Python 2.7 - GraphLab：ZeroDivisionError：float除零

Question

我試圖創建一個使用規範化的tf-idf作爲功能的K-means模型。我得到'ZeroDivisionError：浮動除以零'。以下是代碼。請讓我知道是否需要更多細節。

import graphlab as gl 

      data = gl.SFrame(data) 
      data['tf_idf'] = gl.text_analytics.tf_idf(data['text']) 

      def normalize(d, target=1.0): 
       raw = sum(d.values()) 
       try: 
        factor = target/raw 
       except ZeroDivisionError: 
        print 'Zero Error in file ', d['file_name'] 
       return {key:value*factor for key,value in d.iteritems()} 

      data['tf_idf_norm'] = data['tf_idf'].apply(normalize) 

      print data[0] 

      {'file_name': 'ap-4081.pdf.txt', 
      'tf_idf_norm': {'september': 0.006612160101629999, 'issued': 0.004914445160361691, 'declaration': 0.018380116959675345, 'pursuant': 0.0015236875459684344, 'held': 0.006661456734504585, 'edt': 0.01993691915396277, 'its': 0.0018031759056466382, 'before': 0.000628458524686868, 'prehearing': 0.03603879166997583, 'mail': 0.010151784816687623, 'administrative': 0.0038202023891634983, 'scheduled': 0.02675584978978817, 'division': 0.003714090891806661, 'greater': 0.014401469513143977, 'express': 0.015442536961835316, 'judge': 0.0056255693137487245, 'postal': 0.01448758917369378, 'timely': 0.009547408004733245, 'postponing': 0.023771054663189694, 'james': 0.013851907261754153, 'establishing': 0.015525275482306627, 'securities': 0.0009534453943686734, 'release': 0.000994876598539298, 'served': 0.007549203784675396, 'cliffs': 0.040192712832365154, 'realty': 0.027963087504615878, 'financial': 0.006067940095145491, 'instituting': 0.0047412698163078965, 'are': 0.0024740930507990123, 'fails': 0.013316168540074749, 'proceeding': 0.0031604332608950046, 'appear': 0.010272410560940281, 'for': 0.00039400705802880267, 'defend': 0.01741380246078061, 'asia': 0.028632052997003922, 'deemed': 0.008702433747892771, 'august': 0.04977168128599991, 'exchange': 0.0005249518349832802, 'answers': 0.015575372135328506, 'respondents': 0.022052537701443286, 'corp': 0.010689517733349321, 'eastland': 0.04688688851929564, 'revoked': 0.013668927632973267, 'against': 0.00388458245265655, 'telephonic': 0.016974699222910256, 'incorporated': 0.014218288205022512, 'ltd': 0.014589362228277223, 'postponed': 0.0209823757486391, 'otherwise': 0.007582793422109354, 'respondent': 0.0054516655648239295, 'washington': 0.005091825331541719, 'hearing': 0.02249732139496055, 'registration': 0.00852794089032502, 'conference': 0.03047929459424198, 'america': 0.001440915940409403, 'service': 0., 'holdings': 0.013681846704902636, 'due': 0.006408671617186687, 'commission': 0.0003703379846648254, 'enforcement': 0.0040660794190181156, 'that': 0.0008014938443938574, 'filed': 0.004601893518537033, 'with': 0.0011834598692978579, 'commence': 0.01644634375933502, 'accordance': 0.006995433441162778, 'default': 0.010296776564423474, 'rulings': 0.00878134432538458, 'will': 0.004454693796954499, 'matter': 0.0008886177351788676, 'were': 0.00495349246481796, 'grimes': 0.019846163536283806, 'and': 0.00019120815327678883, 'states': 0.0006306247910547858, 'file': 0.0014093253240757065, 'scheduling': 0.015608961772762466, 'any': 0.0024796720760966906, 'united': 0.0007573801483105002, 'answer': 0.010898516012467644, 'granite': 0.03675899168009445, 'practice': 0.005139863202847838, 'shall': 0.004531342051741035, 'act': 0.0, 'law': 0.003763823781424106, 'oip': 0.051638100949650705, 'rule': 0.0022896158932922445, 'order': 0.0013019082720686934, 'proceedings': 0.005189982291505062, 'the': 0.0003944745275206197, 'section': 0.0023716422033868588}, 
      'tf_idf': {'september': 0.9050645370154226, 'issued': 0.6726833539094077, 'declaration': 2.515848344672878, 'pursuant': 0.20856052215192625, 'held': 0.9118122009441979, 'edt': 2.7289415601335865, 'its': 0.24681655330746285, 'before': 0.08602264841392737, 'prehearing': 4.93294654032065, 'mail': 1.3895641188014474, 'administrative': 0.5229047169927326, 'scheduled': 3.662308599647982, 'division': 0.5083803026181314, 'greater': 1.97125585843607, 'express': 2.113755921043353, 'judge': 0.7700211743422583, 'postal': 1.9830438141881122, 'timely': 1.306837746316985, 'postponing': 3.253753425874317, 'james': 1.8960324371984822, 'establishing': 2.125081070400406, 'securities': 0.1305064609991892, 'release': 0.1361775144891726, 'served': 1.0333259514584336, 'cliffs': 5.501530282373367, 'financial': 0.8305723558472731, 'registration': 1.1672943115358345, 'are': 0.3386508867204352, 'fails': 1.8227011641129327, 'proceeding': 0.43259631074797295, 'appear': 1.4060752258672398, 'for': 0.053931213109576576, 'section': 0.3246275377157642, 'asia': 3.9191210423271863, 'deemed': 1.191178684406377, 'august': 6.812687985048638, 'exchange': 0.07185477698391116, 'answers': 2.1319382401265434, 'respondents': 3.018524887177448, 'corp': 1.4631683549022034, 'eastland': 6.417821014247522, 'revoked': 1.8709864052723948, 'against': 0.531716982797367, 'telephonic': 2.323476452025422, 'incorporated': 1.9461822208839539, 'ltd': 1.9969743877240589, 'postponed': 2.87204240377426, 'otherwise': 1.037923660707063, 'respondent': 0.7462174379555567, 'washington': 0.696962938801067, 'hearing': 3.07940634519689, 'instituting': 0.648979320707021, 'conference': 4.171969254600169, 'law': 0.5151876808461564, 'service': 1.686270670295957, 'holdings': 1.8727547523291366, 'due': 0.8772112775465153, 'commission': 0.050691418761513035, 'enforcement': 0.5565600696713887, 'that': 0.10970751525181831, 'realty': 3.827553848801696, 'with': 0.16199056620216346, 'commence': 2.2511557904457957, 'accordance': 0.9575265316227637, 'default': 1.4094104151733782, 'rulings': 1.2019798695237245, 'will': 0.6097531392036623, 'matter': 0.12163292883290797, 'were': 0.6780281020682886, 'grimes': 2.7165190401350294, 'and': 0.026172342480994967, 'states': 0.08631916435383152, 'file': 0.19290675850759448, 'scheduling': 2.136535949375173, 'any': 0.33941453700573243, 'united': 0.10366928548906945, 'proceedings': 0.7103985456464252, 'answer': 1.4917757884518863, 'granite': 5.031526653127632, 'practice': 0.7035383049574554, 'shall': 0.6202446603049608, 'act': 0.1691336021724683, 'america': 0.19723084414778347, 'oip': 7.068161268029516, 'rule': 0.31339987486008647, 'order': 0.17820364137975558, 'filed': 0.629901660385122, 'the': 0.05399519977243369, 'defend': 2.3835803760951273}, 
      'text': 'united states america before the securities and exchange commission washington administrative proceedings rulings release august administrative proceeding file the matter eastland financial corp granite cliffs incorporated and greater asia realty holdings ltd order postponing hearing and scheduling prehearing conference august the securities and exchange commission issued order instituting proceedings oip against respondents pursuant section the securities exchange act the hearing scheduled commence august august the division enforcement filed declaration service establishing that respondents were served with the oip postal service express mail august accordance with rule practice respondents answers are due august oip order that the hearing scheduled for august postponed and telephonic prehearing conference shall held edt september any respondent that fails timely file answer appear the prehearing conference otherwise defend the proceeding will deemed default and the registration its securities will revoked oip james grimes administrative law judge'} 


      model = gl.clustering.kmeans.create(data,num_clusters=4,features=['tf_idf_norm']) 

[ERROR] graphlab.toolkits._main: Toolkit error: Exception in python callback function evaluation: 
    ZeroDivisionError('float division by zero',): 
    Traceback (most recent call last): 
     File "graphlab/cython/cy_pylambda_workers.pyx", line 426, in graphlab.cython.cy_pylambda_workers._eval_lambda 
     File "graphlab/cython/cy_pylambda_workers.pyx", line 169, in graphlab.cython.cy_pylambda_workers.lambda_evaluator.eval_simple 
     File "<ipython-input-14-405770e0af16>", line 3, in normalize 
    ZeroDivisionError: float division by zero 

    ERROR:graphlab.toolkits._main:Toolkit error: Exception in python callback function evaluation: 
    ZeroDivisionError('float division by zero',): 
    Traceback (most recent call last): 
     File "graphlab/cython/cy_pylambda_workers.pyx", line 426, in graphlab.cython.cy_pylambda_workers._eval_lambda 
     File "graphlab/cython/cy_pylambda_workers.pyx", line 169, in graphlab.cython.cy_pylambda_workers.lambda_evaluator.eval_simple 
     File "<ipython-input-14-405770e0af16>", line 3, in normalize 
    ZeroDivisionError: float division by zero 

    --------------------------------------------------------------------------- 
    ToolkitError        Traceback (most recent call last) 
    <ipython-input-17-1591a6c5df9a> in <module>() 
    ----> 1 model = gl.clustering.kmeans.create(data,num_clusters=4,features=['tf_idf_norm']) 

    /home/praveen/anaconda/lib/python2.7/site-packages/graphlab/toolkits/clustering/kmeans.pyc in create(dataset, num_clusters, features, label, initial_centers, max_iterations, batch_size, verbose) 
     659 
     660  ## Create and return the model 
    --> 661  params = _gl.toolkits._main.run('kmeans_train', opts, verbose) 
     662  return KmeansModel(params['model']) 

    /home/praveen/anaconda/lib/python2.7/site-packages/graphlab/toolkits/_main.pyc in run(toolkit_name, options, verbose, show_progress) 
     87   _get_metric_tracker().track(metric_name, value=1, properties=track_props, send_sys_info=False) 
     88 
    ---> 89   raise ToolkitError(str(message)) 

    ToolkitError: Exception in python callback function evaluation: 
    ZeroDivisionError('float division by zero',): 
    Traceback (most recent call last): 
     File "graphlab/cython/cy_pylambda_workers.pyx", line 426, in graphlab.cython.cy_pylambda_workers._eval_lambda 
     File "graphlab/cython/cy_pylambda_workers.pyx", line 169, in graphlab.cython.cy_pylambda_workers.lambda_evaluator.eval_simple 
     File "<ipython-input-14-405770e0af16>", line 3, in normalize 
    ZeroDivisionError: float division by zero 

UPDATE：

下面的線工作正常。

data['tf_idf_norm'] = data['tf_idf'].apply(lambda x: {key:value*(1.0/sum(x.values())) for key, value in x.iteritems()}) 

Answer 1

iPython我見過有些奇怪的錯誤，有時是不相關的。我首先把它看作一個零錯誤的實際分割（這是一個真正的可能性，你應該用ZeroDivisionError處理程序來解釋這個代碼），但是你的iPython跟蹤表示這個問題是從這裏開始的：print data ['tf_idf_norm'] [0]

這與您的歸零錯誤發生的位置無關。因此，儘管跟蹤似乎暗示着什麼，但我很想說你最大的問題是你試圖用索引來引用數據['td_idf_norm']中的值，這是你無法用字典完成的。當我創建一個類似於你的字典並嘗試在Python shell中引用它時，它會給出「KeyError」

如果要查看字典中的各個值，則需要通過關鍵數據引用它們['td_idf_norm '] ['（你想查看/打印的鍵）']或者你需要遍歷它們。字典是無序的，因此不會有像你試圖用[0]

UPDATE使用索引

這裏是我用來測試出來的主要邏輯代碼：

def normalize(d, target=1.0): 
    raw = sum(d.values()) 
    try: 
     factor = target/raw 
    except ZeroDivisionError: 
     print d 
     print "Tried to divide by zero" 
     raise 
    return {key:value*factor for key, value in d.iteritems()} 


input['tf_idf_norm'] = normalize(input['tf_idf']) 

print input['tf_idf_norm'] 

通過這種處理，如果以某種方式使其成爲零，它應該使用導致它的違規數據線提升它。如果您發現有問題的數據行，並且該數據行更新後仍然看起來錯誤無效。