当前位置: 首页>>代码示例>>Python>>正文


Python Document.read_document方法代码示例

本文整理汇总了Python中document.Document.read_document方法的典型用法代码示例。如果您正苦于以下问题:Python Document.read_document方法的具体用法?Python Document.read_document怎么用?Python Document.read_document使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在document.Document的用法示例。


在下文中一共展示了Document.read_document方法的4个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: Probability

# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import read_document [as 别名]
    def Probability(self, doc, dclass = ""):
        """Calculates the probability for a class dclass given a document doc"""
        if dclass:
            sum_dclass = self.sum_words_in_class(dclass)
            prob = 0

            d = Document(self.__vocabulary)
            d.read_document(doc)

            for j in self.__document_classes:
                sum_j = self.sum_words_in_class(j)
                prod = 1
                for i in d.Words():
                    wf_dclass = 1 + self.__document_classes[dclass].WordFreq(i)
                    wf = 1 + self.__document_classes[j].WordFreq(i)
                    r = wf * sum_dclass / (wf_dclass * sum_j)
                    prod *= r
                prob += prod * self.__document_classes[j].NumberOfDocuments() / self.__document_classes[dclass].NumberOfDocuments()
            if prob != 0:
                return 1 / prob
            else:
                return -1
        else:
            prob_list = []
            for dclass in self.__document_classes:
                prob = self.Probability(doc, dclass)
                prob_list.append([dclass,prob])
            prob_list.sort(key = lambda x: x[1], reverse = True)
            return prob_list
开发者ID:TechBK,项目名称:NLP,代码行数:31,代码来源:pool.py

示例2: DocumentIntersectionWithClasses

# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import read_document [as 别名]
 def DocumentIntersectionWithClasses(self, doc_name):
     res = [doc_name]
     for dc in self.__document_classes:
         d = Document(self.__vocabulary)
         d.read_document(doc_name, learn=False)
         o = self.__document_classes[dc] &  d
         intersection_ratio = len(o) / len(d.Words())
         res += (dc, intersection_ratio)
     return res
开发者ID:TechBK,项目名称:NLP,代码行数:11,代码来源:pool.py

示例3: learn

# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import read_document [as 别名]
 def learn(self, directory, dclass_name):
     """ directory is a path, where the files of the class with the name dclass_name can be found """
     x = DocumentClass(self.__vocabulary)
     dir = os.listdir(directory)
     for file in dir:
         d = Document(self.__vocabulary)
         print(directory + "/" + file)
         d.read_document(directory + "/" +  file, learn = True)
         x = x + d
     self.__document_classes[dclass_name] = x
     x.SetNumberOfDocs(len(dir))
开发者ID:TechBK,项目名称:NLP,代码行数:13,代码来源:pool.py

示例4: learn

# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import read_document [as 别名]
    def learn(self,directory,classname):
        x = DocumentClass()
        dir = os.listdir(directory)

        for file in dir:
            d = Document()
            print(directory + "/" + file)
            d.read_document(directory + "/" +  file)

            x = x + d
        self.__document_classes[classname] = x
        #print(len(dir))
        x.setNumberOfDocs(len(dir))
开发者ID:TechBK,项目名称:NLP-new,代码行数:15,代码来源:pool.py


注:本文中的document.Document.read_document方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。