Last updated on 2026-08-04 02:50:58 CEST.
| Flavor | Version | Tinstall | Tcheck | Ttotal | Status | Flags |
|---|---|---|---|---|---|---|
| r-devel-linux-x86_64-debian-clang | 1.2-29 | 15.47 | 253.21 | 268.68 | ERROR | |
| r-devel-linux-x86_64-debian-gcc | 1.2-29 | 10.53 | 176.39 | 186.92 | ERROR | |
| r-devel-linux-x86_64-fedora-clang | 1.2-29 | 26.00 | 399.87 | 425.87 | ERROR | |
| r-devel-linux-x86_64-fedora-gcc | 1.2-29 | 10.00 | 179.35 | 189.35 | ERROR | |
| r-devel-windows-x86_64 | 1.2-29 | 18.00 | 314.00 | 332.00 | ERROR | |
| r-patched-linux-x86_64 | 1.2-29 | 15.11 | 241.06 | 256.17 | ERROR | |
| r-release-linux-x86_64 | 1.2-29 | 15.17 | 243.80 | 258.97 | ERROR | |
| r-release-macos-arm64 | 1.2-29 | 4.00 | 78.00 | 82.00 | OK | |
| r-release-macos-x86_64 | 1.2-29 | 12.00 | 392.00 | 404.00 | OK | |
| r-release-windows-x86_64 | 1.2-29 | 18.00 | 317.00 | 335.00 | ERROR | |
| r-oldrel-macos-arm64 | 1.2-29 | 3.00 | 81.00 | 84.00 | OK | |
| r-oldrel-macos-x86_64 | 1.2-29 | 12.00 | 597.00 | 609.00 | OK | |
| r-oldrel-windows-x86_64 | 1.2-29 | 24.00 | 384.00 | 408.00 | ERROR |
Version: 1.2-29
Check: examples
Result: ERROR
Running examples in ‘partykit-Ex.R’ failed
The error most likely occurred in:
> base::assign(".ptime", proc.time(), pos = "CheckExEnv")
> ### Name: glmtree
> ### Title: Generalized Linear Model Trees
> ### Aliases: glmtree plot.glmtree predict.glmtree print.glmtree
> ### Keywords: tree
>
> ### ** Examples
>
> if(require("mlbench") && require("vcd")) {
+
+ ## Pima Indians diabetes data
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ ## recursive partitioning of a logistic regression model
+ pid_tree2 <- glmtree(diabetes ~ glucose | pregnant +
+ pressure + triceps + insulin + mass + pedigree + age,
+ data = PimaIndiansDiabetes, family = binomial)
+
+ ## printing whole tree or individual nodes
+ print(pid_tree2)
+ print(pid_tree2, node = 1)
+
+ ## visualization
+ plot(pid_tree2)
+ plot(pid_tree2, tp_args = list(cdplot = TRUE))
+ plot(pid_tree2, terminal_panel = NULL)
+
+ ## estimated parameters
+ coef(pid_tree2)
+ coef(pid_tree2, node = 5)
+ summary(pid_tree2, node = 5)
+
+ ## deviance, log-likelihood and information criteria
+ deviance(pid_tree2)
+ logLik(pid_tree2)
+ AIC(pid_tree2)
+ BIC(pid_tree2)
+
+ ## different types of predictions
+ pid <- head(PimaIndiansDiabetes)
+ predict(pid_tree2, newdata = pid, type = "node")
+ predict(pid_tree2, newdata = pid, type = "response")
+ predict(pid_tree2, newdata = pid, type = "link")
+
+ }
Loading required package: mlbench
Loading required package: vcd
Warning in data("PimaIndiansDiabetes", package = "mlbench") :
data set ‘PimaIndiansDiabetes’ not found
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: glmtree ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
Execution halted
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-patched-linux-x86_64, r-release-linux-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running ‘bugfixes.R’ [5s/7s]
Comparing ‘bugfixes.Rout’ to ‘bugfixes.Rout.save’ ... OK
Running ‘constparty.R’ [5s/6s]
Comparing ‘constparty.Rout’ to ‘constparty.Rout.save’ ... OK
Running ‘regtest-MIA.R’ [2s/2s]
Comparing ‘regtest-MIA.Rout’ to ‘regtest-MIA.Rout.save’ ... OK
Running ‘regtest-cforest.R’ [14s/18s]
Comparing ‘regtest-cforest.Rout’ to ‘regtest-cforest.Rout.save’ ... OK
Running ‘regtest-ctree.R’ [2s/3s]
Comparing ‘regtest-ctree.Rout’ to ‘regtest-ctree.Rout.save’ ... OK
Running ‘regtest-glmtree.R’ [34s/42s]
Running ‘regtest-honesty.R’ [2s/2s]
Running ‘regtest-lmtree.R’ [3s/3s]
Running ‘regtest-nmax.R’ [2s/3s]
Comparing ‘regtest-nmax.Rout’ to ‘regtest-nmax.Rout.save’ ... OK
Running ‘regtest-node.R’ [2s/2s]
Comparing ‘regtest-node.Rout’ to ‘regtest-node.Rout.save’ ... OK
Running ‘regtest-party-random.R’ [2s/3s]
Running ‘regtest-party.R’ [5s/5s]
Comparing ‘regtest-party.Rout’ to ‘regtest-party.Rout.save’ ... OK
Running ‘regtest-split.R’ [2s/2s]
Comparing ‘regtest-split.Rout’ to ‘regtest-split.Rout.save’ ... OK
Running ‘regtest-weights.R’ [2s/3s]
Comparing ‘regtest-weights.Rout’ to ‘regtest-weights.Rout.save’ ... OK
Running the tests in ‘tests/regtest-glmtree.R’ failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-devel-linux-x86_64-debian-clang
Version: 1.2-29
Check: re-building of vignette outputs
Result: ERROR
Error(s) in re-building vignettes:
...
--- re-building ‘constparty.Rnw’ using knitr
--- finished re-building ‘constparty.Rnw’
--- re-building ‘ctree.Rnw’ using knitr
--- finished re-building ‘ctree.Rnw’
--- re-building ‘mob.Rnw’ using knitr
Quitting from mob.Rnw:443-445 [PimaIndiansDiabetes-mob]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
<error/rlang_error>
Error:
! object 'PimaIndiansDiabetes' not found
---
Backtrace:
x
1. +-stats::model.frame(...)
2. \-Formula:::model.frame.Formula(...)
3. +-stats::model.frame(...)
4. +-stats::terms(formula, lhs = lhs, rhs = rhs, data = data, dot = dot)
5. \-Formula:::terms.Formula(...)
6. +-stats::terms(form, ...)
7. \-stats::terms.formula(form, ...)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Error: processing vignette 'mob.Rnw' failed with diagnostics:
object 'PimaIndiansDiabetes' not found
--- failed re-building ‘mob.Rnw’
--- re-building ‘partykit.Rnw’ using knitr
--- finished re-building ‘partykit.Rnw’
SUMMARY: processing the following file failed:
‘mob.Rnw’
Error: Vignette re-building failed.
Execution halted
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-patched-linux-x86_64, r-release-linux-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running ‘bugfixes.R’ [4s/4s]
Comparing ‘bugfixes.Rout’ to ‘bugfixes.Rout.save’ ... OK
Running ‘constparty.R’ [4s/4s]
Comparing ‘constparty.Rout’ to ‘constparty.Rout.save’ ... OK
Running ‘regtest-MIA.R’ [1s/2s]
Comparing ‘regtest-MIA.Rout’ to ‘regtest-MIA.Rout.save’ ... OK
Running ‘regtest-cforest.R’ [8s/8s]
Comparing ‘regtest-cforest.Rout’ to ‘regtest-cforest.Rout.save’ ... OK
Running ‘regtest-ctree.R’ [1s/2s]
Comparing ‘regtest-ctree.Rout’ to ‘regtest-ctree.Rout.save’ ... OK
Running ‘regtest-glmtree.R’ [23s/27s]
Running ‘regtest-honesty.R’ [1s/2s]
Running ‘regtest-lmtree.R’ [2s/2s]
Running ‘regtest-nmax.R’ [1s/2s]
Comparing ‘regtest-nmax.Rout’ to ‘regtest-nmax.Rout.save’ ... OK
Running ‘regtest-node.R’ [1s/2s]
Comparing ‘regtest-node.Rout’ to ‘regtest-node.Rout.save’ ... OK
Running ‘regtest-party-random.R’ [2s/2s]
Running ‘regtest-party.R’ [4s/4s]
Comparing ‘regtest-party.Rout’ to ‘regtest-party.Rout.save’ ... OK
Running ‘regtest-split.R’ [1s/2s]
Comparing ‘regtest-split.Rout’ to ‘regtest-split.Rout.save’ ... OK
Running ‘regtest-weights.R’ [2s/2s]
Comparing ‘regtest-weights.Rout’ to ‘regtest-weights.Rout.save’ ... OK
Running the tests in ‘tests/regtest-glmtree.R’ failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-devel-linux-x86_64-debian-gcc
Version: 1.2-29
Check: for new files in some other directories
Result: NOTE
Found the following files/directories:
‘~/tmp/scratch/Rtmp01QN18’ ‘~/tmp/scratch/Rtmp0VFham’
‘~/tmp/scratch/Rtmp0djtMy’ ‘~/tmp/scratch/Rtmp0e538c’
‘~/tmp/scratch/Rtmp0v9lBa’ ‘~/tmp/scratch/Rtmp2ZasVX’
‘~/tmp/scratch/Rtmp2gBKcf’ ‘~/tmp/scratch/Rtmp35Lh9i’
‘~/tmp/scratch/Rtmp3E8nUE’ ‘~/tmp/scratch/Rtmp4oDoYB’
‘~/tmp/scratch/Rtmp6WM88X’ ‘~/tmp/scratch/Rtmp6cInTY’
‘~/tmp/scratch/Rtmp6rNdEd’ ‘~/tmp/scratch/Rtmp7Lv7Nn’
‘~/tmp/scratch/Rtmp7VO2U8’ ‘~/tmp/scratch/Rtmp7pOZtc’
‘~/tmp/scratch/Rtmp8EK5kp’ ‘~/tmp/scratch/Rtmp8XCdbM’
‘~/tmp/scratch/Rtmp8qiiOV’ ‘~/tmp/scratch/Rtmp9YBxXj’
‘~/tmp/scratch/Rtmp9Zc58N’ ‘~/tmp/scratch/Rtmp9ozunJ’
‘~/tmp/scratch/Rtmp9pGMCB’ ‘~/tmp/scratch/Rtmp9xt3LB’
‘~/tmp/scratch/RtmpA6ASFY’ ‘~/tmp/scratch/RtmpAPorm8’
‘~/tmp/scratch/RtmpAmeMN0’ ‘~/tmp/scratch/RtmpAmzk3Z’
‘~/tmp/scratch/RtmpB0SCdH’ ‘~/tmp/scratch/RtmpBKcH30’
‘~/tmp/scratch/RtmpBzGA6Q’ ‘~/tmp/scratch/RtmpCPW5mR’
‘~/tmp/scratch/RtmpCue6NQ’ ‘~/tmp/scratch/RtmpD1neRI’
‘~/tmp/scratch/RtmpD7KGYU’ ‘~/tmp/scratch/RtmpDFqwsd’
‘~/tmp/scratch/RtmpDS7CJ9’ ‘~/tmp/scratch/RtmpDbFp9F’
‘~/tmp/scratch/RtmpDmmdpm’ ‘~/tmp/scratch/RtmpEQnVmY’
‘~/tmp/scratch/RtmpEbdWbq’ ‘~/tmp/scratch/RtmpFPUzKN’
‘~/tmp/scratch/RtmpFRRBWn’ ‘~/tmp/scratch/RtmpFlcqsC’
‘~/tmp/scratch/RtmpFr4DWo’ ‘~/tmp/scratch/RtmpGIjph8’
‘~/tmp/scratch/RtmpGNUEzM’ ‘~/tmp/scratch/RtmpGXYMM4’
‘~/tmp/scratch/RtmpGpiRKp’ ‘~/tmp/scratch/RtmpHzynMJ’
‘~/tmp/scratch/RtmpI7R1WZ’ ‘~/tmp/scratch/RtmpJ04YQ4’
‘~/tmp/scratch/RtmpJQlt6x’ ‘~/tmp/scratch/RtmpKLuNRg’
‘~/tmp/scratch/RtmpKLxg26’ ‘~/tmp/scratch/RtmpLEXYZP’
‘~/tmp/scratch/RtmpLPe5pI’ ‘~/tmp/scratch/RtmpLjxXv5’
‘~/tmp/scratch/RtmpN163lE’ ‘~/tmp/scratch/RtmpNQUJDc’
‘~/tmp/scratch/RtmpNZjZqE’ ‘~/tmp/scratch/RtmpNq1uwx’
‘~/tmp/scratch/RtmpNqVp3v’ ‘~/tmp/scratch/RtmpNsAIbV’
‘~/tmp/scratch/RtmpO5PmTP’ ‘~/tmp/scratch/RtmpO7F1AA’
‘~/tmp/scratch/RtmpOPT3AL’ ‘~/tmp/scratch/RtmpOrEMcW’
‘~/tmp/scratch/RtmpOyzXQl’ ‘~/tmp/scratch/RtmpPQIOYE’
‘~/tmp/scratch/RtmpPkw5Vt’ ‘~/tmp/scratch/RtmpQxF0TF’
‘~/tmp/scratch/RtmpQzwKtx’ ‘~/tmp/scratch/RtmpR9MoLI’
‘~/tmp/scratch/RtmpRDlZy0’ ‘~/tmp/scratch/RtmpRWwubP’
‘~/tmp/scratch/RtmpRZ8Lmv’ ‘~/tmp/scratch/RtmpRvLchT’
‘~/tmp/scratch/RtmpT4Uq9s’ ‘~/tmp/scratch/RtmpT8vRDF’
‘~/tmp/scratch/RtmpTiEwlH’ ‘~/tmp/scratch/RtmpTjVTMX’
‘~/tmp/scratch/RtmpToydYN’ ‘~/tmp/scratch/RtmpUEzWaR’
‘~/tmp/scratch/RtmpUhz8Ab’ ‘~/tmp/scratch/RtmpUsvuDQ’
‘~/tmp/scratch/RtmpUwkY3j’ ‘~/tmp/scratch/RtmpVGa1d2’
‘~/tmp/scratch/RtmpVfQpYx’ ‘~/tmp/scratch/RtmpW4ReNy’
‘~/tmp/scratch/RtmpWMVO8G’ ‘~/tmp/scratch/RtmpWuLRNc’
‘~/tmp/scratch/RtmpXI9G0n’ ‘~/tmp/scratch/RtmpXkPium’
‘~/tmp/scratch/RtmpZ86Q2R’ ‘~/tmp/scratch/RtmpZWXxnz’
‘~/tmp/scratch/RtmpZdAbnS’ ‘~/tmp/scratch/RtmpZi5BOP’
‘~/tmp/scratch/RtmpZsEZc5’ ‘~/tmp/scratch/Rtmpaa2GyU’
‘~/tmp/scratch/RtmpbJyh7j’ ‘~/tmp/scratch/Rtmpbhqmcz’
‘~/tmp/scratch/Rtmpc6chLM’ ‘~/tmp/scratch/RtmpccNzOo’
‘~/tmp/scratch/Rtmpct00Qi’ ‘~/tmp/scratch/Rtmpe7iGKM’
‘~/tmp/scratch/RtmpeHWAcD’ ‘~/tmp/scratch/Rtmpf8tAPU’
‘~/tmp/scratch/RtmpfP8ehy’ ‘~/tmp/scratch/RtmpgLGidt’
‘~/tmp/scratch/RtmphJSkel’ ‘~/tmp/scratch/RtmphNHDqe’
‘~/tmp/scratch/RtmphVIbbz’ ‘~/tmp/scratch/RtmphYeV32’
‘~/tmp/scratch/RtmpiMq5K2’ ‘~/tmp/scratch/RtmpiNySMD’
‘~/tmp/scratch/RtmpiWgqHp’ ‘~/tmp/scratch/RtmpiXoL85’
‘~/tmp/scratch/RtmpjkUC5H’ ‘~/tmp/scratch/RtmpkX3HiM’
‘~/tmp/scratch/RtmpkZMDwj’ ‘~/tmp/scratch/RtmpkatepL’
‘~/tmp/scratch/Rtmpl6dV1r’ ‘~/tmp/scratch/Rtmpl6hlY6’
‘~/tmp/scratch/RtmplJfIdD’ ‘~/tmp/scratch/Rtmplv3Ukv’
‘~/tmp/scratch/RtmpmEH65r’ ‘~/tmp/scratch/RtmpmrXvMg’
‘~/tmp/scratch/Rtmpn3Bjba’ ‘~/tmp/scratch/RtmpnBhSUh’
‘~/tmp/scratch/RtmpnVRtkt’ ‘~/tmp/scratch/RtmpnuLZdQ’
‘~/tmp/scratch/Rtmpnv99Gx’ ‘~/tmp/scratch/Rtmpnyxb3V’
‘~/tmp/scratch/RtmpoCN07Q’ ‘~/tmp/scratch/Rtmpok8bsw’
‘~/tmp/scratch/Rtmpp7zz43’ ‘~/tmp/scratch/RtmppY1rq6’
‘~/tmp/scratch/RtmppiXz4G’ ‘~/tmp/scratch/Rtmpq7Qbes’
‘~/tmp/scratch/RtmpqN5tbL’ ‘~/tmp/scratch/RtmpqaMBUf’
‘~/tmp/scratch/RtmpqmA3Zo’ ‘~/tmp/scratch/Rtmpqp9tLl’
‘~/tmp/scratch/RtmprG7cdq’ ‘~/tmp/scratch/RtmprrRjTu’
‘~/tmp/scratch/RtmprtWO3Q’ ‘~/tmp/scratch/RtmprvWYZP’
‘~/tmp/scratch/RtmpsNjLlR’ ‘~/tmp/scratch/RtmpseCUul’
‘~/tmp/scratch/Rtmpsedxbx’ ‘~/tmp/scratch/RtmpsxH9yV’
‘~/tmp/scratch/Rtmptgo0lX’ ‘~/tmp/scratch/RtmptoP6xp’
‘~/tmp/scratch/Rtmpu8179L’ ‘~/tmp/scratch/RtmpuCP83T’
‘~/tmp/scratch/RtmpuKwp2g’ ‘~/tmp/scratch/RtmpuhwzTZ’
‘~/tmp/scratch/Rtmpv1GmJh’ ‘~/tmp/scratch/Rtmpv9H7Uf’
‘~/tmp/scratch/RtmpvvNWYO’ ‘~/tmp/scratch/RtmpwVmIIi’
‘~/tmp/scratch/RtmpwdPafM’ ‘~/tmp/scratch/Rtmpwm1zmm’
‘~/tmp/scratch/RtmpxTRsrV’ ‘~/tmp/scratch/Rtmpxa2BVB’
‘~/tmp/scratch/Rtmpxdj0Ci’ ‘~/tmp/scratch/Rtmpy0Iav7’
‘~/tmp/scratch/Rtmpyn9DF3’ ‘~/tmp/scratch/RtmpyuPUB1’
‘~/tmp/scratch/RtmpzJbfgV’ ‘~/tmp/scratch/RtmpzS4013’
‘~/tmp/scratch/RtmpzT1Lk8’ ‘~/tmp/scratch/xvfb-run.0SxL6W’
‘~/tmp/scratch/xvfb-run.16VQaA’ ‘~/tmp/scratch/xvfb-run.1WfVI1’
‘~/tmp/scratch/xvfb-run.2Ga0Tp’ ‘~/tmp/scratch/xvfb-run.2Rjws6’
‘~/tmp/scratch/xvfb-run.3Kgi3B’ ‘~/tmp/scratch/xvfb-run.6dgSB7’
‘~/tmp/scratch/xvfb-run.70R6qr’ ‘~/tmp/scratch/xvfb-run.7WJyV3’
‘~/tmp/scratch/xvfb-run.8FEzBm’ ‘~/tmp/scratch/xvfb-run.8RP7wL’
‘~/tmp/scratch/xvfb-run.8hSeeu’ ‘~/tmp/scratch/xvfb-run.8oexn6’
‘~/tmp/scratch/xvfb-run.9Cg0Ik’ ‘~/tmp/scratch/xvfb-run.9syAgq’
‘~/tmp/scratch/xvfb-run.Clvezy’ ‘~/tmp/scratch/xvfb-run.DitRz5’
‘~/tmp/scratch/xvfb-run.EPW2wz’ ‘~/tmp/scratch/xvfb-run.GDGiIo’
‘~/tmp/scratch/xvfb-run.GZJ1OA’ ‘~/tmp/scratch/xvfb-run.H7Ubjl’
‘~/tmp/scratch/xvfb-run.HFj87B’ ‘~/tmp/scratch/xvfb-run.HInmTy’
‘~/tmp/scratch/xvfb-run.Hq74tl’ ‘~/tmp/scratch/xvfb-run.ICnqUG’
‘~/tmp/scratch/xvfb-run.JdwLQe’ ‘~/tmp/scratch/xvfb-run.MJYrS0’
‘~/tmp/scratch/xvfb-run.N38vGF’ ‘~/tmp/scratch/xvfb-run.NZWQSx’
‘~/tmp/scratch/xvfb-run.OCBWax’ ‘~/tmp/scratch/xvfb-run.OaIAhm’
‘~/tmp/scratch/xvfb-run.OoQPxW’ ‘~/tmp/scratch/xvfb-run.PDXv4y’
‘~/tmp/scratch/xvfb-run.RgkvJ5’ ‘~/tmp/scratch/xvfb-run.SPblLV’
‘~/tmp/scratch/xvfb-run.Sqf70L’ ‘~/tmp/scratch/xvfb-run.StzY6W’
‘~/tmp/scratch/xvfb-run.UW1xTH’ ‘~/tmp/scratch/xvfb-run.Uz5Ja5’
‘~/tmp/scratch/xvfb-run.V84L0W’ ‘~/tmp/scratch/xvfb-run.VqZQLY’
‘~/tmp/scratch/xvfb-run.XY3zmm’ ‘~/tmp/scratch/xvfb-run.Xt5run’
‘~/tmp/scratch/xvfb-run.Y8GM5M’ ‘~/tmp/scratch/xvfb-run.YtBVpB’
‘~/tmp/scratch/xvfb-run.ZLee2f’ ‘~/tmp/scratch/xvfb-run.Zhj1Wv’
‘~/tmp/scratch/xvfb-run.ZwzSXI’ ‘~/tmp/scratch/xvfb-run.a0ioNz’
‘~/tmp/scratch/xvfb-run.bVO7Ki’ ‘~/tmp/scratch/xvfb-run.eNr5xd’
‘~/tmp/scratch/xvfb-run.eV6yVG’ ‘~/tmp/scratch/xvfb-run.h87tSz’
‘~/tmp/scratch/xvfb-run.kQFAQn’ ‘~/tmp/scratch/xvfb-run.kqSnzv’
‘~/tmp/scratch/xvfb-run.lGqsF6’ ‘~/tmp/scratch/xvfb-run.lKo60n’
‘~/tmp/scratch/xvfb-run.lgyTYQ’ ‘~/tmp/scratch/xvfb-run.llyz0m’
‘~/tmp/scratch/xvfb-run.nTj5Xa’ ‘~/tmp/scratch/xvfb-run.oOdk71’
‘~/tmp/scratch/xvfb-run.oRtp9X’ ‘~/tmp/scratch/xvfb-run.oUDkbh’
‘~/tmp/scratch/xvfb-run.ooTbsA’ ‘~/tmp/scratch/xvfb-run.oshWi1’
‘~/tmp/scratch/xvfb-run.r8YwZ4’ ‘~/tmp/scratch/xvfb-run.trh5WS’
‘~/tmp/scratch/xvfb-run.uRthpo’ ‘~/tmp/scratch/xvfb-run.uX8v1l’
‘~/tmp/scratch/xvfb-run.uhpoed’ ‘~/tmp/scratch/xvfb-run.umZfdR’
‘~/tmp/scratch/xvfb-run.v64RsD’ ‘~/tmp/scratch/xvfb-run.vtBfyM’
‘~/tmp/scratch/xvfb-run.wiOYoh’ ‘~/tmp/scratch/xvfb-run.wqKxlS’
‘~/tmp/scratch/xvfb-run.ynWcLe’ ‘~/tmp/scratch/xvfb-run.zhrhDL’
‘/dev/shm/sm_segment.gimli1.1001.11d00000.0’
‘/dev/shm/sm_segment.gimli1.1001.20010000.0’
‘/dev/shm/sm_segment.gimli1.1001.2cfc0000.0’
‘/dev/shm/sm_segment.gimli1.1001.2d170000.0’
‘/dev/shm/sm_segment.gimli1.1001.33240000.0’
‘/dev/shm/sm_segment.gimli1.1001.42350000.0’
‘/dev/shm/sm_segment.gimli1.1001.43510000.0’
‘/dev/shm/sm_segment.gimli1.1001.47580000.0’
‘/dev/shm/sm_segment.gimli1.1001.49bf0000.0’
‘/dev/shm/sm_segment.gimli1.1001.4a9f0000.0’
‘/dev/shm/sm_segment.gimli1.1001.4cbc0000.0’
‘/dev/shm/sm_segment.gimli1.1001.52ea0000.0’
‘/dev/shm/sm_segment.gimli1.1001.6150000.0’
‘/dev/shm/sm_segment.gimli1.1001.62e60000.0’
‘/dev/shm/sm_segment.gimli1.1001.6e030000.0’
‘/dev/shm/sm_segment.gimli1.1001.758a0000.0’
‘/dev/shm/sm_segment.gimli1.1001.8a0b0000.0’
‘/dev/shm/sm_segment.gimli1.1001.8be60000.0’
‘/dev/shm/sm_segment.gimli1.1001.8d460000.0’
‘/dev/shm/sm_segment.gimli1.1001.916e0000.0’
‘/dev/shm/sm_segment.gimli1.1001.91d0000.0’
‘/dev/shm/sm_segment.gimli1.1001.95450000.0’
‘/dev/shm/sm_segment.gimli1.1001.97b50000.0’
‘/dev/shm/sm_segment.gimli1.1001.98240000.0’
‘/dev/shm/sm_segment.gimli1.1001.9a7a0000.0’
‘/dev/shm/sm_segment.gimli1.1001.b6400000.0’
‘/dev/shm/sm_segment.gimli1.1001.b78a0000.0’
‘/dev/shm/sm_segment.gimli1.1001.bd9a0000.0’
‘/dev/shm/sm_segment.gimli1.1001.bff00000.0’
‘/dev/shm/sm_segment.gimli1.1001.c1030000.0’
‘/dev/shm/sm_segment.gimli1.1001.c52b0000.0’
‘/dev/shm/sm_segment.gimli1.1001.c5e60000.0’
‘/dev/shm/sm_segment.gimli1.1001.c72e0000.0’
‘/dev/shm/sm_segment.gimli1.1001.c970000.0’
‘/dev/shm/sm_segment.gimli1.1001.ce210000.0’
‘/dev/shm/sm_segment.gimli1.1001.d18c0000.0’
‘/dev/shm/sm_segment.gimli1.1001.d34a0000.0’
‘/dev/shm/sm_segment.gimli1.1001.d8670000.0’
‘/dev/shm/sm_segment.gimli1.1001.da460000.0’
‘/dev/shm/sm_segment.gimli1.1001.dc9d0000.0’
‘/dev/shm/sm_segment.gimli1.1001.eed50000.0’
‘/dev/shm/sm_segment.gimli1.1001.f1240000.0’
‘/dev/shm/sm_segment.gimli1.1001.fa6a0000.0’
‘/dev/shm/sm_segment.gimli1.1001.fc4b0000.0’
‘/dev/shm/sm_segment.gimli1.1001.fec10000.0’
‘~/.cache/pocl/uncached/tempfile_0ssxDi’
‘~/.cache/pocl/uncached/tempfile_1k7gG2’
‘~/.cache/pocl/uncached/tempfile_1oGxuZ’
‘~/.cache/pocl/uncached/tempfile_1z428K’
‘~/.cache/pocl/uncached/tempfile_211ZfY’
‘~/.cache/pocl/uncached/tempfile_2O4CPt’
‘~/.cache/pocl/uncached/tempfile_2ka5w0’
‘~/.cache/pocl/uncached/tempfile_4vsGCU’
‘~/.cache/pocl/uncached/tempfile_65HaJp’
‘~/.cache/pocl/uncached/tempfile_96SQY9’
‘~/.cache/pocl/uncached/tempfile_AG4lLD’
‘~/.cache/pocl/uncached/tempfile_AK2MoZ’
‘~/.cache/pocl/uncached/tempfile_CMRvxn’
‘~/.cache/pocl/uncached/tempfile_D3uWf6’
‘~/.cache/pocl/uncached/tempfile_E1l6lp’
‘~/.cache/pocl/uncached/tempfile_FaL2cy’
‘~/.cache/pocl/uncached/tempfile_KYsU4s’
‘~/.cache/pocl/uncached/tempfile_LZDUQq’
‘~/.cache/pocl/uncached/tempfile_MDE4bs’
‘~/.cache/pocl/uncached/tempfile_MbD4DX’
‘~/.cache/pocl/uncached/tempfile_MvZQMt’
‘~/.cache/pocl/uncached/tempfile_NA0BJp’
‘~/.cache/pocl/uncached/tempfile_NCVO24’
‘~/.cache/pocl/uncached/tempfile_NvzEOs’
‘~/.cache/pocl/uncached/tempfile_O9qe5U’
‘~/.cache/pocl/uncached/tempfile_OoeMZu’
‘~/.cache/pocl/uncached/tempfile_QrZQbA’
‘~/.cache/pocl/uncached/tempfile_RtkDlE’
‘~/.cache/pocl/uncached/tempfile_Tpdwrp’
‘~/.cache/pocl/uncached/tempfile_ZJzBbK’
‘~/.cache/pocl/uncached/tempfile_aUFS1r’
‘~/.cache/pocl/uncached/tempfile_c5E60N’
‘~/.cache/pocl/uncached/tempfile_gHHiyU’
‘~/.cache/pocl/uncached/tempfile_khgmxK’
‘~/.cache/pocl/uncached/tempfile_lZow5E’
‘~/.cache/pocl/uncached/tempfile_mu6v5b’
‘~/.cache/pocl/uncached/tempfile_ndMlnw’
‘~/.cache/pocl/uncached/tempfile_pf5m0Y’
‘~/.cache/pocl/uncached/tempfile_qw5Wmp’
‘~/.cache/pocl/uncached/tempfile_r9rapS’
‘~/.cache/pocl/uncached/tempfile_raahK6’
‘~/.cache/pocl/uncached/tempfile_sJJhUF’
‘~/.cache/pocl/uncached/tempfile_vXctHx’
‘~/.cache/pocl/uncached/tempfile_wdcCgv’
‘~/.cache/pocl/uncached/tempfile_yLgFg9’
‘~/.cache/pocl/uncached/tempfile_ztZtZg’
Flavor: r-devel-linux-x86_64-debian-gcc
Version: 1.2-29
Check: examples
Result: ERROR
Running examples in ‘partykit-Ex.R’ failed
The error most likely occurred in:
> ### Name: glmtree
> ### Title: Generalized Linear Model Trees
> ### Aliases: glmtree plot.glmtree predict.glmtree print.glmtree
> ### Keywords: tree
>
> ### ** Examples
>
> if(require("mlbench") && require("vcd")) {
+
+ ## Pima Indians diabetes data
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ ## recursive partitioning of a logistic regression model
+ pid_tree2 <- glmtree(diabetes ~ glucose | pregnant +
+ pressure + triceps + insulin + mass + pedigree + age,
+ data = PimaIndiansDiabetes, family = binomial)
+
+ ## printing whole tree or individual nodes
+ print(pid_tree2)
+ print(pid_tree2, node = 1)
+
+ ## visualization
+ plot(pid_tree2)
+ plot(pid_tree2, tp_args = list(cdplot = TRUE))
+ plot(pid_tree2, terminal_panel = NULL)
+
+ ## estimated parameters
+ coef(pid_tree2)
+ coef(pid_tree2, node = 5)
+ summary(pid_tree2, node = 5)
+
+ ## deviance, log-likelihood and information criteria
+ deviance(pid_tree2)
+ logLik(pid_tree2)
+ AIC(pid_tree2)
+ BIC(pid_tree2)
+
+ ## different types of predictions
+ pid <- head(PimaIndiansDiabetes)
+ predict(pid_tree2, newdata = pid, type = "node")
+ predict(pid_tree2, newdata = pid, type = "response")
+ predict(pid_tree2, newdata = pid, type = "link")
+
+ }
Loading required package: mlbench
Loading required package: vcd
Warning in data("PimaIndiansDiabetes", package = "mlbench") :
data set ‘PimaIndiansDiabetes’ not found
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: glmtree ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
Execution halted
Flavors: r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-x86_64, r-release-windows-x86_64, r-oldrel-windows-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running ‘bugfixes.R’ [9s/11s]
Comparing ‘bugfixes.Rout’ to ‘bugfixes.Rout.save’ ... OK
Running ‘constparty.R’ [9s/11s]
Comparing ‘constparty.Rout’ to ‘constparty.Rout.save’ ... OK
Running ‘regtest-MIA.R’
Comparing ‘regtest-MIA.Rout’ to ‘regtest-MIA.Rout.save’ ... OK
Running ‘regtest-cforest.R’ [21s/27s]
Comparing ‘regtest-cforest.Rout’ to ‘regtest-cforest.Rout.save’ ... OK
Running ‘regtest-ctree.R’
Comparing ‘regtest-ctree.Rout’ to ‘regtest-ctree.Rout.save’ ... OK
Running ‘regtest-glmtree.R’ [55s/71s]
Running ‘regtest-honesty.R’
Running ‘regtest-lmtree.R’
Running ‘regtest-nmax.R’
Comparing ‘regtest-nmax.Rout’ to ‘regtest-nmax.Rout.save’ ... OK
Running ‘regtest-node.R’
Comparing ‘regtest-node.Rout’ to ‘regtest-node.Rout.save’ ... OK
Running ‘regtest-party-random.R’
Running ‘regtest-party.R’
Comparing ‘regtest-party.Rout’ to ‘regtest-party.Rout.save’ ... OK
Running ‘regtest-split.R’
Comparing ‘regtest-split.Rout’ to ‘regtest-split.Rout.save’ ... OK
Running ‘regtest-weights.R’
Comparing ‘regtest-weights.Rout’ to ‘regtest-weights.Rout.save’ ... OK
Running the tests in ‘tests/regtest-glmtree.R’ failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-devel-linux-x86_64-fedora-clang
Version: 1.2-29
Check: re-building of vignette outputs
Result: ERROR
Error(s) in re-building vignettes:
--- re-building ‘constparty.Rnw’ using knitr
--- finished re-building ‘constparty.Rnw’
--- re-building ‘ctree.Rnw’ using knitr
--- finished re-building ‘ctree.Rnw’
--- re-building ‘mob.Rnw’ using knitr
Quitting from mob.Rnw:443-445 [PimaIndiansDiabetes-mob]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
<error/rlang_error>
Error:
! object 'PimaIndiansDiabetes' not found
---
Backtrace:
x
1. +-stats::model.frame(...)
2. \-Formula:::model.frame.Formula(...)
3. +-stats::model.frame(...)
4. +-stats::terms(formula, lhs = lhs, rhs = rhs, data = data, dot = dot)
5. \-Formula:::terms.Formula(...)
6. +-stats::terms(form, ...)
7. \-stats::terms.formula(form, ...)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Error: processing vignette 'mob.Rnw' failed with diagnostics:
object 'PimaIndiansDiabetes' not found
--- failed re-building ‘mob.Rnw’
--- re-building ‘partykit.Rnw’ using knitr
--- finished re-building ‘partykit.Rnw’
SUMMARY: processing the following file failed:
‘mob.Rnw’
Error: Vignette re-building failed.
Execution halted
Flavors: r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-x86_64, r-release-windows-x86_64, r-oldrel-windows-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running ‘bugfixes.R’
Comparing ‘bugfixes.Rout’ to ‘bugfixes.Rout.save’ ... OK
Running ‘constparty.R’
Comparing ‘constparty.Rout’ to ‘constparty.Rout.save’ ... OK
Running ‘regtest-MIA.R’
Comparing ‘regtest-MIA.Rout’ to ‘regtest-MIA.Rout.save’ ... OK
Running ‘regtest-cforest.R’
Comparing ‘regtest-cforest.Rout’ to ‘regtest-cforest.Rout.save’ ... OK
Running ‘regtest-ctree.R’
Comparing ‘regtest-ctree.Rout’ to ‘regtest-ctree.Rout.save’ ... OK
Running ‘regtest-glmtree.R’ [26s/27s]
Running ‘regtest-honesty.R’
Running ‘regtest-lmtree.R’
Running ‘regtest-nmax.R’
Comparing ‘regtest-nmax.Rout’ to ‘regtest-nmax.Rout.save’ ... OK
Running ‘regtest-node.R’
Comparing ‘regtest-node.Rout’ to ‘regtest-node.Rout.save’ ... OK
Running ‘regtest-party-random.R’
Running ‘regtest-party.R’
Comparing ‘regtest-party.Rout’ to ‘regtest-party.Rout.save’ ... OK
Running ‘regtest-split.R’
Comparing ‘regtest-split.Rout’ to ‘regtest-split.Rout.save’ ... OK
Running ‘regtest-weights.R’
Comparing ‘regtest-weights.Rout’ to ‘regtest-weights.Rout.save’ ... OK
Running the tests in ‘tests/regtest-glmtree.R’ failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-devel-linux-x86_64-fedora-gcc
Version: 1.2-29
Check: tests
Result: ERROR
Running 'bugfixes.R' [5s]
Comparing 'bugfixes.Rout' to 'bugfixes.Rout.save' ... OK
Running 'constparty.R' [5s]
Comparing 'constparty.Rout' to 'constparty.Rout.save' ... OK
Running 'regtest-MIA.R' [2s]
Comparing 'regtest-MIA.Rout' to 'regtest-MIA.Rout.save' ... OK
Running 'regtest-cforest.R' [9s]
Comparing 'regtest-cforest.Rout' to 'regtest-cforest.Rout.save' ... OK
Running 'regtest-ctree.R' [2s]
Comparing 'regtest-ctree.Rout' to 'regtest-ctree.Rout.save' ... OK
Running 'regtest-glmtree.R' [45s]
Running 'regtest-honesty.R' [2s]
Running 'regtest-lmtree.R' [3s]
Running 'regtest-nmax.R' [2s]
Comparing 'regtest-nmax.Rout' to 'regtest-nmax.Rout.save' ... OK
Running 'regtest-node.R' [1s]
Comparing 'regtest-node.Rout' to 'regtest-node.Rout.save' ... OK
Running 'regtest-party-random.R' [2s]
Running 'regtest-party.R' [5s]
Comparing 'regtest-party.Rout' to 'regtest-party.Rout.save' ... OK
Running 'regtest-split.R' [2s]
Comparing 'regtest-split.Rout' to 'regtest-split.Rout.save' ... OK
Running 'regtest-weights.R' [2s]
Comparing 'regtest-weights.Rout' to 'regtest-weights.Rout.save' ... OK
Running the tests in 'tests/regtest-glmtree.R' failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-devel-windows-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running ‘bugfixes.R’ [5s/7s]
Comparing ‘bugfixes.Rout’ to ‘bugfixes.Rout.save’ ... OK
Running ‘constparty.R’ [5s/7s]
Comparing ‘constparty.Rout’ to ‘constparty.Rout.save’ ... OK
Running ‘regtest-MIA.R’ [2s/4s]
Comparing ‘regtest-MIA.Rout’ to ‘regtest-MIA.Rout.save’ ... OK
Running ‘regtest-cforest.R’ [12s/15s]
Comparing ‘regtest-cforest.Rout’ to ‘regtest-cforest.Rout.save’ ... OK
Running ‘regtest-ctree.R’ [2s/3s]
Comparing ‘regtest-ctree.Rout’ to ‘regtest-ctree.Rout.save’ ... OK
Running ‘regtest-glmtree.R’ [33s/40s]
Running ‘regtest-honesty.R’ [2s/2s]
Running ‘regtest-lmtree.R’ [3s/3s]
Running ‘regtest-nmax.R’ [2s/2s]
Comparing ‘regtest-nmax.Rout’ to ‘regtest-nmax.Rout.save’ ... OK
Running ‘regtest-node.R’ [2s/3s]
Comparing ‘regtest-node.Rout’ to ‘regtest-node.Rout.save’ ... OK
Running ‘regtest-party-random.R’ [2s/3s]
Running ‘regtest-party.R’ [5s/5s]
Comparing ‘regtest-party.Rout’ to ‘regtest-party.Rout.save’ ... OK
Running ‘regtest-split.R’ [2s/2s]
Comparing ‘regtest-split.Rout’ to ‘regtest-split.Rout.save’ ... OK
Running ‘regtest-weights.R’ [2s/3s]
Comparing ‘regtest-weights.Rout’ to ‘regtest-weights.Rout.save’ ... OK
Running the tests in ‘tests/regtest-glmtree.R’ failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-patched-linux-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running ‘bugfixes.R’ [5s/7s]
Comparing ‘bugfixes.Rout’ to ‘bugfixes.Rout.save’ ... OK
Running ‘constparty.R’ [5s/6s]
Comparing ‘constparty.Rout’ to ‘constparty.Rout.save’ ... OK
Running ‘regtest-MIA.R’ [2s/2s]
Comparing ‘regtest-MIA.Rout’ to ‘regtest-MIA.Rout.save’ ... OK
Running ‘regtest-cforest.R’ [12s/13s]
Comparing ‘regtest-cforest.Rout’ to ‘regtest-cforest.Rout.save’ ... OK
Running ‘regtest-ctree.R’ [2s/2s]
Comparing ‘regtest-ctree.Rout’ to ‘regtest-ctree.Rout.save’ ... OK
Running ‘regtest-glmtree.R’ [33s/40s]
Running ‘regtest-honesty.R’ [2s/3s]
Running ‘regtest-lmtree.R’ [3s/3s]
Running ‘regtest-nmax.R’ [2s/3s]
Comparing ‘regtest-nmax.Rout’ to ‘regtest-nmax.Rout.save’ ... OK
Running ‘regtest-node.R’ [2s/2s]
Comparing ‘regtest-node.Rout’ to ‘regtest-node.Rout.save’ ... OK
Running ‘regtest-party-random.R’ [2s/3s]
Running ‘regtest-party.R’ [5s/5s]
Comparing ‘regtest-party.Rout’ to ‘regtest-party.Rout.save’ ... OK
Running ‘regtest-split.R’ [2s/2s]
Comparing ‘regtest-split.Rout’ to ‘regtest-split.Rout.save’ ... OK
Running ‘regtest-weights.R’ [2s/3s]
Comparing ‘regtest-weights.Rout’ to ‘regtest-weights.Rout.save’ ... OK
Running the tests in ‘tests/regtest-glmtree.R’ failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-release-linux-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running 'bugfixes.R' [5s]
Comparing 'bugfixes.Rout' to 'bugfixes.Rout.save' ... OK
Running 'constparty.R' [5s]
Comparing 'constparty.Rout' to 'constparty.Rout.save' ... OK
Running 'regtest-MIA.R' [2s]
Comparing 'regtest-MIA.Rout' to 'regtest-MIA.Rout.save' ... OK
Running 'regtest-cforest.R' [8s]
Comparing 'regtest-cforest.Rout' to 'regtest-cforest.Rout.save' ... OK
Running 'regtest-ctree.R' [2s]
Comparing 'regtest-ctree.Rout' to 'regtest-ctree.Rout.save' ... OK
Running 'regtest-glmtree.R' [43s]
Running 'regtest-honesty.R' [2s]
Running 'regtest-lmtree.R' [3s]
Running 'regtest-nmax.R' [2s]
Comparing 'regtest-nmax.Rout' to 'regtest-nmax.Rout.save' ... OK
Running 'regtest-node.R' [2s]
Comparing 'regtest-node.Rout' to 'regtest-node.Rout.save' ... OK
Running 'regtest-party-random.R' [2s]
Running 'regtest-party.R' [5s]
Comparing 'regtest-party.Rout' to 'regtest-party.Rout.save' ... OK
Running 'regtest-split.R' [2s]
Comparing 'regtest-split.Rout' to 'regtest-split.Rout.save' ... OK
Running 'regtest-weights.R' [2s]
Comparing 'regtest-weights.Rout' to 'regtest-weights.Rout.save' ... OK
Running the tests in 'tests/regtest-glmtree.R' failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-release-windows-x86_64
Version: 1.2-29
Check: tests
Result: ERROR
Running 'bugfixes.R' [8s]
Comparing 'bugfixes.Rout' to 'bugfixes.Rout.save' ... OK
Running 'constparty.R' [7s]
Comparing 'constparty.Rout' to 'constparty.Rout.save' ... OK
Running 'regtest-MIA.R' [3s]
Comparing 'regtest-MIA.Rout' to 'regtest-MIA.Rout.save' ... OK
Running 'regtest-cforest.R' [13s]
Comparing 'regtest-cforest.Rout' to 'regtest-cforest.Rout.save' ... OK
Running 'regtest-ctree.R' [3s]
Comparing 'regtest-ctree.Rout' to 'regtest-ctree.Rout.save' ... OK
Running 'regtest-glmtree.R' [58s]
Running 'regtest-honesty.R' [3s]
Running 'regtest-lmtree.R' [4s]
Running 'regtest-nmax.R' [3s]
Comparing 'regtest-nmax.Rout' to 'regtest-nmax.Rout.save' ... OK
Running 'regtest-node.R' [3s]
Comparing 'regtest-node.Rout' to 'regtest-node.Rout.save' ... OK
Running 'regtest-party-random.R' [3s]
Running 'regtest-party.R' [6s]
Comparing 'regtest-party.Rout' to 'regtest-party.Rout.save' ... OK
Running 'regtest-split.R' [2s]
Comparing 'regtest-split.Rout' to 'regtest-split.Rout.save' ... OK
Running 'regtest-weights.R' [3s]
Comparing 'regtest-weights.Rout' to 'regtest-weights.Rout.save' ... OK
Running the tests in 'tests/regtest-glmtree.R' failed.
Complete output:
> suppressWarnings(RNGversion("3.5.2"))
>
> library("partykit")
Loading required package: grid
Loading required package: libcoin
Loading required package: mvtnorm
>
> set.seed(29)
> n <- 1000
> x <- runif(n)
> z <- runif(n)
> y <- rnorm(n, mean = x * c(-1, 1)[(z > 0.7) + 1], sd = 3)
> z_noise <- factor(sample(1:3, size = n, replace = TRUE))
> d <- data.frame(y = y, x = x, z = z, z_noise = z_noise)
>
>
> fmla <- as.formula("y ~ x | z + z_noise")
> fmly <- gaussian()
> fit <- partykit:::glmfit
>
> # versions of the data
> d1 <- d
> d1$z <- signif(d1$z, digits = 1)
>
> k <- 20
> zs_noise <- matrix(rnorm(n*k), nrow = n)
> colnames(zs_noise) <- paste0("z_noise_", 1:k)
> d2 <- cbind(d, zs_noise)
> fmla2 <- as.formula(paste("y ~ x | z + z_noise +",
+ paste0("z_noise_", 1:k, collapse = " + ")))
>
>
> d3 <- d2
> d3$z <- factor(sample(1:3, size = n, replace = TRUE, prob = c(0.1, 0.5, 0.4)))
> d3$y <- rnorm(n, mean = x * c(-1, 1)[(d3$z == 2) + 1], sd = 3)
>
> ## check weights
> w <- rep(1, n)
> w[1:10] <- 2
> (mw1 <- glmtree(formula = fmla, data = d, weights = w))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 706
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 304
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
> (mw2 <- glmtree(formula = fmla, data = d, weights = w, caseweights = FALSE))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1447422 -0.8138701
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.07006626 0.73278593
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.48
>
>
>
> ## check dfsplit
> (mmfluc2 <- mob(formula = fmla, data = d, fit = partykit:::glmfit))
Model-based recursive partitioning (partykit:::glmfit)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function: 2551.673
> (mmfluc3 <- glmtree(formula = fmla, data = d))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
> (mmfluc3_dfsplit <- glmtree(formula = fmla, data = d, dfsplit = 10))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
>
> ## check tests
> if (require("strucchange"))
+ print(sctest(mmfluc3, node = 1)) # does not yet work
Loading required package: strucchange
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
z z_noise
statistic 2.292499e+01 0.6165335
p.value 7.780038e-04 0.9984952
>
> x <- mmfluc3
> (tst3 <- nodeapply(x, ids = nodeids(x), function(n) n$info$criterion))
$`1`
NULL
$`2`
NULL
$`3`
NULL
>
>
>
>
> ## check logLik and AIC
> logLik(mmfluc2)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3)
'log Lik.' -2551.673 (df=7)
> logLik(mmfluc3_dfsplit)
'log Lik.' -2551.673 (df=16)
> logLik(glm(y ~ x, data = d))
'log Lik.' -2563.694 (df=3)
>
> AIC(mmfluc3)
[1] 5117.347
> AIC(mmfluc3_dfsplit)
[1] 5135.347
>
> ## check pruning
> pr2 <- prune.modelparty(mmfluc2)
> AIC(mmfluc2)
[1] 5117.347
> AIC(pr2)
[1] 5117.347
>
> mmfluc_dfsplit3 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 3)
> mmfluc_dfsplit4 <- glmtree(formula = fmla, data = d, alpha = 0.5, dfsplit = 4)
> pr_dfsplit3 <- prune.modelparty(mmfluc_dfsplit3)
> pr_dfsplit4 <- prune.modelparty(mmfluc_dfsplit4)
> AIC(mmfluc_dfsplit3)
[1] 5142.774
> AIC(mmfluc_dfsplit4)
[1] 5156.774
> AIC(pr_dfsplit3)
[1] 5142.774
> AIC(pr_dfsplit4)
[1] 5124.456
>
> width(mmfluc_dfsplit3)
[1] 8
> width(mmfluc_dfsplit4)
[1] 8
> width(pr_dfsplit3)
[1] 8
> width(pr_dfsplit4)
[1] 3
>
> ## check inner and terminal
> options <- list(NULL,
+ "object",
+ "estfun",
+ c("object", "estfun"))
>
> arguments <- list("inner",
+ "terminal",
+ c("inner", "terminal"))
>
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, inner = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
>
> for (o in options) {
+ print(o)
+ x <- glmtree(formula = fmla, data = d, terminal = o)
+ str(nodeapply(x, ids = nodeids(x), function(n) n$info[c("object", "estfun")]), 2)
+ }
NULL
List of 3
$ 1:List of 2
..$ NA: NULL
..$ NA: NULL
$ 2:List of 2
..$ NA: NULL
..$ NA: NULL
$ 3:List of 2
..$ NA: NULL
..$ NA: NULL
[1] "object"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ NA : NULL
[1] "estfun"
List of 3
$ 1:List of 2
..$ NA : NULL
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ NA : NULL
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ NA : NULL
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
[1] "object" "estfun"
List of 3
$ 1:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:1000, 1:2] -0.1375 -0.0583 -0.0553 0.1043 -0.0744 ...
.. ..- attr(*, "dimnames")=List of 2
$ 2:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:704, 1:2] -0.1291 0.5104 -0.0603 -0.1868 -0.0981 ...
.. ..- attr(*, "dimnames")=List of 2
$ 3:List of 2
..$ object:List of 24
.. ..- attr(*, "class")= chr [1:2] "glm" "lm"
..$ estfun: num [1:296, 1:2] -0.1053 -0.0877 0.0544 -0.1581 0.43 ...
.. ..- attr(*, "dimnames")=List of 2
>
>
> ## check model
> m_mt <- glmtree(formula = fmla, data = d, model = TRUE)
> m_mf <- glmtree(formula = fmla, data = d, model = FALSE)
>
> dim(m_mt$data)
[1] 1000 4
> dim(m_mf$data)
[1] 0 4
>
>
> ## check multiway
> (m_mult <- glmtree(formula = fmla2, data = d3, catsplit = "multiway", minsize = 80))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise + z_noise_1 + z_noise_2 + z_noise_3 + z_noise_4 +
z_noise_5 + z_noise_6 + z_noise_7 + z_noise_8 + z_noise_9 +
z_noise_10 + z_noise_11 + z_noise_12 + z_noise_13 + z_noise_14 +
z_noise_15 + z_noise_16 + z_noise_17 + z_noise_18 + z_noise_19 +
z_noise_20
Fitted party:
[1] root
| [2] z in 1: n = 76
| (Intercept) x
| 0.9859847 -3.2600047
| [3] z in 2: n = 537
| (Intercept) x
| -0.06970187 1.12305074
| [4] z in 3: n = 387
| (Intercept) x
| 0.3824392 -1.8337151
Number of inner nodes: 1
Number of terminal nodes: 3
Number of parameters per node: 2
Objective function (negative log-likelihood): 2511.927
>
>
> ## check parm
> fmla_p <- as.formula("y ~ x + z_noise + z_noise_1 | z + z_noise_2")
> (m_interc <- glmtree(formula = fmla_p, data = d2, parm = 1))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root
| [2] z <= 0.65035: n = 644
| (Intercept) x z_noise2 z_noise3 z_noise_1
| -0.05585503 -1.01257554 0.34044520 -0.16384987 0.24197601
| [3] z > 0.65035: n = 356
| (Intercept) x z_noise2 z_noise3 z_noise_1
| 0.06411865 0.78733976 -0.67811149 -0.14240432 -0.01239154
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 5
Objective function (negative log-likelihood): 2548.32
>
> (m_p3 <- glmtree(formula = fmla_p, data = d2, parm = 3))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x + z_noise + z_noise_1 | z + z_noise_2
Fitted party:
[1] root: n = 1000
(Intercept) x z_noise2 z_noise3 z_noise_1
-0.058855295 -0.340314311 -0.008404682 -0.109839080 0.154798281
Number of inner nodes: 0
Number of terminal nodes: 1
Number of parameters per node: 5
Objective function (negative log-likelihood): 2562.32
>
>
> ## check trim
> (m_tt <- glmtree(formula = fmla, data = d, trim = 0.2))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.70311: n = 704
| (Intercept) x
| -0.1619978 -0.7896293
| [3] z > 0.70311: n = 296
| (Intercept) x
| 0.08683535 0.65598287
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2551.673
>
> (m_tf <- glmtree(formula = fmla, data = d, trim = 300, minsize = 300))
Generalized linear model tree (family: gaussian)
Model formula:
y ~ x | z + z_noise
Fitted party:
[1] root
| [2] z <= 0.6892: n = 691
| (Intercept) x
| -0.1778199 -0.7692901
| [3] z > 0.6892: n = 309
| (Intercept) x
| 0.1065746 0.5562243
Number of inner nodes: 1
Number of terminal nodes: 2
Number of parameters per node: 2
Objective function (negative log-likelihood): 2552.12
>
>
>
> ## check breakties
> m_bt <- glmtree(formula = fmla, data = d1, breakties = TRUE)
> m_df <- glmtree(formula = fmla, data = d1, breakties = FALSE)
>
> all.equal(m_bt, m_df, check.environment = FALSE)
[1] "Component \"node\": Component \"kids\": Component 1: Component 5: Component 6: Mean relative difference: 0.1237503"
[2] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 5: Mean relative difference: 0.1746109"
[3] "Component \"node\": Component \"kids\": Component 2: Component 5: Component 6: Mean relative difference: 0.0443985"
[4] "Component \"node\": Component \"info\": Component \"p.value\": Mean relative difference: 1.100407"
[5] "Component \"node\": Component \"info\": Component \"test\": Mean relative difference: 0.07721086"
[6] "Component \"info\": Component \"call\": target, current do not match when deparsed"
[7] "Component \"info\": Component \"control\": Component \"breakties\": 1 element mismatch"
>
> unclass(m_bt)$node$info$criterion
NULL
> unclass(m_df)$node$info$criterion
NULL
>
> if (requireNamespace("mlbench")) {
+
+ ### example from mob vignette
+ data("PimaIndiansDiabetes", package = "mlbench")
+
+ logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
+ glm(y ~ 0 + x, family = binomial, start = start, ...)
+ }
+
+ pid_formula <- diabetes ~ glucose | pregnant + pressure + triceps +
+ insulin + mass + pedigree + age
+
+ pid_tree <- mob(pid_formula, data = PimaIndiansDiabetes, fit = logit)
+ print(pid_tree)
+ print(nodeapply(pid_tree, ids = nodeids(pid_tree), function(n) n$info$criterion))
+
+ }
Loading required namespace: mlbench
Error in eval(mf, parent.frame()) :
object 'PimaIndiansDiabetes' not found
Calls: mob ... model.frame -> terms -> terms.Formula -> terms -> terms.formula
In addition: Warning message:
In data("PimaIndiansDiabetes", package = "mlbench") :
data set 'PimaIndiansDiabetes' not found
Execution halted
Flavor: r-oldrel-windows-x86_64