Python Evaluation.confusionMatrix方法代码示例

# 需要导入模块: from weka.classifiers import Evaluation [as 别名]
# 或者: from weka.classifiers.Evaluation import confusionMatrix [as 别名]
my_evaluations = []
for key in algo_keys :
   evaluation = Evaluation(data)
   algo = algo_dict[key]
   output = PlainText()  # plain text output for predictions
   output.setHeader(data)
   buffer = StringBuffer() # buffer to use
   output.setBuffer(buffer)
   attRange = Range()                  # no additional attributes output
   outputDistribution = Boolean(False) # we don't want distribution
   evaluation.evaluateModel(algo, data, [output, attRange, outputDistribution])
   my_evaluations.append(evaluation)
   print "------------------------------------"
   print algo.__class__.__name__
   print evaluation.toSummaryString()
   confusion_matrix = evaluation.confusionMatrix()  # confusion matrix
   print "Confusion Matrix:"
   for l in confusion_matrix:
       print '** ', ','.join('%2d'%int(x) for x in l)

# example to collect an individual statistic for all evaluated classifiers
print "------------------------------------"
print "Example to collect an individual statistic for all evaluated classifiers"
print "Kappa"
for index in range(len(algo_keys)):
   evaluation = my_evaluations[index]
   key = algo_keys[index]
   algo = algo_dict[key]
   print algo.__class__.__name__ + ": " + str(evaluation.kappa())

# Example K fold cross validate model against training data

# 需要导入模块: from weka.classifiers import Evaluation [as 别名]
# 或者: from weka.classifiers.Evaluation import confusionMatrix [as 别名]
def runClassifierAlgo(algo, class_index, training_filename, test_filename, do_model, do_eval, do_predict):
    """ If <test_filename>
            Run classifier algorithm <algo> on training data in <training_filename> to build a model
            then test on data in <test_filename> (equivalent of Weka "Supplied test set") 
        else
            do 10 fold CV lassifier algorithm <algo> on data in <training_filename>
        
        <class_index> is the column containing the dependent variable 
        
        http://weka.wikispaces.com/Generating+classifier+evaluation+output+manually
        http://weka.sourceforge.net/doc.dev/weka/classifiers/Evaluation.html
    """
    print ' runClassifierAlgo: training_filename= ', training_filename, ', test_filename=', test_filename
    misc.checkExists(training_filename)

    training_file = FileReader(training_filename)
    training_data = Instances(training_file)
    if test_filename:
        test_file = FileReader(test_filename)
        test_data = Instances(test_file)
    else:
        test_data = training_data

   # set the class Index - the index of the dependent variable
    training_data.setClassIndex(class_index)
    test_data.setClassIndex(class_index)

    # create the model
    if test_filename:
        algo.buildClassifier(training_data)

    evaluation = None
    # only a trained classifier can be evaluated
    if do_eval or do_predict:
        evaluation = Evaluation(test_data)
        buffer = StringBuffer()             # buffer for the predictions
        attRange = Range()                  # no additional attributes output
        outputDistribution = Boolean(False) # we don't want distribution
        if test_filename:
            evaluation.evaluateModel(algo, test_data, [buffer, attRange, outputDistribution])
        else:
           # evaluation.evaluateModel(algo, [String('-t ' + training_filename), String('-c 1')])
           # print evaluation.toSummaryString()
            rand = Random(1)
            evaluation.crossValidateModel(algo, training_data, 4, rand)
            if False:
                print 'percentage correct =', evaluation.pctCorrect()
                print 'area under ROC =', evaluation.areaUnderROC(class_index)
                confusion_matrix = evaluation.confusionMatrix()
                for l in confusion_matrix:
                    print '** ', ','.join('%2d'%int(x) for x in l)

    if verbose:
        if do_model:
            print '--> Generated model:\n'
            print algo.toString()
        if do_eval:
            print '--> Evaluation:\n'
            print evaluation.toSummaryString()
        if do_predict:
            print '--> Predictions:\n'
            print buffer

    return {'model':str(algo), 'eval':str(evaluation.toSummaryString()), 'predict':str(buffer) }