bayes

from numpy import *

import time

starttime = time.time()

def loadDataSet():

    postingList = [['my', 'dog', 'has', 'flea',

                    'problems', 'help', 'please'],

                    ['maybe', 'not', 'take', 'him',

                    'to', 'dog', 'park', 'stupid'],

                    ['my', 'dalmation', 'is', 'so', 'cute',

                    'I', 'love', 'him'],

                    ['stop', 'posting', 'stupid', 'worthless',

                    'garbage'],

                    ['mr', 'licks', 'ate', 'my', 'steak', 'how',

                    'to', 'stop', 'him'],

                    ['quit', 'buying', 'worthless', 'dog', 'food',

                    'stupid']]

    classVec = [0, 1, 0, 1, 0, 1]

    return postingList, classVec

def createVocabList(dataSet): # dataSet = postingList

    vocabSet = set([]) # vocabSet = set(dataSet)

    for document in dataSet:

        vocabSet = vocabSet | set(document) #

    return list(vocabSet) # createVocabList = list(set(dataSet))

def setOfWords2Vec(vocabList, inputSet):

    returnVec = [0] * len(vocabList) # [0, 0 , 0 ,0,..] len(vocabList)  0

    for word in vocabList:

        if word in inputSet:

            returnVec[vocabList.index(word)] = 1 + 1.0

        else:

            returnVec[vocabList.index(word)] = 1.0

            print "the word: %s is not in my Vocabulary!" % word

    return returnVec

def txt2trainxy(filename1, filename2):

    import re

    reg = re.compile(r'\W*') #

    # step 1: loading data...

    print "stet 1: loading data..."

    from os import listdir

    ld1 = listdir('email/' + filename1); ld2 = listdir('email/' + filename2)

    filelist = ld1 + ld2

    trainy = ((filename1 + '\t') * len(ld1) + (filename2 + '\t') * len(ld2)).split()

    trainx = []; fulltext = []; i = 0

    for File in filelist:

        if i < len(ld1):

            fr = reg.split(open('email/' + filename1 + '/' + File).readlines()[0].lower())

        else:

            fr = reg.split(open('email/' + filename2 + '/' + File).readlines()[0].lower())

        trainx.append([f for f in fr if len(f) > 2]) #

        fulltext.extend([f for f in fr if len(f) > 2]) #

        i += 1

    fulltext = list(set(fulltext))

    # set of words

    trainxws = [[list(set(item)).count(strg) + 1.0 for strg in fulltext] for item in trainx]

    # bag of words

    trainxwb = [[item.count(strg) + 1.0 for strg in fulltext] for item in trainx]

    return trainxws, trainxwb, trainy, trainx, fulltext

def testx2vec(testx, fulltext):

    # set of words

    testxws = [list(set(testx)).count(strg) + 1.0 for strg in fulltext] #

    # bag of words

    testxwb = [testx.count(strg) + 1.0 for strg in fulltext] #

    for word in testx:

        if word not in fulltext:

            print "the word: %s is not in my fulltext!" % word

    return testxws, testxwb

def bayes(testx, trainx, trainy, fulltext):

    print "---Getting Prob..."

    s = set(trainy); l = len(trainy); r = len(trainx[0])

    IDs = [[id for id in range(l) if trainy[id] == item] for item in s]

    logproby = [log(array(trainy.count(item)) / float(l)) for item in s]

    numbxv = [sum([trainx[id] for id in ids], 0) for ids in IDs]

    numbx = [sum([trainx[id] for id in ids]) + 2.0 for ids in IDs] #

    probx = [numbxv[i] / float(numbx[i]) for i in range(len(s))]

    logprobx = [[log(p[i]) for i in range(r)] for p in probx]

    print "---Printing Prob..."

    #print probx

    print [fulltext[i] for i in (-array(probx)).argsort()[:,: 5][0]] # argsort() small to big

    print trainy[IDs[0][0]]

    print [fulltext[i] for i in (-array(probx)).argsort()[:,: 5][1]]

    print trainy[IDs[1][0]]

    """

    print IDs

    print numbxv

    print logprobx

    """

    # step 4: showing the result...

    print "---Showing the result..."

    # set of words

    sumlogpxws = sum(array(logprobx) * testx, 1)

    sumlogpxyws = array(sumlogpxws) + array(logproby)

    #print logprobx

    print sumlogpxws

    print sum(array(probx) * testx, 1)

    bestyws = trainy[IDs[sumlogpxyws.argmax()][0]]

    print "---From set of words: ", bestyws

    """

    # bag of words

    sumlogpxwb = sum(array(logprobx) * testxwb, 1)

    sumlogpxywb = array(sumlogpxwb) + array(logproby)

    bestywb = trainy[IDs[sumlogpxywb.argmax()][0]]

    print "---From bag of words: ", bestywb

    """

    return bestyws

def main():

    # step 1: loading data...

    trainxws, trainxwb, trainy, trainx, fulltext = txt2trainxy('spam','ham')

    print fulltext

    # step 2: training...

    print "step 2: training..."

    pass

    # step 3: testing...

    print "step 3: testing..."

    print "---Preparing testdata..."

    import random

    l = len(trainy)

    testid = random.sample(range(l), 20)

    testxxx = [trainxws[i] for i in testid]

    testyyy = [trainy[i] for i in testid]

    testtrainxws = [trainxws[i] for i in range(l) if i not in testid]

    testtrainy = [trainy[i] for i in range(l) if i not in testid]

    print "---Testing now..."

    errorcount = 0; p = len(testid)

    for i in range(p):

        if bayes(testxxx[i], testtrainxws, testtrainy, fulltext) != testyyy[i]:

            errorcount += 1

    print errorcount

    print p

    print "---Errorrate is: ", (errorcount / float(p))

    # step 4: showing the result

    print "step 4: using..."

    testx = ['love', 'my', 'dalmation']

    print "the testx is: ", testx

    print "---Changing testx into vector..."

    testxws, testxwb = testx2vec(testx, fulltext)

    #print testxws

    bayes(testxws, testtrainxws, testtrainy, fulltext)

main()

"""

trainx, trainy = loadDataSet()

fulltext = createVocabList(trainx)

print fulltext

print setOfWords2Vec(fulltext, trainx[0])

trainxws = []

for t in trainx:

    trainxws.append(setOfWords2Vec(fulltext, t))

testEntry1 = ['love', 'my', 'dalmation']

testEntry2 = ['stupid', 'garbage']

bayes(testEntry1, trainxws, trainy, fulltext)

"""