Code Along 3
Maddie Westbrook
2024-02-21
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 transform 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_corr_tbl <- data_binarized_tbl %>%
correlate(price__8.07868822922987_Inf)
data_corr_tbl## # A tibble: 85 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 price 8.07868822922987_Inf 1
## 2 city san_francisco 0.389
## 3 county san_francisco 0.389
## 4 price -Inf_7.52294091807237 -0.342
## 5 price 7.80384330353877_8.07868822922987 -0.330
## 6 price 7.52294091807237_7.80384330353877 -0.328
## 7 sqft 1500_Inf 0.324
## 8 beds -Inf_2 -0.254
## 9 beds 3_Inf 0.241
## 10 sqft -Inf_887 -0.240
## # ℹ 75 more rows# Step 3: Plot
data_corr_tbl %>%
plot_correlation_funnel()## Warning: ggrepel: 69 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
Build Models
Split Data
data <- sample_n(data, 100)
# Split into train and testing data set
set.seed(1234)
data_split <- rsample::initial_split(data)
data_train <- training(data_split)
data_test <- testing(data_split)
# Further split training data set 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)## Warning: package 'usemodels' was built under R version 4.2.3usemodels::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, city) %>%
step_dummy(nhood, city, county, one_hot = TRUE) %>%
step_YeoJohnson(sqft, beds, baths)
xgboost_recipe %>% prep() %>% juice() %>% glimpse## Rows: 75
## Columns: 123
## $ post_id <fct> 4924506156, pre2013_54237, 4710726678, 54046743…
## $ beds <dbl> 0.6548416, 0.6548416, 1.0044630, 1.4127943, 0.6…
## $ baths <dbl> 0.4783079, 0.4783079, 0.6248670, 0.7346705, 0.5…
## $ sqft <dbl> 2.386140, 2.348380, 2.435770, 2.458116, 2.43213…
## $ price <dbl> 7.745003, 7.346010, 7.781139, 7.824046, 7.88231…
## $ tfidf_title_1 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_10 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1000ft <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1200ft <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1300 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1300ft <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_14 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1400ft <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_15 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1550 <dbl> 0.0000000, 0.2961906, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1800 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1ba <dbl> 0.2030538, 0.2030538, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1bd <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1br <dbl> 0.1628872, 0.3257744, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_2 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2.5 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2.5ba <dbl> 0.000000, 0.000000, 0.000000, 0.000000, 0.00000…
## $ tfidf_title_21 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.4056287, 0.0…
## $ tfidf_title_2200 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2500 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.3620107, 0.0…
## $ tfidf_title_2ba <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2bath <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2br <dbl> 0.00000000, 0.00000000, 0.00000000, 0.00000000,…
## $ tfidf_title_3 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_3br <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_6 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_8 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_a <dbl> 0.2520535, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_amp <dbl> 0.2961906, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_and <dbl> 0.0000000, 0.2237099, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_apt <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_available <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_ba <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bath <dbl> 0.00000000, 0.00000000, 0.00000000, 0.00000000,…
## $ tfidf_title_baths <dbl> 0.0000000, 0.0000000, 0.0000000, 0.3620107, 0.4…
## $ tfidf_title_beautiful <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bed <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bedroom <dbl> 0.00000000, 0.00000000, 0.00000000, 0.00000000,…
## $ tfidf_title_br <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_brand <dbl> 0.0000000, 0.2711958, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_city <dbl> 0.0000000, 0.2520535, 0.9241962, 0.0000000, 0.0…
## $ tfidf_title_clara <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_clean <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_come <dbl> 0.2961906, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_condo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_d <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_for <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2891877, 0.0…
## $ tfidf_title_ft <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.4…
## $ tfidf_title_garage <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_great <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_har <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2599332, 0.0…
## $ tfidf_title_hide <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_hill <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_home <dbl> 0.37390037, 0.00000000, 0.00000000, 0.00000000,…
## $ tfidf_title_house <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2891877, 0.0…
## $ tfidf_title_huge <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.4…
## $ tfidf_title_in <dbl> 0.1416495, 0.1416495, 0.5193815, 0.1731272, 0.0…
## $ tfidf_title_large <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_live <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_living <dbl> 0.000000, 0.000000, 1.086032, 0.000000, 0.00000…
## $ tfidf_title_location <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_map <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_mar <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_martinez <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_move <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_near <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_new <dbl> 0.0000000, 0.1869502, 0.0000000, 0.0000000, 0.2…
## $ tfidf_title_now <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_our <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_parking <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.4…
## $ tfidf_title_pleasant <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_posting <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_remodeled <dbl> 0.0000000, 0.2520535, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_rent <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2891877, 0.0…
## $ tfidf_title_resim <dbl> 0.0000000, 0.0000000, 0.0000000, 0.2599332, 0.0…
## $ tfidf_title_san <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_santa <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_spacious <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_sq <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.4…
## $ tfidf_title_şub <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_this <dbl> 0.2237099, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_to <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_today <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_townhouse <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_unit <dbl> 0.0000000, 0.2711958, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_valley <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_view <dbl> 0.2366082, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_w <dbl> 0.2030538, 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> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_게시물을 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_복구 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_사진 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_설정 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_숨김 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_월 <dbl> 0.00000000, 0.00000000, 0.00000000, 0.00000000,…
## $ tfidf_title_이 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_즐겨찾기로 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_지도 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ nhood_mountain.view <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ nhood_santa.clara <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood_union.city <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, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1,…
## $ city_mountain.view <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ city_san.francisco <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,…
## $ city_san.jose <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0,…
## $ city_santa.clara <dbl> 0, 0, 0, 0, 0, 1, 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_other <dbl> 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1,…
## $ county_alameda <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,…
## $ county_contra.costa <dbl> 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1,…
## $ 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, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,…
## $ county_san.mateo <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,…
## $ county_santa.clara <dbl> 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0,…
## $ county_santa.cruz <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_sonoma <dbl> 0, 0, 0, 0, 0, 0, 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(344)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)## i Creating pre-processing data to finalize unknown parameter: mtry## → A | warning: A correlation computation is required, but `estimate` is constant and has 0
## standard deviation, resulting in a divide by 0 error. `NA` will be returned.##
There were issues with some computations A: x1
There were issues with some computations A: x2
There were issues with some computations A: x3
There were issues with some computations A: x4
There were issues with some computations A: x5
There were issues with some computations A: x6
There were issues with some computations A: x7
There were issues with some computations A: x8
There were issues with some computations A: x9
There were issues with some computations A: x10
There were issues with some computations A: x10Evaluate 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 39 1104 28 0.00484 rmse standard 0.367 10 0.0423 Preproces…
## 2 96 1524 23 0.0836 rmse standard 0.394 10 0.0417 Preproces…
## 3 8 1613 36 0.0290 rmse standard 0.422 10 0.0383 Preproces…
## 4 72 768 12 0.112 rmse standard 0.439 10 0.0310 Preproces…
## 5 108 162 7 0.00108 rmse standard 6.14 10 0.0568 Preproces…# Update the model by selecting the best hyperparameters.
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
data_fit <- tune::last_fit(xgboost_fw, data_split)tune::collect_metrics(data_fit)## # A tibble: 2 × 4
## .metric .estimator .estimate .config
## <chr> <chr> <dbl> <chr>
## 1 rmse standard 0.394 Preprocessor1_Model1
## 2 rsq standard 0.218 Preprocessor1_Model1tune::collect_predictions(data_fit) %>%
ggplot(aes(price, .pred)) +
geom_point(alpha = 0.3, fill = "midnightblue") +
geom_abline(lty = 2, color = "gray50") +
coord_fixed()