet,
datingLabels, 3)
print("You will probably like this person:",
resultList[classifierResult - 1])
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input("percentage of time spent playing video games?"))
ffMiles = float(input("frequent filter miles earned per year"))
iceCream = float(input("liters of ice cream consumed per year"))
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
inArr = numpy.array([ffMiles, percentTats, iceCream])
classifierResult = kNN.classify0((inArr - minVals) / ranges, normMat,
datingDataMat, 3)
print("you will probably like this person: ".resultList[classifierResult -
1])
def classifyPerson():
resultlist=['not at all','in small doss','in large does']
percentTats=float(raw_input("percentage of time spent playing video game?"))
ffMiles=float(raw_input("frequent filer miles earned per year?"))
icecream=float(raw_input("liters of ice cream consumed per year?"))
datingDataMat,datingLabel = kNN.file2matrix('datingTestSet2.txt')
normat,rangeval,minval=kNN.autonorm(datingDataMat)
print "normat:%s" %(normat)
inX=array([ffMiles,percentTats,icecream])
retVal=kNN.classify0((inX - minval)/rangeval,normat,datingLabel,3)
print "retval[%d]" %(retVal)
print "resutl:%s " %(resultlist[retVal])
def classifyperson():
result = ['not at all', 'small doses', 'large dose']
ffmiles = float(input('frequent filter miles earned per year:'))
gametimepercent = float(input('% of time spent on game:'))
icecream = float(input('liters of ice cream consumed per year:'))
datamat, labels = kNN.file2matrix('datingTestSet.txt')
normmat, ranges, minvals = kNN.autoNorm(datamat)
inarry = (array([ffmiles, gametimepercent, icecream]) - minvals) / ranges
classifyresult = kNN.classify0(inarry, normmat, labels, 3)
print("you like this person:", result[classifyresult - 1])
return
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input('percentage of time spent playing video games?'))
ffMiles = float(input('frequent flier miles earned per year?'))
iceCream = float(input('liters of ice cream consumed per year?'))
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normData, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
classifierResult = kNN.classify0(inArr, normData, datingLabels, 3)
print('You will probably like this person: ',
resultList[classifierResult - 1])
def classifyPerson():
resultlist = ['not at all','in small doses','in large doses']
games = float(raw_input(
"percentage of time spent playing video games?"))
flymiles = float(raw_input(
"frequent flier miles earned per year?"))
icecream = float(raw_input(
"liters of ice cream consumed per year?"))
datingdata, datinglabel = kNN.file2matrix('datingTestSet2.txt')
normdata, ranges, minv = kNN.autoNorm(datingdata)
inarr = array([flymiles, games, icecream])
result = kNN.classify0((inarr - minv)/ranges, normdata, datinglabel, 3)
print "you will probably like this person:", resultlist[result-1]
def datingClassTest():
hoRatio = 0.550
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3)
print 'the classifier came back with: %s, the real answer is: %s' % (classifierResult, datingLabels[i])
if (classifierResult != datingLabels[i]):
errorCount += 1.0
print "the total error rate is: %f" % (errorCount / float(numTestVecs))
def showDatingInput():
# 输入测试数据
resultList = ['not at all', 'in small doses', 'in large doses']
mPercentGame = float(
raw_input('the percentange of time spent playing vedio games:'))
mPercentMiles = float(raw_input('the miles earned every year:'))
mpercentIce = float(raw_input('the ice cream consumed per year:'))
testArray = [mPercentMiles, mPercentGame, mpercentIce]
mat, labels = kNN.file2matrix('datingTestSet2.txt')
normMat, mRange, mMin = kNN.autoNum(mat)
ansType = kNN.classify0((testArray - mMin) / mRange, normMat, labels, 5)
print 'This guy is mostly', resultList[int(ansType) - 1]
def dating_class_test():
dating_data_mat, dating_labels = file2matrix(DATING_DATA)
norm_data, ranges, min_val = auto_norm(dating_data_mat)
m = norm_data.shape[0]
num_test_vecs = int(m * HO_RATIO)
error_count = 0.0
for i in range(num_test_vecs):
classifier_res = classify0(norm_data[i, :],
norm_data[num_test_vecs:m, :],
dating_labels[num_test_vecs:m], K)
print('the classifier came back with: %d, the real answer is: %d' %
(classifier_res, dating_labels[i]))
if (classifier_res != dating_labels[i]): error_count += 1.0
print("the total error rate is: %f" % (error_count / float(num_test_vecs)))
def datingClassTest():
x = 0.10
Mat, Labels = fileLoad.filematrix0('datingTestSet.txt')
normMat, ranges, minVals = norm.normal(Mat)
m = normMat.shape[0]
numTestVecs = int(m * x)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normMat[i,:],normMat[numTestVecs:m,:],\
Labels[numTestVecs:m],3)
print "the classifier came back with: %d, the real answer is: %d"\
%(classifierResult,Labels[i])
if (classifierResult != Labels[i]): errorCount += 1.0
print "the total error rate is %f" % (errorCount / float(numTestVecs))
def datingClassTest():
hoRatio = 0.10
datingdata, datinglabel = file2matrix('datingTestSet2.txt')
normdata, ranges, minv = autoNorm(datingdata)
m = normdata.shape[0]
numoftest = int(m*hoRatio)
errorcount = 0
for i in range(numoftest):
result = kNN.classify0(normdata[i,:],normdata[numoftest:m,:],
datinglabel[numoftest:m],3)
print "the classifier came back with: %d, the real answer is: %d"\
% (result, datinglabel[i])
if (result != datinglabel[i]): errorcount +=1.0
print "the total error rate is: %f" % (errorcount/float(numoftest))
def classifyPerson():
"""
imput someone information and predicts how much she will like this person
"""
resultList = ['not at all','in small doses','in large doses']
percentTats = float (input(\
"percentage of time spent playing video games?"))
ffMiles = float(input("frequent fliter miles earned per year?"))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
classifierResult = kNN.classify0([ffMiles, percentTats, iceCream ],normMat, \
datingLabels,3)
print ("you will probably like this person : %s" %(resultList[classifierResult - 1]))
def datingSetTest(horate):
datingDataMat,datingLabel=kNN.file2matrix('datingTestSet2.txt')
print "data[%d]:%s,\nlabel:%s" %(datingDataMat.shape[0],datingDataMat,datingLabel)
datingDataMat,rangeval,minval=kNN.autonorm(datingDataMat)
print "data[%d]:%s" %(datingDataMat.shape[0],datingDataMat)
m=datingDataMat.shape[0]
count=int(m*horate)
errcount=0.0
for i in range(1,count):
retVal=kNN.classify0(datingDataMat[i,:],datingDataMat[count:m,:],datingLabel[count:m],3)
print "orignal:%d,calculate:%d"%(datingLabel[i],retVal)
if retVal != datingLabel[i]:
errcount+=1.0
print "error."
print "error rate:%f" %(errcount/float(count))
def datingClassTest():
'''
hoRatio = the ratio of test set
'''
hoRatio = 0.10
datingDataMat, datingLabels = file2matrix("datingTestSet2.txt")
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 5)
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))
def datingClassTest():
hoRatio = 0.10
datingDataMat,datingLabels = kNN.file2matrix('datingTestSet.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
print("the classifier came back with: {0}, the real answer is: {1}".format(classifierResult, datingLabels[i]))
if (classifierResult != datingLabels[i]):
errorCount += 1.0
print("the total error rate is: {0}".format(errorCount/float(numTestVecs)))
def calcErrorRate(trainingFeatureSet, trainingLabelSet, testDataDir):
testFiles = os.listdir(testDataDir)
testDataSetSize = len(testFiles)
errorCount = 0.0
for file in testFiles:
filePath = os.path.join(testDataDir, file)
testData = img2vector(filePath)
trueLabel = file[0] # 测试数据的真实label
predictedLabel = kNN.classify0(testData, trainingFeatureSet, trainingLabelSet, KNN_K)
if predictedLabel != trueLabel:
errorCount += 1
print "Predicted : ", predictedLabel, " True : " , trueLabel, " File : ", file
return errorCount/testDataSetSize
def classifyHandWriting(path, trainingPath):
trainingFileList = listdir(trainingPath)
listlength = len(trainingFileList)
trainingMat = zeros((listlength, 1024))
labels = [];
for i in range(listlength):
filename = trainingFileList[i]
trainingMat[i, :] = kNN.imgVector(trainingPath + '/' + filename)
labels.append(filename.strip().split('.')[0].split('_')[0])
classification = kNN.imgVector(path)
return kNN.classify0(classification, trainingMat, labels, 3)
def testKNN3(self):
hwLabels = []
trainingFileList = os.listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = numpy.zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = kNN.img2vector('trainingDigits/%s' % fileNameStr)
testFileList = os.listdir('testDigits')
fileNameStr = testFileList[0]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = kNN.img2vector('testDigits/%s' % fileNameStr)
c = kNN.classify0(vectorUnderTest, trainingMat, hwLabels, 3)
self.assertEqual(c, 0)
def handwritingClassTest():
hwLabels=[] #保存分类结果
trainingFileList=os.listdir('trainingDigits') #训练数据目录列表
m=len(trainingFileList) #目录中一共有多少个文件
trainingMat=zeros((m,1024)) #
for i in range(m):
fileNameStr=trainingFileList[i]
fileStr=fileNameStr.split('.')[0] #文件名格式为 0_3.txt
classNumStr=int(fileStr.split('_')[0]) #第一部分为文件中实际的值
hwLabels.append(classNumStr)
trainingMat[i,:]=img2vector('trainingDigits/%s'%fileNameStr)
testFileList=os.listdir('testDigits')
errorCount=0.0
mTest=len(testFileList)
for i in range(mTest):
fileNameStr=testFileList[i]
fileStr=fileNameStr.split('.')[0]
classNumStr=int(fileStr.split('_')[0])
#trainingMat 训练图像转化来的向量
#vectorUnderTest 测试图像转化来的向量
vectorUnderTest=img2vector('testDigits/%s'%fileNameStr)
#在kNN分类器中
#vectorUnder是等待分类的数据，trainingMat相当于字曲，hwLabels为结果标号
classifierResult=kNN.classify0(vectorUnderTest,trainingMat,hwLabels,3)
print("the classifier came back with: %d, the real anser is: %d "%(classifierResult,classNumStr))
if(classifierResult!=classNumStr): #classNumStr是由文件名得出的数字
errorCount+=1.0
print("\nthe total number of errors is: %d"%errorCount)
print("\nthe total error rate is: %f"%(errorCount/float(mTest)))
pass
#kNN简单例子
from numpy import *
import operator
random.rand(4,4)
randMat=mat(random.rand(4,4))
randMatI=randMat.I
import kNN
group,labels=kNN.createDataSet()
print(group)
print(labels)
result=kNN.classify0([0,0],group,labels,3)
print(result)
print(kNN.classify0([1,1],group,labels,3))
#reload(kNN)
datingDataMat,datingLabels=kNN.file2matrix('datingTestSet2.txt')
print(datingDataMat)
print(datingLabels[0:20])
#kNN约会推荐系统
import matplotlib
import matplotlib.pyplot as plt
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
train=train_raw.values
test=test_raw.values
labels=train[0::,0:1]
labels=labels[:,0]
i,j=train.shape
result=[]
for ii in range(i):
for jj in range(j):
if (train[ii,jj]>1):
train[ii,jj]=1
for iii in range(i):
result[iii,0]=kNN.classify0(train[iii:iii+1,0::],train,labels,4)
predictions_file = open("out.csv","wb")
open_file_object = csv.writer(predictions_file)
open_file_object.writerows(["Label"])
predictions_file.close()
# Classifying movie genres with k-Nearest Neighbors import kNN group, labels = kNN.createDataSet() print(group) print(labels) result = kNN.classify0([0, 0], group, labels, 3) print(result)
import kNN
import numpy as np
import operator
# kNN example
data_set = np.array([[1.0, 1.0], [1.0, 0.9], [0.1, 0.1], [0.1, 0.2]])
labels = ['A', 'A', 'B', 'B']
in_x = [0.2, 0.3]
classfied = kNN.classify0(in_x, data_set, labels, 3)
print('in_x classified: %s' % classfied)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.set_title('kNN Algorithm Example')
ax.scatter(data_set[0:2, 0], data_set[0:2, 1], c='r', label='A')
ax.scatter(data_set[2:4, 0], data_set[2:4, 1], c='b', label='B')
for i in range(4):
ax.text(data_set[i][0]-0.04, data_set[i][1]-0.01, labels[i])
ax.scatter([0.2], [0.3], c='b')
ax.text(0.21, 0.29, '<-- Data classfied here')
ax.legend(loc='upper left')
plt.show()
FigDating = plt.figure()
group,labels = kNN.createDataSet() #Create the data set with four items(2-D vectors). Each of them one of two labels associated with them
colormap1 = { 'A':'red', 'B':'blue'} #Make a color map
ColoredGroupLabels = []
for things in labels: #Get a vector representing the colors
ColoredGroupLabels.append(colormap1[things]) #for each data item
ax1 = FigDating.add_subplot(311, xlim=(-0.1,1.1), ylim=(-.05,1.15)) #Dividing the figure into 3 sub plots and selecting the top-most
ax1.scatter(group[:,0], group[:,1], s= 20, c= ColoredGroupLabels, marker = 'o' ) #Plotting the data as a scatter plot with color(c) property as per the labelling.
#Testing with new points
testvector = [.2, .2] #first point
answer = kNN.classify0(testvector,group, labels, 3) #classify the first point
# type "print answer" to see result
ax1.scatter(testvector[0], testvector[1], s= 20, c= colormap1[answer], marker = 'x' ) #plot first point
#second point - created, classified and plotted
testvector = [.5, .5]
answer = kNN.classify0(testvector,group, labels, 3)
ax1.scatter(testvector[0], testvector[1], s= 20, c= colormap1[answer], marker = 'x' )
#third point - created, classified and plotted
testvector = [.75, .75]
answer = kNN.classify0(testvector,group, labels, 3)
ax1.scatter(testvector[0], testvector[1], s= 20, c= colormap1[answer], marker = 'x' )
'''Perform K-Nearest Neighbor classification on the datingTestSet2 data set. Do not forget to include the data set in the working directory'''
datingDataMat,datingLabels = kNN.file2matrix('datingTestSet2.txt') # Load data values and labels from the datingTestSet2.txt
datingLabelArray = np.array(datingLabels)
import kNN group, labels = kNN.createDataSet() print (group) print (labels) oneToTest=[0.0,1.0] print (kNN.classify0(oneToTest,group,labels))
def testKNN(self): group, labels = createDataSet() c = kNN.classify0([0, 0], group, labels, 3) self.assertEqual(c, 'B')
#coding:utf-8
import kNN
group, labels = kNN.createDataSet()
print kNN.classify0([0,0],group,labels,3)
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet.txt')
print datingDataMat
print datingLabels[0:20]
'''
import matplotlib
import matplotlib.pyplot as plt
from numpy import array
fig = plt.figure()
ax = fig.add_subplot(121)
ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0*array(datingLabels), 15.0*array(datingLabels))
ax.axis([-2, 25, -0.2, 2.0])
plt.xlabel(u'玩视频游戏所耗时间百分比')
plt.ylabel(u'每周消费的冰淇淋公升数')
ax = fig.add_subplot(122)
ax.scatter(datingDataMat[:,0], datingDataMat[:,1], 15.0*array(datingLabels), 15.0*array(datingLabels))
ax.axis([-5000, 100000, -1, 25])
plt.xlabel(u'每年获取的飞行常客里程数')
plt.ylabel(u'玩视频游戏所耗时间百分比')
plt.show()
'''
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
print normMat
import kNN
import numpy
import matplotlib
import matplotlib.pyplot as plt
print kNN.classify0([0, 0], numpy.array([[1, 0], [2, 1]]), ['A', 'B'], 1)
datingDataMat, datingLabels = kNN.file2matrix('test2.txt')
# datingDataMat = numpy.zeros((3,3))
# datingDataMat[2,:] = [2,1,0]
# print datingDataMat ,datingDataMat[:,2]
print datingLabels
print 15.0*numpy.array(datingLabels)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],15.0*numpy.array(datingLabels),15.0*numpy.array(datingLabels))
plt.show()
# ax.scatter([2,3,1],[3,1,2])
import os import kNN CURRENT_DIR = os.path.dirname(__file__) groups, labels = kNN.createDataset() print kNN.classify0([0,0,0],groups,labels,3) dataSetFile = os.path.join(CURRENT_DIR + '/datingTestSet.txt') datingDataMat,datingLabels = kNN.file2matrix(dataSetFile) print kNN.classify0([40920, 8.326976, 0.953952],groups,labels,3)
