Quick Start

Herdiantri Sufriyana

Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.Department of Medical Physiology, Faculty of Medicine, Universitas Nahdlatul Ulama Surabaya, Surabaya, Indonesia.
herdi@tmu.edu.tw

Emily Chia-Yu Su

Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei, Taiwan.Research Center for Artificial Intelligence in Medicine, Taipei Medical University, Taipei, Taiwan.

2024-05-11

Define Functions and Edges

Start by Defining Causal Structure

Start by defining the causal structure as a data frame of edges:

library(rcausim)

# Load predefined edge data
data(edges)

from	to
B	A
A	D
A	C
B	C
D	C
A	E
C	E

Assist in setting up functions based on these edges:

# Generate function setups from edge definitions
functions <- function_from_edge(edges)
print(functions)

## 0 / 5  vertices have functions.
## Please define functions for:
## B = function(n)
## A = function(B)
## D = function(A)
## C = function(A,B,D)
## E = function(A,C)

Define specific functions:

# Define a function for vertex B
function_B <- function(n){ rnorm(n, mean = 90, sd = 5) }
functions <- define(functions, 'B', function_B)
print(functions)

## 1 / 5  vertices have functions.
## Please define functions for:
## A = function(B)
## D = function(A)
## C = function(A,B,D)
## E = function(A,C)

Start by Defining Functions

You can also start by defining functions directly:

# Define a function for vertex B
function_B <- function(n){ rnorm(n, mean = 90, sd = 5) }

# Define a function for vertex A
function_A <- function(B){ ifelse(B>=95, 1, 0) }

# Combine functions in a list
functions <- list(A = function_A, B = function_B)
functions <- function_from_user(functions)

Ensure the causal structure is a directed acyclic graph (DAG):

library(igraph)

# Set up edges based on functions
edges <- edge_from_function(functions)

# Check if the resulting edges form a DAG
g <- graph_from_data_frame(edges, directed = TRUE)
is_dag(g)

## [1] TRUE

Data Simulation

Generate simulated data based on the predefined functions:

# Assume completed functions setup
data(functions)

# Generate simulated data
set.seed(1)
simulated_data <- data_from_function(functions, n = 100)

B	A	D	C	E
86.86773	0	0.0	0.0000000	0
90.91822	0	0.0	0.0000000	0
85.82186	0	0.0	0.0000000	0
97.97640	0	0.0	0.0000000	0
91.64754	0	0.0	0.0000000	0
85.89766	0	0.0	0.0000000	0
92.43715	0	0.0	0.0000000	0
93.69162	0	0.0	0.0000000	0
92.87891	0	0.0	0.0000000	0
88.47306	0	0.0	0.0000000	0
126.75281	1	0.3	1.0000000	1
91.94922	0	0.0	0.0000000	0
86.89380	0	0.0	0.0000000	0
119.72160	1	0.3	0.9958240	1
95.62465	0	0.0	0.0000000	0
89.77533	0	0.0	0.0000000	0
89.91905	0	0.0	0.0000000	0
115.22897	1	0.3	0.9284346	1
106.05957	1	0.3	0.7908935	1
92.96951	0	0.0	0.0000000	0
94.59489	0	0.0	0.0000000	0
93.91068	0	0.0	0.0000000	0
90.37282	0	0.0	0.0000000	0
80.05324	0	0.0	0.0000000	0
93.09913	0	0.0	0.0000000	0
89.71936	0	0.0	0.0000000	0
89.22102	0	0.0	0.0000000	0
82.64624	0	0.0	0.0000000	0
87.60925	0	0.0	0.0000000	0
92.08971	0	0.0	0.0000000	0
96.79340	0	0.0	0.0000000	0
89.48606	0	0.0	0.0000000	0
91.93836	0	0.0	0.0000000	0
89.73097	0	0.0	0.0000000	0
83.11470	0	0.0	0.0000000	0
87.92503	0	0.0	0.0000000	0
88.02855	0	0.0	0.0000000	0
89.70343	0	0.0	0.0000000	0
95.50013	0	0.0	0.0000000	0
93.81588	0	0.0	0.0000000	0
89.17738	0	0.0	0.0000000	0
88.73319	0	0.0	0.0000000	0
93.48482	0	0.0	0.0000000	0
92.78332	0	0.0	0.0000000	0
86.55622	0	0.0	0.0000000	0
86.46252	0	0.0	0.0000000	0
91.82291	0	0.0	0.0000000	0
93.84266	0	0.0	0.0000000	0
89.43827	0	0.0	0.0000000	0
97.68810	0	0.0	0.0000000	0
91.99053	0	0.0	0.0000000	0
103.87212	1	0.3	0.7580817	0
91.70560	0	0.0	0.0000000	0
84.35318	0	0.0	0.0000000	0
97.16512	0	0.0	0.0000000	0
99.90200	0	0.0	0.0000000	0
88.16389	0	0.0	0.0000000	0
84.77933	0	0.0	0.0000000	0
92.84860	0	0.0	0.0000000	0
135.00043	1	0.3	1.0000000	1
102.00809	1	0.3	0.7301213	0
89.80380	0	0.0	0.0000000	0
93.44870	0	0.0	0.0000000	0
90.14001	0	0.0	0.0000000	0
86.28363	0	0.0	0.0000000	0
90.94396	0	0.0	0.0000000	0
80.97521	0	0.0	0.0000000	0
97.32777	0	0.0	0.0000000	0
90.76627	0	0.0	0.0000000	0
100.86306	1	0.3	0.7129459	0
92.37755	0	0.0	0.0000000	0
86.45027	0	0.0	0.0000000	0
93.05363	0	0.0	0.0000000	0
85.32951	0	0.0	0.0000000	0
83.73183	0	0.0	0.0000000	0
91.45723	0	0.0	0.0000000	0
87.78354	0	0.0	0.0000000	0
90.00553	0	0.0	0.0000000	0
90.37171	0	0.0	0.0000000	0
87.05240	0	0.0	0.0000000	0
87.15666	0	0.0	0.0000000	0
89.32411	0	0.0	0.0000000	0
95.89043	0	0.0	0.0000000	0
82.38217	0	0.0	0.0000000	0
92.96973	0	0.0	0.0000000	0
91.66475	0	0.0	0.0000000	0
95.31550	0	0.0	0.0000000	0
88.47908	0	0.0	0.0000000	0
91.85009	0	0.0	0.0000000	0
91.33549	0	0.0	0.0000000	0
87.28740	0	0.0	0.0000000	0
96.03934	0	0.0	0.0000000	0
110.68100	1	0.3	0.8602150	1
93.50107	0	0.0	0.0000000	0
97.93417	0	0.0	0.0000000	0
92.79243	0	0.0	0.0000000	0
83.61704	0	0.0	0.0000000	0
87.13367	0	0.0	0.0000000	0
83.87694	0	0.0	0.0000000	0
87.63300	0	0.0	0.0000000	0