@@ -31,7 +31,7 @@
@@ -64,7 +64,7 @@
-
-
+
@@ -82,10 +82,10 @@
-diff --git a/docs/authors.html b/docs/authors.html index f5b0bb6..75c5bcc 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -10,23 +10,27 @@ - + - + - + + + + + - - + + - + - - + + @@ -53,7 +57,7 @@ - + diff --git a/docs/bootstrap-toc.css b/docs/bootstrap-toc.css new file mode 100644 index 0000000..5a85941 --- /dev/null +++ b/docs/bootstrap-toc.css @@ -0,0 +1,60 @@ +/*! + * Bootstrap Table of Contents v0.4.1 (http://afeld.github.io/bootstrap-toc/) + * Copyright 2015 Aidan Feldman + * Licensed under MIT (https://github.com/afeld/bootstrap-toc/blob/gh-pages/LICENSE.md) */ + +/* modified from https://github.com/twbs/bootstrap/blob/94b4076dd2efba9af71f0b18d4ee4b163aa9e0dd/docs/assets/css/src/docs.css#L548-L601 */ + +/* All levels of nav */ +nav[data-toggle='toc'] .nav > li > a { + display: block; + padding: 4px 20px; + font-size: 13px; + font-weight: 500; + color: #767676; +} +nav[data-toggle='toc'] .nav > li > a:hover, +nav[data-toggle='toc'] .nav > li > a:focus { + padding-left: 19px; + color: #563d7c; + text-decoration: none; + background-color: transparent; + border-left: 1px solid #563d7c; +} +nav[data-toggle='toc'] .nav > .active > a, +nav[data-toggle='toc'] .nav > .active:hover > a, +nav[data-toggle='toc'] .nav > .active:focus > a { + padding-left: 18px; + font-weight: bold; + color: #563d7c; + background-color: transparent; + border-left: 2px solid #563d7c; +} + +/* Nav: second level (shown on .active) */ +nav[data-toggle='toc'] .nav .nav { + display: none; /* Hide by default, but at >768px, show it */ + padding-bottom: 10px; +} +nav[data-toggle='toc'] .nav .nav > li > a { + padding-top: 1px; + padding-bottom: 1px; + padding-left: 30px; + font-size: 12px; + font-weight: normal; +} +nav[data-toggle='toc'] .nav .nav > li > a:hover, +nav[data-toggle='toc'] .nav .nav > li > a:focus { + padding-left: 29px; +} +nav[data-toggle='toc'] .nav .nav > .active > a, +nav[data-toggle='toc'] .nav .nav > .active:hover > a, +nav[data-toggle='toc'] .nav .nav > .active:focus > a { + padding-left: 28px; + font-weight: 500; +} + +/* from https://github.com/twbs/bootstrap/blob/e38f066d8c203c3e032da0ff23cd2d6098ee2dd6/docs/assets/css/src/docs.css#L631-L634 */ +nav[data-toggle='toc'] .nav > .active > ul { + display: block; +} diff --git a/docs/bootstrap-toc.js b/docs/bootstrap-toc.js new file mode 100644 index 0000000..1cdd573 --- /dev/null +++ b/docs/bootstrap-toc.js @@ -0,0 +1,159 @@ +/*! + * Bootstrap Table of Contents v0.4.1 (http://afeld.github.io/bootstrap-toc/) + * Copyright 2015 Aidan Feldman + * Licensed under MIT (https://github.com/afeld/bootstrap-toc/blob/gh-pages/LICENSE.md) */ +(function() { + 'use strict'; + + window.Toc = { + helpers: { + // return all matching elements in the set, or their descendants + findOrFilter: function($el, selector) { + // http://danielnouri.org/notes/2011/03/14/a-jquery-find-that-also-finds-the-root-element/ + // http://stackoverflow.com/a/12731439/358804 + var $descendants = $el.find(selector); + return $el.filter(selector).add($descendants).filter(':not([data-toc-skip])'); + }, + + generateUniqueIdBase: function(el) { + var text = $(el).text(); + var anchor = text.trim().toLowerCase().replace(/[^A-Za-z0-9]+/g, '-'); + return anchor || el.tagName.toLowerCase(); + }, + + generateUniqueId: function(el) { + var anchorBase = this.generateUniqueIdBase(el); + for (var i = 0; ; i++) { + var anchor = anchorBase; + if (i > 0) { + // add suffix + anchor += '-' + i; + } + // check if ID already exists + if (!document.getElementById(anchor)) { + return anchor; + } + } + }, + + generateAnchor: function(el) { + if (el.id) { + return el.id; + } else { + var anchor = this.generateUniqueId(el); + el.id = anchor; + return anchor; + } + }, + + createNavList: function() { + return $(''); + }, + + createChildNavList: function($parent) { + var $childList = this.createNavList(); + $parent.append($childList); + return $childList; + }, + + generateNavEl: function(anchor, text) { + var $a = $(''); + $a.attr('href', '#' + anchor); + $a.text(text); + var $li = $(''); + $li.append($a); + return $li; + }, + + generateNavItem: function(headingEl) { + var anchor = this.generateAnchor(headingEl); + var $heading = $(headingEl); + var text = $heading.data('toc-text') || $heading.text(); + return this.generateNavEl(anchor, text); + }, + + // Find the first heading level (`
Vignette_tidyrules
+Vignette_tidyrules
Srikanth KS, Amith Kumar UR
-2020-03-09
+2020-06-04
Source:vignettes/tidyrules_vignette.Rmd@@ -101,21 +101,21 @@tidyrules_vignette.Rmd2020-03-09
- @@ -501,7 +494,7 @@Quick-start
-+library("tidyrules") -library("dplyr") -library("C50") -library("pander") - -# build model -c5_model <- C5.0(Species ~ ., data = iris, rules = TRUE) - -# extract rules in a tidy tibble -tidy_rules <- tidyRules(c5_model) - -# View tidy_rules -tidy_rules %>% - select(-c(rule_number,trial_number)) %>% - pandoc.table()library("tidyrules") +library("dplyr") +library("C50") +library("pander") + +# build model +c5_model <- C5.0(Species ~ ., data = iris, rules = TRUE) + +# extract rules in a tidy tibble +tidy_rules <- tidyRules(c5_model) + +# View tidy_rules +tidy_rules %>% + select(-c(rule_number,trial_number)) %>% + pandoc.table()
## ## ----------------------------------------------------------------------- ## id LHS RHS support confidence lift @@ -131,28 +131,28 @@## 4 Petal.Length > 4.9 virginica 46 0.9375 2.8 ## -----------------------------------------------------------------------
Filter rules based on
-RHSorsupportorconfidenceorlift:+# Example 1, filter rules based on support -tidy_rules %>% - filter(support >= 48) %>% - select(LHS, RHS)# Example 1, filter rules based on support +tidy_rules %>% + filter(support >= 48) %>% + select(LHS, RHS)
-## # A tibble: 2 x 2 ## LHS RHS ## <chr> <chr> ## 1 Petal.Length <= 1.9 setosa ## 2 Petal.Length > 1.9 & Petal.Length <= 4.9 & Petal.Width <= 1.7 versicolor+# Example 2, filter rules based on RHS -tidy_rules %>% - filter(RHS == "virginica") %>% - select(LHS, support, confidence, lift)# Example 2, filter rules based on RHS +tidy_rules %>% + filter(RHS == "virginica") %>% + select(LHS, support, confidence, lift)
## # A tibble: 2 x 4 ## LHS support confidence lift ## <chr> <int> <dbl> <dbl> ## 1 Petal.Width > 1.7 46 0.958 2.9 ## 2 Petal.Length > 4.9 46 0.938 2.8Use a
-tidyrulein afilter()function :+iris %>% - filter(eval(parse(text = tidy_rules[3,"LHS"]))) %>% # filter using a C5 rule - count(Species)iris %>% + filter(eval(parse(text = tidy_rules[3,"LHS"]))) %>% # filter using a C5 rule + count(Species)
## # A tibble: 2 x 2 ## Species n ## <fct> <int> @@ -168,18 +168,18 @@Example: Classification using
C5.0In this example we use
-attritiondata fromrsamplepackage. This illustration shows how to extract rules fromC5.0model and applyingfilter()based on tidyrules.-# loading packages -library("tidyrules") -library("C50") -library("dplyr") - -# attrition data load -data("attrition", package = "rsample") -attrition <- as_tibble(attrition) - -glimpse(attrition)## Observations: 1,470 -## Variables: 31 ++# loading packages +library("tidyrules") +library("C50") +library("dplyr") + +# attrition data load +data("attrition", package = "modeldata") +attrition <- as_tibble(attrition) + +glimpse(attrition)
## Rows: 1,470 +## Columns: 31 ## $ Age <int> 41, 49, 37, 33, 27, 32, 59, 30, 38, 36, 35, … ## $ Attrition <fct> Yes, No, Yes, No, No, No, No, No, No, No, No… ## $ BusinessTravel <fct> Travel_Rarely, Travel_Frequently, Travel_Rar… @@ -212,14 +212,14 @@## $ YearsSinceLastPromotion <int> 0, 1, 0, 3, 2, 3, 0, 0, 1, 7, 0, 0, 4, 1, 0,… ## $ YearsWithCurrManager <int> 5, 7, 0, 0, 2, 6, 0, 0, 8, 7, 3, 8, 3, 2, 3,…
As you could see, there are 31 variables and 1470 observations are present this data-set. Here our aim is to predict Attrition using rest of the variables. Let us build a
-C5.0model first.+# our C5 model -c5_att <- C5.0(Attrition ~ ., data = attrition, rules = TRUE) - -# sample rules from C5 -c5_att$output %>% - stringr::str_sub(start = 194L - , end = 578L) %>% - writeLines()# our C5 model +c5_att <- C5.0(Attrition ~ ., data = attrition, rules = TRUE) + +# sample rules from C5 +c5_att$output %>% + stringr::str_sub(start = 194L + , end = 578L) %>% + writeLines()
## ## Rule 1: (521/30, lift 1.1) ## EnvironmentSatisfaction in [Medium-Very_High] @@ -239,10 +239,10 @@## -> class No [0.864]
We get nice and human readable rules. Now problem with
C5.0summary is, you can only read and get a feel of how your predictions made based on rules. But here comes the hard part, imagine if you want to explore further about your data and you want to dig deeper, if you want to know rules which are throwing high lift and confidence, or you may be interested in rules which covers major sub-population. If in case your model is giving too many rules then that is the hardest part to go through each and every rules and identifying best rules out of the summary.What if we have all the rules in a tidy table format so that we could easily use them on the data. Let’s get it done using
- +tidyRules.# Extract rules to a tidy tibble +tr_att <- tidyRules(c5_att) + +tr_att
## # A tibble: 24 x 8 ## id LHS RHS support confidence lift rule_number trial_number ## <int> <chr> <chr> <int> <dbl> <dbl> <int> <int> @@ -271,10 +271,10 @@lift: The result of dividing the rule’s estimated accuracy by the relative frequency of the predicted class in the training set.Let’s have a look at first five rules
- +tr_att %>% + head(5) %>% + select(LHS,RHS) %>% + pandoc.table(split.cells = 60)
## ## ------------------------------------------------------------------- ## LHS RHS @@ -295,11 +295,11 @@## OverTime == 'Yes' & TotalWorkingYears > 2 ## -------------------------------------------------------------------
Now, all the rules are in
- +tibble(a tidy form ofdataframe) format. Let us look at rules which favors only Attrition is equal to “No” and arrange by support.## # A tibble: 3 x 8 ## id LHS RHS support confidence lift rule_number trial_number ## <int> <chr> <chr> <int> <dbl> <dbl> <int> <int> @@ -310,18 +310,18 @@Use rules inside
filter()function.Let’s use a rule within a
-filter(). Say, one need to pick a rule which has largestsupportfor predicted Attrition “Yes”.+# filter a rule with conditions -large_support_rule <- tr_att %>% - filter(RHS == "Yes") %>% - top_n(1, wt = support) %>% - pull(LHS) - -# parseable rule -parseable_rule <- parse(text = large_support_rule) - -# apply filter on data frame using parseable rule -attrition %>% - filter(eval(parseable_rule))# filter a rule with conditions +large_support_rule <- tr_att %>% + filter(RHS == "Yes") %>% + top_n(1, wt = support) %>% + pull(LHS) + +# parseable rule +parseable_rule <- parse(text = large_support_rule) + +# apply filter on data frame using parseable rule +attrition %>% + filter(eval(parseable_rule))
## # A tibble: 57 x 31 ## Age Attrition BusinessTravel DailyRate Department DistanceFromHome ## <int> <fct> <fct> <int> <fct> <int> @@ -349,17 +349,17 @@Rules parsable by python and SQL
-+tr_att_python <- tidyRules(c5_att, language = "python") -tr_att_sql <- tidyRules(c5_att, language = "sql") - -head(tr_att_python$LHS)tr_att_python <- tidyRules(c5_att, language = "python") +tr_att_sql <- tidyRules(c5_att, language = "sql") + +head(tr_att_python$LHS)
- +## [1] "EnvironmentSatisfaction in ['Medium', 'High', 'Very_High'] and JobInvolvement in ['Medium', 'High', 'Very_High'] and OverTime == 'No' and TrainingTimesLastYear > 1 and WorkLifeBalance in ['Better', 'Best']" ## [2] "JobRole == 'Research_Scientist' and OverTime == 'No'" ## [3] "TotalWorkingYears > 2" ## [4] "JobLevel <= 1 and MonthlyIncome <= 2468 and OverTime == 'Yes' and TotalWorkingYears > 2 and YearsAtCompany <= 3" ## [5] "DailyRate <= 722 and JobLevel <= 1 and MonthlyIncome <= 2468 and OverTime == 'Yes' and TotalWorkingYears > 2" ## [6] "EnvironmentSatisfaction in ['Low', 'Medium'] and MaritalStatus in ['Divorced', 'Married'] and NumCompaniesWorked > 4 and OverTime == 'Yes' and PerformanceRating == 'Excellent' and RelationshipSatisfaction in ['Low', 'Medium', 'High']"head(tr_att_sql$LHS)
## [1] "EnvironmentSatisfaction IN ('Medium', 'High', 'Very_High') AND JobInvolvement IN ('Medium', 'High', 'Very_High') AND OverTime = 'No' AND TrainingTimesLastYear > 1 AND WorkLifeBalance IN ('Better', 'Best')" ## [2] "JobRole = 'Research_Scientist' AND OverTime = 'No'" ## [3] "TotalWorkingYears > 2" @@ -373,27 +373,27 @@Example: Classification using
rpartIn this example we will be using
-BreastCancerdata frommlbenchpackage.+library("tidyrules") -library("dplyr") -library("rpart") -# BreastCancer -data(BreastCancer, package = "mlbench") -bc_train <- BreastCancer %>% - select(-Id) %>% - mutate_if(is.ordered, function(x) x <- factor(x,ordered = F)) - -rpart_bc <- rpart(Class ~ ., data = bc_train)library("tidyrules") +library("dplyr") +library("rpart") +# BreastCancer +data(BreastCancer, package = "mlbench") +bc_train <- BreastCancer %>% + select(-Id) %>% + mutate_if(is.ordered, function(x) x <- factor(x,ordered = F)) + +rpart_bc <- rpart(Class ~ ., data = bc_train)
NOTE : Do not forget to convert all
orderedfeatures tofactortype before training the model.One could visualize rpart decision tree using
- +prpfunction fromrpart.plotpackage.
The above tree visual is really nice to get a hang of how decision tree is splitting at each node. But, if you want to pick a terminal node it is really boring and hard since one has to enter the respective filter manually (imagine a situation if you have hundreds of features and a huge tree!!). To get-ride of this problem one could use tidyrules to make life easier.
Let’s extract rules from
- +rpartobject and use those rules further more to extract terminal nodes.# tidyrule extract +rules_bc <- tidyRules(rpart_bc) + +rules_bc
-## # A tibble: 7 x 6 ## id LHS RHS support confidence lift ## <int> <chr> <chr> <int> <dbl> <dbl> @@ -404,10 +404,10 @@## 5 5 Cell.size %in% c('3', '4', '5', '6', '7… benign 15 0.647 0.988 ## 6 6 Cell.size %in% c('3', '4', '5', '6', '7… malig… 61 0.841 2.44 ## 7 7 Cell.size %in% c('3', '4', '5', '6', '7… malig… 171 0.971 2.82
+# filter the data using a rule -bc_train %>% - filter(eval(parse(text = rules_bc[5,"LHS"]))) %>% - as_tibble()# filter the data using a rule +bc_train %>% + filter(eval(parse(text = rules_bc[5,"LHS"]))) %>% + as_tibble()
## # A tibble: 15 x 10 ## Cl.thickness Cell.size Cell.shape Marg.adhesion Epith.c.size Bare.nuclei ## <fct> <fct> <fct> <fct> <fct> <fct> @@ -434,20 +434,20 @@Example: Regression using
CubistIn this example, rules extraction from a regression model (a
-cubistmodel) has been illustrated below. We will be usingAmesHousingdataset for the example.+library("tidyrules") -library("dplyr") -library("Cubist") -# ames housing data set -ames <- AmesHousing::make_ames() -cubist_ames <- cubist(x = ames[, setdiff(colnames(ames), c("Sale_Price"))], - y = log10(ames[["Sale_Price"]]), - committees = 3 - ) - -# rule extract -rules_ames <- tidyRules(cubist_ames) - -rules_ameslibrary("tidyrules") +library("dplyr") +library("Cubist") +# ames housing data set +ames <- AmesHousing::make_ames() +cubist_ames <- cubist(x = ames[, setdiff(colnames(ames), c("Sale_Price"))], + y = log10(ames[["Sale_Price"]]), + committees = 3 + ) + +# rule extract +rules_ames <- tidyRules(cubist_ames) + +rules_ames
## # A tibble: 43 x 9 ## id LHS RHS support mean min max error committee ## <int> <chr> <chr> <int> <dbl> <dbl> <dbl> <dbl> <int> @@ -479,18 +479,11 @@`, then `
`, etc.) that has more than one element. Defaults to 1 (for `
`). + getTopLevel: function($scope) { + for (var i = 1; i <= 6; i++) { + var $headings = this.findOrFilter($scope, 'h' + i); + if ($headings.length > 1) { + return i; + } + } + + return 1; + }, + + // returns the elements for the top level, and the next below it + getHeadings: function($scope, topLevel) { + var topSelector = 'h' + topLevel; + + var secondaryLevel = topLevel + 1; + var secondarySelector = 'h' + secondaryLevel; + + return this.findOrFilter($scope, topSelector + ',' + secondarySelector); + }, + + getNavLevel: function(el) { + return parseInt(el.tagName.charAt(1), 10); + }, + + populateNav: function($topContext, topLevel, $headings) { + var $context = $topContext; + var $prevNav; + + var helpers = this; + $headings.each(function(i, el) { + var $newNav = helpers.generateNavItem(el); + var navLevel = helpers.getNavLevel(el); + + // determine the proper $context + if (navLevel === topLevel) { + // use top level + $context = $topContext; + } else if ($prevNav && $context === $topContext) { + // create a new level of the tree and switch to it + $context = helpers.createChildNavList($prevNav); + } // else use the current $context + + $context.append($newNav); + + $prevNav = $newNav; + }); + }, + + parseOps: function(arg) { + var opts; + if (arg.jquery) { + opts = { + $nav: arg + }; + } else { + opts = arg; + } + opts.$scope = opts.$scope || $(document.body); + return opts; + } + }, + + // accepts a jQuery object, or an options object + init: function(opts) { + opts = this.helpers.parseOps(opts); + + // ensure that the data attribute is in place for styling + opts.$nav.attr('data-toggle', 'toc'); + + var $topContext = this.helpers.createChildNavList(opts.$nav); + var topLevel = this.helpers.getTopLevel(opts.$scope); + var $headings = this.helpers.getHeadings(opts.$scope, topLevel); + this.helpers.populateNav($topContext, topLevel, $headings); + } + }; + + $(function() { + $('nav[data-toggle="toc"]').each(function(i, el) { + var $nav = $(el); + Toc.init($nav); + }); + }); +})(); diff --git a/docs/index.html b/docs/index.html index 8e0c96c..9fcd74d 100644 --- a/docs/index.html +++ b/docs/index.html @@ -6,19 +6,19 @@
Obtain Rules from Rule Based Models as Tidy Dataframe • tidyrules - - - - + + + + + - - +-