erblast / easyalluvial Goto Github PK

require(tidyverse)

# causes memory overflow with dplyr dev version (8GB RAM)
df = ggplot2::diamonds %>%
  mutate_if( is.numeric, cut, 5) %>%
  group_by_all()

sessionInfo()
```
R version 3.5.2 (2018-12-20)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows >= 8 x64 (build 9200)

Matrix products: default

locale:
[1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United States.1252    LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                           LC_TIME=English_United States.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] forcats_0.3.0     stringr_1.3.1     dplyr_0.7.99.9000 purrr_0.2.5       readr_1.3.1       tidyr_0.8.2       tibble_1.4.2      ggplot2_3.1.0    
[9] tidyverse_1.2.1  

loaded via a namespace (and not attached):
 [1] Rcpp_1.0.0       cellranger_1.1.0 pillar_1.3.1     compiler_3.5.2   plyr_1.8.4       tools_3.5.2      jsonlite_1.6     lubridate_1.7.4 
 [9] gtable_0.2.0     nlme_3.1-137     lattice_0.20-38  pkgconfig_2.0.2  rlang_0.3.0.1    cli_1.0.1        rstudioapi_0.8   yaml_2.2.0      
[17] haven_2.0.0      withr_2.1.2      xml2_1.2.0       httr_1.4.0       generics_0.0.2   hms_0.4.2        grid_3.5.2       tidyselect_0.2.5
[25] glue_1.3.0       R6_2.3.0         readxl_1.2.0     modelr_0.1.2     magrittr_1.5     backports_1.1.3  scales_1.0.0     rvest_0.3.2     
[33] assertthat_0.2.0 colorspace_1.3-2 stringi_1.2.4    lazyeval_0.2.1   munsell_0.5.0    broom_0.5.1      crayon_1.3.4 

mtcars2 %>%
  select_if(is.factor) %>%
  alluvial_wide()

mtcars2 %>%
  select_if(is.factor) %>%
  mutate_all(as.character) %>%
  alluvial_wide()

> if (!require(easyalluvial)) {install.packages("easyalluvial",repos = "http://cran.us.r-project.org"); 
+         require(easyalluvial)}
Loading required package: easyalluvial
Warning in install.packages :
  package ‘easyalluvial’ is not available for this version of R

A version of this package for your version of R might be available elsewhere,
see the ideas at
https://cran.r-project.org/doc/manuals/r-patched/R-admin.html#Installing-packages

> if (!require(parcats)) {install.packages("parcats",repos = "http://cran.us.r-project.org"); 
+         require(parcats)}
Loading required package: parcats
Warning in install.packages :
  package ‘parcats’ is not available for this version of R

A version of this package for your version of R might be available elsewhere,
see the ideas at
https://cran.r-project.org/doc/manuals/r-patched/R-admin.html#Installing-packages

Dear maintainer,
 
package ggalluvial_0.12.5.tar.gz has been auto-processed. The auto-check found problems when checking the first order strong reverse dependencies.
Please reply-all and explain: Is this expected or do you need to fix anything in your package? If expected, have all maintainers of affected packages been informed well in advance? Are there false positives in our results?
 
*** Changes to worse in reverse dependencies ***
Debian: [<https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/reverseDependencies/summary.txt>](https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/reverseDependencies/summary.txt)
 
Log dir: [<https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/>](https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/)
The files will be removed after roughly 7 days.
 
Pretests:
Windows: [<https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/Windows/00check.log>](https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/Windows/00check.log)
Debian: [<https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/Debian/00check.log>](https://win-builder.r-project.org/incoming_pretest/ggalluvial_0.12.5_20230213_172426/Debian/00check.log)
 
Last published version on CRAN:
 
CRAN Web: [<https://cran.r-project.org/package=ggalluvial>](https://cran.r-project.org/package=ggalluvial)
 
Best regards,
CRAN teams' auto-check service


Package check result: OK

Changes to worse in reverse depends:

Package: easyalluvial
Check: whether package can be installed
New result: ERROR
  Installation failed.

install.packages("titanic") # only data in package
data("titanic_train",package="titanic")
library(tidyverse)
str(titanic_train)

d <- titanic_train %>% as_tibble %>%
  mutate(title=str_replace_all(string = Name, # extract title as general feature
                               pattern = "^[[:alpha:][:space:]'-]+,\\s+(the\\s)?(\\w+)\\..+",
                               replacement = "\\2")) %>%
  mutate(title=str_trim(title),
         title=case_when(title %in% c('Mlle','Ms')~'Miss', # normalize some titles
                         title=='Mme'~ 'Mrs',
                         title %in% c('Capt','Don','Major','Sir','Jonkheer', 'Col')~'Sir',
                         title %in% c('Dona', 'Lady', 'Countess')~'Lady',
                         TRUE~title)) %>%
  mutate(title=as_factor(title),
         Survived=factor(Survived,levels = c(0,1),labels=c("no","yes")),
         Sex=as_factor(Sex),
         Pclass=factor(Pclass,ordered = T)) %>%
  group_by(title) %>% # impute Age by median in current title
  mutate(Age=replace_na(Age,replace = median(Age,na.rm = T))) %>% ungroup
table(d$title,d$Sex) # look on title distribution        
caret::nearZeroVar(x = d,saveMetrics = T) # search and drop some unusefull features (PassengerId,Name,Ticket)
d <- d %>% select_at(vars(-c(PassengerId,Name,Ticket)))
d %>% summarise_all(~sum(is.na(.))) # control NAs

library(ranger)
m <- ranger(formula = Survived~.,data = d,mtry = 6,min.node.size = 5, num.trees = 600,
            importance = "permutation")

library(easyalluvial)
imp <- importance(m) %>% as.data.frame %>% tidy_imp(imp = .,df=d)
alluvial_wide(data = select(d,Survived,title,Pclass,Sex,Fare),fill_by = "first_variable") # ok, it work but i wont describe model (not describe data)

gds <- get_data_space(df = d,imp,degree = 4) # Error in Summary.factor(c(1L, 2L, 3L, 2L, 1L, 1L, 1L, 4L, 2L, 2L, 3L,  : ‘max’ not meaningful for factors

# ok, don`t  give up and try caret
library(caret)
trc <- trainControl(method = "none")
m <- train(Survived~.,data = d,method="rf",trControl=trc,importance=T)
alluvial_model_response_caret(train = m,degree = 4,bins=5,stratum_label_size = 2.8) # Error in tidy_imp(imp, df) : not all listed important variables found in input data

   > 
   > data = as_tibble(mtcars)
   > categoricals = c('cyl', 'vs', 'am', 'gear', 'carb')
   > numericals = c('mpg', 'cyl', 'disp', 'hp', 'drat', 'wt', 'qsec')
   > max_variables = 5
   > 
   > data = data %>%
   +   mutate_at( vars(categoricals), as.factor )
   > 
   > 
   > alluvial_wide( data = data
   +                 , max_variables = max_variables
   +                 , fill_by = 'first_variable' )
   Error: No role currently exists for column(s): 'easyalluvialid'. Please use `update_role()` instead.
   Execution halted