Python Bayes.train方法代碼示例

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
def treinar():

    print """>>> Carregando categorias..."""
    CATEGORIAS = os.listdir('./data')
    if '.svn' in CATEGORIAS:
        CATEGORIAS.remove('.svn')


    print ">>> Instanciando treinador\n"    
    guesser = Bayes()
    try:
        for categoria in CATEGORIAS:
            print ">>> Treinando categoria %s" % categoria
            arquivos = os.listdir("%s/%s" % (CAMINHO_CATEGORIAS, categoria))
            if '.svn' in arquivos:
                arquivos.remove('.svn')
            for arquivo in arquivos:
                arquivo = open('%s/%s/%s' % (CAMINHO_CATEGORIAS, categoria, arquivo), 'r')               
                texto = arquivo.read()
                guesser.train(categoria, texto)
        print "\n>>> Salvando base de conhecimento...\n"
        guesser.save("conhecimento.bay")
        print "Voil?!\n"
    except:
        print "N?o foi poss?vel treinar a base"

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
def retrain(request):
    # Retrain your brain
    user = User.objects.get(user=request.user)
    posts = Post.objects.filter(user=user)
    bayes = Brain.objects.get(user=user)
    brain = Bayes()
    #brain.loads(base64.decodestring(bayes.data))

    tagcount = 0
    # retrain the brain based on existing tags
    for post in posts:
        print post.title, "::",
        for tag in post.tags.all():
            text = "%s %s %s" % (post.title, post.author, post.summary)
            brain.train(tag, text)
            tagcount += 1
            print tag,
        print
    brain.save('%s.db' % user)
    bayes.data = base64.encodestring(brain.saves())
    bayes.save()

    message = 'Found %s tags' % tagcount
    params = {'Messages': [message,]}
    return response(request, 'mainapp/index.html', params)

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
class Guesser(object):
    
    def __init__(self, project):
        self.project = project
        self.bayes = Bayes()
        self._train()
        self.data = []
        self.best = []
    
    def _train(self):
        for sentence in self.project.classified():
            self.bayes.train(sentence.get_classification(), sentence.sentence)
    
    def guess(self):
        for sentence in self.project.to_classify():
            data = {'sentence_id': sentence.id}
            data['guesses'] = self.bayes.guess(sentence.sentence)
            self.data.append(data)
        return self.data
    
    def best_matches(self):
        if not self.data: return []
        for matches in self.data:
            try:
                matches['guesses'] = sorted(matches['guesses'], key=lambda x:x[1], reverse=True)[0]
            except:
                matches['guesses'] = (None, None)
            match = {}
            match['id'] = matches['sentence_id']
            match['guess'] = matches['guesses'][0]
            match['certainty'] = matches['guesses'][1]
            self.best.append(match)
        return self.best

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
 def train(self,bucket,words):
   """
   Nominate a bucket to which the words apply, and train accordingly
   """
   if bucket != "" and words != "":
     try:
       Bayes.train(self,bucket,words)
       Bayes.save(self,self.brain)
     except:
       print "Failed to learn"
   else:
     return None

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
 def action_train(self, cr, uid, ids, context=None):
     cat_obj = self.pool.get('crm.bayes.categories')
     group_obj = self.pool.get('crm.bayes.group')
     message_obj = self.pool.get('crm.bayes.test.guess')
     
     for id in ids:
         cat_id = self.read(cr, uid, id, ['category_id','name'])         
         cat_id = cat_id[0]['category_id']
         if  result :
             max_list = max(result, key=lambda k: k[1])
             if cat_id:
                 cat_guess_msg = cat_obj.read(cr, uid, cat_id, ['train_messages'])
                 cat_obj.write(cr, uid, cat_id, {'train_messages' :cat_guess_msg['train_messages'] + 1})
             if max_list[1] > 0 and not cat_id:
                 cat_id = cat_obj.search(cr, uid, [('name','=',max_list[0])])[0]
                 cat_guess_msg = cat_obj.read(cr, uid, cat_id, ['guess_messages'])
                 cat_obj.write(cr, uid, cat_id, {'guess_messages' :cat_guess_msg['guess_messages'] + 1})
                 self.write(cr, uid, ids, {'category_id':cat_id})
         if cat_id :
             cat_rec = cat_obj.read(cr, uid, cat_id, [])
             guesser = Bayes()
             data = ""
             for rec in group_obj.browse(cr, uid, [cat_rec['group_id'][0]]):
                 if rec['train_data']:
                     data += rec['train_data']
             if data :
                 myfile = file(file_path+"crm_bayes.bay", 'w')
                 myfile.write(data)
                 myfile.close()
                 guesser.load(file_path+"crm_bayes.bay")
                 
             guesser.train(cat_rec['name'], message_obj.read(cr, uid, id)[0]['name'])
             guesser.save(file_path+"crm_bayes.bay")
             myfile = file(file_path+"crm_bayes.bay", 'r')
             data=""
             for fi in myfile.readlines():
                 data += fi 
             cr.execute("select sum(train_messages) as tot_train,sum(guess_messages) as tot_guess from crm_bayes_categories where group_id=%d"% cat_rec['group_id'][0])
             rec = cr.dictfetchall()
             if not rec[0]['tot_guess']:
                 rec[0]['tot_guess'] =0
             percantage = float(rec[0]['tot_guess'] *100)  / float(rec[0]['tot_guess'] + rec[0]['tot_train'])
             group_obj.write(cr, uid, cat_rec['group_id'][0], {'train_data': data,'automate_test':percantage})            
         else :
             raise osv.except_osv(_('Error !'),_('Please Select Category! '))
     return {
         'view_type': 'form', 
         "view_mode": 'form', 
         'res_model': 'crm.bayes.train.message', 
         'type': 'ir.actions.act_window', 
         'target':'new', 
      }

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
    def getCategoryGuesses(self, corpus1, corpus2, corpus3):
        from reverend.thomas import Bayes

        # instantiate guesser
        guesser = Bayes()

        # train category guesser with first corpus
        guesser.train('first reference text', corpus1)
        guesser.train('second reference text', corpus2)
    
        # compare with second corpus
        guesses = guesser.guess(corpus3)
        
        return guesses

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
def treino (self):    
        banco_do_jornal = Server()
        genero=[banco_do_jornal[doc] for doc in GENEROS]
         #treinando o reverend
        from reverend.thomas import Bayes
        guesser = Bayes()
        guesser.train('artigo', ' '.join(genero[0][doc]['texto'] for doc in genero[0]))
        guesser.train('resenha',' '.join(genero[6][doc]['texto'] for doc in genero[6]))  
        guesser.train('noticia',' '.join(genero[1][doc]['texto'] for doc in genero [1]))
        guesser.train('cronica',' '.join(genero[5][doc]['texto']for doc in genero[5] if 'texto' in genero[5][doc] ))
        guesser.train('horoscopo',' '.join(genero[3][doc]['texto']for doc in genero[3]))
        guesser.train('manchete',' '.join(genero[2][doc]['titulo']for doc in genero[2]))
        guesser.train('receita',' '.join(genero[4][doc]['texto']for doc in genero[4]))
        guesser.save('my_guesser.bay')
        variavel = guesser.guess('Cidad?o se descuidou e roubaram seu celular. Como era um executivo e n?o sabia mais viver sem celular, ficou furioso. Deu parte do roubo, de Quara?.? Pois ?.? Carol.? Hein?? Meu nome. ? Carol.? Ah. Voc?s s?o...? N?o, n?o. Nos conhecemos h? pouco.? Escute Carol. Eu trouxe uma encomenda para o Amleto. De Quara?. Uma pessegada, mas n?o me lembro do endere?o.')
        print  'Resultado = ', variavel

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
 def treino (self):    
     banco_do_jornal = Server()
     genero=[banco_do_jornal[doc] for doc in GENEROS]
      #treinando o reverend
     from reverend.thomas import Bayes
     guesser = Bayes()
     guesser.train('artigo', ' '.join(genero[0][doc]['texto'] for doc in genero[0]))
     guesser.train('resenha',' '.join(genero[6][doc]['texto'] for doc in genero[6]))  
     guesser.train('noticia',' '.join(genero[1][doc]['texto'] for doc in genero [1]))
     guesser.train('cronica',' '.join(genero[5][doc]['texto']for doc in genero[5] if 'texto' in genero[5][doc] ))
     guesser.train('horoscopo',' '.join(genero[3][doc]['texto']for doc in genero[3]))
     guesser.train('manchete',' '.join(genero[2][doc]['titulo']for doc in genero[2]))
     guesser.train('receita',' '.join(genero[4][doc]['texto']for doc in genero[4]))
     guesser.save('my_guesser.bay')
     variavel = guesser.guess('Bolo de chocolate :ingredientes : 6 ovos, 2 xicaras de farinha, 1 colher de achocolatado, 1 lata de leite condensado, 2 copos de leite e 3 colheres de açucar')
     print  'Resultado = ', variavel

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
def mark(request, flag):
    
    id = request.GET.get('post', None)
    feed = request.GET.get('feed', None)
    category = request.GET.get('category') 
    tag = request.GET.get('tag') or None
    
    try:
        if feed:
           posts = Post.objects.filter(feed=feed)
        else:
           posts = Post.objects.filter(id=id)
    except Post.DoesNotExist:
        return HttpResponseRedirect('/')
    
    bayes = Brain.objects.get(user=request.user) #login required
    brain = Bayes()
    brain.loads(base64.decodestring(bayes.data))
    
    if flag in ('read', 'unread'):
        flag = flag == 'read'
        posts.update(read=flag) 
    else:
        for post in posts:
            text = "%s %s %s" % (post.title, post.author, post.summary)
            t1 = Tag.objects.get(id=flag)
            if t1 in post.tags.all() and not feed:
                post.tags.remove(t1) 
                brain.untrain(t1.name, text)
            else:
                post.tags.add(t1)
                brain.train(t1.name, text)
            post.save()    
        
    bayes.data = base64.encodestring(brain.saves())
    bayes.save()
        
    if category:
       return HttpResponseRedirect('/?category=%s' % category)
    elif feed:
       return HttpResponseRedirect('/?feed=%s' % feed)
    elif tag:
       return HttpResponseRedirect('/?tag=%s' % tag)
    else:
       return HttpResponseRedirect('/')

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
def read(request, id):
    try:
        post = Post.objects.get(id=id)
        post.read = True
        post.save()

        try:
            bayes = Brain.objects.get(user=request.user) #login required
            brain = Bayes()
            brain.loads(base64.decodestring(bayes.data))
            text = post.title + ' ' + post.author + post.summary
            brain.train('Interesting', text)        
            bayes.data = base64.encodestring(brain.saves())
            bayes.save()
        except Exception, e:
            print "Couldn't train %s because %s" % (post.title, e)

        return HttpResponseRedirect(post.link)

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
    def getLanguageGuesses(self, stopWords, corpus, languages):
        from reverend.thomas import Bayes

        # charset
        charset = 'us-ascii'

        # instantiate guesser
        guesser = Bayes()

        # go through language in order to train guesser
        for selectLanguage in languages:
            if selectLanguage != 'automatic':
                stopWordString = stopWords.getStopWordString(selectLanguage)
                guesser.train(selectLanguage, stopWordString.encode(charset, 'replace'))
        
        # get list of possible languages
        languageGuesses = guesser.guess(corpus.encode(charset, 'replace'))
        
        return languageGuesses

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
 def trained(self, cr, uid, ids, context=None):
     for id in ids:
         record = self.read(cr, uid, id, ['category_id','description'])
         if not record['description'] :
             raise osv.except_osv(_('Error!'),_("Description Not Define!"))
         if not record['category_id']:
             raise osv.except_osv(_('Error!'),_("Statistics Category Not Define!"))
         group_obj = self.pool.get('crm.bayes.group')
         cat_obj = self.pool.get('crm.bayes.categories')
         cat_rec = cat_obj.read(cr, uid, record['category_id'][0], [])
         guesser = Bayes()
         data =""
         for rec in group_obj.browse(cr, uid, [cat_rec['group_id'][0]]):
             if rec['train_data']:
                 data += rec['train_data']
         if data :
             myfile = file(file_path+"crm_bayes.bay", 'w')
             myfile.write(data)
             myfile.close()
             guesser.load(file_path+"crm_bayes.bay")
         guesser.train(cat_rec['name'], record['description'])
         guesser.save(file_path+"crm_bayes.bay")
         myfile = file(file_path+"crm_bayes.bay", 'r')
         data=""
         for fi in myfile.readlines():
             data += fi
         cat_obj.write(cr, uid, record['category_id'][0], {'train_messages':int(cat_rec['train_messages']) + 1})
         cr.execute("select sum(train_messages) as tot_train,sum(guess_messages) as tot_guess from crm_bayes_categories where group_id=%d"% cat_rec['group_id'][0])
         rec = cr.dictfetchall()
         if not rec[0]['tot_guess']:
             rec[0]['tot_guess'] =0
         percantage = float(rec[0]['tot_guess'] *100)  / float(rec[0]['tot_guess'] + rec[0]['tot_train'])
         group_obj.write(cr, uid, cat_rec['group_id'][0], {'train_data': data,'automate_test':percantage})            
         
         self.write(cr, uid, id, {'state_bayes':'trained'})
     return True

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
from reverend.thomas import Bayes


guesser = Bayes()

for each in ('north','south','east','west'):
    guesser.train('do_move', 'to the %s' % each)
    guesser.train('do_move', 'head %s' % each)
    guesser.train('do_move', 'spin %s' % each)
    
    # if we don't do this 'do_move' is going to get too dominant
    guesser.train('do_take', 'grab')
    guesser.train('do_take', 'grab the')
    guesser.train('do_take', 'pick up')
    guesser.train('do_take', 'pick up the')
    guesser.train('do_take', 'lift')
    guesser.train('do_take', 'lift the')
    guesser.train('do_take', 'fetch')
    guesser.train('do_take', 'fetch the')

bulk = """wear suit of armour
put on suit of armour
use armor
climb into armour
wear the armor
place armour on me
place armor on self"""
for line in bulk.splitlines():
    guesser.train('do_take', line)

guesser.save('commands.bays')

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
from reverend.thomas import Bayes
guesser = Bayes()
guesser.train('french', 'le la les du un une je il elle de en')
guesser.train('german', 'der die das ein eine')
guesser.train('spanish', 'el uno una las de la en')
guesser.train('english', 'the it she he they them are were to')
guesser.guess('they went to el cantina')
guesser.guess('they were flying planes')
guesser.train('english', 'the rain in spain falls mainly on the plain')
guesser.save('my_guesser.bay')

# 需要導入模塊: from reverend.thomas import Bayes [as 別名]
# 或者: from reverend.thomas.Bayes import train [as 別名]
from reverend.thomas import Bayes

guesser = Bayes()
guesser.train('fish', 'salmon trout cod carp')
guesser.train('fowl', 'hen chicken duck goose')

guesser.guess('chicken tikka marsala')

guesser.untrain('fish','salmon carp')