Goal: to predict the rental prices in the SF rental market Click here for the data.

Import Data

rent <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2022/2022-07-05/rent.csv')

skimr::skim(rent)
Data summary
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 distributions
    mutate(price = log(price))

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

library(correlationfunnel)

# 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 test and train 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]> Fold10
library(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, city) %>%
  step_dummy(nhood, city, county, one_hot = TRUE) %>%
  step_YeoJohnson(sqft, beds, baths)

xgboost_recipe %>% prep() %>% juice() %>% glimpse()
## Rows: 75
## Columns: 124
## $ post_id                <fct> pre2013_63453, pre2013_14418, 5421737679, pre20…
## $ beds                   <dbl> 0.7989824, 1.3802110, 1.3802110, 0.7989824, 2.2…
## $ baths                  <dbl> 0.4373524, 0.4373524, 0.5496599, 0.4373524, 0.4…
## $ sqft                   <dbl> 1.560766, 1.562757, 1.563156, 1.555870, 1.57135…
## $ price                  <dbl> 7.709757, 7.207860, 7.681099, 7.309881, 9.46885…
## $ tfidf_title_1          <dbl> 0.4239053, 0.0000000, 0.1348790, 0.0000000, 0.0…
## $ tfidf_title_1.5        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1.5ba      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 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_1000ft2    <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1200       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1200ft     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1995       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_1ba        <dbl> 0.0000000, 0.2599332, 0.0000000, 0.3898998, 0.0…
## $ tfidf_title_1bd        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_1br        <dbl> 0.2830002, 0.0000000, 0.0000000, 0.6603338, 0.0…
## $ tfidf_title_2          <dbl> 0.0000000, 0.1648521, 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> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2300       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2400       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_2ba        <dbl> 0.0000000, 0.0000000, 0.2366082, 0.0000000, 0.0…
## $ tfidf_title_2bath      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2bd        <dbl> 0.0000000, 0.0000000, 0.2961906, 0.0000000, 0.0…
## $ tfidf_title_2bed       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_2br        <dbl> 0.0000000, 0.1648521, 0.1348790, 0.0000000, 0.0…
## $ tfidf_title_3          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_3ba        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_3br        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ 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_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, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_650ft      <dbl> 0.000000, 0.000000, 0.000000, 0.608443, 0.00000…
## $ tfidf_title_7          <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_700ft      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_8          <dbl> 0.0000000, 0.3620107, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_a          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_al         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_amp        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_and        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_apartment  <dbl> 0.3341999, 0.0000000, 0.2126726, 0.0000000, 0.0…
## $ tfidf_title_appliances <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_available  <dbl> 0.3341999, 0.2599332, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_ba         <dbl> 0.3190846, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bath       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bathroom   <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bd         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_beautiful  <dbl> 0.0000000, 0.0000000, 0.2237099, 0.0000000, 1.2…
## $ tfidf_title_bed        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_bedroom    <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_br         <dbl> 0.3515442, 0.2734232, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_community  <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_condo      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_downtown   <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_family     <dbl> 0.0000000, 0.3620107, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_feb        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_floor      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_for        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_from       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_ft         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_garage     <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_great      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_har        <dbl> 0.0000000, 0.0000000, 0.2366082, 0.0000000, 0.0…
## $ tfidf_title_hide       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_home       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.9…
## $ tfidf_title_house      <dbl> 0.0000000, 0.3314615, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_in         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_large      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_luxury     <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_new        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_newly      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_now        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_of         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_on         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.5430161, 0.0…
## $ tfidf_title_one        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_patio      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_pic        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_pool       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_posting    <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_remodeled  <dbl> 0.0000000, 0.0000000, 0.0000000, 0.5430161, 0.0…
## $ tfidf_title_rent       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_resim      <dbl> 0.0000000, 0.0000000, 0.2366082, 0.0000000, 0.0…
## $ tfidf_title_restore    <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_richmond   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_room       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_san        <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_single     <dbl> 0.0000000, 0.3620107, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_spacious   <dbl> 0.0000000, 0.0000000, 0.2366082, 0.0000000, 0.0…
## $ tfidf_title_sq         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_storage    <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_şub        <dbl> 0.0000000, 0.0000000, 0.2711958, 0.0000000, 0.0…
## $ tfidf_title_sunny      <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_the        <dbl> 0.0000000, 0.0000000, 0.2711958, 0.0000000, 0.0…
## $ tfidf_title_this       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_to         <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_townhome   <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.0…
## $ tfidf_title_view       <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 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_图片       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_地图       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tfidf_title_月         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood_san.jose.north   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood_santa.clara      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood_sunnyvale        <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ nhood_other            <dbl> 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1,…
## $ city_san.francisco     <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0,…
## $ city_san.jose          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 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_sunnyvale         <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ city_other             <dbl> 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1,…
## $ county_alameda         <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_contra.costa    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_marin           <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ county_napa            <dbl> 0, 0, 1, 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, 1, 0, 0, 0, 1, 0,…
## $ county_san.mateo       <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,…
## $ county_santa.clara     <dbl> 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0,…
## $ county_santa.cruz      <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,…
## $ county_solano          <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, 1, 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)

Evaluate 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   0.476    10  0.0503 Preproces…
## 2    96  1524    23    0.0836  rmse    standard   0.486    10  0.0585 Preproces…
## 3     8  1613    36    0.0290  rmse    standard   0.536    10  0.0512 Preproces…
## 4    73   768    12    0.112   rmse    standard   0.537    10  0.0777 Preproces…
## 5   109   162     7    0.00108 rmse    standard   6.13     10  0.0969 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       0.386 Preprocessor1_Model1
## 2 rsq     standard       0.213 Preprocessor1_Model1
tune::collect_predictions(data_fit) %>%
    ggplot(aes(price, .pred)) +
    geom_point(alpha = 0.3, fill = "midnightblue") +
    geom_abline(lty = 2, color = "grey50") +
    coord_fixed()

Make Predictions