CRAN Package Check Results for Package ingredients

Last updated on 2020-02-27 17:50:58 CET.

Flavor Version Tinstall Tcheck Ttotal Status Flags
r-devel-linux-x86_64-debian-clang 1.0 6.28 320.22 326.50 ERROR
r-devel-linux-x86_64-debian-gcc 1.0 4.93 247.18 252.11 ERROR
r-devel-linux-x86_64-fedora-clang 1.0 424.68 OK
r-devel-linux-x86_64-fedora-gcc 1.0 413.33 OK
r-devel-windows-ix86+x86_64 1.0 20.00 424.00 444.00 OK
r-devel-windows-ix86+x86_64-gcc8 1.0 16.00 349.00 365.00 OK
r-patched-linux-x86_64 1.0 6.13 310.81 316.94 OK
r-patched-solaris-x86 1.0 621.80 OK
r-release-linux-x86_64 1.0 5.73 304.13 309.86 OK
r-release-windows-ix86+x86_64 1.0 16.00 312.00 328.00 OK
r-release-osx-x86_64 1.0 OK
r-oldrel-windows-ix86+x86_64 1.0 10.00 304.00 314.00 OK
r-oldrel-osx-x86_64 1.0 OK

Check Details

Version: 1.0
Check: examples
Result: ERROR
    Running examples in 'ingredients-Ex.R' failed
    The error most likely occurred in:
    
    > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
    > ### Name: plotD3.aggregated_profiles_explainer
    > ### Title: Plots Aggregated Ceteris Paribus Profiles in D3 with r2d3
    > ### Package.
    > ### Aliases: plotD3.aggregated_profiles_explainer
    >
    > ### ** Examples
    >
    > library("DALEX")
    Welcome to DALEX (version: 1.0).
    Find examples and detailed introduction at: https://pbiecek.github.io/ema/
    
    
    Attaching package: 'DALEX'
    
    The following object is masked from 'package:ingredients':
    
     feature_importance
    
    > library("randomForest")
    randomForest 4.6-14
    Type rfNews() to see new features/changes/bug fixes.
    >
    > # smaller data, quicker example
    > titanic_small <- select_sample(titanic_imputed, n = 500, seed = 1313)
    >
    > # build a model
    > model_titanic_rf <- randomForest(survived ~., data = titanic_small)
    Warning in randomForest.default(m, y, ...) :
     The response has five or fewer unique values. Are you sure you want to do regression?
    >
    > explain_titanic_rf <- explain(model_titanic_rf,
    + data = titanic_small[,-8],
    + y = titanic_small[,8],
    + label = "Random Forest v7")
    Preparation of a new explainer is initiated
     -> model label : Random Forest v7
     -> data : 500 rows 7 cols
     -> target variable : 500 values
     -> model_info : package randomForest , ver. 4.6.14 , task regression ( <1b>[33m default <1b>[39m )
     -> predict function : yhat.randomForest will be used ( <1b>[33m default <1b>[39m )
     -> predicted values : numerical, min = 0.02519995 , mean = 0.3007432 , max = 0.9799076
     -> residual function : difference between y and yhat ( <1b>[33m default <1b>[39m )
     -> residuals : numerical, min = -0.7228011 , mean = 0.001256827 , max = 0.8084979
     <1b>[32m A new explainer has been created! <1b>[39m
    >
    > selected_passangers <- select_sample(titanic_small, n = 100)
    > cp_rf <- ceteris_paribus(explain_titanic_rf, selected_passangers)
    >
    > pdp_rf_p <- aggregate_profiles(cp_rf, type = "partial", variable_type = "numerical")
    > pdp_rf_p$`_label_` <- "RF_partial"
    > pdp_rf_c <- aggregate_profiles(cp_rf, type = "conditional", variable_type = "numerical")
    > pdp_rf_c$`_label_` <- "RF_conditional"
    > pdp_rf_a <- aggregate_profiles(cp_rf, type = "accumulated", variable_type = "numerical")
    > pdp_rf_a$`_label_` <- "RF_accumulated"
    >
    > plotD3(pdp_rf_p, pdp_rf_c, pdp_rf_a, scale_plot = TRUE)
    Error in UseMethod("droplevels") :
     no applicable method for 'droplevels' applied to an object of class "character"
    Calls: plotD3 -> plotD3.aggregated_profiles_explainer -> droplevels
    Execution halted
Flavor: r-devel-linux-x86_64-debian-clang

Version: 1.0
Check: tests
Result: ERROR
     Running 'testthat.R' [183s/199s]
    Running the tests in 'tests/testthat.R' failed.
    Complete output:
     > library(testthat)
     > library(DALEX)
     Welcome to DALEX (version: 1.0).
     Find examples and detailed introduction at: https://pbiecek.github.io/ema/
    
     > library(ingredients)
    
     Attaching package: 'ingredients'
    
     The following object is masked from 'package:DALEX':
    
     feature_importance
    
     The following object is masked from 'package:testthat':
    
     describe
    
     >
     > test_check("ingredients")
     randomForest 4.6-14
     Type rfNews() to see new features/changes/bug fixes.
     Preparation of a new explainer is initiated
     -> model label : RF
     -> data : 461 rows 9 cols
     -> target variable : 461 values
     -> model_info : package randomForest , ver. 4.6.14 , task classification ( <1b>[33m default <1b>[39m )
     -> predict function : yhat.randomForest will be used ( <1b>[33m default <1b>[39m )
     -> predicted values : numerical, min = 0 , mean = 0.3930672 , max = 0.996
     -> residual function : difference between y and yhat ( <1b>[33m default <1b>[39m )
     -> residuals : numerical, min = -0.652 , mean = 0.01257267 , max = 0.898
     <1b>[32m A new explainer has been created! <1b>[39m
     -- 1. Error: plotD3 Ceteris Paribus and plotD3 Aggregated Profiles (@test_plotD3
     no applicable method for 'droplevels' applied to an object of class "character"
     Backtrace:
     1. ingredients::plotD3(...)
     2. ingredients:::plotD3.ceteris_paribus_explainer(...)
     3. base::droplevels(all_profiles$`_vname_`)
    
     Preparation of a new explainer is initiated
     -> model label : RF
     -> data : 65 rows 4 cols
     -> target variable : 65 values
     -> model_info : package randomForest , ver. 4.6.14 , task classification ( <1b>[33m default <1b>[39m )
     -> predict function : yhat.randomForest will be used ( <1b>[33m default <1b>[39m )
     -> predicted values : numerical, min = 0.006 , mean = 0.3797846 , max = 0.948
     -> residual function : difference between y and yhat ( <1b>[33m default <1b>[39m )
     -> residuals : numerical, min = -0.45 , mean = 0.05098462 , max = 0.768
     <1b>[32m A new explainer has been created! <1b>[39m
     == testthat results ===========================================================
     [ OK: 113 | SKIPPED: 0 | WARNINGS: 5 | FAILED: 1 ]
     1. Error: plotD3 Ceteris Paribus and plotD3 Aggregated Profiles (@test_plotD3.R#45)
    
     Error: testthat unit tests failed
     In addition: Warning message:
     In Ops.factor(y, predict_function(model, data)) :
     '-' not meaningful for factors
     Execution halted
Flavor: r-devel-linux-x86_64-debian-clang

Version: 1.0
Check: examples
Result: ERROR
    Running examples in ‘ingredients-Ex.R’ failed
    The error most likely occurred in:
    
    > base::assign(".ptime", proc.time(), pos = "CheckExEnv")
    > ### Name: plotD3.aggregated_profiles_explainer
    > ### Title: Plots Aggregated Ceteris Paribus Profiles in D3 with r2d3
    > ### Package.
    > ### Aliases: plotD3.aggregated_profiles_explainer
    >
    > ### ** Examples
    >
    > library("DALEX")
    Welcome to DALEX (version: 1.0.1).
    Find examples and detailed introduction at: https://pbiecek.github.io/ema/
    
    
    Attaching package: ‘DALEX’
    
    The following object is masked from ‘package:ingredients’:
    
     feature_importance
    
    > library("randomForest")
    randomForest 4.6-14
    Type rfNews() to see new features/changes/bug fixes.
    >
    > # smaller data, quicker example
    > titanic_small <- select_sample(titanic_imputed, n = 500, seed = 1313)
    >
    > # build a model
    > model_titanic_rf <- randomForest(survived ~., data = titanic_small)
    Warning in randomForest.default(m, y, ...) :
     The response has five or fewer unique values. Are you sure you want to do regression?
    >
    > explain_titanic_rf <- explain(model_titanic_rf,
    + data = titanic_small[,-8],
    + y = titanic_small[,8],
    + label = "Random Forest v7")
    Preparation of a new explainer is initiated
     -> model label : Random Forest v7
     -> data : 500 rows 7 cols
     -> target variable : 500 values
     -> model_info : package randomForest , ver. 4.6.14 , task regression ( <1b>[33m default <1b>[39m )
     -> predict function : yhat.randomForest will be used ( <1b>[33m default <1b>[39m )
     -> predicted values : numerical, min = 0.02519995 , mean = 0.3007432 , max = 0.9799076
     -> residual function : difference between y and yhat ( <1b>[33m default <1b>[39m )
     -> residuals : numerical, min = -0.7228011 , mean = 0.001256827 , max = 0.8084979
     <1b>[32m A new explainer has been created! <1b>[39m
    >
    > selected_passangers <- select_sample(titanic_small, n = 100)
    > cp_rf <- ceteris_paribus(explain_titanic_rf, selected_passangers)
    >
    > pdp_rf_p <- aggregate_profiles(cp_rf, type = "partial", variable_type = "numerical")
    > pdp_rf_p$`_label_` <- "RF_partial"
    > pdp_rf_c <- aggregate_profiles(cp_rf, type = "conditional", variable_type = "numerical")
    > pdp_rf_c$`_label_` <- "RF_conditional"
    > pdp_rf_a <- aggregate_profiles(cp_rf, type = "accumulated", variable_type = "numerical")
    > pdp_rf_a$`_label_` <- "RF_accumulated"
    >
    > plotD3(pdp_rf_p, pdp_rf_c, pdp_rf_a, scale_plot = TRUE)
    Error in UseMethod("droplevels") :
     no applicable method for 'droplevels' applied to an object of class "character"
    Calls: plotD3 -> plotD3.aggregated_profiles_explainer -> droplevels
    Execution halted
Flavor: r-devel-linux-x86_64-debian-gcc

Version: 1.0
Check: tests
Result: ERROR
     Running ‘testthat.R’ [141s/208s]
    Running the tests in ‘tests/testthat.R’ failed.
    Complete output:
     > library(testthat)
     > library(DALEX)
     Welcome to DALEX (version: 1.0.1).
     Find examples and detailed introduction at: https://pbiecek.github.io/ema/
    
     > library(ingredients)
    
     Attaching package: 'ingredients'
    
     The following object is masked from 'package:DALEX':
    
     feature_importance
    
     The following object is masked from 'package:testthat':
    
     describe
    
     >
     > test_check("ingredients")
     randomForest 4.6-14
     Type rfNews() to see new features/changes/bug fixes.
     Preparation of a new explainer is initiated
     -> model label : RF
     -> data : 461 rows 9 cols
     -> target variable : 461 values
     -> model_info : package randomForest , ver. 4.6.14 , task classification ( <1b>[33m default <1b>[39m )
     -> predict function : yhat.randomForest will be used ( <1b>[33m default <1b>[39m )
     -> predicted values : numerical, min = 0 , mean = 0.3930672 , max = 0.996
     -> residual function : difference between y and yhat ( <1b>[33m default <1b>[39m )
     -> residuals : numerical, min = -0.652 , mean = 0.01257267 , max = 0.898
     <1b>[32m A new explainer has been created! <1b>[39m
     ── 1. Error: plotD3 Ceteris Paribus and plotD3 Aggregated Profiles (@test_plotD3
     no applicable method for 'droplevels' applied to an object of class "character"
     Backtrace:
     1. ingredients::plotD3(...)
     2. ingredients:::plotD3.ceteris_paribus_explainer(...)
     3. base::droplevels(all_profiles$`_vname_`)
    
     Preparation of a new explainer is initiated
     -> model label : RF
     -> data : 65 rows 4 cols
     -> target variable : 65 values
     -> model_info : package randomForest , ver. 4.6.14 , task classification ( <1b>[33m default <1b>[39m )
     -> predict function : yhat.randomForest will be used ( <1b>[33m default <1b>[39m )
     -> predicted values : numerical, min = 0.006 , mean = 0.3797846 , max = 0.948
     -> residual function : difference between y and yhat ( <1b>[33m default <1b>[39m )
     -> residuals : numerical, min = -0.45 , mean = 0.05098462 , max = 0.768
     <1b>[32m A new explainer has been created! <1b>[39m
     ══ testthat results ═══════════════════════════════════════════════════════════
     [ OK: 113 | SKIPPED: 0 | WARNINGS: 5 | FAILED: 1 ]
     1. Error: plotD3 Ceteris Paribus and plotD3 Aggregated Profiles (@test_plotD3.R#45)
    
     Error: testthat unit tests failed
     In addition: Warning message:
     In Ops.factor(y, predict_function(model, data)) :
     '-' not meaningful for factors
     Execution halted
Flavor: r-devel-linux-x86_64-debian-gcc