CRAN Package Check Results for Package CBDA

Last updated on 2020-08-07 01:49:38 CEST.

Check Details

Version: 1.0.0
Check: dependencies in R code
Result: NOTE
    Namespace in Imports field not imported from: ‘prettydoc’
     All declared Imports should be used.
Flavors: r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-patched-solaris-x86, r-release-macos-x86_64, r-oldrel-macos-x86_64

Version: 1.0.0
Check: tests
Result: ERROR
     Running ‘CBDA_test_training.R’ [174s/196s]
    Running the tests in ‘tests/CBDA_test_training.R’ failed.
    Complete output:
     > # Attach the CBDA library
     > suppressPackageStartupMessages(library(CBDA))
     > suppressPackageStartupMessages(library(randomForest ))
     > suppressPackageStartupMessages(library(glmnet ))
     > suppressPackageStartupMessages(library(SuperLearner))
     > suppressPackageStartupMessages(library(bartMachine))
     >
     > library(CBDA, quietly = TRUE, verbose = FALSE)
     > CBDA_initialization()
     package missForest already installed
     package stats already installed
     package utils already installed
     package prettydoc already installed
     package foreach already installed
     package SuperLearner already installed
     package knockoff already installed
     package caret already installed
     package smotefamily already installed
     package parallel already installed
     package doParallel already installed
     package glmnet already installed
     Loading required package: prettydoc
     Loading required package: knockoff
     Loading required package: caret
     Loading required package: lattice
     Loading required package: ggplot2
    
     Attaching package: 'ggplot2'
    
     The following object is masked from 'package:randomForest':
    
     margin
    
     Loading required package: smotefamily
     Loading required package: parallel
     Loading required package: doParallel
     missForest stats utils prettydoc foreach SuperLearner
     TRUE TRUE TRUE TRUE TRUE TRUE
     knockoff caret smotefamily parallel doParallel glmnet
     TRUE TRUE TRUE TRUE TRUE TRUE
     >
     > # Set the specs for the synthetic dataset to be tested
     > n = 300 # number of observations
     > p = 100 # number of variables
     >
     > # Generate a nxp matrix of IID variables (e.g., ~N(0,1))
     > X1 = matrix(rnorm(n*p), nrow=n, ncol=p)
     >
     > # Setting the nonzero variables - signal variables
     > #nonzero=c(1,100,200,300,400,500,600,700,800,900)
     > nonzero=c(10,20,30,40,50,60,70,80,90,100)
     >
     > # Set the signal amplitude (for noise level = 1)
     > amplitude = 10
     >
     > # Allocate the nonzero coefficients in the correct places
     > beta = amplitude * (1:p %in% nonzero)
     >
     > # Generate a linear model with a bias (e.g., white noise ~N(0,1))
     > ztemp <- function() X1 %*% beta + rnorm(n)
     > z = ztemp()
     >
     > # Pass it through an inv-logit function to
     > # generate the Bernoulli response variable Ytemp
     > pr = 1/(1+exp(-z))
     > Ytemp = rbinom(n,1,pr)
     > X2 <- cbind(Ytemp,X1)
     >
     > dataset_file ="Binomial_dataset.txt"
     >
     > # Save the synthetic dataset
     > a <- tempdir()
     > write.table(X2, file = file.path(a, dataset_file), sep=",")
     >
     > # Load the Synthetic dataset
     > #Data = read.csv(paste0(file.path(a),'/',dataset_file),header = TRUE)
     > Data = read.csv(file.path(a, dataset_file),header = TRUE)
     > Ytemp <- Data[,1] # set the outcome
     > original_names_Data <- names(Data)
     > cols_to_eliminate=1
     > Xtemp <- Data[-cols_to_eliminate] # set the matrix X of features/covariates
     > original_names_Xtemp <- names(Xtemp)
     >
     > # Add more wrappers/algorithms to the SuperLearner ensemble predictor
     > # It can be commented out if only the default set of algorithms are used,
     > # e.g., algorithm_list = c("SL.glm","SL.xgboost","SL.glmnet","SL.svm",
     > # "SL.randomForest","SL.bartMachine")
     > # This defines a "new" wrapper, based on the default SL.glmnet
     > SL.glmnet.0.75 <- function(..., alpha = 0.75,family="binomial"){
     + SL.glmnet(..., alpha = alpha, family = family)}
     >
     > # Using Support Vector Machine and the new Glmnet wrapper above
     > #test_example <- c("SL.glmnet","SL.glmnet.0.75")
     > test_example <- c("SL.glmnet","SL.svm","SL.randomForest","SL.bartMachine")
     >
     > ## SINGLE CORE EXAMPLE - TRAINING/LEARNING ONLY
     > CBDA_singlecore_training <- CBDA.training(Ytemp , Xtemp , M = 8 ,
     + Nrow_min = 60, Nrow_max = 80,
     + top = 6, max_covs = 6 , min_covs = 3,
     + algorithm_list = test_example , label = "SINGLE_CORE" ,
     + workspace_directory = a)
     Subsampling size = 8
    
     Case Sampling Range - CSR (%) = 60_80 %
    
     Feature Sampling Range - FSR (%) = 5_15 %
    
     Learning/Training steps initiated successfully !!
     Loading required namespace: e1071
     Completion %
     12.5
     Completion %
     25
     Completion %
     37.5
     Completion %
     50
     Completion %
     62.5
     Completion %
     75
     Completion %
     87.5
     Error in sample.int(length(x), size, replace, prob) :
     cannot take a sample larger than the population when 'replace = FALSE'
     Calls: CBDA.training
     Execution halted
Flavor: r-patched-linux-x86_64