Python ProgressCounter.endUpdate方法代码示例

# 需要导入模块: from Utils.ProgressCounter import ProgressCounter [as 别名]
# 或者: from Utils.ProgressCounter.ProgressCounter import endUpdate [as 别名]
def compareExamples(examples1, examples2, features1, features2=None):
    ExampleUtils.readExamples(examples1)
    exampleIter1 = ExampleUtils.readExamples(examples1)
    exampleIter2 = ExampleUtils.readExamples(examples2)
    features1 = IdSet(filename=features1)
    if features2 != None:
        features2 = IdSet(filename=features2)
    else:
        features2 = features1
    # Compare feature sets
    if set(features1.Ids.keys()) != set(features2.Ids.keys()):
        print "Feature sets differ"
    # Compare examples
    counter = ProgressCounter(step=1)
    for e1, e2 in itertools.izip(exampleIter1, exampleIter2):
        counter.update()
        assert e1[0] == e2[0], (removeFeatures(e1), removeFeatures(e2))
        if e1[1] != e2[1]:
            print "Class differs"
            print "  E1", removeFeatures(e1)
            print "  E2", removeFeatures(e2)
        f1 = getFeatureNames(e1, features1)
        f2 = getFeatureNames(e2, features2)
        f1Set = set(f1)
        f2Set = set(f2)
        f1Only = f1Set.difference(f2Set)
        f2Only = f2Set.difference(f1Set)
        if len(f1Only) > 0 or len(f2Only) > 0:
            print "Features differ"
            print "  E1", removeFeatures(e1)
            print "  E2", removeFeatures(e2)
            if len(f1Only) > 0:
                print "  E1-only features:", f1Only
            if len(f2Only) > 0:
                print "  E2-only features:", f2Only
        else:
            assert len(f1) == len(f2)
            fCount = 0
            differ = False
            for feature1, feature2 in zip(f1, f2):
                #f1Id = features1.getId(feature1, createIfNotExist=False)
                #if f1Id == 454 or feature1 == "e1_strength_Positive_regulation":
                #    print "!!!!!!!!!!!", 454, feature1, e1[2][f1Id]
                if feature1 != feature2:
                    if not differ:
                        print "Feature order differs for example", e1[0]
                        differ = True
                    print "[" + feature1 + "/" + feature2 + "](" + str(fCount) + ") ",
                else:
                    f1Id = features1.getId(feature1, createIfNotExist=False)
                    f2Id = features2.getId(feature2, createIfNotExist=False)
                    f1Value = e1[2][f1Id]
                    f2Value = e2[2][f2Id]
                    if f1Value != f2Value:
                        if not differ:
                            print "Feature values differ", e1[0]
                            differ = True
                        print "[" + feature1 + "/" + str(f1Id) + "]" + "[" + str(f1Value) + "/" + str(f2Value) + "]" + "(" + str(fCount) + ") ",
                fCount += 1              
            if differ:
                print
    counter.endUpdate()

# 需要导入模块: from Utils.ProgressCounter import ProgressCounter [as 别名]
# 或者: from Utils.ProgressCounter.ProgressCounter import endUpdate [as 别名]

#.........这里部分代码省略.........
        if output.endswith(".gz"):
            outfile = gzip.open(output, openStyle)
        else:
            outfile = open(output, openStyle)
        
        # Build examples
        self.exampleCount = 0
        if type(input) in types.StringTypes:
            self.elementCounts = self.getElementCounts(input)
            if self.elementCounts["sentences"] > 0:
                self.progress = ProgressCounter(self.elementCounts["sentences"], "Build examples")
            else:
                self.elementCounts = None
                self.progress = ProgressCounter(None, "Build examples")
        else:
            self.elementCounts = None
            self.progress = ProgressCounter(None, "Build examples")
        
        self.calculatePredictedRange(self.getSentences(input, self.parse, self.tokenization))
        
        inputIterator = getCorpusIterator(input, None, self.parse, self.tokenization)            
        
        #goldIterator = []
        if gold != None:
            goldIterator = getCorpusIterator(gold, None, self.parse, self.tokenization)
            for inputSentences, goldSentences in itertools.izip_longest(inputIterator, goldIterator, fillvalue=None):
                assert inputSentences != None
                assert goldSentences != None
                self.processDocument(inputSentences, goldSentences, outfile)
        else:
            for inputSentences in inputIterator:
                self.processDocument(inputSentences, None, outfile)
        outfile.close()
        self.progress.endUpdate()
        
        # Show statistics
        print >> sys.stderr, "Examples built:", self.exampleCount
        print >> sys.stderr, "Features:", len(self.featureSet.getNames())
        if self.exampleStats.getExampleCount() > 0:
            self.exampleStats.printStats()
    
        # Save Ids
        if allowNewIds:
            self.saveIds()
    
    def processDocument(self, sentences, goldSentences, outfile):
        #calculatePredictedRange(self, sentences)            
        for i in range(len(sentences)):
            sentence = sentences[i]
            goldSentence = None
            if goldSentences != None:
                goldSentence = goldSentences[i]
            self.progress.update(1, "Building examples ("+sentence.sentence.get("id")+"): ")
            self.processSentence(sentence, outfile, goldSentence)
    
    def processSentence(self, sentence, outfile, goldSentence=None):
        if sentence.sentenceGraph != None:
            goldGraph = None
            if goldSentence != None:
                goldGraph = goldSentence.sentenceGraph
            self.exampleCount += self.buildExamplesFromGraph(sentence.sentenceGraph, outfile, goldGraph)

    @classmethod
    def run(cls, input, output, parse, tokenization, style, classIds=None, featureIds=None, gold=None, append=False, allowNewIds=True):
        print >> sys.stderr, "Running", cls.__name__
        print >> sys.stderr, "  input:", input