放假期間我們學(xué)習(xí)一下基礎(chǔ)的東西

Corrplot軟件包簡介

介紹

所述corrplot包是相關(guān)矩陣，置信區(qū)間的圖形顯示。它還包含一些進(jìn)行矩陣重新排序的算法。另外，corrplot擅長細(xì)節(jié)，包括選擇顏色，文本標(biāo)簽，顏色標(biāo)簽，布局等。

可視化方法

有七個可視化方法（參數(shù)method中）corrplot包，命名"circle"，"square"，"ellipse"，"number"，"shade"，"color"，"pie"。

正相關(guān)以藍(lán)色顯示，負(fù)相關(guān)以紅色顯示。顏色強(qiáng)度和圓圈的大小與相關(guān)系數(shù)成正比。

library(corrplot)

## corrplot 0.84 loaded

M <- cor(mtcars)

corrplot(M, method = "circle")

image

corrplot(M, method = "square")

image

corrplot(M, method = "ellipse")

image

corrplot(M, method = "number") # Display the correlation coefficient

image

corrplot(M, method = "shade")

image

corrplot(M, method = "color")

image

corrplot(M, method = "pie")

image

布局

共有三種布局類型（參數(shù)type）：

• "full"（默認(rèn)）：顯示完整的相關(guān)矩陣
• "upper"：顯示相關(guān)矩陣的上三角
• "lower"：顯示相關(guān)矩陣的下三角

corrplot(M, type = "upper")

image

corrplot.mixed() 是混合可視化樣式的包裝函數(shù)。

corrplot.mixed(M)

image

corrplot.mixed(M, lower.col = "black", number.cex = .7)

image

corrplot.mixed(M, lower = "ellipse", upper = "circle")

image

corrplot.mixed(M, lower = "square", upper = "circle", tl.col = "black")

image

重新排序相關(guān)矩陣

相關(guān)矩陣可以根據(jù)相關(guān)系數(shù)重新排序。這對于確定矩陣中隱藏的結(jié)構(gòu)和圖案很重要。有在corrplot（參數(shù)四種方法order）的名字命名 "AOE"，"FPC"，"hclust"，"alphabet"。在序列化包中可以找到更多算法 。

您還可以通過function手動“重新排序”矩陣corrMatOrder()。

• "AOE"一個我ai

  a i = { 棕褐色（e i 2 / e i 1），如果 ? 我1 > 0 ;棕褐色（e i 2 / e i 1）+ π ，除此以外。ai={tan?(ei2/ei1),if ei1>0;tan?(ei2/ei1)+π,otherwise.

  ? 1e1? 2e2

• "FPC" 對于第一個主成分訂單。

• "hclust"層次聚類順序，以及"hclust.method"要使用的聚集方法。"hclust.method"應(yīng)該是一個 "ward"，"single"，"complete"，"average"，"mcquitty"，"median"或 "centroid"。

• "alphabet" 按字母順序排列。

corrplot(M, order = "AOE")

image

corrplot(M, order = "hclust")

image

corrplot(M, order = "FPC")

image

corrplot(M, order = "alphabet")

image

如果使用"hclust"，則corrplot()可以基于層次聚類的結(jié)果在相關(guān)矩陣圖的周圍繪制矩形。

corrplot(M, order = "hclust", addrect = 2)

image

corrplot(M, order = "hclust", addrect = 3)

image

Change background color to lightblue

corrplot(M, type = "upper", order = "hclust",

col = c("black", "white"), bg = "lightblue")

image

使用不同的色譜

col1 <- colorRampPalette(c("#7F0000", "red", "#FF7F00", "yellow", "white",
                           "cyan", "#007FFF", "blue", "#00007F"))
col2 <- colorRampPalette(c("#67001F", "#B2182B", "#D6604D", "#F4A582",
                           "#FDDBC7", "#FFFFFF", "#D1E5F0", "#92C5DE",
                           "#4393C3", "#2166AC", "#053061"))
col3 <- colorRampPalette(c("red", "white", "blue")) 
col4 <- colorRampPalette(c("#7F0000", "red", "#FF7F00", "yellow", "#7FFF7F",
                           "cyan", "#007FFF", "blue", "#00007F"))
whiteblack <- c("white", "black")
## using these color spectra
corrplot(M, order = "hclust", addrect = 2, col = col1(100))

image

corrplot(M, order = "hclust", addrect = 2, col = col2(50))

image

corrplot(M, order = "hclust", addrect = 2, col = col3(20))

image

corrplot(M, order = "hclust", addrect = 2, col = col4(10))

image

corrplot(M, order = "hclust", addrect = 2, col = whiteblack, bg = "gold2")

image

還可以使用標(biāo)準(zhǔn)調(diào)色板（包grDevices）

corrplot(M, order = "hclust", addrect = 2, col = heat.colors(100))

image

corrplot(M, order = "hclust", addrect = 2, col = terrain.colors(100))

image

corrplot(M, order = "hclust", addrect = 2, col = cm.colors(100))

image

corrplot(M, order = "hclust", addrect = 2, col = gray.colors(100))

image

其他選擇是使用RcolorBrewer包。

library(RColorBrewer)

corrplot(M, type = "upper", order = "hclust",

col = brewer.pal(n = 8, name = "RdBu"))

image

corrplot(M, type = "upper", order = "hclust",

col = brewer.pal(n = 8, name = "RdYlBu"))

image

corrplot(M, type = "upper", order = "hclust",

col = brewer.pal(n = 8, name = "PuOr"))

image

更改文本標(biāo)簽和圖例的顏色和旋轉(zhuǎn)

參數(shù)cl.*用于顏色圖例，tl.*如果用于文本圖例。對于文本標(biāo)簽，tl.col（文本標(biāo)簽顏色）和tl.srt（文本標(biāo)簽字符串旋轉(zhuǎn)）用于更改文本顏色和旋轉(zhuǎn)。

這里有些例子。

## remove color legend and text legend 

corrplot(M, order = "AOE", cl.pos = "n", tl.pos = "n")

image

## bottom  color legend, diagonal text legend, rotate text label

corrplot(M, order = "AOE", cl.pos = "b", tl.pos = "d", tl.srt = 60)

image

## a wider color legend with numbers right aligned

corrplot(M, order = "AOE", cl.ratio = 0.2, cl.align = "r")

image

 ## text labels rotated 45 degrees

corrplot(M, type = "lower", order = "hclust", tl.col = "black", tl.srt = 45)

image

處理非相關(guān)矩陣

corrplot(abs(M),order = "AOE", col = col3(200), cl.lim = c(0, 1))

image

## visualize a  matrix in [-100, 100]

ran <- round(matrix(runif(225, -100,100), 15))

corrplot(ran, is.corr = FALSE, method = "square")

image

## a beautiful color legend 

corrplot(ran, is.corr = FALSE, method = "ellipse", cl.lim = c(-100, 100))

image

如果矩陣是矩形，則可以使用win.asp參數(shù)調(diào)整縱橫比， 以使矩陣呈現(xiàn)為正方形。

ran <- matrix(rnorm(70), ncol = 7)

corrplot(ran, is.corr = FALSE, win.asp = .7, method = "circle")

image

處理缺失（NA）值

默認(rèn)情況下，corrplot將NA值呈現(xiàn)為"?"字符。使用na.label 參數(shù)，可以使用不同的值（最多支持兩個字符）。

M2 <- M

diag(M2) = NA

corrplot(M2)

image

corrplot(M2, na.label = "o")

image

corrplot(M2, na.label = "NA")

image

在標(biāo)簽中使用“ plotmath”表達(dá)式

從version開始0.78，可以 在變量名稱中使用 plotmath表達(dá)式。要激活plotmath渲染，前綴的人物之一的標(biāo)簽":"，"="或"$"。

M2 <- M[1:5,1:5]

colnames(M2) <- c("alpha", "beta", ":alpha+beta", ":a[0]", "=a[beta]")

rownames(M2) <- c("alpha", "beta", NA, "$a[0]", "$ a[beta]")

corrplot(M2)

image

將相關(guān)圖與顯著性檢驗相結(jié)合

res1 <- cor.mtest(mtcars, conf.level = .95)

res2 <- cor.mtest(mtcars, conf.level = .99)

 ## specialized the insignificant value according to the significant level

corrplot(M, p.mat = res1$p, sig.level = .2)

image

corrplot(M, p.mat = res1$p, sig.level = .05)

image

corrplot(M, p.mat = res1$p, sig.level = .01)

image

## leave blank on no significant coefficient

corrplot(M, p.mat = res1$p, insig = "blank")

image

 ## add p-values on no significant coefficient

corrplot(M, p.mat = res1$p, insig = "p-value")

image

## add all p-values

corrplot(M, p.mat = res1$p, insig = "p-value", sig.level = -1)

image

 ## add cross on no significant coefficient 

corrplot(M, p.mat = res1$p, order = "hclust", insig = "pch", addrect = 3)

image

可視化置信區(qū)間

corrplot(M, low = res1$lowCI, upp = res1$uppCI, order = "hclust",

rect.col = "navy", plotC = "rect", cl.pos = "n")

image

corrplot(M, p.mat = res1$p, low = res1$lowCI, upp = res1$uppCI,

order = "hclust", pch.col = "red", sig.level = 0.01,

addrect = 3, rect.col = "navy", plotC = "rect", cl.pos = "n")

image

res1 <- cor.mtest(mtcars, conf.level = .95)

corrplot(M, p.mat = res1$p, insig = "label_sig",

sig.level = c(.001, .01, .05), pch.cex = .9, pch.col = "white")

image

corrplot(M, p.mat = res1$p, method = "color",

insig = "label_sig", pch.col = "white")

image

corrplot(M, p.mat = res1$p, method = "color", type = "upper",

sig.level = c(.001, .01, .05), pch.cex = .9,

insig = "label_sig", pch.col = "white", order = "AOE")

image

corrplot(M, p.mat = res1$p, insig = "label_sig", pch.col = "white",

pch = "p<.05", pch.cex = .5, order = "AOE")

image

自定義相關(guān)圖

# matrix of the p-value of the correlation

p.mat <- cor.mtest(mtcars)$p

head(p.mat[, 1:5])

##              [,1]         [,2]         [,3]         [,4]         [,5]

## [1,] 0.000000e+00 6.112687e-10 9.380327e-10 1.787835e-07 1.776240e-05

## [2,] 6.112687e-10 0.000000e+00 1.802838e-12 3.477861e-09 8.244636e-06

## [3,] 9.380327e-10 1.802838e-12 0.000000e+00 7.142679e-08 5.282022e-06

## [4,] 1.787835e-07 3.477861e-09 7.142679e-08 0.000000e+00 9.988772e-03

## [5,] 1.776240e-05 8.244636e-06 5.282022e-06 9.988772e-03 0.000000e+00

## [6,] 1.293959e-10 1.217567e-07 1.222320e-11 4.145827e-05 4.784260e-06

# Specialized the insignificant value according to the significant level

corrplot(M, type = "upper", order = "hclust", 

p.mat = p.mat, sig.level = 0.01)

image

# Leave blank on no significant coefficient

corrplot(M, type = "upper", order = "hclust", 

p.mat = p.mat, sig.level = 0.01, insig = "blank")

image

在上圖中，p值> 0.01的相關(guān)被認(rèn)為是無關(guān)緊要的。在這種情況下，相關(guān)系數(shù)值留為空白或添加叉號。

col <- colorRampPalette(c("#BB4444", "#EE9988", "#FFFFFF", "#77AADD", "#4477AA"))

corrplot(M, method = "color", col = col(200),

type = "upper", order = "hclust", number.cex = .7,

addCoef.col = "black", # Add coefficient of correlation

tl.col = "black", tl.srt = 90, # Text label color and rotation

# Combine with significance

p.mat = p.mat, sig.level = 0.01, insig = "blank", 

# hide correlation coefficient on the principal diagonal

diag = FALSE)

image

探索大型功能矩陣

# generating large feature matrix (cols=features, rows=samples)

num_features <- 60 # how many features

num_samples <- 300 # how many samples

DATASET <- matrix(runif(num_features * num_samples),

 nrow = num_samples, ncol = num_features)

# setting some dummy names for the features e.g. f23

colnames(DATASET) <- paste0("f", 1:ncol(DATASET))

 # let's make 30% of all features to be correlated with feature "f1"

 num_feat_corr <- num_features * .3

 idx_correlated_features <- as.integer(seq(from = 1,

to = num_features,

 length.out = num_feat_corr))[-1]

 for (i in idx_correlated_features) {

DATASET[,i] <- DATASET[,1] + runif(num_samples) # adding some noise

  }

 corrplot(cor(DATASET), diag = FALSE, order = "FPC",

tl.pos = "td", tl.cex = 0.5, method = "color", type = "upper")

image

生活很好，等你超越