R Under development (unstable) (2023-11-25 r85635 ucrt) -- "Unsuffered Consequences"
Copyright (C) 2023 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> # DEMO FOR SEMTREE
> 
> 
> require("semtree")
Loading required package: semtree
Loading required package: OpenMx
> require("lavaan")
Loading required package: lavaan
This is lavaan 0.6-16
lavaan is FREE software! Please report any bugs.
> 
> # ORGANIZE DATA BY TYPE FOR COVARIATES.
> # SOME COVARIATES ARE ORGANIZED IN THE DATA. MODEL VARIABLES AND 
> # COVARIATES DO NOT NEED TO BE ORDERED IN THE DATASET. ONLY VARIABLE
> # TYPE NEEDS TO BE DEFINED FOR THE COVARIATES (FACTOR/ORDERED/NUMERIC)
> # BE AWARE OF THE EXPONENTIAL GROWTH OF MODEL COMPARISON WITH INCREASES
> # IN NUMBER OF FACTORS PER A COVARIATE.
> 
> data(lgcm)
> 
> lgcm$agegroup <- as.ordered(lgcm$agegroup)
> lgcm$training <- as.factor(lgcm$training)
> lgcm$noise <- as.numeric(lgcm$noise)
> 
> # LOAD IN LAVAAN MODEL.
> # A SIMPLE LINEAR GROWTH MODEL WITH 5 TIME POINTS FROM SIMULATED DATA
> 
> lgcModelstr <- '
+ g0 =~ 1*o1 + 1*o2 + 1*o3 + 1*o4 + 1*o5;
+ g1 =~ 0*o1 + 1*o2 + 2*o3 + 3*o4 + 4*o5;
+ g0 ~~ g0; g0 ~ mui*1;
+ g1 ~~ g1; g1 ~ sli*1;
+ g0 ~~ g1;
+ o1 ~~ o1; o1 ~ 0*1;
+ o2 ~~ o2; o2 ~ 0*1;
+ o3 ~~ o3; o3 ~ 0*1;
+ o4 ~~ o4; o4 ~ 0*1;
+ o5 ~~ o5; o5 ~ 0*1;
+ '
> lgcModel <- lavaan(lgcModelstr, lgcm, do.fit=TRUE)
> 
> # TREE CONTROL OPTIONS.
> # TO OBTAIN BASIC/DEFAULT SMETREE OPTIONS, SIMPLY TPYE THE FOLLOWING:
> 
> controlOptions <- semtree.control()
> 
> # THE CONTENTS OF THE DEFAULT CONTROLS CAN THEN BE VIEWED.
> 
> controlOptions
 SEM-Tree control:
 ▔▔▔▔▔▔▔▔▔▔ 
● Splitting Method: naive
● Alpha Level: 0.05
● Bonferroni Correction:FALSE
● Minimum Number of Cases: 20
● Maximum Tree Depth: NA
● Number of CV Folds: 5
● Exclude Heywood Cases: TRUE
● Test Invariance Alpha Level: NA
● Use all Cases: FALSE
● Verbosity: FALSE
● Progress Bar: TRUE
● Seed: NA
> 
> # AND MODEL OPTIONS CAN BE CHANGED BY REDEFINING ELEMENTS OF THE 
> # CONTROL OBJECT.
> 
> controlOptions$alpha <- 0.01
> 
> # RUN TREE.
> 
> tree <- semtree(model=lgcModel, data=lgcm, control = controlOptions)
✖ Variable noise is numeric but has only few unique values. Consider recoding as ordered factor.
✔ Tree construction finished [took 2s].
> 
> # SEE PLOT.
> # THE PLOT FUNCTION WILL SHOW ALL FREE PARAMETERS AT EACH TERMINAL NODE.
> # THIS CAN CREATE UNREADABLE FIGURES FOR MODELS WITH MANY FREE PARAMETERS.
> 
> plot(tree)
> 
> # SEE SUMMARY.
> # OVERALL MODEL FACTS ARE GIVEN WITH THE SUMMARY FUNCTION.
> 
> summary(tree)
SEMtree Summary
Template model:  
Total Sample Size:  400 
Number of nodes:  5 
Number of leaf nodes:  3 
Free Parameters:  10  ( g0~~g0 mui g1~~g1 sli g0~~g1 o1~~o1 o2~~o2 o3~~o3 o4~~o4 o5~~o5 )
> 
> # summary(treeConstrained)
> 
> # USING THE PRINT FUNCTION WILL PROVIDE AN OVERVIEW OF THE MODEL
> # SPLITS, LR TESTS WITH DF, AND SUBGROUP SIZES (N).
> 
> print(tree)
SEMtree with numbered nodes
 |-[1] agegroup > 0 [N=400 LR=1258.08, df=10]
 |   |-[2] TERMINAL [N=200]
 |   |-[3] training  in [ 0  ] [N=200 LR=40.85, df=10]
 |   |   |-[4] TERMINAL [N=100]
 |   |   |-[5] TERMINAL [N=100]
> 
> # GET NODE PARAMETERS (leafs only as default).
> # THE DEFAULT IS ONLY DISPLAYING LEAF NODE PARAMETER ESTIMATES.
> 
> parameters(tree)
            2      4      5
g0~~g0  0.082  0.104  0.085
mui     5.017  1.941  2.005
g1~~g1  0.499  0.674  1.629
sli    -0.142 -0.494 -1.084
g0~~g1 -0.011  0.028 -0.044
o1~~o1  0.068  0.048  0.042
o2~~o2  0.049  0.069  0.049
o3~~o3  0.043  0.053  0.053
o4~~o4  0.055  0.039  0.063
o5~~o5  0.037  0.048  0.011
> 
> # TO GET ALL PARAMETER ESTIMATES FOR EVERY NODE CHANGE THE DEFAULT TO.
> 
> parameters(tree, leafs.only=FALSE)
            1      2      3      4      5
g0~~g0  2.410  0.082  0.095  0.104  0.085
mui     3.496  5.017  1.973  1.941  2.005
g1~~g1  0.973  0.499  1.239  0.674  1.629
sli    -0.466 -0.142 -0.789 -0.494 -1.084
g0~~g1  0.477 -0.011 -0.017  0.028 -0.044
o1~~o1  0.052  0.068  0.045  0.048  0.042
o2~~o2  0.058  0.049  0.059  0.069  0.049
o3~~o3  0.047  0.043  0.053  0.053  0.053
o4~~o4  0.052  0.055  0.051  0.039  0.063
o5~~o5  0.036  0.037  0.030  0.048  0.011
> 
> # SUBTREE FUNCTION.
> # IF ONLY A SUBSET OF THE TREE IS TO BE EXAMINED, THEN THE TREE CAN 
> # BE PARED. THIS IS DONE WITH A SUBSET FUNCTION WHICH STORES THE TREE
> # FROM A GIVEN NODE ON. IF THE TREE FROM NODE 2 ON IS DESIRED, THEN:
> 
> treeSub <- subtree(tree, startNode=3)
> 
> 
> # ALTERNATIVE SPLIT RULE
> 
> controlOptions$method <- "fair"
> tree2 <- semtree(model=lgcModel, data=lgcm, control = controlOptions)
✖ Variable noise is numeric but has only few unique values. Consider recoding as ordered factor.
✔ Tree construction finished [took 3s].
> 
> # disabled for time restrictions on CRAN
> #controlOptions$method <- "cv"
> #tree3 <- semtree(model=lgcModel, data=lgcm, control = controlOptions)
> 
> proc.time()
   user  system elapsed 
   6.79    0.32    7.11