WOLFRAM

Wolfram 语言与系统参考资料中心

CorrelationDistance[u,v]

给出向量 u 和 v 之间的相关系数位距.

更多信息
Details and Options Details and Options
范例  
基本范例  
范围  
应用  
属性和关系  
参见
技术笔记
相关指南
历史
按以下格式引用：

CorrelationDistance

CorrelationDistance[u,v]

给出向量 u 和 v 之间的相关系数位距.

更多信息

范例

打开所有单元 关闭所有单元

基本范例  (2)

两个向量之间的相关位距：

Wolfram Language code: CorrelationDistance[{a, b, c}, {x, y, z}]

两个数值向量之间的相关位距：

Wolfram Language code: CorrelationDistance[{1, 2, 3}, {3, 5, 10}]

范围  (2)

计算相等长度的任何向量之间的位距：

Wolfram Language code: CorrelationDistance[RandomReal[5, 100], RandomReal[5, 100]]

计算任何精度的向量之间的位距：

Wolfram Language code: CorrelationDistance[N[{1, 5, 2, 3, 10}, 50], N[{4, 15, 20, 5, 5}, 50]]

应用  (1)

使用相关位距的聚类数据：

Wolfram Language code: FindClusters[{{2, 3}, {5, 10}, {4, 5}, {2, 2}}, DistanceFunction -> CorrelationDistance]

属性和关系  (3)

相关位距包括根据范数调整的点积：

Wolfram Language code: u = {a, b, c}; v = {x, y, z};
Wolfram Language code: 1 - (u - Mean[u]).(v - Mean[v]) / (Norm[u - Mean[u]]Norm[v - Mean[v]])
Wolfram Language code: CorrelationDistance[u, v] == %

相关位距包括由从均值确定的欧几里德位距的点积：

Wolfram Language code: u = {a, b, c}; v = {x, y, z};
Wolfram Language code: scale = (EuclideanDistance[u, Mean[u]]EuclideanDistance[v, Mean[v]])
Wolfram Language code: CorrelationDistance[u, v] == 1 - (u - Mean[u]).(v - Mean[v]) / scale

CorrelationDistance 等价于向量的 CosineDistance 进行大小为其均值的平移：

Wolfram Language code: u = {a, b, c}; v = {x, y, z};
Wolfram Language code: CorrelationDistance[u, v] == CosineDistance[u - Mean[u], v - Mean[v]]
Wolfram Research (2007)，CorrelationDistance，Wolfram 语言函数，https://reference.wolfram.com/language/ref/CorrelationDistance.html.

文本

Wolfram Research (2007)，CorrelationDistance，Wolfram 语言函数，https://reference.wolfram.com/language/ref/CorrelationDistance.html.

CMS

Wolfram 语言. 2007. "CorrelationDistance." Wolfram 语言与系统参考资料中心. Wolfram Research. https://reference.wolfram.com/language/ref/CorrelationDistance.html.

APA

Wolfram 语言. (2007). CorrelationDistance. Wolfram 语言与系统参考资料中心. 追溯自 https://reference.wolfram.com/language/ref/CorrelationDistance.html 年

BibTeX

@misc{reference.wolfram_2026_correlationdistance, author="Wolfram Research", title="{CorrelationDistance}", year="2007", howpublished="\url{https://reference.wolfram.com/language/ref/CorrelationDistance.html}", note=[Accessed: 13-September-2026]}

BibLaTeX

@online{reference.wolfram_2026_correlationdistance, organization={Wolfram Research}, title={CorrelationDistance}, year={2007}, url={https://reference.wolfram.com/language/ref/CorrelationDistance.html}, note=[Accessed: 13-September-2026]}