-
-
Save labouz/c2af9fbc6e2aededeac52daef00725f2 to your computer and use it in GitHub Desktop.
NYC Airbnb prices with xgboost and racing for R-Ladies Miami
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(tidyverse) | |
library(tidymodels) | |
library(textrecipes) | |
library(finetune) | |
library(vip) | |
## data from here: https://www.kaggle.com/c/sliced-s01e05-WXx7h8/data | |
train_raw <- read_csv("train.csv") | |
#--- explore data -----------------------------------------------------------# | |
train_raw %>% | |
group_by(neighbourhood) %>% | |
summarise(n = n(), | |
price = median(price)) %>% | |
filter(n > 10) %>% | |
slice_max(price, n = 15) %>% | |
ggplot(aes(price, fct_reorder(neighbourhood, price))) + | |
geom_col() + | |
scale_x_continuous(labels = scales::dollar_format(), expand = c(0,0)) + | |
labs(y = NULL, x = "Median price per night", | |
title = "Airbnb prices in NYC by neighborhood", | |
subtitle = "Top 15 most expensive neighborhoods") | |
train_raw %>% | |
ggplot(aes(longitude, latitude, z = log(price))) + | |
stat_summary_hex(fun = median, alpha = 0.8, bins = 70) + | |
scale_fill_viridis_b() + | |
labs(fill = "Median price (log)") | |
train_raw %>% | |
ggplot(aes(price, fill = neighbourhood_group)) + | |
geom_histogram(position = "identity", alpha = 0.5, bins = 20) + | |
scale_x_log10(labels = scales::dollar_format()) + | |
labs(fill = NULL, x = "price per night") | |
#--- build model ------------------------------------------------------------# | |
set.seed(123) | |
nyc_split <- train_raw %>% | |
mutate(price = log(price + 1)) %>% | |
initial_split(strata = price) | |
nyc_train <- training(nyc_split) | |
nyc_test <- testing(nyc_split) | |
set.seed(234) | |
nyc_folds <- vfold_cv(nyc_train, v = 5, strata = price) | |
nyc_rec <- recipe(price ~ latitude + longitude + neighbourhood + room_type + | |
minimum_nights + number_of_reviews + availability_365 + name, | |
data = nyc_train) %>% | |
step_other(neighbourhood, threshold = 0.02) %>% | |
step_tokenize(name) %>% | |
step_stopwords(name) %>% | |
step_tokenfilter(name, max_tokens = 30) %>% | |
step_tfidf(name) %>% | |
step_dummy(all_nominal_predictors()) | |
xgb_spec <- | |
boost_tree( | |
trees = tune(), | |
min_n = tune(), | |
mtry = tune(), | |
learn_rate = 0.01 | |
) %>% | |
set_engine("xgboost") %>% | |
set_mode("regression") | |
xgb_wf <- workflow(nyc_rec, xgb_spec) | |
#--- tune & evaluate model -------------------------------------------------# | |
doParallel::registerDoParallel() | |
set.seed(345) | |
xgb_rs <- tune_race_anova( | |
xgb_wf, | |
resamples = nyc_folds, | |
grid = 15, | |
control = control_race(verbose_elim = TRUE) | |
) | |
plot_race(xgb_rs) | |
show_best(xgb_rs) | |
xgb_last <- | |
xgb_wf %>% | |
finalize_workflow(select_best(xgb_rs, "rmse")) %>% | |
last_fit(nyc_split) | |
collect_metrics(xgb_last) | |
extract_workflow(xgb_last) %>% | |
extract_fit_parsnip() %>% | |
vip(geom = "point", num_features = 15) | |
extract_workflow(xgb_last) %>% | |
augment(nyc_test) %>% | |
mutate(.resid = price - .pred) %>% | |
ggplot(aes(longitude, latitude, color = .resid)) + | |
geom_point(alpha = 0.2) + | |
scale_color_viridis_c(limits = c(-1, 1)) + | |
labs(color = "Residuals") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment