Python TrainedDataの例

コード例 #1

ファイル: trainer.py プロジェクト: matiastafernaberry/charruanews

class Trainer(object):
    """docstring for Trainer"""
    def __init__(self, tokenizer):
        super(Trainer, self).__init__()
        #print dir(tokenizer)
        self.tokenizer = tokenizer
        self.data = TrainedData()
        #print dir(self.data)

    def train(self, text, className):
        """
        enhances trained data using the given text and class
        """
        self.data.increaseClass(className)

        tokens = self.tokenizer.tokenize(text)
        #print tokens
        a = []
        for token in tokens:
            #print "previo: " + token
            #token = token.strip()
            token = self.tokenizer.remove_stop_words(token)
            token = self.tokenizer.remove_punctuation(token)

            if (token != "stopword"):
                #print token
                a.append(token)

                self.data.increaseToken(token, className)

        print a

コード例 #2

ファイル: trainer.py プロジェクト: WhiteAndBlackFox/naive_bayes_classifier

class Trainer(object):
    def __init__(self, tokenizer):
        super(Trainer, self).__init__()
        self.tokenizer = tokenizer
        self.data = TrainedData()

    def train(self, text, className):
        self.data.increaseClass(className)

        tokens = self.tokenizer.tokenize(text)
        for token in tokens:
            token = self.tokenizer.remove_stop_words(token)
            token = self.tokenizer.remove_punctuation(token)
            self.data.increaseToken(token, className)

コード例 #3

ファイル: trainer.py プロジェクト: eliyaalfa/ML-NBCalgorithm

class Trainer(object):
    """docstring for Trainer"""
    def __init__(self, tokenizer):
        super(Trainer, self).__init__()
        self.tokenizer = tokenizer
        self.data = TrainedData()

    def train(self, text, className):
        """
        enhances trained data using the given text and class
        """
        self.data.increaseClass(className)

        tokens = self.tokenizer.tokenize(text)
        for token in tokens:
            self.data.increaseToken(token, className)

コード例 #4

ファイル: trainer.py プロジェクト: GeorgeMcIntire/naive-bayes-classifier

class Trainer(object):
    
    """docstring for Trainer"""
    def __init__(self, tokenizer):
        super(Trainer, self).__init__()
        self.tokenizer = tokenizer
        self.data = TrainedData()

    def train(self, text, className):
        """
        enhances trained data using the given text and class
        """
        self.data.increaseClass(className)
        
        tokens = self.tokenizer.tokenize(text)
        for token in tokens:
            self.data.increaseToken(token, className)

コード例 #5

 def __init__(self, tokenizer):
     super(Trainer, self).__init__()
     self.tokenizer = tokenizer
     self.data = TrainedData()