classifiers.py 文件源码

def _calc_entropy(self, data_set):
        """
        compute the entropy of the data_set
        :param data_set: the data_set you want to calculator entropy
        :return: x, x is a numerical value represent the entropy
        """
        class_list = [example[-1] for example in data_set]
        unique_class = set(class_list)
        record_num = len(data_set)
        entropy = 0.0
        for item in unique_class:
            item_data = self._find_record_with_value(-1, data_set, item)
            probability = len(item_data) / record_num
            entropy -= probability * math.log2(probability)
        return entropy