after the dir is created there is no message where it was created and if the process was successful
be more verbose and let the user know that the process was OK and where is the outpur
(see verbose parameter in DALEX::explain)

Assigned: Mateusz

if the dir already exists issue an warning before any file will be overridden

Assigned: Mateusz

Assigned: Adam

without explicit permission of the user

• such behaviour leads to very unpleasant situations

(I manage to recover data only thanks to the dropbox)

Comments to make them visible

Assigned: Mateusz

in the README there is a link to example application
https://adamr.shinyapps.io/xai2shiny/

but there is no link to source code of this example

As a new HTML file included in package

Assigned: Mateusz

Assigned: Mateusz

Assigned: Adam

Hi @Adamoso it's me again! I've updated your package to the most recent version and now I'm getting the following error:

Error in withSpinner(uiOutput("textPred"), hide.ui = FALSE) : 
  unused argument (hide.ui = FALSE)

Reproducible example:

library(xai2shiny) # devtools::install_github("ModelOriented/xai2shiny")
library(lares) # devtools::install_github("laresbernardo/lares")
ignore <- c("PassengerId","Ticket","Cabin")
model <- h2o_automl(dft, Survived, ignore = ignore, quiet = FALSE)
explainer <- h2o_explainer(model$datasets$test, model = model$model, y = "Survived", ignore = ignore)
xai2shiny(explainer)

Assigned: Mateusz

Assigned: Mateusz

right now the name of the dir is hardcoded to 'xai2shiny'
it is a good default but allow for something else as well

Assigned: Mateusz

see for example https://mi2datalab.github.io/modelDown_example/

on the bottom there is an information when and how given app was created

as in https://github.com/ModelOriented/ArenaR/#acknowledgments

Assigned: Mateusz

See an attachement
something is wrong with the layout

Adding into created HTML file

Assigned: Adam

now BreakDown has a title,
SHAP nas no title
CeterisParibus and both title and subtitle

Assigned: Adam

either through travis or github actions
see for example https://github.com/ModelOriented/modelStudio

I have tested the code with two regressions models: xgboost and glm. The results produce an AUC plot, which is meaningless for regressions.

Assigned: Adam

Error running xai2shiny function, something about a missing comma?

Load libraries

Data transformations

suppressMessages(library(tidyverse))
suppressMessages(library(data.table))

Saving data to disk

suppressMessages(library(feather))
suppressMessages(library(arrow))
suppressMessages(library(here))

Feature engineering

suppressMessages(library(recipes))
suppressMessages(library(yardstick))

Machine learning

suppressMessages(library(tidymodels))
suppressMessages(library(themis))

Explainer

suppressMessages(library(DALEX))

dir <- "/home/paulc/projects_Paul/31_user_journey"

Load models

lasso_model <- readRDS(paste0(dir, "/R/models/02_glmnet/", "final_model_smote.Rds"))
ranger_model <- readRDS(paste0(dir, "/R/models/03_randomForest/", "final_model_smote.Rds"))

Read data

path <- paste0(dir, "/R/data/processed/", "data_final.parquet")
df.data <- setDT(read_parquet(path))

Delete col_to_del

col_to_del <- c("username", "user_id", "start_activity",
"end_activity", "cohort", "min_to_purchase",
"token_bonus_ratio", "first_purchase")
df.data[, (col_to_del) := NULL]

Split the data into training and testing sets

set.seed(2020)
train_test_split <- df.data %>%
initial_split(prop = 0.8, strata = label_fct)

Set recipie

recipie_num <- training(train_test_split) %>%
recipe(label_fct ~. ) %>% # Fomula
step_mutate(label_fct = as.factor(label_fct)) %>%
step_normalize(all_predictors()) %>%
step_smote(label_fct) %>%
prep()

create the final data

df.train <- as.data.frame(juice(recipie_num))
df.test <- as.data.frame(bake(recipie_num, new_data = testing(train_test_split)))

binary variable for explainer

df.testing_original <- testing(train_test_split)
yTest <- as.integer(ifelse(df.testing_original$label_fct == "yes", 1, 0))

df.test <- df.test %>%
select(-label_fct)

custom_predict <- function(object, newdata) {pred <- predict(object, newdata, type = "prob")
response <- pred$.pred_yes
return(response)}

lasso_explainer <- DALEX::explain(model = lasso_model,
data = df.test,
y = yTest,
predict_function = custom_predict,
label = "Lasso",
colorize = FALSE)
#> Preparation of a new explainer is initiated
#> -> model label : Lasso
#> -> data : 20514 rows 5 cols
#> -> target variable : 20514 values
#> -> predict function : custom_predict
#> -> predicted values : numerical, min = 0.1982451 , mean = 0.35857 , max = 0.9535754
#> -> model_info : package parsnip , ver. 0.1.3 , task classification ( default )
#> -> residual function : difference between y and yhat ( default )
#> -> residuals : numerical, min = -0.9535754 , mean = -0.3346352 , max = 0.8017549
#> A new explainer has been created!

ranger_explainer <- DALEX::explain(model = ranger_model,
data = df.test,
y = yTest,
predict_function = custom_predict,
label = "Random Forest",
colorize = FALSE)
#> Preparation of a new explainer is initiated
#> -> model label : Random Forest
#> -> data : 20514 rows 5 cols
#> -> target variable : 20514 values
#> -> predict function : custom_predict
#> -> predicted values : numerical, min = 0.2152264 , mean = 0.3666207 , max = 0.9012534
#> -> model_info : package parsnip , ver. 0.1.3 , task classification ( default )
#> -> residual function : difference between y and yhat ( default )
#> -> residuals : numerical, min = -0.9012534 , mean = -0.3426858 , max = 0.7847736
#> A new explainer has been created!
library(xai2shiny)
xai2shiny(lasso_explainer, ranger_explainer)
#> Loading required package: shiny
#> Error in parse(file, keep.source = FALSE, srcfile = src, encoding = enc) :
#> /tmp/RtmpdRkELf/xai2shiny/app.R:11:1: unexpected ','
#> 10: library(parsnip)
#> 11: ,
#> ^
#> Possible missing comma at:
#> 30: if(!is.null(header)) tags$li(class="header",header),
#> ^
#> Possible extra comma at:
#> 127: column(width = 3, uiOutput("pdpvariable"),),
#> ^
#> Possible missing comma at:
#> 153: nulls <- sapply(obs, function(x) length(x) == 0)
#> ^
#> Error in sourceUTF8(fullpath, envir = new.env(parent = sharedEnv)): Error sourcing /tmp/RtmpdRkELf/xai2shiny/app.R
sessionInfo()
#> R version 4.0.2 (2020-06-22)
#> Platform: x86_64-pc-linux-gnu (64-bit)
#> Running under: CentOS Linux 7 (Core)
#>
#> Matrix products: default
#> BLAS/LAPACK: /usr/lib64/libopenblasp-r0.3.3.so
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
#> [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
#> [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
#> [9] LC_ADDRESS=C LC_TELEPHONE=C
#> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
#>
#> attached base packages:
#> [1] stats graphics grDevices datasets utils methods base
#>
#> other attached packages:
#> [1] shiny_1.5.0 xai2shiny_0.1.0 DALEX_2.0
#> [4] themis_0.1.2 workflows_0.2.0 tune_0.1.1
#> [7] rsample_0.0.8 parsnip_0.1.3 modeldata_0.0.2
#> [10] infer_0.5.3 dials_0.0.9 scales_1.1.1
#> [13] broom_0.7.0 tidymodels_0.1.1.9000 yardstick_0.0.7
#> [16] recipes_0.1.13 here_0.1 arrow_1.0.0.20200728
#> [19] feather_0.3.5 data.table_1.12.8 forcats_0.5.0
#> [22] stringr_1.4.0 dplyr_1.0.2 purrr_0.3.4
#> [25] readr_1.4.0 tidyr_1.1.2 tibble_3.0.4
#> [28] ggplot2_3.3.2 tidyverse_1.3.0
#>
#> loaded via a namespace (and not attached):
#> [1] readxl_1.3.1 mlr_2.17.1 backports_1.1.10
#> [4] fastmatch_1.1-0 plyr_1.8.6 shinydashboard_0.7.1
#> [7] splines_4.0.2 listenv_0.8.0 digest_0.6.26
#> [10] foreach_1.5.0 htmltools_0.5.0 fansi_0.4.1
#> [13] magrittr_1.5 checkmate_2.0.0 BBmisc_1.11
#> [16] unbalanced_2.0 doParallel_1.0.15 globals_0.13.0
#> [19] modelr_0.1.8 gower_0.2.2 colorspace_1.4-1
#> [22] blob_1.2.1 rvest_0.3.5 haven_2.3.1
#> [25] xfun_0.17 crayon_1.3.4 jsonlite_1.7.1
#> [28] survival_3.1-12 iterators_1.0.12 glue_1.4.2
#> [31] gtable_0.3.0 ipred_0.9-9 shape_1.4.4
#> [34] DBI_1.1.0 Rcpp_1.0.5 xtable_1.8-4
#> [37] GPfit_1.0-8 bit_1.1-15.2 lava_1.6.8
#> [40] prodlim_2019.11.13 glmnet_4.0-2 httr_1.4.1
#> [43] sourcetools_0.1.7 FNN_1.1.3 ellipsis_0.3.1
#> [46] pkgconfig_2.0.3 ParamHelpers_1.14 nnet_7.3-14
#> [49] dbplyr_1.4.4 tidyselect_1.1.0 rlang_0.4.8
#> [52] DiceDesign_1.8-1 later_1.1.0.1 munsell_0.5.0
#> [55] cellranger_1.1.0 tools_4.0.2 cli_2.1.0
#> [58] generics_0.0.2 ranger_0.12.1 evaluate_0.14
#> [61] fastmap_1.0.1 yaml_2.2.1 knitr_1.30
#> [64] bit64_0.9-7 fs_1.4.2 shinycssloaders_1.0.0
#> [67] RANN_2.6.1 future_1.19.1 whisker_0.4
#> [70] mime_0.9 xml2_1.3.2 compiler_4.0.2
#> [73] rstudioapi_0.11 reprex_0.3.0 lhs_1.0.2
#> [76] stringi_1.5.3 highr_0.8 lattice_0.20-41
#> [79] Matrix_1.2-18 shinyjs_2.0.0 vctrs_0.3.4
#> [82] pillar_1.4.6 lifecycle_0.2.0 furrr_0.1.0
#> [85] httpuv_1.5.4 R6_2.4.1 promises_1.1.1
#> [88] renv_0.12.0-12 codetools_0.2-16 MASS_7.3-51.6
#> [91] assertthat_0.2.1 rprojroot_1.3-2 shinyWidgets_0.5.4
#> [94] ROSE_0.0-3 withr_2.3.0 parallel_4.0.2
#> [97] hms_0.5.3 grid_4.0.2 rpart_4.1-15
#> [100] timeDate_3043.102 class_7.3-17 rmarkdown_2.3
#> [103] parallelMap_1.5.0 pROC_1.16.2 lubridate_1.7.9
Created on 2020-10-22 by the reprex package (v0.3.0)

some methods (like feature importance) have important parameters like N
what about showing such parameters in the menu

that will be easier to analyse

line 23

# TODO: create observation based on average data for each variable
chosen_observation <- data[1,-8]