ggcorrplot|相关性矩阵可视化神器完整教程
欢迎来到医科研，这里是白介素2的读书笔记，跟我一起聊临床与科研的故事, 生物医学数据挖掘，R语言，TCGA、GEO, SEER数据挖掘。
-ggcorrplot可视化相关性矩阵-
ggcorrplot(): A graphical display of a correlation matrix using ggplot2.
cor_pmat(): 计算相关性矩阵 p-values.
ggcorrplot(corr, method = c(“square”, “circle”), type = c(“full”, “lower”, “upper”), ggtheme = ggplot2::theme_minimal, title = "“, show.legend = TRUE, legend.title =”Corr“, show.diag = FALSE, colors = c(”blue“,”white“,”red“), outline.color =”gray“, hc.order = FALSE, hc.method =”complete“, lab = FALSE, lab_col =”black“, lab_size = 4, p.mat = NULL, sig.level = 0.05, insig = c(”pch“,”blank“), pch = 4, pch.col =”black“, pch.cex = 5, tl.cex = 12, tl.col =”black", tl.srt = 45, digits = 2)
cor_pmat(x, …)
对象
ggcorrplot(): 返回 ggplot2对象
cor_pmat(): 返回相关系数矩阵pvalue
实例运用
计算相关系数矩阵
library(ggcorrplot)
## Loading required package: ggplot2
data(mtcars)
corr <- round(cor(mtcars), 1)
corr
## mpg cyl disp hp drat wt qsec vs am gear carb
## mpg 1.0 -0.9 -0.8 -0.8 0.7 -0.9 0.4 0.7 0.6 0.5 -0.6
## cyl -0.9 1.0 0.9 0.8 -0.7 0.8 -0.6 -0.8 -0.5 -0.5 0.5
## disp -0.8 0.9 1.0 0.8 -0.7 0.9 -0.4 -0.7 -0.6 -0.6 0.4
## hp -0.8 0.8 0.8 1.0 -0.4 0.7 -0.7 -0.7 -0.2 -0.1 0.7
## drat 0.7 -0.7 -0.7 -0.4 1.0 -0.7 0.1 0.4 0.7 0.7 -0.1
## wt -0.9 0.8 0.9 0.7 -0.7 1.0 -0.2 -0.6 -0.7 -0.6 0.4
## qsec 0.4 -0.6 -0.4 -0.7 0.1 -0.2 1.0 0.7 -0.2 -0.2 -0.7
## vs 0.7 -0.8 -0.7 -0.7 0.4 -0.6 0.7 1.0 0.2 0.2 -0.6
## am 0.6 -0.5 -0.6 -0.2 0.7 -0.7 -0.2 0.2 1.0 0.8 0.1
## gear 0.5 -0.5 -0.6 -0.1 0.7 -0.6 -0.2 0.2 0.8 1.0 0.3
## carb -0.6 0.5 0.4 0.7 -0.1 0.4 -0.7 -0.6 0.1 0.3 1.0
计算相关系数矩阵pvalue
p.mat <- cor_pmat(mtcars)
p.mat
## mpg cyl disp hp drat
## mpg 0.000000e+00 6.112687e-10 9.380327e-10 1.787835e-07 1.776240e-05
## cyl 6.112687e-10 0.000000e+00 1.802838e-12 3.477861e-09 8.244636e-06
## disp 9.380327e-10 1.802838e-12 0.000000e+00 7.142679e-08 5.282022e-06
## hp 1.787835e-07 3.477861e-09 7.142679e-08 0.000000e+00 9.988772e-03
## drat 1.776240e-05 8.244636e-06 5.282022e-06 9.988772e-03 0.000000e+00
## wt 1.293959e-10 1.217567e-07 1.222320e-11 4.145827e-05 4.784260e-06
## qsec 1.708199e-02 3.660533e-04 1.314404e-02 5.766253e-06 6.195826e-01
## vs 3.415937e-05 1.843018e-08 5.235012e-06 2.940896e-06 1.167553e-02
## am 2.850207e-04 2.151207e-03 3.662114e-04 1.798309e-01 4.726790e-06
## gear 5.400948e-03 4.173297e-03 9.635921e-04 4.930119e-01 8.360110e-06
## carb 1.084446e-03 1.942340e-03 2.526789e-02 7.827810e-07 6.211834e-01
## wt qsec vs am gear
## mpg 1.293959e-10 1.708199e-02 3.415937e-05 2.850207e-04 5.400948e-03
## cyl 1.217567e-07 3.660533e-04 1.843018e-08 2.151207e-03 4.173297e-03
## disp 1.222320e-11 1.314404e-02 5.235012e-06 3.662114e-04 9.635921e-04
## hp 4.145827e-05 5.766253e-06 2.940896e-06 1.798309e-01 4.930119e-01
## drat 4.784260e-06 6.195826e-01 1.167553e-02 4.726790e-06 8.360110e-06
## wt 0.000000e+00 3.388683e-01 9.798492e-04 1.125440e-05 4.586601e-04
## qsec 3.388683e-01 0.000000e+00 1.029669e-06 2.056621e-01 2.425344e-01
## vs 9.798492e-04 1.029669e-06 0.000000e+00 3.570439e-01 2.579439e-01
## am 1.125440e-05 2.056621e-01 3.570439e-01 0.000000e+00 5.834043e-08
## gear 4.586601e-04 2.425344e-01 2.579439e-01 5.834043e-08 0.000000e+00
## carb 1.463861e-02 4.536949e-05 6.670496e-04 7.544526e-01 1.290291e-01
## carb
## mpg 1.084446e-03
## cyl 1.942340e-03
## disp 2.526789e-02
## hp 7.827810e-07
## drat 6.211834e-01
## wt 1.463861e-02
## qsec 4.536949e-05
## vs 6.670496e-04
## am 7.544526e-01
## gear 1.290291e-01
## carb 0.000000e+00
可视化相关系数矩阵
# method = "square" or "circle"
ggcorrplot(corr)
ggcorrplot(corr, method = "circle")
相关系数矩阵层次聚类
# Reordering the correlation matrix
# --------------------------------
# using hierarchical clustering
ggcorrplot(corr, hc.order = TRUE, outline.color = "white")
下三角导出
# Types of correlogram layout
# --------------------------------
# Get the lower triangle
ggcorrplot(corr,
hc.order = TRUE, type = "lower",
outline.color = "white"# 鸽子边缘颜色
)
上三角导出
# Get the upeper triangle
ggcorrplot(corr,
hc.order = TRUE, type = "upper",
outline.color = "white"
)
改变颜色和主题
# Change colors and theme
# --------------------------------
# Argument colors
ggcorrplot(corr,
hc.order = TRUE, type = "lower",
outline.color = "white",
ggtheme = ggplot2::theme_gray,
colors = c("#6D9EC1", "white", "#E46726")
)
增加相关性系数
# Add correlation coefficients
# --------------------------------
# argument lab = TRUE
ggcorrplot(corr,
hc.order = TRUE, type = "lower",
lab = TRUE,## 显示相关性系数
ggtheme = ggplot2::theme_dark(),
)
增加统计学水平
# Add correlation significance level
# --------------------------------
# Argument p.mat
# Barring the no significant coefficient
ggcorrplot(corr,
hc.order = TRUE,
type = "lower", p.mat = p.mat
)
未达统计学水平则空白
# Leave blank on no significant coefficient
ggcorrplot(corr,
p.mat = p.mat, hc.order = TRUE,
type = "lower", insig = "blank"
)
改变相关性系数小数点
# Changing number of digits for correlation coeffcient
# --------------------------------
ggcorrplot(cor(mtcars),
type = "lower",
insig = "blank",
lab = TRUE,
digits = 3
)
参考资料
官方文档