Python svmutil.svm_load_model函数代码示例

def matchPers(p1, rgdP, conf, score = None):
    global svmModel, mt_tmp, SVMfeatures
    if not svmModel:
        if 'featureSet' in conf:
            SVMfeatures = getattr(importlib.import_module('featureSet'), conf['featureSet'])
            svmModel = svm_load_model('conf/person_' + conf['featureSet'] + '.model')
        else:  #default
            SVMfeatures = getattr(importlib.import_module('featureSet'), 'personDefault')
            svmModel = svm_load_model('conf/personDefault.model')
    nodeScore = nodeSim(p1, rgdP)
    #pFam = conf['families'].find_one({ 'children': p1['_id']}) #find fam if p in 'children'
    pFam = getFamilyFromChild(p1['_id'], conf['families'], conf['relations'])
    #rgdFam = conf['match_families'].find_one({ 'children': rgdP['_id']})
    rgdFam = getFamilyFromChild(rgdP['_id'], conf['match_families'], conf['match_relations'])
    famScore = familySim(pFam, conf['persons'], rgdFam, conf['match_persons']) 
    cand_matchtxt = mt_tmp.matchtextPerson(rgdP, conf['match_persons'], conf['match_families'], conf['match_relations'])
    matchtxt = mt_tmp.matchtextPerson(p1, conf['persons'], conf['families'], conf['relations'])
    cosScore = cos(matchtxt, cand_matchtxt)
    if score is None and 'featureSet' in conf:  #score not used by deault
        try:  #Lucene FIX
            #from luceneUtils import search
            import traceback
            candidates = search(matchtxt, p1['sex'], ant=100, config=conf) #Lucene search
            score = 0.0
            for (kid,sc) in candidates:
                if str(kid) == str(rgdP['_id']):
                    score = sc
                    break
        #except:  #use cos instead ?? if problems running Java in Bottle
        except Exception, e:
            exc_type, exc_value, exc_traceback = sys.exc_info()
            traceback.print_exception(exc_type, exc_value, exc_traceback)

def cons_train_sample_for_cla(filename,indexes,dic_path,glo_aff_path,result_save_path,model_path,LSA_path,LSA_model_path,decom_meas,delete):
    dic_list = read_dic(dic_path,dtype=str)
    glo_aff_list = read_list(glo_aff_path)
    f= file(filename,'r')
    fs = file(result_save_path,'w')
    fd = file(dust_save_path,'w')
    m= svm_load_model(model_path)
    lsa_m = svm_load_model(LSA_model_path)
    U = load_lsa_model(LSA_path,"U")
    for line in f.readlines():
        text = line.strip().split(tc_splitTag)
        if len(text)!=line_length:
            fd.write(line)
            continue
        text_temp=""
        for i in indexes:
            text_temp+=str_splitTag+text[i]  
        vec = cons_vec_for_cla(text_temp.strip().split(str_splitTag),dic_list,glo_aff_list)
        y,x=cons_svm_problem(text[0],vec)
        p_lab,p_acc,p_sc=svm_predict(y,x,m)
 
        if  decom_meas==1:
            weight = cal_weight(p_sc[0][0])
            #vec = [value*weight for value in vec ] 
            vec = [0]*len(vec)
            for key in x[0].keys():
               vec[int(key)-1]= weight*float(x[0][key])    
            vec = pre_doc_svds(vec,U)
            y,x=cons_svm_problem(text[0],vec)
            lsa_lab,lsa_acc,lsa_sc = svm_predict(y,x,lsa_m)
            fs.write(text[0]+"\t"+str(p_sc[0][0])+"\t"+str(lsa_sc[0][0])+"\t"+text[1]+"\t"+text[2]+"\n")
        else :
            fs.write(text[0]+"\t"+str(p_sc[0][0])+"\t"+text[1]+"\t"+text[2]+"\n")
    f.close()
    fs.close()

def get_fearure_weights(yprob, years=range(2004,2017), normalize=False, binary_features=False, top10_type='sum', reg=1e-3):
    from svmutil import svm_load_model
    d=(102,103)[binary_features]
    W=np.array([]).reshape(0,d)
    periods=[]  
    for y in years:
        periods.append(get_year_str(y))
#         alpha, SV = get_alpha_and_SV('/home/arya/out/model.'+periods[-1])
        model = svm_load_model('/home/arya/out/model.'+periods[-1])
        alpha = np.array(map(lambda x: abs(x[0]), model.get_sv_coef()))
        SV = model.get_SV()
        X=np.zeros((len(SV),d))
        
        for i in range(len(SV)):
            for k,v in SV[i].items():
                if k>0:
                    X[i,k-1]=v
        W=np.append(W,alpha.dot(X)[None,:],axis=0)
    np.set_printoptions(linewidth='1000', precision=3, edgeitems=55, suppress=True)
    
    W=W+reg
    if normalize:
        W=W/ W.sum(1)[:,None]
    print ('UnNormalized','Normalized')[normalize], 'Feature Weights:'
    print W
    
    if top10_type=='sum':
        sumW= W.sum(0)
        indices = range(len(sumW))
        indices.sort(lambda x,y: -cmp(sumW[x], sumW[y]))
        top10=indices[:10]
    elif top10_type =='genbank':
        yprob = yprob  / yprob.sum(0)
        err0 =  abs(W[:11,:]-yprob[:,0][:,None]).sum(0)
        indices = range(len(err0))
        indices.sort(lambda x,y: -cmp(err0[x], err0[y]))
        top10=indices[:10]
    elif top10_type=='geo':
        yprob = yprob  / yprob.sum(0)
        err1 =  abs(W[:11,:]-yprob[:,1][:,None]).sum(0)
        indices = range(len(err1))
        indices.sort(lambda x,y: -cmp(err1[x], err1[y]))
        top10=indices[:10]
    elif top10_type == 'all':
        top10 = range(W.shape[1])
    else:
        print top10_type , 'not found'
        exit(1)
    top10=sorted(top10)
    print top10, top10_type
#     exit(1)
    info="""
    W: t x d matrix of weights which each line contains A weight correponding to time t (periods[t]
    periods: t x 1 string list which each element contains the period, e.g. 2004-2008
    top10: Top 10 features which has A larger sum over all the periods 
    """
    Data={'W':W, 'periods':periods, 'top10':top10, 'info':info}
    save_data_pkl(Data, '/home/arya/out/trends{}{}.pkl'.format(('_unnormalized','_normalized')[normalize],('_integer','_binary')[binary_features]))
    
    return W,periods, top10

    def __setstate__(self, state):
        self.svm_model_fp = state['svm_model_fp']
        self.svm_label_map_fp = state['svm_label_map_fp']
        self.train_params = state['train_params']
        self.normalize = state['normalize']

        # C libraries/pointers don't survive across processes.
        if '__LOCAL__' in state:
            fd, fp = tempfile.mkstemp()
            try:
                os.close(fd)

                self.svm_label_map = state['__LOCAL_LABELS__']

                # write model binary to file, then load via libSVM
                with open(fp, 'wb') as model_f:
                    model_f.write(state['__LOCAL_MODEL__'])

                self.svm_model = svmutil.svm_load_model(fp)

            finally:
                os.remove(fp)
        else:
            self.svm_model = None
            self._reload_model()

def _get_classifier(svm_name=None):
  """
  If need be, initializes, and then returns a classifier trained to
  differentiate between different ions and water. Also returns of options for
  gathering features.

  To use the classifier, you will need to pass it to
  svm.libsvm.svm_predict_probability. Ion prediction is already encapsulated by
  predict_ion, so most users should just call that.

  Parameters
  ----------
  svm_name : str, optional
      The SVM to use for prediction. By default, the SVM trained on heavy atoms
      and calcium in the presence of anomalous data is used. See
      chem_data/classifiers for a full list of SVMs available.

  Returns
  -------
  svm.svm_model
      The libsvm classifier used to predict the identities of ion sites.
  dict of str, bool
      Options to pass to ion_vector when collecting features about these sites.
  tuple of ((tuple of numpy.array of float, numpy.array of float),
            tuple of float)
      The scaling parameters passed to scale_to.
  numpy.array of bool
      The features of the vector that were selected as important for
      classification. Useful for both asserting that ion_vector is returning
      something of the correct size as well as only selection features that
      actually affect classification.

  See Also
  --------
  svm.libsvm.svm_predict_probability
  mmtbx.ions.svm.predict_ion
  phenix_dev.ion_identification.nader_ml.ions_train_svms
  """
  assert (svmutil is not None)
  global _CLASSIFIER, _CLASSIFIER_OPTIONS

  if not svm_name or str(svm_name) == "Auto" :
    svm_name = _DEFAULT_SVM_NAME

  if svm_name not in _CLASSIFIER:
    svm_path = os.path.join(CLASSIFIERS_PATH, "{}.model".format(svm_name))
    options_path = os.path.join(CLASSIFIERS_PATH,
                                "{}_options.pkl".format(svm_name))
    try:
      _CLASSIFIER[svm_name] = svmutil.svm_load_model(svm_path)
    except IOError as err:
      if err.errno != errno.ENOENT:
        raise err
      else:
        _CLASSIFIER[svm_name] = None
        _CLASSIFIER_OPTIONS[svm_name] = (None, None, None)
    _CLASSIFIER_OPTIONS[svm_name] = load(options_path)

  vector_options, scaling, features = _CLASSIFIER_OPTIONS[svm_name]
  return _CLASSIFIER[svm_name], vector_options, scaling, features

def classify(filename, classLabel=0):
    str = "/Thu_Life/CS/SVM/data/trainData/Test_SVMFile/singleSVM_TestFile"
    f = open(str, "wb")
    t = VSM.TextToVector2(filename)
    slabel = ("%d ") % classLabel
    if len(t) > 0:
        f.write(slabel)
        for k in range(len(t)):
            str1 = ("%d:%d ") % (t[k][0], t[k][1])
            f.write(str1)
        f.write("\r\n")
    else:
        print "The text can't be classified to the Four Labels!"
        return "Can't be classified ! "
    f.close()
    y, x = svmutil.svm_read_problem(str)
    model = svmutil.svm_load_model("../SVMTrainFile250.model")
    label, b, c = svmutil.svm_predict(y, x, model)
    print "label", label
    if label[0] == 1:
        print "类别：财经"
        return "财经"
    elif label[0] == 2:
        print "类别：IT"
        return "IT"
    elif label[0] == 3:
        print "类别:旅游"
        return "旅游"
    elif label[0] == 4:
        print "类别：体育"
        return "体育"

def predict_all(request):
    '''Predicts points in an array'''
    
    width = float( request.POST.get("width", "None") )
    height = float( request.POST.get("height", "None") )
    
    model = svmutil.svm_load_model('libsvm.model')
    
    # Get grid of points to query
    points = []
    for counterY in [ 1.0 / 15.0 * y for y in range(0, 15) ]:
        for counterX in [ 1.0 / 15.0 * x for x in range(0, 15) ]:
            points.append([counterX, counterY])
    
    #for counterY in [ 1.0 / 10.0 * x for x in range(0, 10) ]:
    #    for counterX in [ 1.0 / 10.0 * y for y in range(0, 10) ]:
    #        label , acc, val = svmutil.svm_predict( [0], [[counterX, counterY]], model )
    #        results[i] = [counterX, counterY, label] 
    #        i = i + 1
    
    #results["length"] = i
    
    # Get labels
    labels, acc, val = svmutil.svm_predict([0] * len(points), points, model)
    
    results = {}
    for index, value in enumerate(points):
        results[index] = {  "x" : points[index][0], 
                            "y" : points[index][1], 
                            "label" : labels[index] }
    results["length"] = len(points)

    return json(results)

def predict(request):
    predictX = float( request.POST.get("x", -1) )
    predictY = float( request.POST.get("y", -1) )
    
    predictLabel = int( request.POST.get("label", -1) )
    
    if predictX == -1 or predictY == -1 or predictLabel == -1:
        return django.http.HttpResponse("Missing Params")
    
    points = models.Point2d.objects.all()
    
    # Storing the information to be presented to SVM
    labels = []
    inputs = []
    
    # For each point, store the information into arrays
    #for p in points:
    #    labels.append( p.label )
    #    inputs.append([p.x, p.y])
    
    #prob = svm.svm_problem(labels, inputs)
    #param = svm.svm_parameter('-t 2 -c 100')
    #model = svmutil.svm_train(prob, param)
    #svmutil.svm_save_model('libsvm.model', model)
    model = svmutil.svm_load_model('libsvm.model')
    
    p_label , acc, val = svmutil.svm_predict([0], [[predictX, predictY]], model)
   
    data = {'x': predictX, 'y': predictY, 'label': int( p_label[0] ) }
    return json(data)

 def __init__(self,train_feature_file = TRAIN_FEATURE_FILE):
     if os.path.exists(SAVED_MODEL):
         self.model = svmutil.svm_load_model(SAVED_MODEL)
     else:
         y, x = svmutil.svm_read_problem(train_feature_file)
         self.model = svmutil.svm_train(y, x, '-c 4')
         svmutil.svm_save_model(SAVED_MODEL,self.model)

def trainSVMAndSave(modelLoc, kernel, labels):
    if os.path.exists(modelLoc):
        return svm_load_model(modelLoc)
    else:
        model = trainSVM(kernel, labels)
        svm_save_model(modelLoc, model)
        return model

def predict(V, yy):
    m = svmutil.svm_load_model("sample.model")
    x = [list(map(lambda z: z * 10, list(t))) for t in V]
    y = [0 if t < 0 else 1 for t in yy]
    p_label, p_acc, p_val = svmutil.svm_predict(y, x, m)
    print(y)
    print(p_label)
    print(x[10])

 def think(self,text):
     from twss.twss import twss_lite
     import pickle
     from svmutil import svm_load_model
     input = open(self.vocab)
     vocabList = pickle.load(input)
     input.close()
     model = svm_load_model(self.model)
     return "That's what she said!" if twss_lite(text,vocabList,model) == 1 else ""

 def _reload_model(self):
     """
     Reload SVM model from configured file path.
     """
     if self.svm_model_fp and os.path.isfile(self.svm_model_fp):
         self.svm_model = svmutil.svm_load_model(self.svm_model_fp)
     if self.svm_label_map_fp and os.path.isfile(self.svm_label_map_fp):
         with open(self.svm_label_map_fp, "rb") as f:
             self.svm_label_map = cPickle.load(f)

def main():
    try:
        lModel = svmutil.svm_load_model(sys.argv[1])
        lRanges = read_ranges(sys.argv[2])
        lFile = sys.argv[3]
        lBlockSize = int(sys.argv[4])
    except IndexError, pExc:
        print "Usage: " + sys.argv[0] + " <model-file> <range-file> "\
                "<problem-file> <block-size>"
        sys.exit(-1)

    def _reload_model(self):
        """
        Reload SVM model from configured file path.
        """
        if self.svm_model_elem and not self.svm_model_elem.is_empty():
            svm_model_tmp_fp = self.svm_model_elem.write_temp()
            self.svm_model = svmutil.svm_load_model(svm_model_tmp_fp)
            self.svm_model_elem.clean_temp()

        if self.svm_label_map_elem and not self.svm_label_map_elem.is_empty():
            self.svm_label_map = \
                cPickle.loads(self.svm_label_map_elem.get_bytes())