Code Along 1: SF Rental Market
Jordan Lanowy
2024-09-17
Goal: to predict the rental prices in the SF rental market Click here for the data.
Import Data
rent <- read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-07-05/rent.csv')## Rows: 200796 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): post_id, nhood, city, county, address, title, descr, details
## dbl (9): date, year, price, beds, baths, sqft, room_in_apt, lat, lon
##
## 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(rent)| Name | rent |
| Number of rows | 200796 |
| Number of columns | 17 |
| _______________________ | |
| Column type frequency: | |
| character | 8 |
| numeric | 9 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| post_id | 0 | 1.00 | 9 | 14 | 0 | 200796 | 0 |
| nhood | 0 | 1.00 | 4 | 43 | 0 | 167 | 0 |
| city | 0 | 1.00 | 5 | 19 | 0 | 104 | 0 |
| county | 1394 | 0.99 | 4 | 13 | 0 | 10 | 0 |
| address | 196888 | 0.02 | 1 | 38 | 0 | 2869 | 0 |
| title | 2517 | 0.99 | 2 | 298 | 0 | 184961 | 0 |
| descr | 197542 | 0.02 | 13 | 16975 | 0 | 3025 | 0 |
| details | 192780 | 0.04 | 4 | 595 | 0 | 7667 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| date | 0 | 1.00 | 20095718.38 | 44694.07 | 20000902.00 | 20050227.00 | 20110924.00 | 20120805.0 | 20180717.00 | ▁▇▁▆▃ |
| year | 0 | 1.00 | 2009.51 | 4.48 | 2000.00 | 2005.00 | 2011.00 | 2012.0 | 2018.00 | ▁▇▁▆▃ |
| price | 0 | 1.00 | 2135.36 | 1427.75 | 220.00 | 1295.00 | 1800.00 | 2505.0 | 40000.00 | ▇▁▁▁▁ |
| beds | 6608 | 0.97 | 1.89 | 1.08 | 0.00 | 1.00 | 2.00 | 3.0 | 12.00 | ▇▂▁▁▁ |
| baths | 158121 | 0.21 | 1.68 | 0.69 | 1.00 | 1.00 | 2.00 | 2.0 | 8.00 | ▇▁▁▁▁ |
| sqft | 136117 | 0.32 | 1201.83 | 5000.22 | 80.00 | 750.00 | 1000.00 | 1360.0 | 900000.00 | ▇▁▁▁▁ |
| room_in_apt | 0 | 1.00 | 0.00 | 0.04 | 0.00 | 0.00 | 0.00 | 0.0 | 1.00 | ▇▁▁▁▁ |
| lat | 193145 | 0.04 | 37.67 | 0.35 | 33.57 | 37.40 | 37.76 | 37.8 | 40.43 | ▁▁▅▇▁ |
| lon | 196484 | 0.02 | -122.21 | 0.78 | -123.20 | -122.42 | -122.26 | -122.0 | -74.20 | ▇▁▁▁▁ |
data <- rent %>%
# treat missing values
select(-address, -descr, -details, -lat, -lon, -date, -year, -room_in_apt) %>%
na.omit() %>%
# log tansform variables with pos-skewed distribution
mutate(price = log(price))
skimr::skim(data)| Name | data |
| Number of rows | 14394 |
| Number of columns | 9 |
| _______________________ | |
| Column type frequency: | |
| character | 5 |
| numeric | 4 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| post_id | 0 | 1 | 10 | 14 | 0 | 14394 | 0 |
| nhood | 0 | 1 | 4 | 38 | 0 | 143 | 0 |
| city | 0 | 1 | 5 | 14 | 0 | 85 | 0 |
| county | 0 | 1 | 4 | 13 | 0 | 10 | 0 |
| title | 0 | 1 | 6 | 298 | 0 | 14075 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| price | 0 | 1 | 7.82 | 0.45 | 5.86 | 7.52 | 7.8 | 8.08 | 10.09 | ▁▃▇▁▁ |
| beds | 0 | 1 | 2.32 | 1.03 | 0.00 | 2.00 | 2.0 | 3.00 | 8.00 | ▂▇▁▁▁ |
| baths | 0 | 1 | 1.77 | 0.74 | 1.00 | 1.00 | 2.0 | 2.00 | 8.00 | ▇▂▁▁▁ |
| sqft | 0 | 1 | 1273.44 | 698.09 | 110.00 | 887.00 | 1100.0 | 1500.00 | 22000.00 | ▇▁▁▁▁ |
Explore Data
Identify good predictors
sqft
data %>%
ggplot(aes(price, sqft)) +
scale_y_log10()+
geom_point()
beds
data %>%
ggplot(aes(price, as.factor(beds))) +
geom_boxplot()
title
data %>%
# tokenize title
unnest_tokens(output = word, input = title) %>%
# 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 = 20) %>%
# plot
ggplot(aes(price, fct_reorder(word, price))) +
geom_point() +
labs(y = "Words in Title")
EDA shortcut
# Step 1: Prepare data
data_binarized_tbl <- data %>%
select(-post_id, -title) %>%
binarize
data_binarized_tbl %>% glimpse## Rows: 14,394
## Columns: 85
## $ nhood__campbell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__concord_/_pleasant_hill_/_martinez` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__cupertino <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__daly_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__danville_/_san_ramon` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__dublin_/_pleasanton` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__fairfield_/_vacaville` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__foster_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__hayward_/_castro_valley` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__milpitas <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__mountain_view <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__napa_county <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__palo_alto <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__petaluma <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__pittsburg_/_antioch` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__rohnert_pk_/_cotati` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_francisco <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_jose_central <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_jose_east <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_jose_north <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_jose_south <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_jose_west <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_mateo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__san_rafael <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__santa_clara <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__santa_cruz <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__santa_rosa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__SOMA_/_south_beach` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__sunnyvale <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood__union_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__vallejo_/_benicia` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__willow_glen_/_cambrian` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `nhood__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ city__cambrian <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__campbell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__concord <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__cupertino <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__daly_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__dublin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__fairfield <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__foster_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__hayward <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__milpitas <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__mountain_view <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__napa_county <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__oakland <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__palo_alto <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__petaluma <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__pittsburg <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__rohnert_park <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__san_francisco <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__san_jose <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__san_mateo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__san_rafael <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__san_ramon <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__santa_clara <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__santa_cruz <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__santa_rosa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__sunnyvale <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__union_city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city__vallejo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `city__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ county__alameda <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ county__contra_costa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__marin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__napa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__san_francisco <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__san_mateo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__santa_clara <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__santa_cruz <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__solano <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county__sonoma <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `price__-Inf_7.52294091807237` <dbl> 0, 1, 0, 1, 0, 1, 1, 0, 0,…
## $ price__7.52294091807237_7.80384330353877 <dbl> 0, 0, 1, 0, 0, 0, 0, 1, 1,…
## $ price__7.80384330353877_8.07868822922987 <dbl> 1, 0, 0, 0, 1, 0, 0, 0, 0,…
## $ price__8.07868822922987_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `beds__-Inf_2` <dbl> 0, 1, 0, 1, 1, 1, 0, 0, 1,…
## $ beds__2_3 <dbl> 0, 0, 1, 0, 0, 0, 1, 1, 0,…
## $ beds__3_Inf <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ `baths__-Inf_2` <dbl> 0, 1, 1, 1, 1, 1, 0, 0, 1,…
## $ baths__2_Inf <dbl> 1, 0, 0, 0, 0, 0, 1, 1, 0,…
## $ `sqft__-Inf_887` <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 1,…
## $ sqft__887_1100 <dbl> 0, 0, 0, 1, 0, 0, 0, 1, 0,…
## $ sqft__1100_1500 <dbl> 0, 0, 1, 0, 1, 1, 0, 0, 0,…
## $ sqft__1500_Inf <dbl> 1, 0, 0, 0, 0, 0, 1, 0, 0,…# step 2: correlate
data_correlate_tbl <- data_binarized_tbl %>%
correlate(price__8.07868822922987_Inf)
# step 3: Plot
data_correlate_tbl %>%
plot_correlation_funnel()## Warning: ggrepel: 69 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
Build Data
data <- sample_n(data, 100)
# Split data into train and test 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 [67/8]> Fold01
## 2 <split [67/8]> Fold02
## 3 <split [67/8]> Fold03
## 4 <split [67/8]> Fold04
## 5 <split [67/8]> Fold05
## 6 <split [68/7]> Fold06
## 7 <split [68/7]> Fold07
## 8 <split [68/7]> Fold08
## 9 <split [68/7]> Fold09
## 10 <split [68/7]> Fold10library(usemodels)
usemodels::use_xgboost(price ~ ., data = data_train)## xgboost_recipe <-
## recipe(formula = price ~ ., 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(6804)
## 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 = price ~ ., data = data_train) %>%
recipes::update_role(post_id, new_role = "id variable") %>%
step_tokenize(title) %>%
step_tokenfilter(title, max_tokens = 100) %>%
step_tfidf(title) %>%
step_other(nhood) %>%
step_dummy(nhood, city, county, one_hot = TRUE) %>%
step_log(sqft, beds, baths)
xgboost_recipe %>% prep() %>% juice() %>% glimpse()## Rows: 75
## Columns: 158
## $ post_id <fct> 5975833688, 4632750225, 5615302354, 4014316666,…
## $ beds <dbl> 0.0000000, 0.6931472, 0.6931472, 0.6931472, 1.0…
## $ baths <dbl> 0.0000000, 0.0000000, 0.9162907, 0.6931472, 0.6…
## $ sqft <dbl> 6.309918, 7.003065, 7.029973, 7.170120, 7.09340…
## $ price <dbl> 7.647309, 7.575585, 8.022897, 7.899153, 8.16365…
## $ tfidf_title_1 <dbl> 0.00000000, 0.31977116, 0.07267526, 0.00000000,…
## $ tfidf_title_1.5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_10 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1100ft <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1200 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1200ft <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1259ft <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_14 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1550 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_16 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1750 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1bath <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1br <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2 <dbl> 0.00000000, 0.26582719, 0.06041527, 0.29536354,…
## $ tfidf_title_2.5 <dbl> 0.0000000, 0.0000000, 0.1480953, 0.0000000, 0.0…
## $ tfidf_title_2.5ba <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.00000…
## $ tfidf_title_2595 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2ba <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2bath <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_2bd <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_2br <dbl> 0.00000000, 0.00000000, 0.06441209, 0.15745178,…
## $ tfidf_title_3 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.1…
## $ tfidf_title_3000ft <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_3250 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_3400 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_3ba <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_3bd <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_3br <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.1…
## $ tfidf_title_4 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_4br <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_5br <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_6 <dbl> 0.0000000, 0.0000000, 0.1659390, 0.0000000, 0.0…
## $ tfidf_title_8 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_9 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_al <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.3…
## $ tfidf_title_apartment <dbl> 1.2304045, 0.0000000, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_apt <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_area <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_available <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_ba <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bath <dbl> 0.00000000, 0.24141859, 0.05486786, 0.13412144,…
## $ tfidf_title_bathroom <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_bd <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bdrm <dbl> 0.0000000, 0.7301316, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_beach <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_beautiful <dbl> 0.0000000, 0.0000000, 0.1183041, 0.0000000, 0.0…
## $ tfidf_title_bed <dbl> 0.00000000, 0.00000000, 0.07901231, 0.19314120,…
## $ tfidf_title_bedroom <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.1…
## $ tfidf_title_br <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_clara <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_close <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_community <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_condo <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_cottage <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_cruz <dbl> 0.0000000, 0.0000000, 0.0000000, 0.3620107, 0.0…
## $ tfidf_title_d <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_dryer <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_emeryville <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.3…
## $ tfidf_title_floor <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_for <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_great <dbl> 1.491577, 0.000000, 0.000000, 0.000000, 0.00000…
## $ tfidf_title_har <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_hide <dbl> 0.0000000, 0.0000000, 0.1118550, 0.0000000, 0.0…
## $ tfidf_title_home <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_house <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_in <dbl> 0.00000000, 0.33771505, 0.07675342, 0.00000000,…
## $ tfidf_title_jose <dbl> 0.0000000, 0.0000000, 0.2961906, 0.0000000, 0.0…
## $ tfidf_title_large <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_map <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2891877, 0.0…
## $ tfidf_title_new <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_nice <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_north <dbl> 0.000000, 0.000000, 0.331878, 0.000000, 0.00000…
## $ tfidf_title_now <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_oca <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_one <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_pic <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2891877, 0.0…
## $ tfidf_title_posting <dbl> 0.0000000, 0.0000000, 0.2237099, 0.0000000, 0.0…
## $ tfidf_title_remodeled <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_rent <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_resim <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_restore <dbl> 0.0000000, 0.0000000, 0.1260268, 0.0000000, 0.0…
## $ tfidf_title_san <dbl> 0.0000000, 0.0000000, 0.2520535, 0.0000000, 0.0…
## $ tfidf_title_santa <dbl> 0.0000000, 0.0000000, 0.0000000, 0.3080654, 0.0…
## $ tfidf_title_spacious <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.1…
## $ tfidf_title_şub <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_this <dbl> 0.0000000, 0.0000000, 0.1945515, 0.0000000, 0.0…
## $ tfidf_title_to <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.00000…
## $ tfidf_title_today <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_townhouse <dbl> 0.0000000, 0.0000000, 0.1260268, 0.0000000, 0.0…
## $ tfidf_title_two <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_unit <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_view <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_w <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_with <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_게시물 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_사진 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_월 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_이 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_지도 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ nhood_milpitas <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood_other <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ city_alameda <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_belmont <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_berkeley <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_brentwood <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_burlingame <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_campbell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_concord <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,…
## $ city_corralitos <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_daly.city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_el.sobrante <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,…
## $ city_emeryville <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_foster.city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_gilroy <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_healdsburg <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_los.altos <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_los.gatos <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_menlo.park <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_millbrae <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,…
## $ city_milpitas <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_morgan.hill <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_mountain.view <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,…
## $ city_novato <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_oakland <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_palo.alto <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_petaluma <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_pittsburg <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0,…
## $ city_redwood.city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_richmond <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_san.francisco <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ city_san.jose <dbl> 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0,…
## $ city_san.mateo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_san.rafael <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_san.ramon <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_santa.clara <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_santa.cruz <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_santa.rosa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_scotts.valley <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_soquel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_sunnyvale <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_union.city <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_vallejo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,…
## $ city_watsonville <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_alameda <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_contra.costa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0,…
## $ county_marin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_san.francisco <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ county_san.mateo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,…
## $ county_santa.clara <dbl> 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1,…
## $ county_santa.cruz <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_solano <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,…
## $ county_sonoma <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…# 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 hyperparameters
set.seed(30220)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)## i Creating pre-processing data to finalize unknown parameter: mtry## → A | error: [16:45:07] src/data/data.cc:1104: Check failed: valid: Input data contains `inf` or `nan`
## Stack trace:
## [bt] (0) 1 xgboost.so 0x000000010a0f5c3c dmlc::LogMessageFatal::~LogMessageFatal() + 124
## [bt] (1) 2 xgboost.so 0x000000010a18311c unsigned long long xgboost::SparsePage::Push<xgboost::data::DenseAdapterBatch>(xgboost::data::DenseAdapterBatch const&, float, int) + 988
## [bt] (2) 3 xgboost.so 0x000000010a1762d0 xgboost::data::SimpleDMatrix::SimpleDMatrix<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int) + 272
## [bt] (3) 4 xgboost.so 0x000000010a1828fc xgboost::DMatrix* xgboost::DMatrix::Create<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&) + 60
## [bt] (4) 5 xgboost.so 0x000000010a2aa6f0 XGDMatrixCreateFromMat_omp##
There were issues with some computations A: x1
→ B | warning: ! There are new levels in a factor: `petaluma`, `burlingame`, `morgan hill`,
## and `belmont`.
## There were issues with some computations A: x1
There were issues with some computations A: x5 B: x1
→ C | error: [16:45:08] src/data/data.cc:1104: Check failed: valid: Input data contains `inf` or `nan`
## Stack trace:
## [bt] (0) 1 xgboost.so 0x000000010a0f5c3c dmlc::LogMessageFatal::~LogMessageFatal() + 124
## [bt] (1) 2 xgboost.so 0x000000010a18311c unsigned long long xgboost::SparsePage::Push<xgboost::data::DenseAdapterBatch>(xgboost::data::DenseAdapterBatch const&, float, int) + 988
## [bt] (2) 3 xgboost.so 0x000000010a1762d0 xgboost::data::SimpleDMatrix::SimpleDMatrix<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int) + 272
## [bt] (3) 4 xgboost.so 0x000000010a1828fc xgboost::DMatrix* xgboost::DMatrix::Create<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&) + 60
## [bt] (4) 5 xgboost.so 0x000000010a2aa6f0 XGDMatrixCreateFromMat_omp
## There were issues with some computations A: x5 B: x1
There were issues with some computations A: x5 B: x2 C: x1
There were issues with some computations A: x5 B: x3 C: x2
There were issues with some computations A: x5 B: x4 C: x3
There were issues with some computations A: x5 B: x5 C: x4
→ D | error: [16:45:09] src/data/data.cc:1104: Check failed: valid: Input data contains `inf` or `nan`
## Stack trace:
## [bt] (0) 1 xgboost.so 0x000000010a0f5c3c dmlc::LogMessageFatal::~LogMessageFatal() + 124
## [bt] (1) 2 xgboost.so 0x000000010a18311c unsigned long long xgboost::SparsePage::Push<xgboost::data::DenseAdapterBatch>(xgboost::data::DenseAdapterBatch const&, float, int) + 988
## [bt] (2) 3 xgboost.so 0x000000010a1762d0 xgboost::data::SimpleDMatrix::SimpleDMatrix<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int) + 272
## [bt] (3) 4 xgboost.so 0x000000010a1828fc xgboost::DMatrix* xgboost::DMatrix::Create<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&) + 60
## [bt] (4) 5 xgboost.so 0x000000010a2aa6f0 XGDMatrixCreateFromMat_omp
## There were issues with some computations A: x5 B: x5 C: x4
There were issues with some computations A: x5 B: x5 C: x5 D: x6
There were issues with some computations A: x5 B: x5 C: x5 D: x11
There were issues with some computations A: x5 B: x5 C: x5 D: x18
There were issues with some computations A: x5 B: x5 C: x5 D: x24
→ E | error: [16:45:10] src/data/data.cc:1104: Check failed: valid: Input data contains `inf` or `nan`
## Stack trace:
## [bt] (0) 1 xgboost.so 0x000000010a0f5c3c dmlc::LogMessageFatal::~LogMessageFatal() + 124
## [bt] (1) 2 xgboost.so 0x000000010a18311c unsigned long long xgboost::SparsePage::Push<xgboost::data::DenseAdapterBatch>(xgboost::data::DenseAdapterBatch const&, float, int) + 988
## [bt] (2) 3 xgboost.so 0x000000010a1762d0 xgboost::data::SimpleDMatrix::SimpleDMatrix<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int) + 272
## [bt] (3) 4 xgboost.so 0x000000010a1828fc xgboost::DMatrix* xgboost::DMatrix::Create<xgboost::data::DenseAdapter>(xgboost::data::DenseAdapter*, float, int, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> > const&) + 60
## [bt] (4) 5 xgboost.so 0x000000010a2aa6f0 XGDMatrixCreateFromMat_omp
## There were issues with some computations A: x5 B: x5 C: x5 D: x24
There were issues with some computations A: x5 B: x5 C: x5 D: x30 E: …
There were issues with some computations A: x5 B: x5 C: x5 D: x30 E: …
There were issues with some computations A: x5 B: x5 C: x5 D: x30 E: …## Warning: All models failed. Run `show_notes(.Last.tune.result)` for more
## information.