Merge pull request #30 from ModelOriented/before_cran

v0.1.9

Author: hbaniecki

.Rbuildignore

@@ -15,4 +15,5 @@ modelStudio_my_test.R
 ^CRAN-RELEASE$
 ^cran-comments\.md$
 ^pkgdown.*$
-CONTRIBUTING.md
+^LICENSE$
+^CONTRIBUTING.md

.travis.yml

@@ -2,6 +2,10 @@ language: R
 sudo: false
 cache: packages
 
+env:
+  global:
+  - R_CHECK_ARGS="--timings --run-donttest"
+  
 r:
   - release
   - devel

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-## Contribute to modelStudio
+# Contribute to modelStudio
 
 #### **Did you find a bug?**
 

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: modelStudio
 Title: Interactive Studio with Explanations for ML Predictive Models
-Version: 0.1.8
+Version: 0.1.9
 Authors@R:
     c(person("Hubert", "Baniecki", role = c("aut", "cre"),
              email = "[email protected]",
@@ -10,22 +10,22 @@ Authors@R:
 Description: Automate explanation of machine learning predictive models.
   This package generates advanced interactive and animated model explanations in the form
   of a serverless HTML site. It combines 'R' with 'D3.js' to produce plots and descriptions
-  for local and global explanations. The whole is greater than the sum of its parts,
-  so it also supports EDA (Exploratory Data Analysis) on top of that. 'modelStudio' is
-  a fast and condensed way to get all the answers without much effort. 
+  for various local and global explanations. Tools for model exploration unite with
+  tools for EDA (Exploratory Data Analysis) to give a broad overview of the model behaviour.
+  'modelStudio' is a fast and condensed way to get all the answers without much effort. 
   Break down your model and look into its ingredients with only a few lines of code.
 Depends: R (>= 3.5.0)
-License: file LICENSE
+License: GPL-2
 Encoding: UTF-8
 LazyData: true
 RoxygenNote: 6.1.1
 Imports:
     iBreakDown (>= 0.9.9),
-    ingredients (>= 0.3.9),
+    ingredients (>= 0.4.0),
     r2d3,
     jsonlite
 Suggests:
-    DALEX,
+    DALEX (>= 0.4.9),
     parallelMap,
     randomForest,
     knitr,

NEWS.md

@@ -1,6 +1,9 @@
+# modelStudio 0.1.9
+* This version requires `DALEX 0.4.9` and `ingredients 0.4.0`
+
 # modelStudio 0.1.8
-* change "Shapley Values" to "SHAP Values"
-* Lower `B` default value from 25 to 15
+* change `Shapley Values` to `SHAP Values`
+* Lower `B` default value from 25 to 15, `N` default value from 500 to 400
 
 # modelStudio 0.1.7
 * fix tests for CRAN

R/modelStudio.R

@@ -1,4 +1,4 @@
-#' @title Generates interactive studio to explain predictive model
+#' @title Generate Interactive Studio with Explanations for the Model
 #'
 #' @description
 #' This tool uses your model, data and new observations, to provide local
@@ -7,29 +7,29 @@
 #'
 #' Find more details about plots in \href{https://pbiecek.github.io/PM_VEE/}{Predictive Models: Explore, Explain, and Debug}
 #'
-#' @param object an explainer created with function \code{DALEX::explain()} or a model to be explained.
-#' @param new_observation a new observation with columns that correspond to variables used in the model.
-#' @param facet_dim dimensions of the grid. Default is \code{c(2,2)}.
-#' @param time in ms. Set animation length. Default is \code{500}.
-#' @param max_features maximum number of features to be included in Break Down and SHAP Values plots. Default is \code{10}.
-#' @param N number of observations used for calculation of partial dependency profiles. Default is \code{500}.
-#' @param B number of random paths used for calculation of SHAP values. Default is \code{15}.
-#' @param show_info verbose progress bar on console? Default is \code{TRUE}.
-#' @param parallel speed up computation using \code{parallelMap::parallelMap()}.
+#' @param object An \code{explainer} created with function \code{DALEX::explain()} or a model to be explained.
+#' @param new_observation A new observation with columns that correspond to variables used in the model.
+#' @param facet_dim Dimensions of the grid. Default is \code{c(2,2)}.
+#' @param time Time in ms. Set animation length. Default is \code{500}.
+#' @param max_features Maximum number of features to be included in Break Down and SHAP Values plots. Default is \code{10}.
+#' @param N Number of observations used for calculation of partial dependency profiles. Default is \code{400}.
+#' @param B Number of random paths used for calculation of SHAP values. Default is \code{15}.
+#' @param show_info Verbose progress bar on the console. Default is \code{TRUE}.
+#' @param parallel Speed up the computation using \code{parallelMap::parallelMap()}.
 #' See \href{https://modeloriented.github.io/modelStudio/articles/vignette_modelStudio.html#parallel-computation}{\bold{vignette}}.
 #' @param viewer Default is \code{external} to display in an external RStudio window.
 #' Use \code{browser} to display in an external browser or
 #' \code{internal} to use the RStudio internal viewer pane for output.
-#' @param options customize \code{modelStudio}. See \code{\link{modelStudioOptions}} and
+#' @param options Customize \code{modelStudio}. See \code{\link{modelStudioOptions}} and
 #' \href{https://modeloriented.github.io/modelStudio/articles/vignette_modelStudio.html#plot-options}{\bold{vignette}}.
-#' @param ... other parameters.
-#' @param data validation dataset, will be extracted from \code{object} if it is an explainer.
+#' @param ... Other parameters.
+#' @param data Validation dataset, will be extracted from \code{object} if it is an explainer.
 #' NOTE: It is best when target variable is not present in the \code{data}.
-#' @param y true labels for \code{data}, will be extracted from \code{object} if it is an explainer.
-#' @param predict_function predict function, will be extracted from \code{object} if it is an explainer.
-#' @param label a name of the model, will be extracted from \code{object} if it is an explainer.
+#' @param y True labels for \code{data}, will be extracted from \code{object} if it is an \code{explainer}.
+#' @param predict_function Predict function, will be extracted from \code{object} if it is an \code{explainer}.
+#' @param label A name of the model, will be extracted from \code{object} if it is an \code{explainer}.
 #'
-#' @return an object of the \code{r2d3} class
+#' @return An object of the \code{r2d3} class.
 #'
 #' @importFrom utils head tail setTxtProgressBar txtProgressBar installed.packages
 #' @importFrom stats aggregate predict
@@ -100,7 +100,7 @@ modelStudio.explainer <- function(object,
                                   facet_dim = c(2,2),
                                   time = 500,
                                   max_features = 10,
-                                  N = 500,
+                                  N = 400,
                                   B = 15,
                                   show_info = TRUE,
                                   parallel = FALSE,
@@ -139,7 +139,7 @@ modelStudio.default <- function(object,
                                 facet_dim = c(2,2),
                                 time = 500,
                                 max_features = 10,
-                                N = 500,
+                                N = 400,
                                 B = 15,
                                 show_info = TRUE,
                                 parallel = FALSE,

R/modelStudioOptions.R

@@ -1,20 +1,20 @@
-#' @title Get modified options for modelStudio
+#' @title Modifiy options and pass them to modelStudio
 #'
 #' @description This function returns default options for \code{\link{modelStudio}}.
-#' It is possible to modify values of this list and pass it to \code{options}
+#' It is possible to modify values of this list and pass it to the \code{options}
 #' parameter in the main function. \strong{WARNING: Editing default options may cause
 #' unintended behavior.}
 #'
-#' @param ... options to change, \code{option_name = value}.
+#' @param ... Options to change, \code{option_name = value}.
 #'
-#' @return \code{list} of options for modelStudio
+#' @return \code{list} of options for \code{modelStudio}.
 #'
 #' \subsection{Main options:}{
 #' \describe{
 #' \item{scale_plot}{\code{TRUE} Makes every plot the same height, ignores \code{bar_width}.}
-#' \item{show_subtitle}{\code{TRUE} Should subtitle be displayed?}
+#' \item{show_subtitle}{\code{TRUE} Should the subtitle be displayed?}
 #' \item{subtitle}{\code{label} parameter from \code{explainer}.}
-#' \item{margin_*}{plot margins. Change \code{margin_left} for longer/shorter axis labels.}
+#' \item{margin_*}{Plot margins. Change \code{margin_left} for longer/shorter axis labels.}
 #' \item{w}{\code{420} in px. Inner plot width.}
 #' \item{h}{\code{280} in px. Inner plot height.}
 #' \item{bar_width}{\code{16} in px. Default width of bars for all plots,
@@ -32,13 +32,13 @@
 #' one of \code{[bd,sv,cp,fi,pd,ad,fd]}.\cr
 #'
 #' \describe{
-#' \item{**_title}{plot specific title. Default varies.}
-#' \item{**_subtitle}{plot specific subtitle. Default is \code{subtitle}.}
-#' \item{**_bar_width}{plot specific width of bars. Default is \code{bar_width},
+#' \item{**_title}{Plot specific title. Default varies.}
+#' \item{**_subtitle}{Plot specific subtitle. Default is \code{subtitle}.}
+#' \item{**_bar_width}{Plot specific width of bars. Default is \code{bar_width},
 #' ignored when \code{scale_plot = TRUE}.}
-#' \item{**_line_size}{\code{line_size} plot specific width of lines. Default is \code{line_size}.}
-#' \item{**_point_size}{plot specific point radius. Default is \code{point_size}.}
-#' \item{**_*_color}{plot specific \code{[bar,line,point]} color. Default is \code{[bar,line,point]_color}.}
+#' \item{**_line_size}{\code{line_size} Plot specific width of lines. Default is \code{line_size}.}
+#' \item{**_point_size}{Plot specific point radius. Default is \code{point_size}.}
+#' \item{**_*_color}{Plot specific \code{[bar,line,point]} color. Default is \code{[bar,line,point]_color}.}
 #' }
 #' }
 #'

README.md

@@ -5,16 +5,16 @@
 [![Build Status](https://travis-ci.org/ModelOriented/modelStudio.svg?branch=master)](https://travis-ci.org/ModelOriented/modelStudio)
 [![Coverage Status](https://codecov.io/gh/ModelOriented/modelStudio/branch/master/graph/badge.svg)](https://codecov.io/github/ModelOriented/modelStudio?branch=master)
 [![DrWhy-eXtrAI](https://img.shields.io/badge/DrWhy-AutoMat-ae2c87)](http://drwhy.ai/#AutoMat)
+[![JOSS-status](https://joss.theoj.org/papers/9eec8c9d1969fbd44b3ea438a74af911/status.svg)](https://joss.theoj.org/papers/9eec8c9d1969fbd44b3ea438a74af911)
 
 ## Overview
 
 The `modelStudio` package automates explanation of machine learning predictive models. This package generates advanced interactive and animated model explanations in the form of a serverless HTML site.
 
 It combines **R** with **D3.js** to produce plots and descriptions
-for local and global explanations. The whole is greater than the sum of its parts,
-so it also supports EDA (Exploratory Data Analysis) on top of that. `modelStudio` is
-a fast and condensed way to get all the answers without much effort. Break down your model
-and look into its ingredients with only a few lines of code.
+for various local and global explanations. Tools for model exploration unite with
+tools for EDA (Exploratory Data Analysis) to give a broad overview of the model behaviour. 
+`modelStudio` is a fast and condensed way to get all the answers without much effort. Break down your model and look into its ingredients with only a few lines of code.
 
 [See a demo](https://modeloriented.github.io/modelStudio/demo.html)   [Read the vignette: modelStudio - perks and features](https://modeloriented.github.io/modelStudio/articles/vignette_modelStudio.html)  
 
@@ -36,8 +36,6 @@ devtools::install_github("ModelOriented/modelStudio")
 
 This package bases on `DALEX` explainers created with `DALEX::explain()`.
 
-**Demo works on the new version of DALEX** ``` devtools::install_github("ModelOriented/DALEX") ```
-
 ```r
 library("modelStudio")
 
@@ -86,4 +84,4 @@ and [`r2d3::save_d3_png()`](https://rstudio.github.io/r2d3/articles/publishing.h
 
 ## Acknowledgments
 
-Work on this package was financially supported by the 'NCN Opus grant 2016/21/B/ST6/02176'.
+Work on this package was financially supported by the `NCN Opus grant 2016/21/B/ST6/02176`.