DM/ML学习实践(一)

//数据挖掘&机器学习实践

1.简单的手写数字识别

原理：可以先通过多次手写的图片生成训练集，然后利用knn就行了……代码如下(下面代码需要安装PIL/numpy库，PIL安装有点坑==官方的貌似还有点问题。。。)

//knn.py
from numpy import *
import operator
import os

def createDataSet():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('	')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(round(float(listFromLine[-1])))
        index += 1
    return returnMat,classLabelVector

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

def datingClassTest():
    hoRatio = 0.1
    datingDataMat, datingLabels = file2matrix('C:\Python27\source.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:], normMat[numTestVecs:m, :],
                                     datingLabels[numTestVecs:m], 3);
        print "result :%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 img2vector(filename):
    returnVect = zeros((1, 1024))
    fr = open(filename, 'r')
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0, 32*i+j] = int(lineStr[j])
    return returnVect

def handwritingClassTest():
    hwLabels = []
    trainingFileList = os.listdir('D:\PDF_BOOK\ML\machinelearninginaction\Ch02\traing\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('D:\PDF_BOOK\ML\machinelearninginaction\Ch02\traing\trainingDigits\%s' % fileNameStr)
    testFileList = os.listdir('D:\PDF_BOOK\ML\machinelearninginaction\Ch02\traing\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('D:\PDF_BOOK\ML\machinelearninginaction\Ch02\traing\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 "
the total number of errors is %d" % errorCount
    print "
the total error rate is %f" % (errorCount/float(mTest))

def judgeClass(filename):
    hwLabels = []
    trainingFileList = os.listdir('D:\PDF_BOOK\ML\machinelearninginaction\Ch02\traing\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('D:\PDF_BOOK\ML\machinelearninginaction\Ch02\traing\trainingDigits\%s' % fileNameStr)
    testVector = img2vector(filename)
    result = classify0(testVector, trainingMat, hwLabels, 3)
    return result

import Image, ImageDraw, ImageFont, ImageFilter
import random
import array
from numpy import *
import sys
import knn

s = '2'

filename = 'C:\Users\lg\Desktop\' + s + '.txt'
im = Image.open('C:\Users\lg\Desktop\'+s+'.png')
f = open(filename, 'w+')

data = zeros(32*32)
for x in range(32):
    for y in range(32):
        val = 1
        if im.getpixel((x, y)) == (255, 255, 255):
            val = 0
        data[32*y+x] = val

for x in range(32):
    for y in range(32):
        f.write(str(int(data[32*x+y])))
    if (x != 31): f.write('
')
f.close()
print knn.judgeClass(filename)

后续的功能或者识别加强慢慢再补==，先挖坑，慢慢填。。。