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,:] = kNN.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 = kNN.img2vector('testDigits/%s' % 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("\nthe total number of errors is: {0}".format(errorCount))
print("\nthe total error rate is: {0}".format(errorCount/float(mTest)))
def mainTest():
hwLabels = []
trainingFileList = 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)
# build the kdtree
print "start to build kd tree ..."
print hwLabels
kd_tree = KDNode()
kd_tree = createKDTree(kd_tree, trainingMat, hwLabels)
print "kd tree finished"
#print_kdtree(kd_tree)
#exit(0)
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 = KNN(kd_tree, 5, vectorUnderTest[0])
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 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 img2vectorTest():
testVector = kNN.img2vector('testDigits/0_13.txt')
print(testVector[0, 0:32])
line = line.strip()
print line
line = line.split()
print line
print zero[1, ]
##########Ch02###########
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
if (False):
print datingDataMat
print datingLabels[0:20]
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0 * array(datingLabels), 15.0 * array(datingLabels))
plt.show()
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
print normMat
print ranges
print minVals
kNN.datingClassTest()
kNN.classifyPerson()
testVector = kNN.img2vector('digits/testDigits/0_13.txt')
print testVector[0, 0:31]
print testVector[0, 32:63]
kNN.handwritingClassTest()
from numpy import *
from os import listdir
# kNN.handwritingClassTest()
hwLabels = []
trainingFileList = listdir('trainingDigits') # 加载训练数据
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, :] = kNN.img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('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 = kNN.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 += 1.0
ax = fig.add_subplot(111)
ax.scatter(datamat[:,1], datamat[:,2], 15.0*array(labels), 15.0*array(labels))
plt.show()
'''
normmat, ranges, minvals = kNN.autoNorm(datamat)
print(normmat)
print(ranges)
print(minvals)
# kNN.datingClassTest(0.2,7)
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
# classifyperson()
testvector = kNN.img2vector('testDigits/0_13.txt')
kNN.handwritingClassTest()
#!/usr/bin/python
# -*- coding:utf-8 -*-
import kNN
'''
我们用来测试数据k-紧邻算法
'''
'''
从文件中拿数据
'''
reload(kNN)
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
print datingDataMat
normMat, ranges, minVals = kNN.autoNorm((datingDataMat))
print normMat
kNN.datingClassTest()
print normMat
testvector = kNN.img2vector('0_13.txt')
print testvector[0, 0:31]
import kNN
from numpy import *
import operator
# 2.2
import matplotlib
import matplotlib.pyplot as plt
# 2.3
from os import listdir
group, labels = kNN.createDataSet()
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
testVector = kNN.img2vector(
'machinelearninginaction/Ch02/digits/testDigits/0_0.txt')
# print(group)
# print(labels)
# print(datingDataMat)
# print("=====I'm split line.==========")
# print(datingLabels[0:20])
# print(normMat)
# print(ranges)
# print("=====I'm split line.==========")
# print(minVals)
# print("=====I'm split line.==========")
print(testVector)
# 2.1
#coding:utf-8
import kNN
testVector = kNN.img2vector('testDigits/0_13.txt')
print testVector[0, 0:31]
print testVector[0, 32:63]
kNN.handwritingClassTest()
import kNN
group, labels = kNN.create_dataset()
print(kNN.classify0([0, 0], group, labels, 3))
dating_data_mat, dating_labels = kNN.file2matrix('./CH02/datingTestSet.txt')
norm_mat, ranges, min_values = kNN.auto_norm(dating_data_mat)
kNN.dating_class_test('./CH02/datingTestSet.txt')
kNN.classify_person('./CH02/datingTestSet2.txt')
test_vec = kNN.img2vector('./CH02/digits/testDigits/0_13.txt')
kNN.handwriting_class_test('./CH02/digits/trainingDigits',
'./CH02/digits/testDigits')
# for i in range(numTestVecs):
# classifierResult = kNN.classify0(normanDataSet[i, :], normanDataSet[numTestVecs:, :], datingLabels[numTestVecs:], 3)
# # print(classifierResult)
# if (classifierResult != datingLabels[i]) : errorCount += 1
#
# print("错误率为：%f" % (errorCount/(m*hoRatio)))
# persentTags = input('测试')
# print(persentTags)
# 从文件名解析分类数字（训练集），将特征载入矩阵，标签存入列表
trainingFileList = os.listdir('trainingDigits')
m = len(trainingFileList)
trainingMat = np.zeros((m, 1024))
hwLabels = []
for i in range(m):
classNumStr = int(trainingFileList[i].split('.')[0].split('_')[0])
trainingMat[i, :] = kNN.img2vector('trainingDigits/%s' %
trainingFileList[i])
hwLabels.append(classNumStr)
# 从文件名解析分类数字（测试集）
testFileList = os.listdir('testDigits')
mTest = len(testFileList)
testMat = np.zeros((m, 1024))
errorCount = 0
for i in range(mTest):
classNumStr = int(testFileList[i].split('.')[0].split('_')[0])
vectorUnderTest = kNN.img2vector('testDigits/%s' % testFileList[i])
classifierResult = kNN.classify0(vectorUnderTest, trainingMat, hwLabels, 3)
if (classNumStr != classifierResult): errorCount += 1
print('错误率为：%f' % (errorCount / mTest))
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2])
plt.show()
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0 * np.array(datingLabels), 15.0 * np.array(datingLabels))
plt.show()
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1],
15.0 * np.array(datingLabels), 15.0 * np.array(datingLabels))
plt.show()
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
normMat
ranges
minVals
# 调用标准化函数，把数据集处理
#调用分类器
kNN.datingClassTest()
# 调用函数，把图像信息转化成向量
tectVector = kNN.img2vector('testDights/0_13.txt')
tectVector
# 调用函数预测图像中出现的手写字
kNN.handwritingClassTest()
#2.2.3 准备数据：归一化数值 normMat, ranges, minVals = kNN.autoNorm(datingDataMat) print 'normMat:',normMat print 'ranges:',ranges print 'minVals:',minVals #2.2.4 测试算法：作为完整程序验证分类器 kNN.datingClassTest() #2.2.5 使用算法：构建完整可用系统 kNN.classifyPerson() #2.3.1准备数据：将图像转化为测试向量 testVector=kNN.img2vector(homedir+'testDigits/0_13.txt') print 'testVector[0,0:31]:',testVector[0,0:31] #2.3.2 测试算法：使用k近邻算法识别手写数字 kNN. handwritingClassTest() # inX=[0,0] # dataSet=group # k=3 # # dataSetSize = dataSet.shape[0] # print 'dataSetSize:',dataSetSize # diffMat = tile(inX, (dataSetSize, 1)) - dataSet # print 'diffMat:',diffMat # sqDiffMat = diffMat ** 2 # print 'sqDiffMat:',sqDiffMat
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
print(datingDataMat)
print(datingLabels[0:20])
# scatter plot
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1],
15.0 * np.array(datingLabels), 15.0 * np.array(datingLabels))
plt.show()
# normalization
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
print(normMat)
print(ranges)
print(minVals)
# test error rate
kNN.datingClassTest()
# predict
kNN.classifyPerson()
# handwriting nums recognition
# load daata
testVector = kNN.img2vector('dataset/testDigits/0_13.txt')
print(testVector[0, 0:31])
# handwriting class test
kNN.handwritingClassTest()
def main7():
'''
手写数字识别系统
'''
testVector = kNN.img2vector('testDigits/0_0.txt')
kNN.handwritingClassTest()
#coding=utf-8
from numpy import *
import kNN
reload(kNN)
testVector = kNN.img2vector('testDigits/0_13.txt') #读取文件数据
print(testVector[0, 0:31])
print(testVector[0, 32:63])
# coding: gbk
""" This is a test for recognition of handwritten numbers with kNN """
import kNN
################################################################################
# #
# 手写数字识别 #
# #
################################################################################
# 测试函数
#testVector = kNN.img2vector('./data/digits/0_0.txt')
#print(testVector[0,0:31])
#print(testVector[0,32:63])
# 分类器 + 测试
#kNN.handwritingTest()
# png 图片数字识别
trainingMat, hwLabels = kNN.handwritingClassTraining()
for i in range(10):
filepath = kNN.png2vec("./data/digits/MyDigits/%d.png" % i)
vecUnderTest = kNN.img2vector(filepath)
res = kNN.classify0(vecUnderTest, trainingMat, hwLabels, 3)
print("The handwriting number is: %d (%d for real)" % (res, i))
