Python IdSet.write方法代码示例

# 需要导入模块: from Core.IdSet import IdSet [as 别名]
# 或者: from Core.IdSet.IdSet import write [as 别名]
class ExampleBuilder:
    structureAnalyzer = None
    """ 
    ExampleBuilder is the abstract base class for specialized example builders.
    Example builders take some data and convert it to examples usable by e.g. SVMs.
    An example builder writes three files, an example-file (in extended Joachim's
    SVM format) and .class_names and .feature_names files, which contain the names
    for the class and feature id-numbers. An example builder can also be given
    pre-existing sets of class and feature ids (optionally in files) so that the
    generated examples are consistent with other, previously generated examples.
    """    
    def __init__(self, classSet=None, featureSet=None):
        if(type(classSet) == types.StringType):
            self.classSet = IdSet(filename=classSet)
        else:
            self.classSet = classSet
        
        if(type(featureSet) == types.StringType):
            self.featureSet = IdSet(filename=featureSet)
        else:
            self.featureSet = featureSet
        
        self.featureTag = ""      
        self.exampleStats = ExampleStats()
        self.parse = None
        self.tokenization = None
        #self.idFileTag = None
        self.classIdFilename = None
        self.featureIdFilename = None
        
        self.styles = None
        self._defaultParameters = None
        self._parameterValueLimits = None
        self._setDefaultParameters(["sentenceLimit"])
        self.debug = False
    
    def _setDefaultParameters(self, defaults=None, valueLimits=None):
        # Initialize
        if self._defaultParameters == None:
            self._defaultParameters = {}
        if self._parameterValueLimits == None:
            self._parameterValueLimits = {}
        newParameters = Utils.Parameters.get({}, defaults, valueLimits=valueLimits)
        self._defaultParameters.update(newParameters)
        if valueLimits != None:
            self._parameterValueLimits.update(valueLimits)
    
    def getParameters(self, parameters):
        return Utils.Parameters.get(parameters, defaults=self._defaultParameters, valueLimits=self._parameterValueLimits)
    
    def setFeature(self, name, value):
        self.features[self.featureSet.getId(self.featureTag+name)] = value
    
    def getElementCounts(self, filename):
        print >> sys.stderr, "Counting elements:",
        if filename.endswith(".gz"):
            f = gzip.open(filename, "rt")
        else:
            f = open(filename, "rt")
        counts = {"documents":0, "sentences":0}
        for line in f:
            if "<document" in line:
                counts["documents"] += 1
            elif "<sentence" in line:
                counts["sentences"] += 1
        f.close()
        print >> sys.stderr, counts
        return counts

    def saveIds(self):
        if self.classIdFilename != None:
            print >> sys.stderr, "Saving class names to", self.classIdFilename
            self.classSet.write(self.classIdFilename)
        else:
            print >> sys.stderr, "Class names not saved"
        if self.featureIdFilename != None:
            print >> sys.stderr, "Saving feature names to", self.featureIdFilename
            self.featureSet.write(self.featureIdFilename)
        else:
            print >> sys.stderr, "Feature names not saved"

    def processCorpus(self, input, output, gold=None, append=False, allowNewIds=True, structureAnalyzer=None):
        # Create intermediate paths if needed
        if os.path.dirname(output) != "" and not os.path.exists(os.path.dirname(output)):
            os.makedirs(os.path.dirname(output))
        # Open output file
        openStyle = "wt"
        if append:
            #print "Appending examples"
            openStyle = "at"
        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:
#.........这里部分代码省略.........

# 需要导入模块: from Core.IdSet import IdSet [as 别名]
# 或者: from Core.IdSet.IdSet import write [as 别名]
            ExampleUtils.appendExamples(exampleCache, outFile)
            exampleCache = []
    ExampleUtils.appendExamples(exampleCache, outFile)
    outFile.close()
    print "Added", addCount, "polynomial features"

if __name__=="__main__":
    # Import Psyco if available
    try:
        import psyco
        psyco.full()
        print >> sys.stderr, "Found Psyco, using"
    except ImportError:
        print >> sys.stderr, "Psyco not installed"
        
    from optparse import OptionParser # For using command line options
    optparser = OptionParser()
    optparser.add_option("-i", "--ids", default=None, dest="ids", help="")
    optparser.add_option("-e", "--examples", default=None, dest="examples", help="")
    optparser.add_option("-j", "--idOutput", default=None, dest="idOutput", help="")
    optparser.add_option("-o", "--output", default=None, dest="output", help="")
    optparser.add_option("-w", "--weights", default=None, dest="weights", help="")
    optparser.add_option("-c", "--cutoff", type="float", default=10.0, dest="cutoff", help="")
    (options, args) = optparser.parse_args()

    #classIds = IdSet(filename="/usr/share/biotext/GeniaChallenge/extension-data/genia/edge-examples/genia-edge-ids.class_names")
    featureIds = IdSet(filename=options.ids)
    weightFeatures = readWeights(options.weights, options.cutoff)
    polynomizeExamples(options.examples, options.output, weightFeatures, featureIds)
    featureIds.write(options.idOutput)

# 需要导入模块: from Core.IdSet import IdSet [as 别名]
# 或者: from Core.IdSet.IdSet import write [as 别名]
       "Localization", 
       "Negative_regulation", 
       "Phosphorylation", 
       "Positive_regulation", 
       "Protein_catabolism", 
       "Regulation", 
       "Transcription"]

classSet = IdSet(filename=TRIGGER_IDS+".class_names")
for triggerClass in triggerClasses:
    makeOneClassExamples(TRIGGER_TRAIN_EXAMPLE_FILE, TRIGGER_TRAIN_EXAMPLE_FILE + "-" + triggerClass, triggerClass, classSet)
    makeOneClassExamples(TRIGGER_TEST_EXAMPLE_FILE, TRIGGER_TEST_EXAMPLE_FILE + "-" + triggerClass, triggerClass, classSet)
    d = {"neg":1, triggerClass:classSet.getId(triggerClass, False)}
    triggerClassIds = IdSet(idDict = d)
    TRIGGER_CLASS_IDS = "trigger-ids-"+triggerClass+".class_names"
    triggerClassIds.write(TRIGGER_CLASS_IDS)

    print >> sys.stderr, "Trigger models for parse", PARSE_TAG, "for class", triggerClass
    TRIGGER_CLASSIFIER_PARAMS="c:" + options.triggerParams
    if "local" not in options.csc:
        clear = False
        if "clear" in options.csc: clear = True
        if "louhi" in options.csc:
            c = CSCConnection(CSC_WORKDIR+"/trigger-models-"+triggerClass, "[email protected]", clear)
        else:
            c = CSCConnection(CSC_WORKDIR+"/trigger-models-"+triggerClass, "[email protected]", clear)
    else:
        c = None
    bestTriggerModel = optimize(CLASSIFIER, Ev, TRIGGER_TRAIN_EXAMPLE_FILE+"-"+triggerClass, TRIGGER_TEST_EXAMPLE_FILE+"-"+triggerClass,\
        TRIGGER_CLASS_IDS, TRIGGER_CLASSIFIER_PARAMS, "trigger-models-"+triggerClass, None, c, False)[1]