tree n. 特里〔姓氏〕。 n. 1.树〔主要指乔木,也可指较大的灌木〕。 ★玫瑰可以称为 bush, 也可以称为 tree. 2.木料,木材;木构件;〔古语〕绞首台;〔the tree〕(钉死耶稣的)十字架;鞋楦。 3.树形(物),世系图,家系 (=family tree);【数学】树(形);【化学】树状晶体。 a banana tree 香蕉树。 an axle-tree 心棒,轴料。 a boot-tree 靴楦[型]。 a saddle-tree 鞍架。 at the top of the tree 在最高地位。 tree of Buddha 菩提树。 tree of heaven 臭椿。 tree of knowledge (of good and evil) 【圣经】知道善恶的树,智慧之树。 tree of life 生命之树,生命力的源泉【植物;植物学】金钟柏。 up a tree 〔口语〕进退两难,不知所措。 vt. 赶(猎兽等)上树躲避;〔口语〕使处于困境;穷追;把鞋型插入(鞋内)。
Application of classification tree in credit risk analysis 递归分类树在信用风险分析中的应用
In this paper, we propose a modified minimize entropy principle approach ( mmepa ) and extract classification rule, and then build the classification tree model 在这里,提出一种基于mmepa(改进的最小熵原理方法)的决策树构造方法,并通过一个实例对其进行说明,用此方法提取分类规则,构造决策树模型。
This study employed six data mining methods, including logistic regression, discriminant analysis, artificial neural networks, k-nearest-neighbors, na ? ve bayes classifier, and classification trees, to find the most important factors of earthquake-caused landslide 本研究利用六种资料探勘方法,包括逻辑回归、判别分析、类神经网络、最近邻法、贝氏分类器、分类树,探讨影响地震引起山崩的重要因子。
To be dealed agaist extended data, this thesis has improved on and come true arithmetic of time sequence model, and amended conventional decision tree arithmetic, introduced the decision tree arithmetic for extended data, namely threshold value control approach . according to threshold value and concept hierarchy, threshold value control approach can set up the concise and statistic classification tree . at the same time, based on the theory of the concept lattice, this thesis introduces the arithmetic of mining association rules based on quantified concept lattice reduced by uncertainty coefficient 针对泛化后的数据,本文改进并实现时间序列模式发现算法;修改了传统的决策树算法,提出了一种适合于泛化数据的决策树构造算法:阈值控制法,阈值控制法通过阈值和概念层次的控制,可以建立简洁明了、具有统计意义的分类树;在概念格理论基础上提出了基于不确定系数法挖掘关联规则的算法。
This study uses classification tree to 1 . choose important variables for delivery launder, 2 . rank the importance of variables, and 3 . classify three levels of quantity of launder and examine under what conditions of variables for high level consuming class of laundry by analyzing the multiple response tables to provide a reference of marketing stratagem 本研究利用分类树多变量统计探究技术做:一、筛选影响衣物外洗件数多寡之相关变数,二、排序各个变数的重要性,三、将外洗量之多寡分成三个等级,由分析多变反应交叉表,可以得到每一个等级是在那些变数的那些条件下发生的,以供作洗衣业者对未来行销策略规划参考之依据。