CRAN Package Check Results for Package gamboostLSS

Last updated on 2020-12-31 00:46:43 CET.

Flavor Version Tinstall Tcheck Ttotal Status Flags
r-devel-linux-x86_64-debian-clang 2.0-1.1 11.42 291.74 303.16 ERROR
r-devel-linux-x86_64-debian-gcc 2.0-1.1 9.54 215.13 224.67 ERROR
r-devel-linux-x86_64-fedora-clang 2.0-1.1 365.86 ERROR
r-devel-linux-x86_64-fedora-gcc 2.0-1.1 359.07 ERROR
r-devel-windows-ix86+x86_64 2.0-1.1 23.00 369.00 392.00 ERROR
r-patched-linux-x86_64 2.0-1.1 13.22 277.01 290.23 OK
r-patched-solaris-x86 2.0-1.1 357.30 OK --no-vignettes
r-release-linux-x86_64 2.0-1.1 11.17 274.58 285.75 WARN
r-release-macos-x86_64 2.0-1.1 OK
r-release-windows-ix86+x86_64 2.0-1.1 23.00 274.00 297.00 OK
r-oldrel-macos-x86_64 2.0-1.1 OK
r-oldrel-windows-ix86+x86_64 2.0-1.1 14.00 256.00 270.00 OK

Check Details

Version: 2.0-1.1
Check: tests
Result: ERROR
     Running 'bugfixes.R' [5s/5s]
     Running 'regtest-families.R' [10s/12s]
     Running 'regtest-gamboostLSS.R' [9s/10s]
     Running 'regtest-glmboostLSS.R' [7s/8s]
     Running 'regtest-mstop.R' [5s/5s]
     Running 'regtest-noncyclic_fitting.R' [14s/15s]
     Running 'regtest-stabilization.R' [33s/36s]
     Running 'regtest-stabsel.R' [11s/9s]
    Running the tests in 'tests/regtest-noncyclic_fitting.R' failed.
    Complete output:
     > require("gamboostLSS")
     Loading required package: gamboostLSS
     Loading required package: mboost
     Loading required package: parallel
     Loading required package: stabs
    
     Attaching package: 'gamboostLSS'
    
     The following object is masked from 'package:stats':
    
     model.weights
    
     >
     > ###negbin dist, linear###
     >
     > set.seed(2611)
     > x1 <- rnorm(1000)
     > x2 <- rnorm(1000)
     > x3 <- rnorm(1000)
     > x4 <- rnorm(1000)
     > x5 <- rnorm(1000)
     > x6 <- rnorm(1000)
     > mu <- exp(1.5 + x1^2 +0.5 * x2 - 3 * sin(x3) -1 * x4)
     > sigma <- exp(-0.2 * x4 +0.2 * x5 +0.4 * x6)
     > y <- numeric(1000)
     > for (i in 1:1000)
     + y[i] <- rnbinom(1, size = sigma[i], mu = mu[i])
     > dat <- data.frame(x1, x2, x3, x4, x5, x6, y)
     >
     > #fit models at number of params + 1
     >
     > #glmboost
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     >
     > #linear baselearner with bols
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bols")
     >
     > #nonlinear bbs baselearner
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bbs")
     >
     > #reducing model and increasing it afterwards should yield the same fit
     >
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bols")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     > ## check cvrisk for noncyclic models
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     > cvr1 <- cvrisk(model, grid = 1:50, cv(model.weights(model), B = 5))
     Starting cross-validation...
     [Fold: 1]
    
     [Fold: 2]
     [ 1] ......[ 1] .................................................. -- risk: 1805.447
     .[ 41] .................
     Final risk: 1799.837
     ..
     [Fold: 3]
     ......[ 1] ............. -- risk: 1734.54
     [ 41] ...................
     Final risk: 1732.471
     ...
     [Fold: 4]
     ........[ 1] ................... -- risk: 1836.44
     .[ 41] ................
     Final risk: 1830.995
     ..
     [Fold: 5]
     ......[ 1] ........................ -- risk: 1644.972
     .[ 41] ...................
     Final risk: 1643.654
     ....................... -- risk: 1748.201
     [ 41] .........
     Final risk: 1745.054
     > cvr1
    
     Cross-validated
     glmboostLSS(formula = y ~ ., data = dat, families = NBinomialLSS(), control = boost_control(mstop = 3), method = "noncyclic")
    
     1 2 3 4 5 6 7 8
     4.857889 4.857889 4.854336 4.851760 4.848367 4.845487 4.843456 4.840692
     9 10 11 12 13 14 15 16
     4.837335 4.835769 4.833281 4.831312 4.829041 4.827176 4.824955 4.822376
     17 18 19 20 21 22 23 24
     4.820667 4.819740 4.817552 4.816011 4.813472 4.812703 4.810620 4.809356
     25 26 27 28 29 30 31 32
     4.807388 4.806713 4.804566 4.803307 4.801508 4.800541 4.799011 4.798048
     33 34 35 36 37 38 39 40
     4.796181 4.795305 4.793928 4.793380 4.791924 4.790579 4.789696 4.788866
     41 42 43 44 45 46 47 48
     4.787808 4.786352 4.785354 4.784043 4.783679 4.782704 4.781571 4.780256
     49 50
     4.779861 4.778943
    
     Optimal number of boosting iterations: 50
     > plot(cvr1)
     >
     > risk(model, merge = TRUE)
     mu sigma sigma sigma mu
     4755.327 4755.327 4752.028 4749.214 4746.600
     > risk(model, merge = FALSE)
     $mu
     [1] 4755.327 4746.600
    
     $sigma
     [1] 4755.327 4752.028 4749.214
    
     attr(,"class")
     [1] "inbag"
     >
     >
     > ## test that mstop = 0 is possible
     > compare_models <- function (m1, m2) {
     + stopifnot(all.equal(coef(m1), coef(m2)))
     + stopifnot(all.equal(predict(m1), predict(m2)))
     + stopifnot(all.equal(fitted(m1), fitted(m2)))
     + stopifnot(all.equal(selected(m1), selected(m2)))
     + stopifnot(all.equal(risk(m1), risk(m2)))
     + ## remove obvious differences from objects
     + m1$control <- m2$control <- NULL
     + m1$call <- m2$call <- NULL
     + if (!all.equal(m1, m2))
     + stop("Objects of offset model + 1 step and model with 1 step not identical")
     + invisible(NULL)
     + }
     >
     > # set up models
     > mod <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 0))
     > mod2 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     > mod3 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     >
     > lapply(coef(mod), function(x) stopifnot(is.null(x)))
     $mu
     NULL
    
     $sigma
     NULL
    
     >
     > mstop(mod3) <- 0
     > mapply(compare_models, m1 = mod, m2 = mod3)
     Error in !all.equal(m1, m2) : invalid argument type
     Calls: mapply -> <Anonymous>
     Execution halted
Flavor: r-devel-linux-x86_64-debian-clang

Version: 2.0-1.1
Check: tests
Result: ERROR
     Running ‘bugfixes.R’ [3s/5s]
     Running ‘regtest-families.R’ [7s/10s]
     Running ‘regtest-gamboostLSS.R’ [6s/9s]
     Running ‘regtest-glmboostLSS.R’ [5s/8s]
     Running ‘regtest-mstop.R’ [3s/5s]
     Running ‘regtest-noncyclic_fitting.R’ [10s/13s]
     Running ‘regtest-stabilization.R’ [23s/31s]
     Running ‘regtest-stabsel.R’ [8s/9s]
    Running the tests in ‘tests/regtest-noncyclic_fitting.R’ failed.
    Complete output:
     > require("gamboostLSS")
     Loading required package: gamboostLSS
     Loading required package: mboost
     Loading required package: parallel
     Loading required package: stabs
    
     Attaching package: 'gamboostLSS'
    
     The following object is masked from 'package:stats':
    
     model.weights
    
     >
     > ###negbin dist, linear###
     >
     > set.seed(2611)
     > x1 <- rnorm(1000)
     > x2 <- rnorm(1000)
     > x3 <- rnorm(1000)
     > x4 <- rnorm(1000)
     > x5 <- rnorm(1000)
     > x6 <- rnorm(1000)
     > mu <- exp(1.5 + x1^2 +0.5 * x2 - 3 * sin(x3) -1 * x4)
     > sigma <- exp(-0.2 * x4 +0.2 * x5 +0.4 * x6)
     > y <- numeric(1000)
     > for (i in 1:1000)
     + y[i] <- rnbinom(1, size = sigma[i], mu = mu[i])
     > dat <- data.frame(x1, x2, x3, x4, x5, x6, y)
     >
     > #fit models at number of params + 1
     >
     > #glmboost
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     >
     > #linear baselearner with bols
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bols")
     >
     > #nonlinear bbs baselearner
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bbs")
     >
     > #reducing model and increasing it afterwards should yield the same fit
     >
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bols")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     > ## check cvrisk for noncyclic models
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     > cvr1 <- cvrisk(model, grid = 1:50, cv(model.weights(model), B = 5))
     Starting cross-validation...
     [Fold: 1]
    
     [Fold: 2]
     [ 1] .....[ 1] .......................................................................... -- risk: 1734.54
     . -- risk: 1805.447
     [ 41] .[ 41] ..............
     Final risk: 1732.471
     ...
     Final risk: 1799.837
    
     [Fold: 3]
    
     [Fold: 4]
     [ 1] ....[ 1] ......................................................... -- risk: 1836.44
     [ 41] ..............
     Final risk: 1830.995
     ...
     [Fold: 5]
     ....[ 1] ............. -- risk: 1644.972
     [ 41] ............
     Final risk: 1643.654
     ............................... -- risk: 1748.201
     [ 41] .........
     Final risk: 1745.054
     > cvr1
    
     Cross-validated
     glmboostLSS(formula = y ~ ., data = dat, families = NBinomialLSS(), control = boost_control(mstop = 3), method = "noncyclic")
    
     1 2 3 4 5 6 7 8
     4.857889 4.857889 4.854336 4.851760 4.848367 4.845487 4.843456 4.840692
     9 10 11 12 13 14 15 16
     4.837335 4.835769 4.833281 4.831312 4.829041 4.827176 4.824955 4.822376
     17 18 19 20 21 22 23 24
     4.820667 4.819740 4.817552 4.816011 4.813472 4.812703 4.810620 4.809356
     25 26 27 28 29 30 31 32
     4.807388 4.806713 4.804566 4.803307 4.801508 4.800541 4.799011 4.798048
     33 34 35 36 37 38 39 40
     4.796181 4.795305 4.793928 4.793380 4.791924 4.790579 4.789696 4.788866
     41 42 43 44 45 46 47 48
     4.787808 4.786352 4.785354 4.784043 4.783679 4.782704 4.781571 4.780256
     49 50
     4.779861 4.778943
    
     Optimal number of boosting iterations: 50
     > plot(cvr1)
     >
     > risk(model, merge = TRUE)
     mu sigma sigma sigma mu
     4755.327 4755.327 4752.028 4749.214 4746.600
     > risk(model, merge = FALSE)
     $mu
     [1] 4755.327 4746.600
    
     $sigma
     [1] 4755.327 4752.028 4749.214
    
     attr(,"class")
     [1] "inbag"
     >
     >
     > ## test that mstop = 0 is possible
     > compare_models <- function (m1, m2) {
     + stopifnot(all.equal(coef(m1), coef(m2)))
     + stopifnot(all.equal(predict(m1), predict(m2)))
     + stopifnot(all.equal(fitted(m1), fitted(m2)))
     + stopifnot(all.equal(selected(m1), selected(m2)))
     + stopifnot(all.equal(risk(m1), risk(m2)))
     + ## remove obvious differences from objects
     + m1$control <- m2$control <- NULL
     + m1$call <- m2$call <- NULL
     + if (!all.equal(m1, m2))
     + stop("Objects of offset model + 1 step and model with 1 step not identical")
     + invisible(NULL)
     + }
     >
     > # set up models
     > mod <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 0))
     > mod2 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     > mod3 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     >
     > lapply(coef(mod), function(x) stopifnot(is.null(x)))
     $mu
     NULL
    
     $sigma
     NULL
    
     >
     > mstop(mod3) <- 0
     > mapply(compare_models, m1 = mod, m2 = mod3)
     Error in !all.equal(m1, m2) : invalid argument type
     Calls: mapply -> <Anonymous>
     Execution halted
Flavor: r-devel-linux-x86_64-debian-gcc

Version: 2.0-1.1
Check: tests
Result: ERROR
     Running ‘bugfixes.R’
     Running ‘regtest-families.R’ [12s/13s]
     Running ‘regtest-gamboostLSS.R’ [11s/13s]
     Running ‘regtest-glmboostLSS.R’
     Running ‘regtest-mstop.R’
     Running ‘regtest-noncyclic_fitting.R’ [18s/20s]
     Running ‘regtest-stabilization.R’ [38s/45s]
     Running ‘regtest-stabsel.R’ [12s/11s]
    Running the tests in ‘tests/regtest-noncyclic_fitting.R’ failed.
    Complete output:
     > require("gamboostLSS")
     Loading required package: gamboostLSS
     Loading required package: mboost
     Loading required package: parallel
     Loading required package: stabs
    
     Attaching package: 'gamboostLSS'
    
     The following object is masked from 'package:stats':
    
     model.weights
    
     >
     > ###negbin dist, linear###
     >
     > set.seed(2611)
     > x1 <- rnorm(1000)
     > x2 <- rnorm(1000)
     > x3 <- rnorm(1000)
     > x4 <- rnorm(1000)
     > x5 <- rnorm(1000)
     > x6 <- rnorm(1000)
     > mu <- exp(1.5 + x1^2 +0.5 * x2 - 3 * sin(x3) -1 * x4)
     > sigma <- exp(-0.2 * x4 +0.2 * x5 +0.4 * x6)
     > y <- numeric(1000)
     > for (i in 1:1000)
     + y[i] <- rnbinom(1, size = sigma[i], mu = mu[i])
     > dat <- data.frame(x1, x2, x3, x4, x5, x6, y)
     >
     > #fit models at number of params + 1
     >
     > #glmboost
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     >
     > #linear baselearner with bols
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bols")
     >
     > #nonlinear bbs baselearner
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bbs")
     >
     > #reducing model and increasing it afterwards should yield the same fit
     >
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bols")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     > ## check cvrisk for noncyclic models
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     > cvr1 <- cvrisk(model, grid = 1:50, cv(model.weights(model), B = 5))
     Starting cross-validation...
     [Fold: 1]
    
     [Fold: 2]
     [ 1] .........[ 1] .............................................................. -- risk: 1805.447
     [ 41] ................
     Final risk: 1799.837
     .. -- risk: 1734.54
    
     [Fold: 3]
     [ 41] ........[ 1] ...
     Final risk: 1732.471
     ...
     [Fold: 4]
     ....[ 1] .................................................. -- risk: 1836.44
     .[ 41] .................
     Final risk: 1830.995
     ..
     [Fold: 5]
     ........[ 1] .... -- risk: 1644.972
     .[ 41] ..............
     Final risk: 1643.654
     ................................ -- risk: 1748.201
     [ 41] .........
     Final risk: 1745.054
     > cvr1
    
     Cross-validated
     glmboostLSS(formula = y ~ ., data = dat, families = NBinomialLSS(), control = boost_control(mstop = 3), method = "noncyclic")
    
     1 2 3 4 5 6 7 8
     4.857889 4.857889 4.854336 4.851760 4.848367 4.845487 4.843456 4.840692
     9 10 11 12 13 14 15 16
     4.837335 4.835769 4.833281 4.831312 4.829041 4.827176 4.824955 4.822376
     17 18 19 20 21 22 23 24
     4.820667 4.819740 4.817552 4.816011 4.813472 4.812703 4.810620 4.809356
     25 26 27 28 29 30 31 32
     4.807388 4.806713 4.804566 4.803307 4.801508 4.800541 4.799011 4.798048
     33 34 35 36 37 38 39 40
     4.796181 4.795305 4.793928 4.793380 4.791924 4.790579 4.789696 4.788866
     41 42 43 44 45 46 47 48
     4.787808 4.786352 4.785354 4.784043 4.783679 4.782704 4.781571 4.780256
     49 50
     4.779861 4.778943
    
     Optimal number of boosting iterations: 50
     > plot(cvr1)
     >
     > risk(model, merge = TRUE)
     mu sigma sigma sigma mu
     4755.327 4755.327 4752.028 4749.214 4746.600
     > risk(model, merge = FALSE)
     $mu
     [1] 4755.327 4746.600
    
     $sigma
     [1] 4755.327 4752.028 4749.214
    
     attr(,"class")
     [1] "inbag"
     >
     >
     > ## test that mstop = 0 is possible
     > compare_models <- function (m1, m2) {
     + stopifnot(all.equal(coef(m1), coef(m2)))
     + stopifnot(all.equal(predict(m1), predict(m2)))
     + stopifnot(all.equal(fitted(m1), fitted(m2)))
     + stopifnot(all.equal(selected(m1), selected(m2)))
     + stopifnot(all.equal(risk(m1), risk(m2)))
     + ## remove obvious differences from objects
     + m1$control <- m2$control <- NULL
     + m1$call <- m2$call <- NULL
     + if (!all.equal(m1, m2))
     + stop("Objects of offset model + 1 step and model with 1 step not identical")
     + invisible(NULL)
     + }
     >
     > # set up models
     > mod <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 0))
     > mod2 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     > mod3 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     >
     > lapply(coef(mod), function(x) stopifnot(is.null(x)))
     $mu
     NULL
    
     $sigma
     NULL
    
     >
     > mstop(mod3) <- 0
     > mapply(compare_models, m1 = mod, m2 = mod3)
     Error in !all.equal(m1, m2) : invalid argument type
     Calls: mapply -> <Anonymous>
     Execution halted
Flavor: r-devel-linux-x86_64-fedora-clang

Version: 2.0-1.1
Check: tests
Result: ERROR
     Running ‘bugfixes.R’
     Running ‘regtest-families.R’ [12s/16s]
     Running ‘regtest-gamboostLSS.R’ [10s/12s]
     Running ‘regtest-glmboostLSS.R’
     Running ‘regtest-mstop.R’
     Running ‘regtest-noncyclic_fitting.R’ [16s/18s]
     Running ‘regtest-stabilization.R’ [39s/45s]
     Running ‘regtest-stabsel.R’ [12s/11s]
    Running the tests in ‘tests/regtest-noncyclic_fitting.R’ failed.
    Complete output:
     > require("gamboostLSS")
     Loading required package: gamboostLSS
     Loading required package: mboost
     Loading required package: parallel
     Loading required package: stabs
    
     Attaching package: 'gamboostLSS'
    
     The following object is masked from 'package:stats':
    
     model.weights
    
     >
     > ###negbin dist, linear###
     >
     > set.seed(2611)
     > x1 <- rnorm(1000)
     > x2 <- rnorm(1000)
     > x3 <- rnorm(1000)
     > x4 <- rnorm(1000)
     > x5 <- rnorm(1000)
     > x6 <- rnorm(1000)
     > mu <- exp(1.5 + x1^2 +0.5 * x2 - 3 * sin(x3) -1 * x4)
     > sigma <- exp(-0.2 * x4 +0.2 * x5 +0.4 * x6)
     > y <- numeric(1000)
     > for (i in 1:1000)
     + y[i] <- rnbinom(1, size = sigma[i], mu = mu[i])
     > dat <- data.frame(x1, x2, x3, x4, x5, x6, y)
     >
     > #fit models at number of params + 1
     >
     > #glmboost
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     >
     > #linear baselearner with bols
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bols")
     >
     > #nonlinear bbs baselearner
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bbs")
     >
     > #reducing model and increasing it afterwards should yield the same fit
     >
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bols")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     > ## check cvrisk for noncyclic models
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     > cvr1 <- cvrisk(model, grid = 1:50, cv(model.weights(model), B = 5))
     Starting cross-validation...
     [Fold: 1]
    
     [Fold: 2]
     [ 1] ..........[ 1] ................................................... -- risk: 1805.447
     [ 41] ...............
     Final risk: 1799.837
     ...
     [Fold: 3]
     .......... -- risk: 1734.54
     [ 1] .[ 41] ....................
     Final risk: 1732.471
     ...
     [Fold: 4]
     ........[ 1] .................................... -- risk: 1836.44
     [ 41] .............
     Final risk: 1830.995
     ..
     [Fold: 5]
     .....[ 1] ...................... -- risk: 1644.972
     .[ 41] ..................
     Final risk: 1643.654
     .................. -- risk: 1748.201
     [ 41] .........
     Final risk: 1745.054
     > cvr1
    
     Cross-validated
     glmboostLSS(formula = y ~ ., data = dat, families = NBinomialLSS(), control = boost_control(mstop = 3), method = "noncyclic")
    
     1 2 3 4 5 6 7 8
     4.857889 4.857889 4.854336 4.851760 4.848367 4.845487 4.843456 4.840692
     9 10 11 12 13 14 15 16
     4.837335 4.835769 4.833281 4.831312 4.829041 4.827176 4.824955 4.822376
     17 18 19 20 21 22 23 24
     4.820667 4.819740 4.817552 4.816011 4.813472 4.812703 4.810620 4.809356
     25 26 27 28 29 30 31 32
     4.807388 4.806713 4.804566 4.803307 4.801508 4.800541 4.799011 4.798048
     33 34 35 36 37 38 39 40
     4.796181 4.795305 4.793928 4.793380 4.791924 4.790579 4.789696 4.788866
     41 42 43 44 45 46 47 48
     4.787808 4.786352 4.785354 4.784043 4.783679 4.782704 4.781571 4.780256
     49 50
     4.779861 4.778943
    
     Optimal number of boosting iterations: 50
     > plot(cvr1)
     >
     > risk(model, merge = TRUE)
     mu sigma sigma sigma mu
     4755.327 4755.327 4752.028 4749.214 4746.600
     > risk(model, merge = FALSE)
     $mu
     [1] 4755.327 4746.600
    
     $sigma
     [1] 4755.327 4752.028 4749.214
    
     attr(,"class")
     [1] "inbag"
     >
     >
     > ## test that mstop = 0 is possible
     > compare_models <- function (m1, m2) {
     + stopifnot(all.equal(coef(m1), coef(m2)))
     + stopifnot(all.equal(predict(m1), predict(m2)))
     + stopifnot(all.equal(fitted(m1), fitted(m2)))
     + stopifnot(all.equal(selected(m1), selected(m2)))
     + stopifnot(all.equal(risk(m1), risk(m2)))
     + ## remove obvious differences from objects
     + m1$control <- m2$control <- NULL
     + m1$call <- m2$call <- NULL
     + if (!all.equal(m1, m2))
     + stop("Objects of offset model + 1 step and model with 1 step not identical")
     + invisible(NULL)
     + }
     >
     > # set up models
     > mod <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 0))
     > mod2 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     > mod3 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     >
     > lapply(coef(mod), function(x) stopifnot(is.null(x)))
     $mu
     NULL
    
     $sigma
     NULL
    
     >
     > mstop(mod3) <- 0
     > mapply(compare_models, m1 = mod, m2 = mod3)
     Error in !all.equal(m1, m2) : invalid argument type
     Calls: mapply -> <Anonymous>
     Execution halted
Flavor: r-devel-linux-x86_64-fedora-gcc

Version: 2.0-1.1
Check: tests
Result: ERROR
     Running 'bugfixes.R' [5s]
     Running 'regtest-families.R' [15s]
     Running 'regtest-gamboostLSS.R' [11s]
     Running 'regtest-glmboostLSS.R' [10s]
     Running 'regtest-mstop.R' [6s]
     Running 'regtest-noncyclic_fitting.R' [18s]
     Running 'regtest-stabilization.R' [46s]
     Running 'regtest-stabsel.R' [10s]
    Running the tests in 'tests/regtest-noncyclic_fitting.R' failed.
    Complete output:
     > require("gamboostLSS")
     Loading required package: gamboostLSS
     Loading required package: mboost
     Loading required package: parallel
     Loading required package: stabs
    
     Attaching package: 'gamboostLSS'
    
     The following object is masked from 'package:stats':
    
     model.weights
    
     >
     > ###negbin dist, linear###
     >
     > set.seed(2611)
     > x1 <- rnorm(1000)
     > x2 <- rnorm(1000)
     > x3 <- rnorm(1000)
     > x4 <- rnorm(1000)
     > x5 <- rnorm(1000)
     > x6 <- rnorm(1000)
     > mu <- exp(1.5 + x1^2 +0.5 * x2 - 3 * sin(x3) -1 * x4)
     > sigma <- exp(-0.2 * x4 +0.2 * x5 +0.4 * x6)
     > y <- numeric(1000)
     > for (i in 1:1000)
     + y[i] <- rnbinom(1, size = sigma[i], mu = mu[i])
     > dat <- data.frame(x1, x2, x3, x4, x5, x6, y)
     >
     > #fit models at number of params + 1
     >
     > #glmboost
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     >
     > #linear baselearner with bols
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bols")
     >
     > #nonlinear bbs baselearner
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic",
     + baselearner = "bbs")
     >
     > #reducing model and increasing it afterwards should yield the same fit
     >
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bols")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     >
     > model <- gamboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 50), method = "noncyclic",
     + baselearner = "bbs")
     >
     > m_co <- coef(model)
     >
     > mstop(model) <- 5
     > mstop(model) <- 50
     >
     > stopifnot(all.equal(m_co, coef(model)))
     >
     > ## check cvrisk for noncyclic models
     > model <- glmboostLSS(y ~ ., families = NBinomialLSS(), data = dat,
     + control = boost_control(mstop = 3), method = "noncyclic")
     > cvr1 <- cvrisk(model, grid = 1:50, cv(model.weights(model), B = 5))
     Starting cross-validation...
     [Fold: 1]
     [ 1] ........................................ -- risk: 1805.447
     [ 41] .........
     Final risk: 1799.837
    
     [Fold: 2]
     [ 1] ........................................ -- risk: 1734.54
     [ 41] .........
     Final risk: 1732.471
    
     [Fold: 3]
     [ 1] ........................................ -- risk: 1836.44
     [ 41] .........
     Final risk: 1830.995
    
     [Fold: 4]
     [ 1] ........................................ -- risk: 1644.972
     [ 41] .........
     Final risk: 1643.654
    
     [Fold: 5]
     [ 1] ........................................ -- risk: 1748.201
     [ 41] .........
     Final risk: 1745.054
     > cvr1
    
     Cross-validated
     glmboostLSS(formula = y ~ ., data = dat, families = NBinomialLSS(), control = boost_control(mstop = 3), method = "noncyclic")
    
     1 2 3 4 5 6 7 8
     4.857889 4.857889 4.854336 4.851760 4.848367 4.845487 4.843456 4.840692
     9 10 11 12 13 14 15 16
     4.837335 4.835769 4.833281 4.831312 4.829041 4.827176 4.824955 4.822376
     17 18 19 20 21 22 23 24
     4.820667 4.819740 4.817552 4.816011 4.813472 4.812703 4.810620 4.809356
     25 26 27 28 29 30 31 32
     4.807388 4.806713 4.804566 4.803307 4.801508 4.800541 4.799011 4.798048
     33 34 35 36 37 38 39 40
     4.796181 4.795305 4.793928 4.793380 4.791924 4.790579 4.789696 4.788866
     41 42 43 44 45 46 47 48
     4.787808 4.786352 4.785354 4.784043 4.783679 4.782704 4.781571 4.780256
     49 50
     4.779861 4.778943
    
     Optimal number of boosting iterations: 50
     > plot(cvr1)
     >
     > risk(model, merge = TRUE)
     mu sigma sigma mu mu sigma mu mu
     1770.175 1770.175 1768.441 1768.050 1767.677 1766.076 1765.724 1765.388
     sigma mu mu sigma mu mu sigma sigma
     1763.912 1763.594 1763.292 1761.933 1761.646 1761.373 1760.615 1759.371
     mu mu mu sigma sigma mu mu sigma
     1759.107 1758.855 1758.614 1757.906 1756.754 1756.521 1756.299 1755.650
     mu mu sigma sigma mu mu mu sigma
     1755.432 1755.224 1754.151 1753.555 1753.354 1753.162 1752.977 1751.993
     sigma mu mu mu sigma sigma mu mu
     1751.437 1751.259 1751.089 1750.925 1750.025 1749.507 1749.349 1749.182
     mu sigma sigma mu mu mu sigma sigma
     1749.036 1748.201 1747.724 1747.584 1747.450 1747.321 1746.559 1746.116
     mu mu mu sigma
     1745.992 1745.873 1745.759 1745.054
     > risk(model, merge = FALSE)
     $mu
     [1] 4755.327 4746.600
    
     $sigma
     [1] 4755.327 4752.028 4749.214
    
     attr(,"class")
     [1] "inbag"
     >
     >
     > ## test that mstop = 0 is possible
     > compare_models <- function (m1, m2) {
     + stopifnot(all.equal(coef(m1), coef(m2)))
     + stopifnot(all.equal(predict(m1), predict(m2)))
     + stopifnot(all.equal(fitted(m1), fitted(m2)))
     + stopifnot(all.equal(selected(m1), selected(m2)))
     + stopifnot(all.equal(risk(m1), risk(m2)))
     + ## remove obvious differences from objects
     + m1$control <- m2$control <- NULL
     + m1$call <- m2$call <- NULL
     + if (!all.equal(m1, m2))
     + stop("Objects of offset model + 1 step and model with 1 step not identical")
     + invisible(NULL)
     + }
     >
     > # set up models
     > mod <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 0))
     > mod2 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     > mod3 <- glmboostLSS(y ~ ., data = dat, method = "noncyclic", control = boost_control(mstop = 1))
     >
     > lapply(coef(mod), function(x) stopifnot(is.null(x)))
     $mu
     NULL
    
     $sigma
     NULL
    
     >
     > mstop(mod3) <- 0
     > mapply(compare_models, m1 = mod, m2 = mod3)
     Error in !all.equal(m1, m2) : invalid argument type
     Calls: mapply -> <Anonymous>
     Execution halted
Flavor: r-devel-windows-ix86+x86_64

Version: 2.0-1.1
Check: re-building of vignette outputs
Result: WARN
    Error(s) in re-building vignettes:
     ...
    --- re-building ‘gamboostLSS_Tutorial.Rnw’ using Sweave
    Loading required package: R2BayesX
    Loading required package: BayesXsrc
    Loading required package: colorspace
    Loading required package: mgcv
    Loading required package: nlme
    This is mgcv 1.8-33. For overview type 'help("mgcv-package")'.
    Loading required package: gamboostLSS
    Loading required package: mboost
    Loading required package: parallel
    Loading required package: stabs
    
    Attaching package: 'gamboostLSS'
    
    The following object is masked from 'package:stats':
    
     model.weights
    
    Loading required namespace: BayesX
    Error: processing vignette 'gamboostLSS_Tutorial.Rnw' failed with diagnostics:
    Running ‘texi2dvi’ on ‘gamboostLSS_Tutorial.tex’ failed.
    LaTeX errors:
    ! Undefined control sequence.
    <recently read> \Hy@colorlink
    
    l.107 \begin{document}
    
    ! Undefined control sequence.
    \close@pdflink ->\Hy@endcolorlink
     \Hy@VerboseLinkStop \pdfendlink
    l.107 \begin{document}
    
    ! Undefined control sequence.
    <recently read> \Hy@colorlink
    
    l.107 \begin{document}
    
    ! Undefined control sequence.
    \close@pdflink ->\Hy@endcolorlink
     \Hy@VerboseLinkStop \pdfendlink
    l.107 \begin{document}
    
    ! Undefined control sequence.
    \hyper@linkurl ...tionraw >>}\relax \Hy@colorlink
     \@urlcolor #1\Hy@xspace@en...
    l.107 \begin{document}
    
    ! Undefined control sequence.
    \close@pdflink ->\Hy@endcolorlink
     \Hy@VerboseLinkStop \pdfendlink
    l.107 \begin{document}
    
    --- failed re-building 'gamboostLSS_Tutorial.Rnw'
    
    SUMMARY: processing the following file failed:
     'gamboostLSS_Tutorial.Rnw'
    
    Error: Vignette re-building failed.
    Execution halted
Flavor: r-release-linux-x86_64