Apply4
Tindra Bergstrand
2024-10-03
Goal: To predict the the price of IKEA furniture Click here for the data
Import data
ikea <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/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`Explore 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 | ▇▅▂▁▁ |
data_ikea1 <- ikea %>%
# Treat missing values
select(-old_price, -link, -...1) %>%
na.omit() %>%
# Log transform variables with pos-skewed distributions
mutate(price = log(price)) %>%
mutate(across(is.logical, as.factor))## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `across(is.logical, as.factor)`.
## Caused by warning:
## ! Use of bare predicate functions was deprecated in tidyselect 1.1.0.
## ℹ Please use wrap predicates in `where()` instead.
## # Was:
## data %>% select(is.logical)
##
## # Now:
## data %>% select(where(is.logical))Identify good predictors
# Category
data_ikea1 %>%
ggplot(aes(price, category)) +
geom_boxplot()
# Designer
data_ikea1 %>%
#tokenize title
unnest_tokens(output = word, input = short_description) %>%
# calculate avg rent per word
group_by(word) %>%
summarise(price = mean(price),
n = n()) %>%
ungroup() %>%
filter(n > 10, !str_detect(word, "\\d")) %>%
slice_max(order_by = price, n = 10) %>%
# Plot
ggplot(aes(price, fct_reorder(word, price))) +
geom_point() +
labs(y = "Producsts")
EDA shortcut
# Step 1:Prepare data
#Select
#take out short description, and keep designer
binarized_table <- data_ikea1 %>%
select(price, height, width, depth, sellable_online, category, designer, other_colors) %>%
binarize()
binarized_table %>% glimpse()## Rows: 1,899
## Columns: 58
## $ `price__-Inf_5.68697535633982` <dbl> 1, 1, 0, 1, 1, 1, 0, …
## $ price__5.68697535633982_6.52209279817015 <dbl> 0, 0, 1, 0, 0, 0, 1, …
## $ price__6.52209279817015_7.37085996851068 <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ price__7.37085996851068_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `height__-Inf_71` <dbl> 0, 1, 0, 0, 0, 0, 0, …
## $ height__71_92 <dbl> 0, 0, 1, 0, 0, 0, 0, …
## $ height__92_171 <dbl> 1, 0, 0, 1, 1, 1, 1, …
## $ height__171_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `width__-Inf_60` <dbl> 1, 0, 1, 1, 1, 1, 1, …
## $ width__60_93 <dbl> 0, 1, 0, 0, 0, 0, 0, …
## $ width__93_161.5 <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ width__161.5_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `depth__-Inf_40` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ depth__40_47 <dbl> 0, 0, 1, 1, 1, 1, 1, …
## $ depth__47_60 <dbl> 1, 1, 0, 0, 0, 0, 0, …
## $ depth__60_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ sellable_online__TRUE <dbl> 1, 1, 1, 1, 1, 1, 1, …
## $ `sellable_online__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ category__Bar_furniture <dbl> 1, 1, 1, 1, 1, 1, 1, …
## $ category__Beds <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Bookcases_&_shelving_units` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Cabinets_&_cupboards` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ category__Chairs <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Chests_of_drawers_&_drawer_units` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Children's_furniture` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ category__Nursery_furniture <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ category__Outdoor_furniture <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Sideboards,_buffets_&_console_tables` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Sofas_&_armchairs` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__Tables_&_desks` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__TV_&_media_furniture` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ category__Wardrobes <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `category__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Andreas_Fredriksson <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Carina_Bengs <dbl> 0, 0, 1, 0, 0, 0, 1, …
## $ designer__Carl_Öjerstam <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Ebba_Strandmark <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Ehlén_Johansson <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `designer__Ehlén_Johansson/IKEA_of_Sweden` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Eva_Lilja_Löwenhielm <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Francis_Cayouette <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Gillis_Lundgren <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Henrik_Preutz <dbl> 1, 0, 0, 0, 0, 0, 0, …
## $ designer__IKEA_of_Sweden <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `designer__IKEA_of_Sweden/Ehlén_Johansson` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `designer__IKEA_of_Sweden/Jon_Karlsson` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Johan_Kroon <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Jon_Karlsson <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `designer__Jon_Karlsson/IKEA_of_Sweden` <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `designer__K_Hagberg/M_Hagberg` <dbl> 0, 0, 0, 1, 1, 1, 0, …
## $ designer__Mia_Lagerman <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Nike_Karlsson <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Ola_Wihlborg <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Studio_Copenhagen <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ designer__Tord_Björklund <dbl> 0, 0, 0, 0, 0, 0, 0, …
## $ `designer__-OTHER` <dbl> 0, 1, 0, 0, 0, 0, 0, …
## $ other_colors__No <dbl> 0, 1, 1, 1, 1, 1, 1, …
## $ other_colors__Yes <dbl> 1, 0, 0, 0, 0, 0, 0, …# Step 2: Correlate
corr_tbl <- binarized_table %>%
correlate(price__7.37085996851068_Inf)
corr_tbl## # A tibble: 58 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 price 7.37085996851068_Inf 1
## 2 width 161.5_Inf 0.579
## 3 depth 60_Inf 0.447
## 4 category Sofas_&_armchairs 0.379
## 5 width -Inf_60 -0.374
## 6 price -Inf_5.68697535633982 -0.336
## 7 price 6.52209279817015_7.37085996851068 -0.333
## 8 price 5.68697535633982_6.52209279817015 -0.331
## 9 category Wardrobes 0.279
## 10 height -Inf_71 -0.277
## # ℹ 48 more rows# Step 3: Plot
## Label only strong correlations
corr_tbl %>%
filter(abs(correlation) > 0.3) %>%
plot_correlation_funnel()
Build models
Split data
data_ikea2 <- data_ikea1 %>%
select(-other_colors)
# Split into train and test data set
set.seed(1234)
ikea_split <- rsample::initial_split(data_ikea2, prop = 0.75)
ikea_train <- training(ikea_split)
ikea_test <- testing(ikea_split)# Specify recipe
ikea_recipe <- recipe(price ~ ., data = ikea_train) %>%
update_role(item_id, new_role = "id variable") %>%
step_tokenize(short_description) %>%
step_tokenfilter(short_description, max_tokens = 100) %>%
step_tfidf(short_description) %>%
step_other(category, name, sellable_online, designer, threshold = 0.2) %>%
step_dummy(category, name, sellable_online, designer, one_hot = TRUE) %>%
step_YeoJohnson(width, height) %>%
step_impute_knn(all_predictors())
ikea_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 1,424
## Columns: 113
## $ item_id <dbl> 19282962, 29320911, 49276549, 802…
## $ depth <dbl> 151, 60, 47, 52, 47, 47, 44, 45, …
## $ height <dbl> 12.95187, 21.33670, 14.11837, 16.…
## $ width <dbl> 9.034855, 7.442056, 5.426853, 6.9…
## $ price <dbl> 7.595890, 7.833996, 6.429719, 6.4…
## $ tfidf_short_description_1 <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_10 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_120x40x64 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_140x200 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_147x147 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_150x44x236 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_150x60x236 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_150x66x236 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_2 <dbl> 0.8840660, 0.0000000, 0.5304396, …
## $ tfidf_short_description_200x66x236 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_25x51x70 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_3 <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_4 <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_41x101 <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_41x61 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_5 <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_50x51x70 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_6 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_60x50x128 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_61x101 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_74 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_75 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_8 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_80x30x202 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_99x44x56 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_and <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_armchair <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_armrest <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_armrests <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_backrest <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_bar <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_baskets <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_bed <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_bench <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_bookcase <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_box <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_cabinet <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_cabinets <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_castors <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_chair <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_chaise <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_changing <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_chest <dbl> 0.0000000, 0.0000000, 0.5867714, …
## $ `tfidf_short_description_children's` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_clothes <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_cm <dbl> 0.0000000, 0.2905183, 0.1743110, …
## $ tfidf_short_description_combination <dbl> 0.0000000, 0.6909039, 0.0000000, …
## $ tfidf_short_description_corner <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_cover <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_desk <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_door <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_doors <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_drawer <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_drawers <dbl> 0.0000000, 0.0000000, 0.5004936, …
## $ tfidf_short_description_feet <dbl> 0.00000, 0.00000, 0.00000, 0.0000…
## $ tfidf_short_description_foldable <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_for <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_frame <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_glass <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_highchair <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_in <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_inserts <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_junior <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_leg <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_legs <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_lock <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_longue <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_mesh <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_modular <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_module <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_mounted <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_of <dbl> 0.0000000, 0.0000000, 0.5753102, …
## $ tfidf_short_description_on <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_outdoor <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_panel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_plinth <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_rail <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_seat <dbl> 0.7549716, 0.0000000, 0.0000000, …
## $ tfidf_short_description_section <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_sections <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_shelf <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_shelves <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_shelving <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_sliding <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_smart <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_sofa <dbl> 0.7660576, 0.0000000, 0.0000000, …
## $ tfidf_short_description_step <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_stool <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_storage <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_table <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_top <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_tv <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_underframe <dbl> 0.000000, 0.000000, 0.000000, 0.0…
## $ tfidf_short_description_unit <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_upright <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_w <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_wall <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ tfidf_short_description_wardrobe <dbl> 0.0000000, 0.7815769, 0.0000000, …
## $ tfidf_short_description_wire <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_short_description_with <dbl> 0.0000000, 0.0000000, 0.0000000, …
## $ category_Bookcases...shelving.units <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ category_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, …
## $ name_BESTÅ <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ name_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ sellable_online_TRUE. <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ sellable_online_other <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ designer_IKEA.of.Sweden <dbl> 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, …
## $ designer_other <dbl> 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, …# Specify model
xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), mtry = tune(), learn_rate = tune()) %>%
set_mode("regression") %>%
set_engine("xgboost")
# Combine recipe and model using workflow
xgboost_workflow <-
workflow() %>%
add_recipe(ikea_recipe) %>%
add_model(xgboost_spec)
# Create cross-validation folds
set.seed(2345)
ikea_cv <- vfold_cv(ikea_train, v = 5)
# Tune hyperperameters
set.seed(3456)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = ikea_cv,
grid = 10)## i Creating pre-processing data to finalize unknown parameter: mtryEvaluate models
tune::show_best(xgboost_tune, metric = "rmse")## # A tibble: 5 × 10
## mtry trees min_n learn_rate .metric .estimator mean n std_err .config
## <int> <int> <int> <dbl> <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 58 1741 3 0.0868 rmse standard 0.380 5 0.0123 Preproces…
## 2 13 1578 15 0.130 rmse standard 0.397 5 0.0138 Preproces…
## 3 83 922 22 0.204 rmse standard 0.407 5 0.0165 Preproces…
## 4 67 656 18 0.0521 rmse standard 0.412 5 0.0175 Preproces…
## 5 43 1808 39 0.0128 rmse standard 0.430 5 0.0159 Preproces…# Update de model by selecting the best hyperparameter
xgboost_fw <- tune::finalize_workflow(xgboost_workflow,
tune::select_best(xgboost_tune, metric = "rmse"))
# Fit the model on the entire training data and test it on the test data
ikea_fit <- tune::last_fit(xgboost_fw, ikea_split)tune::collect_metrics(ikea_fit)## # A tibble: 2 × 4
## .metric .estimator .estimate .config
## <chr> <chr> <dbl> <chr>
## 1 rmse standard 0.311 Preprocessor1_Model1
## 2 rsq standard 0.937 Preprocessor1_Model1tune::collect_predictions(ikea_fit) %>%
ggplot(aes(price, .pred)) +
geom_point(alpha = 0.3, color = "purple4") +
geom_abline(lty = 2, color = "gray30") +
coord_fixed()
Rapport
Tried to switch threshold to 0.05 and max_token to 100 rmse=0.363 rsq=0.915, conclusion rmse better rsq worse
Switching threshold to 0.2 = rmse=359 and rsq=0.917 (rmse worse than original, raq same)
Switch max_token to 50 rmse=357 and rsq=918 (bothe better than original)
Keept max_token at 100 and threshold at 0.2, instead switch grid to 10 = rmse=0.354 rsq=0.919 (both better)
Max_Token 50 = worse rmse=0.372 rsq=0.911
Max_Token back to 100 and grid witch to 10 = rmse = 0.313 and rsq = 0.936 ( best one yet)
Added designer as a category which made it even better: rsme=0.311 rsq=0.937
Final
I will keep designer as a category, have the grid at 10, max_token at 100 and threshold at 0.2, I believe that is a pretty good model