Directed Acyclic Graphs

Authors

[Editor] Hu Zheng;

[Contributors]

Note

Hiplot website

This page is the tutorial for source code version of the Hiplot Directed Acyclic Graphs plugin. You can also use the Hiplot website to achieve no code ploting. For more information please see the following link:

https://hiplot.cn/basic/ggdag?lang=en

Visualizing directed acyclic graphs.

Setup

System Requirements: Cross-platform (Linux/MacOS/Windows)
Programming language: R
Dependent packages: ggdag

# Install packages
if (!requireNamespace("ggdag", quietly = TRUE)) {
  install.packages("ggdag")
}

# Load packages
library(ggdag)

Data Preparation

# Load data
tidy_ggdag <- dagify(
  y ~ x + z2 + w2 + w1,
  x ~ z1 + w1 + w2,
  z1 ~ w1 + v,
  z2 ~ w2 + v,
  w1 ~ ~w2, # bidirected path
  exposure = "x",
  outcome = "y") %>%
  tidy_dagitty()

# View data
head(tidy_ggdag)

$data
# A tibble: 13 × 8
   name       x        y direction to      xend   yend circular
   <chr>  <dbl>    <dbl> <fct>     <chr>  <dbl>  <dbl> <lgl>   
 1 v      1.50  -0.00694 ->        z1     0.511  1.01  FALSE   
 2 v      1.50  -0.00694 ->        z2     0.502 -1.01  FALSE   
 3 w1    -0.933  0.593   ->        x     -0.315  0.472 FALSE   
 4 w1    -0.933  0.593   ->        y     -0.939 -0.585 FALSE   
 5 w1    -0.933  0.593   ->        z1     0.511  1.01  FALSE   
 6 w1    -0.933  0.593   <->       w2    -0.322 -0.470 FALSE   
 7 w2    -0.322 -0.470   ->        x     -0.315  0.472 FALSE   
 8 w2    -0.322 -0.470   ->        y     -0.939 -0.585 FALSE   
 9 w2    -0.322 -0.470   ->        z2     0.502 -1.01  FALSE   
10 x     -0.315  0.472   ->        y     -0.939 -0.585 FALSE   
11 y     -0.939 -0.585   <NA>      <NA>  NA     NA     FALSE   
12 z1     0.511  1.01    ->        x     -0.315  0.472 FALSE   
13 z2     0.502 -1.01    ->        y     -0.939 -0.585 FALSE   

$dag
dag {
v
w1
w2
x [exposure]
y [outcome]
z1
z2
v -> z1
v -> z2
w1 -> x
w1 -> y
w1 -> z1
w1 <-> w2
w2 -> x
w2 -> y
w2 -> z2
x -> y
z1 -> x
z2 -> y
}

Visualization

# Directed Acyclic Graphs
p <- ggdag(tidy_ggdag) +
  theme_dag() 

p