apply 5
2026-03-06
Goal is to predict attrition #import data
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.2 ✔ tibble 3.3.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.2
## ✔ purrr 1.2.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(correlationfunnel)## ══ Using correlationfunnel? ════════════════════════════════════════════════════
## You might also be interested in applied data science training for business.
## </> Learn more at - www.business-science.io </>ikea <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2020/2020-11-03/ikea.csv')## New names:
## Rows: 3694 Columns: 14
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (7): name, category, old_price, link, other_colors, short_description, d... dbl
## (6): ...1, item_id, price, depth, height, width lgl (1): sellable_online
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`#clean data
skimr::skim(ikea)| Name | ikea |
| Number of rows | 3694 |
| Number of columns | 14 |
| _______________________ | |
| Column type frequency: | |
| character | 7 |
| logical | 1 |
| numeric | 6 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| name | 0 | 1 | 3 | 27 | 0 | 607 | 0 |
| category | 0 | 1 | 4 | 36 | 0 | 17 | 0 |
| old_price | 0 | 1 | 4 | 13 | 0 | 365 | 0 |
| link | 0 | 1 | 52 | 163 | 0 | 2962 | 0 |
| other_colors | 0 | 1 | 2 | 3 | 0 | 2 | 0 |
| short_description | 0 | 1 | 3 | 63 | 0 | 1706 | 0 |
| designer | 0 | 1 | 3 | 1261 | 0 | 381 | 0 |
Variable type: logical
| skim_variable | n_missing | complete_rate | mean | count |
|---|---|---|---|---|
| sellable_online | 0 | 1 | 0.99 | TRU: 3666, FAL: 28 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| …1 | 0 | 1.00 | 1846.50 | 1066.51 | 0 | 923.25 | 1846.5 | 2769.75 | 3693 | ▇▇▇▇▇ |
| item_id | 0 | 1.00 | 48632396.79 | 28887094.10 | 58487 | 20390574.00 | 49288078.0 | 70403572.75 | 99932615 | ▇▇▇▇▇ |
| price | 0 | 1.00 | 1078.21 | 1374.65 | 3 | 180.90 | 544.7 | 1429.50 | 9585 | ▇▁▁▁▁ |
| depth | 1463 | 0.60 | 54.38 | 29.96 | 1 | 38.00 | 47.0 | 60.00 | 257 | ▇▃▁▁▁ |
| height | 988 | 0.73 | 101.68 | 61.10 | 1 | 67.00 | 83.0 | 124.00 | 700 | ▇▂▁▁▁ |
| width | 589 | 0.84 | 104.47 | 71.13 | 1 | 60.00 | 80.0 | 140.00 | 420 | ▇▅▂▁▁ |
ikea <- ikea %>% na.omit()factors_vec <- ikea %>% select(item_id, price, depth, height, width, -...1) %>% names()
ikea_clean <- ikea %>%
#mutate(Education = Education %>% as.factor()) %>%
#address factors imported as numeric
mutate(across(all_of(factors_vec), as.factor))
#drop zero variance variables#explore data
ikea_clean %>% count(name) ## # A tibble: 289 × 2
## name n
## <chr> <int>
## 1 ADDE 1
## 2 AGAM 4
## 3 AGEN 1
## 4 ALEX 7
## 5 ALGOT 24
## 6 ALGOT / BROR 1
## 7 ALGOT / SKÅDIS 1
## 8 ANGERSBY 1
## 9 ANTILOP 4
## 10 ARKELSTORP 2
## # ℹ 279 more rowsikea_clean %>%
ggplot(aes(name)) +
geom_bar()
correlation plot
#step 1
ikea_binarized <- ikea_clean %>%
select(-item_id) %>%
binarize()
ikea_binarized %>%glimpse()## Rows: 1,899
## Columns: 180
## $ `...1__-Inf_799.5` <dbl> …
## $ ...1__799.5_1653 <dbl> …
## $ ...1__1653_2474.5 <dbl> …
## $ ...1__2474.5_Inf <dbl> …
## $ name__ALGOT <dbl> …
## $ name__BEKANT <dbl> …
## $ name__BESTÅ <dbl> …
## $ `name__BILLY_/_OXBERG` <dbl> …
## $ name__BRIMNES <dbl> …
## $ name__BROR <dbl> …
## $ name__EKET <dbl> …
## $ name__GRÖNLID <dbl> …
## $ name__HAVSTA <dbl> …
## $ name__HAVSTEN <dbl> …
## $ name__HEMNES <dbl> …
## $ name__IVAR <dbl> …
## $ name__JONAXEL <dbl> …
## $ name__KALLAX <dbl> …
## $ name__LIDHULT <dbl> …
## $ name__LIXHULT <dbl> …
## $ name__NORDLI <dbl> …
## $ name__PAX <dbl> …
## $ name__PLATSA <dbl> …
## $ `name__STUVA_/_FRITIDS` <dbl> …
## $ name__TROFAST <dbl> …
## $ name__VALLENTUNA <dbl> …
## $ name__VIMLE <dbl> …
## $ `name__-OTHER` <dbl> …
## $ category__Bar_furniture <dbl> …
## $ category__Beds <dbl> …
## $ `category__Bookcases_&_shelving_units` <dbl> …
## $ `category__Cabinets_&_cupboards` <dbl> …
## $ category__Chairs <dbl> …
## $ `category__Chests_of_drawers_&_drawer_units` <dbl> …
## $ `category__Children's_furniture` <dbl> …
## $ category__Nursery_furniture <dbl> …
## $ category__Outdoor_furniture <dbl> …
## $ `category__Sideboards,_buffets_&_console_tables` <dbl> …
## $ `category__Sofas_&_armchairs` <dbl> …
## $ `category__Tables_&_desks` <dbl> …
## $ `category__TV_&_media_furniture` <dbl> …
## $ category__Wardrobes <dbl> …
## $ `category__-OTHER` <dbl> …
## $ price__175 <dbl> …
## $ price__195 <dbl> …
## $ price__225 <dbl> …
## $ price__275 <dbl> …
## $ price__295 <dbl> …
## $ price__345 <dbl> …
## $ price__375 <dbl> …
## $ price__395 <dbl> …
## $ price__495 <dbl> …
## $ price__595 <dbl> …
## $ price__695 <dbl> …
## $ price__995 <dbl> …
## $ `price__-OTHER` <dbl> …
## $ old_price__No_old_price <dbl> …
## $ `old_price__-OTHER` <dbl> …
## $ sellable_online__1 <dbl> …
## $ `sellable_online__-OTHER` <dbl> …
## $ `link__https://www.ikea.com/sa/en/p/besta-burs-tv-bench-high-gloss-white-30269129/` <dbl> …
## $ `link__-OTHER` <dbl> …
## $ other_colors__No <dbl> …
## $ other_colors__Yes <dbl> …
## $ `short_description__3-seat_sofa` <dbl> …
## $ `short_description__3-seat_sofa-bed` <dbl> …
## $ short_description__Armchair <dbl> …
## $ short_description__Chair <dbl> …
## $ `short_description__Wardrobe,__________150x66x236_cm` <dbl> …
## $ `short_description__-OTHER` <dbl> …
## $ designer__Andreas_Fredriksson <dbl> …
## $ designer__Carina_Bengs <dbl> …
## $ designer__Carl_Öjerstam <dbl> …
## $ designer__Ebba_Strandmark <dbl> …
## $ designer__Ehlén_Johansson <dbl> …
## $ `designer__Ehlén_Johansson/IKEA_of_Sweden` <dbl> …
## $ designer__Eva_Lilja_Löwenhielm <dbl> …
## $ designer__Francis_Cayouette <dbl> …
## $ designer__Gillis_Lundgren <dbl> …
## $ designer__Henrik_Preutz <dbl> …
## $ designer__IKEA_of_Sweden <dbl> …
## $ `designer__IKEA_of_Sweden/Ehlén_Johansson` <dbl> …
## $ `designer__IKEA_of_Sweden/Jon_Karlsson` <dbl> …
## $ designer__Johan_Kroon <dbl> …
## $ designer__Jon_Karlsson <dbl> …
## $ `designer__Jon_Karlsson/IKEA_of_Sweden` <dbl> …
## $ `designer__K_Hagberg/M_Hagberg` <dbl> …
## $ designer__Mia_Lagerman <dbl> …
## $ designer__Nike_Karlsson <dbl> …
## $ designer__Ola_Wihlborg <dbl> …
## $ designer__Studio_Copenhagen <dbl> …
## $ designer__Tord_Björklund <dbl> …
## $ `designer__-OTHER` <dbl> …
## $ depth__25 <dbl> …
## $ depth__28 <dbl> …
## $ depth__30 <dbl> …
## $ depth__35 <dbl> …
## $ depth__36 <dbl> …
## $ depth__37 <dbl> …
## $ depth__38 <dbl> …
## $ depth__39 <dbl> …
## $ depth__40 <dbl> …
## $ depth__41 <dbl> …
## $ depth__42 <dbl> …
## $ depth__44 <dbl> …
## $ depth__45 <dbl> …
## $ depth__47 <dbl> …
## $ depth__48 <dbl> …
## $ depth__49 <dbl> …
## $ depth__50 <dbl> …
## $ depth__51 <dbl> …
## $ depth__52 <dbl> …
## $ depth__55 <dbl> …
## $ depth__57 <dbl> …
## $ depth__58 <dbl> …
## $ depth__60 <dbl> …
## $ depth__66 <dbl> …
## $ depth__82 <dbl> …
## $ depth__94 <dbl> …
## $ depth__98 <dbl> …
## $ depth__164 <dbl> …
## $ `depth__-OTHER` <dbl> …
## $ height__35 <dbl> …
## $ height__38 <dbl> …
## $ height__45 <dbl> …
## $ height__64 <dbl> …
## $ height__70 <dbl> …
## $ height__74 <dbl> …
## $ height__75 <dbl> …
## $ height__76 <dbl> …
## $ height__78 <dbl> …
## $ height__79 <dbl> …
## $ height__80 <dbl> …
## $ height__83 <dbl> …
## $ height__84 <dbl> …
## $ height__85 <dbl> …
## $ height__87 <dbl> …
## $ height__90 <dbl> …
## $ height__91 <dbl> …
## $ height__95 <dbl> …
## $ height__100 <dbl> …
## $ height__101 <dbl> …
## $ height__102 <dbl> …
## $ height__104 <dbl> …
## $ height__128 <dbl> …
## $ height__147 <dbl> …
## $ height__176 <dbl> …
## $ height__179 <dbl> …
## $ height__190 <dbl> …
## $ height__192 <dbl> …
## $ height__197 <dbl> …
## $ height__201 <dbl> …
## $ height__202 <dbl> …
## $ height__236 <dbl> …
## $ `height__-OTHER` <dbl> …
## $ width__35 <dbl> …
## $ width__40 <dbl> …
## $ width__41 <dbl> …
## $ width__42 <dbl> …
## $ width__44 <dbl> …
## $ width__45 <dbl> …
## $ width__46 <dbl> …
## $ width__50 <dbl> …
## $ width__56 <dbl> …
## $ width__60 <dbl> …
## $ width__70 <dbl> …
## $ width__80 <dbl> …
## $ width__89 <dbl> …
## $ width__90 <dbl> …
## $ width__99 <dbl> …
## $ width__100 <dbl> …
## $ width__120 <dbl> …
## $ width__140 <dbl> …
## $ width__150 <dbl> …
## $ width__160 <dbl> …
## $ width__180 <dbl> …
## $ width__200 <dbl> …
## $ width__240 <dbl> …
## $ width__300 <dbl> …
## $ `width__-OTHER` <dbl> …#step 2L correlation
ikea_correlation <- ikea_binarized %>%
correlate(sellable_online__1)## Warning: Expected 2 pieces. Additional pieces discarded in 1 rows [69].ikea_correlation## # A tibble: 180 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 sellable_online 1 1
## 2 sellable_online -OTHER -1
## 3 name TROFAST -0.332
## 4 width 42 -0.327
## 5 depth 30 -0.235
## 6 category Children's_furniture -0.144
## 7 category Nursery_furniture -0.128
## 8 height 101 -0.113
## 9 designer Studio_Copenhagen -0.112
## 10 price 275 -0.110
## # ℹ 170 more rows#step 3: plot
ikea_correlation %>%
correlationfunnel::plot_correlation_funnel()## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the correlationfunnel package.
## Please report the issue at
## <https://github.com/business-science/correlationfunnel/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: The `size` argument of `element_rect()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the correlationfunnel package.
## Please report the issue at
## <https://github.com/business-science/correlationfunnel/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: ggrepel: 162 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps