CodeAlong2
Brady Martin
2025-02-13
Goal: Build a regression model to predict the cost (cost_km_millions) of the transit project. Click here for the data.
Import Data
transit_cost <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2021/2021-01-05/transit_cost.csv')## Rows: 544 Columns: 20
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (11): country, city, line, start_year, end_year, tunnel_per, source1, cu...
## dbl (9): e, rr, length, tunnel, stations, cost, year, ppp_rate, cost_km_mil...
##
## 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.skimr::skim(transit_cost)| Name | transit_cost |
| Number of rows | 544 |
| Number of columns | 20 |
| _______________________ | |
| Column type frequency: | |
| character | 11 |
| numeric | 9 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| country | 7 | 0.99 | 2 | 2 | 0 | 56 | 0 |
| city | 7 | 0.99 | 4 | 16 | 0 | 140 | 0 |
| line | 7 | 0.99 | 2 | 46 | 0 | 366 | 0 |
| start_year | 53 | 0.90 | 4 | 9 | 0 | 40 | 0 |
| end_year | 71 | 0.87 | 1 | 4 | 0 | 36 | 0 |
| tunnel_per | 32 | 0.94 | 5 | 7 | 0 | 134 | 0 |
| source1 | 12 | 0.98 | 4 | 54 | 0 | 17 | 0 |
| currency | 7 | 0.99 | 2 | 3 | 0 | 39 | 0 |
| real_cost | 0 | 1.00 | 1 | 10 | 0 | 534 | 0 |
| source2 | 10 | 0.98 | 3 | 16 | 0 | 12 | 0 |
| reference | 19 | 0.97 | 3 | 302 | 0 | 350 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| e | 7 | 0.99 | 7738.76 | 463.23 | 7136.00 | 7403.00 | 7705.00 | 7977.00 | 9510.00 | ▇▇▂▁▁ |
| rr | 8 | 0.99 | 0.06 | 0.24 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 | ▇▁▁▁▁ |
| length | 5 | 0.99 | 58.34 | 621.20 | 0.60 | 6.50 | 15.77 | 29.08 | 12256.98 | ▇▁▁▁▁ |
| tunnel | 32 | 0.94 | 29.38 | 344.04 | 0.00 | 3.40 | 8.91 | 21.52 | 7790.78 | ▇▁▁▁▁ |
| stations | 15 | 0.97 | 13.81 | 13.70 | 0.00 | 4.00 | 10.00 | 20.00 | 128.00 | ▇▁▁▁▁ |
| cost | 7 | 0.99 | 805438.12 | 6708033.07 | 0.00 | 2289.00 | 11000.00 | 27000.00 | 90000000.00 | ▇▁▁▁▁ |
| year | 7 | 0.99 | 2014.91 | 5.64 | 1987.00 | 2012.00 | 2016.00 | 2019.00 | 2027.00 | ▁▁▂▇▂ |
| ppp_rate | 9 | 0.98 | 0.66 | 0.87 | 0.00 | 0.24 | 0.26 | 1.00 | 5.00 | ▇▂▁▁▁ |
| cost_km_millions | 2 | 1.00 | 232.98 | 257.22 | 7.79 | 134.86 | 181.25 | 241.43 | 3928.57 | ▇▁▁▁▁ |
data <- transit_cost %>%
# Treat missing values
select(-cost, -currency, -source2, -source1, -reference) %>%
na.omit() %>%
# Convert character columns to factors
mutate(across(where(is.character), as.factor)) %>%
# Convert rr to a factor
mutate(rr = factor(rr)) %>%
# log transform variables with pos-skewed distributions
mutate(cost_km_millions = log(cost_km_millions))
skimr::skim(data)| Name | data |
| Number of rows | 437 |
| Number of columns | 15 |
| _______________________ | |
| Column type frequency: | |
| factor | 8 |
| numeric | 7 |
| ________________________ | |
| Group variables | None |
Variable type: factor
| skim_variable | n_missing | complete_rate | ordered | n_unique | top_counts |
|---|---|---|---|---|---|
| country | 0 | 1 | FALSE | 55 | CN: 169, IN: 27, TR: 20, ES: 15 |
| city | 0 | 1 | FALSE | 135 | Bei: 21, Sha: 18, Ist: 15, Mum: 13 |
| line | 0 | 1 | FALSE | 322 | Lin: 9, Lin: 8, Lin: 8, Lin: 6 |
| start_year | 0 | 1 | FALSE | 37 | 201: 51, 201: 37, 202: 36, 201: 35 |
| end_year | 0 | 1 | FALSE | 36 | 202: 58, 202: 44, 202: 42, 201: 27 |
| rr | 0 | 1 | FALSE | 2 | 0: 405, 1: 32 |
| tunnel_per | 0 | 1 | FALSE | 119 | 100: 245, 0.0: 51, 20.: 3, 35.: 3 |
| real_cost | 0 | 1 | FALSE | 429 | 240: 3, 175: 2, 300: 2, 416: 2 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| e | 0 | 1 | 7695.93 | 482.31 | 7136.00 | 7355.00 | 7592.00 | 7928.00 | 9510.00 | ▇▅▂▁▁ |
| length | 0 | 1 | 20.60 | 21.90 | 0.60 | 6.10 | 15.00 | 28.20 | 200.00 | ▇▁▁▁▁ |
| tunnel | 0 | 1 | 13.64 | 15.49 | 0.00 | 3.30 | 8.40 | 20.00 | 160.00 | ▇▁▁▁▁ |
| stations | 0 | 1 | 13.79 | 14.02 | 0.00 | 4.00 | 10.00 | 20.00 | 128.00 | ▇▁▁▁▁ |
| year | 0 | 1 | 2014.51 | 5.91 | 1987.00 | 2012.00 | 2016.00 | 2018.00 | 2027.00 | ▁▁▂▇▂ |
| ppp_rate | 0 | 1 | 0.72 | 0.89 | 0.00 | 0.24 | 0.27 | 1.25 | 5.00 | ▇▂▁▁▁ |
| cost_km_millions | 0 | 1 | 5.23 | 0.63 | 2.05 | 4.89 | 5.22 | 5.50 | 8.28 | ▁▁▇▁▁ |
Explore Data
Identify good predictors.
Length
data %>%
ggplot(aes(cost_km_millions, length)) +
scale_y_log10() +
geom_point()
Tunnel
data %>%
ggplot(aes(cost_km_millions, tunnel)) +
scale_y_log10() +
geom_point()## Warning in scale_y_log10(): log-10 transformation introduced infinite values.
Stations
data %>%
ggplot(aes(cost_km_millions, as.factor(year))) +
geom_boxplot()
city
data %>%
group_by(city) %>%
filter(n() > 5) %>%
ungroup() %>%
# Plot
ggplot(aes(cost_km_millions, fct_reorder(city, cost_km_millions))) +
geom_point() +
labs(y = "City of Transit Project")
EDA shortcut
# Step 1: Prepare data
data_binarized_tbl <- data %>%
select(-e, -line) %>%
binarize()
data_binarized_tbl %>% glimpse()## Rows: 437
## Columns: 124
## $ country__BG <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__CA <dbl> 1, 1, 1, 1, 1, 0, …
## $ country__CN <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__DE <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__ES <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__FR <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__IN <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__IT <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__JP <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__KR <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__RU <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__SA <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__SE <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__TH <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__TR <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__TW <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__US <dbl> 0, 0, 0, 0, 0, 0, …
## $ country__VN <dbl> 0, 0, 0, 0, 0, 0, …
## $ `country__-OTHER` <dbl> 0, 0, 0, 0, 0, 1, …
## $ city__Bangkok <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Barcelona <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Beijing <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Changchun <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Changsha <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Chengdu <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Chongqing <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Dongguan <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Guangzhou <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Guiyang <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Hangzhou <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Istanbul <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Madrid <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Mumbai <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Nanjing <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__New_York <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Paris <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Riyadh <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Seoul <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Shanghai <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Shenzhen <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Sofia <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Taipei <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Tianjin <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Tokyo <dbl> 0, 0, 0, 0, 0, 0, …
## $ city__Toronto <dbl> 0, 1, 1, 1, 1, 0, …
## $ city__Wuhan <dbl> 0, 0, 0, 0, 0, 0, …
## $ `city__-OTHER` <dbl> 1, 0, 0, 0, 0, 1, …
## $ start_year__2000 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2001 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2003 <dbl> 0, 0, 0, 0, 0, 1, …
## $ start_year__2005 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2006 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2007 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2008 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2009 <dbl> 0, 1, 0, 0, 0, 0, …
## $ start_year__2010 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2011 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2012 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2013 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2014 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2015 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2016 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2017 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2018 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2019 <dbl> 0, 0, 0, 0, 0, 0, …
## $ start_year__2020 <dbl> 1, 0, 1, 1, 1, 0, …
## $ start_year__2021 <dbl> 0, 0, 0, 0, 0, 0, …
## $ `start_year__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2000 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2008 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2009 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2010 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2011 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2012 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2013 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2014 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2015 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2016 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2017 <dbl> 0, 1, 0, 0, 0, 0, …
## $ end_year__2018 <dbl> 0, 0, 0, 0, 0, 1, …
## $ end_year__2019 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2020 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2021 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2022 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2023 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2024 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2025 <dbl> 1, 0, 0, 0, 0, 0, …
## $ end_year__2026 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2027 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2028 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2029 <dbl> 0, 0, 0, 0, 0, 0, …
## $ end_year__2030 <dbl> 0, 0, 1, 1, 1, 0, …
## $ `end_year__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, …
## $ rr__0 <dbl> 1, 1, 1, 1, 1, 1, …
## $ rr__1 <dbl> 0, 0, 0, 0, 0, 0, …
## $ `length__-Inf_6.1` <dbl> 1, 0, 0, 0, 0, 0, …
## $ length__6.1_15 <dbl> 0, 1, 1, 0, 1, 1, …
## $ length__15_28.2 <dbl> 0, 0, 0, 1, 0, 0, …
## $ length__28.2_Inf <dbl> 0, 0, 0, 0, 0, 0, …
## $ `tunnel_per__0.00%` <dbl> 0, 0, 0, 0, 0, 0, …
## $ `tunnel_per__100.00%` <dbl> 0, 1, 1, 0, 1, 0, …
## $ `tunnel_per__-OTHER` <dbl> 1, 0, 0, 1, 0, 1, …
## $ `tunnel__-Inf_3.3` <dbl> 0, 0, 0, 0, 0, 0, …
## $ tunnel__3.3_8.4 <dbl> 1, 0, 1, 0, 1, 1, …
## $ tunnel__8.4_20 <dbl> 0, 1, 0, 1, 0, 0, …
## $ tunnel__20_Inf <dbl> 0, 0, 0, 0, 0, 0, …
## $ `stations__-Inf_4` <dbl> 0, 0, 1, 0, 0, 0, …
## $ stations__4_10 <dbl> 1, 1, 0, 0, 1, 1, …
## $ stations__10_20 <dbl> 0, 0, 0, 1, 0, 0, …
## $ stations__20_Inf <dbl> 0, 0, 0, 0, 0, 0, …
## $ `year__-Inf_2012` <dbl> 0, 0, 0, 0, 0, 1, …
## $ year__2012_2016 <dbl> 0, 1, 0, 0, 0, 0, …
## $ year__2016_2018 <dbl> 1, 0, 1, 0, 0, 0, …
## $ year__2018_Inf <dbl> 0, 0, 0, 1, 1, 0, …
## $ `ppp_rate__-Inf_0.2379` <dbl> 0, 0, 0, 0, 0, 0, …
## $ ppp_rate__0.2379_0.266 <dbl> 0, 0, 0, 0, 0, 0, …
## $ ppp_rate__0.266_1.25 <dbl> 1, 1, 1, 1, 1, 0, …
## $ ppp_rate__1.25_Inf <dbl> 0, 0, 0, 0, 0, 1, …
## $ real_cost__2400 <dbl> 0, 0, 0, 0, 0, 0, …
## $ `real_cost__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, …
## $ `cost_km_millions__-Inf_4.89170486143161` <dbl> 0, 0, 0, 0, 0, 0, …
## $ cost_km_millions__4.89170486143161_5.21602212382121 <dbl> 0, 0, 0, 0, 0, 0, …
## $ cost_km_millions__5.21602212382121_5.49843791070471 <dbl> 0, 0, 0, 0, 0, 0, …
## $ cost_km_millions__5.49843791070471_Inf <dbl> 1, 1, 1, 1, 1, 1, …# Step 2: Correlate
data_corr_tbl <- data_binarized_tbl %>%
correlate(cost_km_millions__5.49843791070471_Inf)
data_corr_tbl## # A tibble: 124 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 cost_km_millions 5.49843791070471_Inf 1
## 2 cost_km_millions -Inf_4.89170486143161 -0.334
## 3 cost_km_millions 5.21602212382121_5.49843791070471 -0.332
## 4 cost_km_millions 4.89170486143161_5.21602212382121 -0.332
## 5 country US 0.304
## 6 country CN -0.273
## 7 country -OTHER 0.206
## 8 city New_York 0.187
## 9 start_year 2010 0.169
## 10 city -OTHER 0.169
## # ℹ 114 more rows# Step 3: Plot
data_corr_tbl %>%
plot_correlation_funnel()## Warning: ggrepel: 89 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
Build Models
Split data
#data <- sample_n(data, 100)
# Split into training and testing dataset
set.seed(1234)
data_split <- rsample::initial_split(data)
data_train <- training(data_split)
data_test <- testing(data_split)
# Further split training dataset for cross-validation
set.seed(2345)
data_cv <- rsample::vfold_cv(data_train)
data_cv## # 10-fold cross-validation
## # A tibble: 10 × 2
## splits id
## <list> <chr>
## 1 <split [294/33]> Fold01
## 2 <split [294/33]> Fold02
## 3 <split [294/33]> Fold03
## 4 <split [294/33]> Fold04
## 5 <split [294/33]> Fold05
## 6 <split [294/33]> Fold06
## 7 <split [294/33]> Fold07
## 8 <split [295/32]> Fold08
## 9 <split [295/32]> Fold09
## 10 <split [295/32]> Fold10Evaluate Models
usemodels::use_xgboost(cost_km_millions ~ ., data = data_train)## xgboost_recipe <-
## recipe(formula = cost_km_millions ~ ., data = data_train) %>%
## step_zv(all_predictors())
##
## xgboost_spec <-
## boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune(),
## loss_reduction = tune(), sample_size = tune()) %>%
## set_mode("classification") %>%
## set_engine("xgboost")
##
## xgboost_workflow <-
## workflow() %>%
## add_recipe(xgboost_recipe) %>%
## add_model(xgboost_spec)
##
## set.seed(24468)
## xgboost_tune <-
## tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))# Specify recipe
xgboost_recipe <-
recipe(formula = cost_km_millions ~ ., data = data_train) %>%
recipes::update_role(e, new_role = "id variable") %>%
step_tokenize(line) %>%
step_tokenfilter(line, max_tokens = 100) %>%
step_tfidf(line) %>%
step_other(city) %>%
step_dummy(country, city, one_hot = TRUE) %>%
step_log(ppp_rate, stations, tunnel, length)
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 327
## Columns: 169
## $ e <dbl> 7808, 7945, 8177, 7338, 7360, 8139, 7408, 946…
## $ start_year <fct> 2019, 2016, 2014, 2013, 2010, 2005, 2007, 201…
## $ end_year <fct> 2024, 2020, 2017, 2019, 2013, 2008, 2014, 202…
## $ rr <fct> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ length <dbl> 2.0579625, 3.5496174, 3.7062281, 3.6109179, 1…
## $ tunnel_per <fct> 100.00%, 100.00%, 14.00%, 100.00%, 0.00%, 0.0…
## $ tunnel <dbl> 2.0579625, 3.5496174, 1.7404662, 3.6109179, -…
## $ stations <dbl> 1.9459101, 2.8332133, 2.9957323, 3.3322045, 1…
## $ year <dbl> 2019, 2015, 2013, 2016, 2012, 2005, 2011, 201…
## $ ppp_rate <dbl> -1.4346446, -1.3536336, 0.5988365, 0.5306283,…
## $ real_cost <fct> 1775.13, 6174.12, 9103.64, 5100, 416, 218.89,…
## $ cost_km_millions <dbl> 5.423672, 5.178520, 5.410202, 4.926078, 4.595…
## $ tfidf_line_1 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_10 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_11 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_12 <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_13 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_13a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_13b <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_14 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_15 <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_16 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_17 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_18 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_19 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_2 <dbl> 0.5139313, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_2020 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_2020s <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_22 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_27 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_28 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_2a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_2b <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_3 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_4 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_4a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_5 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_5a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_6 <dbl> 0.000000, 1.670547, 0.000000, 0.000000, 0.000…
## $ tfidf_line_63 <dbl> 0.000000, 0.000000, 0.000000, 2.896507, 0.000…
## $ tfidf_line_7 <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_7a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_8 <dbl> 0.9336722, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_9 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_a <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_access <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_airport <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, …
## $ tfidf_line_and <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_arenastaden <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_aubervilliers <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_avenue <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_b <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_b1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_bahn <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_barkarby <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_bart <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_bc1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_blue <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_branch <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_c <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_circle <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_circular <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_east <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_eastern <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_express <dbl> 0.00000, 0.00000, 0.00000, 0.00000, 0.00000, …
## $ tfidf_line_extension <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_feeder <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_first <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_green <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_half <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_line <dbl> 0.2256866, 0.4513733, 0.0000000, 0.0000000, 0…
## $ tfidf_line_lines <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_link <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_m1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_m11 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_m3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_m4 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_m7 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_m8 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_metro <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_monorail <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_mrt <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_north <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_northern <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_orange <dbl> 0.00000, 0.00000, 4.70048, 0.00000, 0.00000, …
## $ tfidf_line_phase <dbl> 0.3648299, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_phase1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_pink <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_project <dbl> 0.000000, 0.000000, 0.000000, 2.551455, 0.000…
## $ tfidf_line_purple <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_rail <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_railway <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_red <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0…
## $ tfidf_line_ring <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_s1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_second <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_section <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_sergeli <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_south <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_southern <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_sukhumvit <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_taoyuan <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_to <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_tunnel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_u <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.000…
## $ tfidf_line_u55 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_underground <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_urban <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_west <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_western <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tfidf_line_yellow <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_AE <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_AR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_AT <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_AU <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_BD <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_BE <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_BG <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_BH <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_BR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ country_CA <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_CH <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_CL <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_CN <dbl> 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, …
## $ country_CZ <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_DE <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_DK <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_EC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_EG <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_ES <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_FI <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_FR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ country_GR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ country_HU <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_ID <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_IL <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_IN <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_IR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_IT <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_JP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_KR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_KW <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_MX <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_MY <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_NL <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_NO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_NZ <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_PA <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_PE <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_PH <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_PK <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_PL <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_PT <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_RO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_RU <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_SA <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_SE <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_SG <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_TH <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_TR <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_TW <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ country_UA <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_UK <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_US <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_UZ <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ country_VN <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ city_Beijing <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ city_other <dbl> 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 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(xgboost_recipe) %>%
add_model(xgboost_spec)
# Tune hyperparmeters
set.seed(234)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)## i Creating pre-processing data to finalize unknown parameter: mtry## → A | error: Some columns are non-numeric. The data cannot be converted to numeric matrix: 'start_year', 'end_year', 'rr', 'tunnel_per', 'real_cost'.## There were issues with some computations A: x1There were issues with some computations A: x7There were issues with some computations A: x16There were issues with some computations A: x23There were issues with some computations A: x31There were issues with some computations A: x40There were issues with some computations A: x47There were issues with some computations A: x50## Warning: All models failed. Run `show_notes(.Last.tune.result)` for more
## information.