• 火狐截图_2020-02-11T08-36-22.554Z.png

ggplot2 : Quick correlation matrix heatmap - R software and data visualization

ggplot2：速绘相关性矩阵热图-R软件和数据可视化

1. 构建数据

rm(list = ls())
library(ggplot2)
mydata <- mtcars[, c(1, 3, 4, 5, 6, 7)]
head(mydata)
                   mpg disp  hp drat    wt  qsec
Mazda RX4         21.0  160 110 3.90 2.620 16.46
Mazda RX4 Wag     21.0  160 110 3.90 2.875 17.02
Datsun 710        22.8  108  93 3.85 2.320 18.61
Hornet 4 Drive    21.4  258 110 3.08 3.215 19.44
Hornet Sportabout 18.7  360 175 3.15 3.440 17.02
Valiant           18.1  225 105 2.76 3.460 20.22

#compute the correlation matrix
cormat <- round(cor(mydata), 2)
head(cormat)
       mpg  disp    hp  drat    wt  qsec
mpg   1.00 -0.85 -0.78  0.68 -0.87  0.42
disp -0.85  1.00  0.79 -0.71  0.89 -0.43
hp   -0.78  0.79  1.00 -0.45  0.66 -0.71
drat  0.68 -0.71 -0.45  1.00 -0.71  0.09
wt   -0.87  0.89  0.66 -0.71  1.00 -0.17
qsec  0.42 -0.43 -0.71  0.09 -0.17  1.00

#create the correlation heatmap with ggplot2
library(reshape2)
melted_cormat <- melt(cormat)
head(melted_cormat)
  Var1 Var2 value
1  mpg  mpg  1.00
2 disp  mpg -0.85
3   hp  mpg -0.78
4 drat  mpg  0.68
5   wt  mpg -0.87
6 qsec  mpg  0.42

2. 默认绘图 geom_tile()

#The function geom_tile()[ggplot2 package] is used to visualize the correlation matrix :
ggplot(data = melted_cormat, aes(x=Var1, y=Var2, fill=value)) +
  geom_tile()

• Rplot01.png

3. 重塑数据(上三角)

# Get upper triangle of the correlation matrix
get_upper_tri <- function(cormat){
  cormat[lower.tri(cormat)]<- NA
  return(cormat)
}
upper_tri <- get_upper_tri(cormat)
upper_tri
     mpg  disp    hp  drat    wt  qsec
mpg    1 -0.85 -0.78  0.68 -0.87  0.42
disp  NA  1.00  0.79 -0.71  0.89 -0.43
hp    NA    NA  1.00 -0.45  0.66 -0.71
drat  NA    NA    NA  1.00 -0.71  0.09
wt    NA    NA    NA    NA  1.00 -0.17
qsec  NA    NA    NA    NA    NA  1.00

#melt the correlation matrix
library(reshape2)
melted_cormat <- melt(upper_tri,na.rm = T)

4. 美化矩阵热图

# Heatmap
ggplot(data = melted_cormat, aes(x=Var2, y=Var1, fill = value)) +
  geom_tile(color = "white") +
  scale_fill_gradient2(low = "blue", high = "red", mid = "white",
                       midpoint = 0, limit = c(-1, 1), space = "Lab",
                       name="Pearson\nCorrelation") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, vjust = 1, 
                                  size = 12, hjust = 1)) +
  coord_fixed()

• Rplot02.png

5. 添加相关系数

#Add correlation coefficients on the heatmap
ggplot(data = melted_cormat, aes(x=Var2, y=Var1, fill = value)) +
  geom_tile(color = "white") +
  scale_fill_gradient2(low = "blue", high = "red", mid = "white",
                       midpoint = 0, limit = c(-1, 1), space = "Lab",
                       name="Pearson\nCorrelation") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, vjust = 1, 
                                   size = 12, hjust = 1)) +
  coord_fixed() + 
  geom_text(aes(Var2, Var1, label = value), color = "black", size = 4) 

• 03.png