r_final_proj_part1
Luke Bergman
2024-04-16
Packages Needed
library(tidymodels)
library(tidyverse)
library(baguette)
library(vip)
library(pdp)
library(here)
library(kernlab)
library(ggplot2)
library(earth)retention <- read.csv('data/customer_retention.csv')
sum(is.na(retention))## [1] 11Cleaning up dataset:
retention <- retention %>%
mutate(Status = factor(Status)) %>%
na.omit
sum(is.na(retention))## [1] 0We now have 0 null variables, and can go ahead with processing the data.
Machine Learning:
For our first model, we will look at logistic regression.
set.seed(123)
log_split <- initial_split(retention, prop = .7, strata = Status)
log_train <- training(log_split)
log_test <- testing(log_split)set.seed(123)
log_kfolds <- vfold_cv(log_train, v = 5, strata = Status)
results <- logistic_reg() %>%
fit_resamples(Status ~ ., log_kfolds)## → A | warning: prediction from rank-deficient fit; attr(*, "non-estim") has doubtful cases##
There were issues with some computations A: x1
There were issues with some computations A: x2
There were issues with some computations A: x4
There were issues with some computations A: x5
There were issues with some computations A: x5collect_metrics(results)## # A tibble: 2 × 6
## .metric .estimator mean n std_err .config
## <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 accuracy binary 0.799 5 0.00401 Preprocessor1_Model1
## 2 roc_auc binary 0.845 5 0.00521 Preprocessor1_Model1We found an roc_auc value of .8448, which is good, but should be able to be improved.
final_fit <- logistic_reg() %>%
fit(Status ~ ., data = log_train)
tidy(final_fit)## # A tibble: 31 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 1.02 0.969 1.05 2.95e- 1
## 2 GenderMale -0.0461 0.0779 -0.592 5.54e- 1
## 3 SeniorCitizen 0.258 0.101 2.55 1.08e- 2
## 4 PartnerYes -0.141 0.0925 -1.52 1.29e- 1
## 5 DependentsYes -0.0475 0.108 -0.441 6.59e- 1
## 6 Tenure -0.0646 0.00762 -8.47 2.35e-17
## 7 PhoneServiceYes -0.0417 0.774 -0.0539 9.57e- 1
## 8 MultipleLinesNo phone service NA NA NA NA
## 9 MultipleLinesYes 0.442 0.211 2.10 3.56e- 2
## 10 InternetServiceFiber optic 1.48 0.950 1.56 1.18e- 1
## # ℹ 21 more rowsfinal_fit %>%
predict(log_test) %>%
bind_cols(log_test %>% select(Status)) %>%
conf_mat(truth = Status, estimate = .pred_class)## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from rank-deficient fit; attr(*, "non-estim") has doubtful cases## Truth
## Prediction Current Left
## Current 1362 225
## Left 178 332We find that our model is usually predicting correctly, but we are experiencing some false positives.
Next up, we will assess a Mars Model
set.seed(123) # for reproducibility
mars_split <- initial_split(retention, prop = .7, strata = Status)
mars_train <- training(mars_split)
mars_test <- testing(mars_split)mars_recipe <- recipe(Status ~ ., data = mars_train) %>%
step_YeoJohnson(all_numeric_predictors()) %>%
step_normalize(all_numeric_predictors())set.seed(123)
kfolds <- vfold_cv(mars_train, v = 5, strata = Status)mars_mod <- mars(num_terms = tune(), prod_degree = tune()) %>%
set_mode('classification')mars_grid <- grid_regular(num_terms(range = c(1,30)), prod_degree(), levels = 40)mars_wf <- workflow() %>%
add_recipe(mars_recipe) %>%
add_model(mars_mod)tuning_results <- mars_wf %>%
tune_grid(resamples = kfolds, grid = mars_grid)tuning_results %>%
collect_metrics() %>%
filter(.metric == "roc_auc") %>%
arrange(desc(mean))## # A tibble: 60 × 8
## num_terms prod_degree .metric .estimator mean n std_err .config
## <int> <int> <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 15 1 roc_auc binary 0.850 5 0.00509 Preprocessor1_M…
## 2 16 1 roc_auc binary 0.849 5 0.00502 Preprocessor1_M…
## 3 18 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 4 19 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 5 20 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 6 21 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 7 22 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 8 23 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 9 24 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## 10 25 1 roc_auc binary 0.849 5 0.00503 Preprocessor1_M…
## # ℹ 50 more rowsHere we find a max roc_auc of .8499, but we hope that we can still do better.
autoplot(tuning_results)
Next we will finalize our workflow object with the optimal hyperparameter values,
best_hyperparameters <- select_best(tuning_results, metric = "roc_auc")
final_wf <- workflow() %>%
add_recipe(mars_recipe) %>%
add_model(mars_mod) %>%
finalize_workflow(best_hyperparameters)Then we fit our final workflow object across the full training set data
final_fit <- final_wf %>%
fit(data = mars_train)final_fit %>%
extract_fit_parsnip() %>%
vip()
This model shows our most important features to be tenure, total
charges, and payment method.
final_fit %>%
predict(mars_test) %>%
bind_cols(mars_test %>% select(Status)) %>%
conf_mat(truth = Status, estimate = .pred_class)## Truth
## Prediction Current Left
## Current 1382 245
## Left 158 312Decision Trees
dt_mod <- decision_tree(mode = 'classification') %>%
set_engine("rpart")
model_recipe <- recipe(Status ~ ., data = log_train)
dt_fit <- workflow() %>%
add_recipe(model_recipe) %>%
add_model(dt_mod) %>%
fit(data = log_train)rpart.plot::rpart.plot(dt_fit$fit$fit$fit)## Warning: Cannot retrieve the data used to build the model (so cannot determine roundint and is.binary for the variables).
## To silence this warning:
## Call rpart.plot with roundint=FALSE,
## or rebuild the rpart model with model=TRUE.
The root node of the decision tree is contract = 1 year or 2 years
set.seed(123)
kfold <- vfold_cv(log_train, v = 5)
dt_results <- fit_resamples(dt_mod, model_recipe, kfold)
collect_metrics(dt_results)## # A tibble: 2 × 6
## .metric .estimator mean n std_err .config
## <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 accuracy binary 0.785 5 0.00552 Preprocessor1_Model1
## 2 roc_auc binary 0.803 5 0.00777 Preprocessor1_Model1The decision tree gave us a roc_auc of .8033, which is not an optimal value. With further tuning, we can hope to create an even better model.
dt_mod <- decision_tree(
mode = "classification",
cost_complexity = tune(),
tree_depth = tune(),
min_n = tune()
) %>%
set_engine("rpart")
dt_hyper_grid <- grid_regular(
cost_complexity(),
tree_depth(),
min_n(),
levels = 5
)
set.seed(123)
dt_results <- tune_grid(dt_mod, model_recipe, resamples = kfold, grid = dt_hyper_grid)
show_best(dt_results, metric = "roc_auc", n = 5)## # A tibble: 5 × 9
## cost_complexity tree_depth min_n .metric .estimator mean n std_err
## <dbl> <int> <int> <chr> <chr> <dbl> <int> <dbl>
## 1 0.0000000001 15 40 roc_auc binary 0.814 5 0.00780
## 2 0.0000000178 15 40 roc_auc binary 0.814 5 0.00780
## 3 0.00000316 15 40 roc_auc binary 0.814 5 0.00780
## 4 0.0000000001 11 40 roc_auc binary 0.814 5 0.00827
## 5 0.0000000178 11 40 roc_auc binary 0.814 5 0.00827
## # ℹ 1 more variable: .config <chr>We now got the roc_auc up to .8142, which is better, but still not the optimal model.
dt_best_model <- select_best(dt_results, metric = 'roc_auc')
dt_final_wf <- workflow() %>%
add_recipe(model_recipe) %>%
add_model(dt_mod) %>%
finalize_workflow(dt_best_model)
dt_final_fit <- dt_final_wf %>%
fit(data = log_train)
dt_final_fit %>%
extract_fit_parsnip() %>%
vip(20)
We find that with decision trees, the most important features are
tenure, contract, and total charges.
dt_final_fit %>%
predict(log_test) %>%
bind_cols(log_test %>% select(Status)) %>%
conf_mat(truth = Status, estimate = .pred_class)## Truth
## Prediction Current Left
## Current 1346 275
## Left 194 282Finally, we will look at a Random Forest
set.seed(123)
rf_split <- initial_split(retention, prop = 0.7, strata = Status)
rf_train <- training(rf_split)
rf_test <- testing(rf_split)
rf_recipe <- recipe(Status ~ ., data = rf_train)
rf_mod <- rand_forest(mode = "classification") %>%
set_engine("ranger")
set.seed(123)
rf_kfold <- vfold_cv(rf_train, v = 5)
rf_results <- fit_resamples(rf_mod, rf_recipe, rf_kfold)## Warning: package 'ranger' was built under R version 4.3.3collect_metrics(rf_results)## # A tibble: 2 × 6
## .metric .estimator mean n std_err .config
## <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 accuracy binary 0.798 5 0.00509 Preprocessor1_Model1
## 2 roc_auc binary 0.837 5 0.0103 Preprocessor1_Model1This model gives us a roc_auc of .8368, but with hyperparameter tuning we hope to do even better.
rf_mod <- rand_forest(
mode = "classification",
trees = tune(),
mtry = tune(),
min_n = tune()) %>%
set_engine("ranger", importance = "impurity")
rf_hyper_grid <- grid_regular(
trees(range = c(50, 800)),
mtry(range = c(2, 50)),
min_n(range = c(1, 20)),
levels = 5)
set.seed(123)
rf_results <- tune_grid(rf_mod, rf_recipe, resamples = rf_kfold, grid = rf_hyper_grid)## → A | warning: 26 columns were requested but there were 19 predictors in the data. 19 will be used.##
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
→ B | warning: 38 columns were requested but there were 19 predictors in the data. 19 will be used.
## There were issues with some computations A: x5
There were issues with some computations A: x5 B: x1
There were issues with some computations A: x5 B: x2
There were issues with some computations A: x5 B: x3
There were issues with some computations A: x5 B: x4
There were issues with some computations A: x5 B: x5
→ C | warning: 50 columns were requested but there were 19 predictors in the data. 19 will be used.
## There were issues with some computations A: x5 B: x5
There were issues with some computations A: x5 B: x5 C: x1
There were issues with some computations A: x5 B: x5 C: x2
There were issues with some computations A: x5 B: x5 C: x3
There were issues with some computations A: x5 B: x5 C: x4
There were issues with some computations A: x5 B: x5 C: x5
There were issues with some computations A: x6 B: x5 C: x5
There were issues with some computations A: x7 B: x5 C: x5
There were issues with some computations A: x8 B: x5 C: x5
There were issues with some computations A: x9 B: x5 C: x5
There were issues with some computations A: x10 B: x5 C: x5
There were issues with some computations A: x10 B: x6 C: x5
There were issues with some computations A: x10 B: x7 C: x5
There were issues with some computations A: x10 B: x8 C: x5
There were issues with some computations A: x10 B: x9 C: x5
There were issues with some computations A: x10 B: x10 C: x5
There were issues with some computations A: x10 B: x10 C: x6
There were issues with some computations A: x10 B: x10 C: x7
There were issues with some computations A: x10 B: x10 C: x8
There were issues with some computations A: x10 B: x10 C: x9
There were issues with some computations A: x10 B: x10 C: x10
There were issues with some computations A: x11 B: x10 C: x10
There were issues with some computations A: x12 B: x10 C: x10
There were issues with some computations A: x13 B: x10 C: x10
There were issues with some computations A: x14 B: x10 C: x10
There were issues with some computations A: x15 B: x10 C: x10
There were issues with some computations A: x15 B: x11 C: x10
There were issues with some computations A: x15 B: x12 C: x10
There were issues with some computations A: x15 B: x13 C: x10
There were issues with some computations A: x15 B: x14 C: x10
There were issues with some computations A: x15 B: x15 C: x10
There were issues with some computations A: x15 B: x15 C: x11
There were issues with some computations A: x15 B: x15 C: x12
There were issues with some computations A: x15 B: x15 C: x13
There were issues with some computations A: x15 B: x15 C: x14
There were issues with some computations A: x15 B: x15 C: x15
There were issues with some computations A: x16 B: x15 C: x15
There were issues with some computations A: x17 B: x15 C: x15
There were issues with some computations A: x18 B: x15 C: x15
There were issues with some computations A: x19 B: x15 C: x15
There were issues with some computations A: x20 B: x15 C: x15
There were issues with some computations A: x20 B: x16 C: x15
There were issues with some computations A: x20 B: x17 C: x15
There were issues with some computations A: x20 B: x18 C: x15
There were issues with some computations A: x20 B: x19 C: x15
There were issues with some computations A: x20 B: x20 C: x15
There were issues with some computations A: x20 B: x20 C: x16
There were issues with some computations A: x20 B: x20 C: x17
There were issues with some computations A: x20 B: x20 C: x18
There were issues with some computations A: x20 B: x20 C: x19
There were issues with some computations A: x20 B: x20 C: x20
There were issues with some computations A: x21 B: x20 C: x20
There were issues with some computations A: x22 B: x20 C: x20
There were issues with some computations A: x23 B: x20 C: x20
There were issues with some computations A: x24 B: x20 C: x20
There were issues with some computations A: x25 B: x20 C: x20
There were issues with some computations A: x25 B: x21 C: x20
There were issues with some computations A: x25 B: x22 C: x20
There were issues with some computations A: x25 B: x23 C: x20
There were issues with some computations A: x25 B: x24 C: x20
There were issues with some computations A: x25 B: x25 C: x20
There were issues with some computations A: x25 B: x25 C: x21
There were issues with some computations A: x25 B: x25 C: x22
There were issues with some computations A: x25 B: x25 C: x23
There were issues with some computations A: x25 B: x25 C: x24
There were issues with some computations A: x25 B: x25 C: x25
There were issues with some computations A: x26 B: x25 C: x25
There were issues with some computations A: x27 B: x25 C: x25
There were issues with some computations A: x28 B: x25 C: x25
There were issues with some computations A: x29 B: x25 C: x25
There were issues with some computations A: x30 B: x25 C: x25
There were issues with some computations A: x30 B: x26 C: x25
There were issues with some computations A: x30 B: x27 C: x25
There were issues with some computations A: x30 B: x28 C: x25
There were issues with some computations A: x30 B: x29 C: x25
There were issues with some computations A: x30 B: x30 C: x25
There were issues with some computations A: x30 B: x30 C: x26
There were issues with some computations A: x30 B: x30 C: x27
There were issues with some computations A: x30 B: x30 C: x28
There were issues with some computations A: x30 B: x30 C: x29
There were issues with some computations A: x30 B: x30 C: x30
There were issues with some computations A: x31 B: x30 C: x30
There were issues with some computations A: x32 B: x30 C: x30
There were issues with some computations A: x33 B: x30 C: x30
There were issues with some computations A: x34 B: x30 C: x30
There were issues with some computations A: x35 B: x30 C: x30
There were issues with some computations A: x35 B: x31 C: x30
There were issues with some computations A: x35 B: x32 C: x30
There were issues with some computations A: x35 B: x33 C: x30
There were issues with some computations A: x35 B: x34 C: x30
There were issues with some computations A: x35 B: x35 C: x30
There were issues with some computations A: x35 B: x35 C: x31
There were issues with some computations A: x35 B: x35 C: x32
There were issues with some computations A: x35 B: x35 C: x33
There were issues with some computations A: x35 B: x35 C: x34
There were issues with some computations A: x35 B: x35 C: x35
There were issues with some computations A: x36 B: x35 C: x35
There were issues with some computations A: x37 B: x35 C: x35
There were issues with some computations A: x38 B: x35 C: x35
There were issues with some computations A: x39 B: x35 C: x35
There were issues with some computations A: x40 B: x35 C: x35
There were issues with some computations A: x40 B: x36 C: x35
There were issues with some computations A: x40 B: x37 C: x35
There were issues with some computations A: x40 B: x38 C: x35
There were issues with some computations A: x40 B: x39 C: x35
There were issues with some computations A: x40 B: x40 C: x35
There were issues with some computations A: x40 B: x40 C: x36
There were issues with some computations A: x40 B: x40 C: x37
There were issues with some computations A: x40 B: x40 C: x38
There were issues with some computations A: x40 B: x40 C: x39
There were issues with some computations A: x40 B: x40 C: x40
There were issues with some computations A: x41 B: x40 C: x40
There were issues with some computations A: x42 B: x40 C: x40
There were issues with some computations A: x43 B: x40 C: x40
There were issues with some computations A: x44 B: x40 C: x40
There were issues with some computations A: x45 B: x40 C: x40
There were issues with some computations A: x45 B: x41 C: x40
There were issues with some computations A: x45 B: x42 C: x40
There were issues with some computations A: x45 B: x43 C: x40
There were issues with some computations A: x45 B: x44 C: x40
There were issues with some computations A: x45 B: x45 C: x40
There were issues with some computations A: x45 B: x45 C: x41
There were issues with some computations A: x45 B: x45 C: x42
There were issues with some computations A: x45 B: x45 C: x43
There were issues with some computations A: x45 B: x45 C: x44
There were issues with some computations A: x45 B: x45 C: x45
There were issues with some computations A: x46 B: x45 C: x45
There were issues with some computations A: x47 B: x45 C: x45
There were issues with some computations A: x48 B: x45 C: x45
There were issues with some computations A: x49 B: x45 C: x45
There were issues with some computations A: x50 B: x45 C: x45
There were issues with some computations A: x50 B: x46 C: x45
There were issues with some computations A: x50 B: x47 C: x45
There were issues with some computations A: x50 B: x48 C: x45
There were issues with some computations A: x50 B: x49 C: x45
There were issues with some computations A: x50 B: x50 C: x45
There were issues with some computations A: x50 B: x50 C: x46
There were issues with some computations A: x50 B: x50 C: x47
There were issues with some computations A: x50 B: x50 C: x48
There were issues with some computations A: x50 B: x50 C: x49
There were issues with some computations A: x50 B: x50 C: x50
There were issues with some computations A: x51 B: x50 C: x50
There were issues with some computations A: x52 B: x50 C: x50
There were issues with some computations A: x53 B: x50 C: x50
There were issues with some computations A: x54 B: x50 C: x50
There were issues with some computations A: x55 B: x50 C: x50
There were issues with some computations A: x55 B: x51 C: x50
There were issues with some computations A: x55 B: x52 C: x50
There were issues with some computations A: x55 B: x53 C: x50
There were issues with some computations A: x55 B: x54 C: x50
There were issues with some computations A: x55 B: x55 C: x50
There were issues with some computations A: x55 B: x55 C: x51
There were issues with some computations A: x55 B: x55 C: x52
There were issues with some computations A: x55 B: x55 C: x53
There were issues with some computations A: x55 B: x55 C: x54
There were issues with some computations A: x55 B: x55 C: x55
There were issues with some computations A: x56 B: x55 C: x55
There were issues with some computations A: x57 B: x55 C: x55
There were issues with some computations A: x58 B: x55 C: x55
There were issues with some computations A: x59 B: x55 C: x55
There were issues with some computations A: x60 B: x55 C: x55
There were issues with some computations A: x60 B: x56 C: x55
There were issues with some computations A: x60 B: x57 C: x55
There were issues with some computations A: x60 B: x58 C: x55
There were issues with some computations A: x60 B: x59 C: x55
There were issues with some computations A: x60 B: x60 C: x55
There were issues with some computations A: x60 B: x60 C: x56
There were issues with some computations A: x60 B: x60 C: x57
There were issues with some computations A: x60 B: x60 C: x58
There were issues with some computations A: x60 B: x60 C: x59
There were issues with some computations A: x60 B: x60 C: x60
There were issues with some computations A: x61 B: x60 C: x60
There were issues with some computations A: x62 B: x60 C: x60
There were issues with some computations A: x63 B: x60 C: x60
There were issues with some computations A: x64 B: x60 C: x60
There were issues with some computations A: x65 B: x60 C: x60
There were issues with some computations A: x65 B: x61 C: x60
There were issues with some computations A: x65 B: x62 C: x60
There were issues with some computations A: x65 B: x63 C: x60
There were issues with some computations A: x65 B: x64 C: x60
There were issues with some computations A: x65 B: x65 C: x60
There were issues with some computations A: x65 B: x65 C: x61
There were issues with some computations A: x65 B: x65 C: x62
There were issues with some computations A: x65 B: x65 C: x63
There were issues with some computations A: x65 B: x65 C: x64
There were issues with some computations A: x65 B: x65 C: x65
There were issues with some computations A: x66 B: x65 C: x65
There were issues with some computations A: x67 B: x65 C: x65
There were issues with some computations A: x68 B: x65 C: x65
There were issues with some computations A: x69 B: x65 C: x65
There were issues with some computations A: x70 B: x65 C: x65
There were issues with some computations A: x70 B: x66 C: x65
There were issues with some computations A: x70 B: x67 C: x65
There were issues with some computations A: x70 B: x68 C: x65
There were issues with some computations A: x70 B: x69 C: x65
There were issues with some computations A: x70 B: x70 C: x65
There were issues with some computations A: x70 B: x70 C: x66
There were issues with some computations A: x70 B: x70 C: x67
There were issues with some computations A: x70 B: x70 C: x68
There were issues with some computations A: x70 B: x70 C: x69
There were issues with some computations A: x70 B: x70 C: x70
There were issues with some computations A: x71 B: x70 C: x70
There were issues with some computations A: x72 B: x70 C: x70
There were issues with some computations A: x73 B: x70 C: x70
There were issues with some computations A: x74 B: x70 C: x70
There were issues with some computations A: x75 B: x70 C: x70
There were issues with some computations A: x75 B: x71 C: x70
There were issues with some computations A: x75 B: x72 C: x70
There were issues with some computations A: x75 B: x73 C: x70
There were issues with some computations A: x75 B: x74 C: x70
There were issues with some computations A: x75 B: x75 C: x70
There were issues with some computations A: x75 B: x75 C: x71
There were issues with some computations A: x75 B: x75 C: x72
There were issues with some computations A: x75 B: x75 C: x73
There were issues with some computations A: x75 B: x75 C: x74
There were issues with some computations A: x75 B: x75 C: x75
There were issues with some computations A: x76 B: x75 C: x75
There were issues with some computations A: x77 B: x75 C: x75
There were issues with some computations A: x78 B: x75 C: x75
There were issues with some computations A: x79 B: x75 C: x75
There were issues with some computations A: x80 B: x75 C: x75
There were issues with some computations A: x80 B: x76 C: x75
There were issues with some computations A: x80 B: x77 C: x75
There were issues with some computations A: x80 B: x78 C: x75
There were issues with some computations A: x80 B: x79 C: x75
There were issues with some computations A: x80 B: x80 C: x75
There were issues with some computations A: x80 B: x80 C: x76
There were issues with some computations A: x80 B: x80 C: x77
There were issues with some computations A: x80 B: x80 C: x78
There were issues with some computations A: x80 B: x80 C: x79
There were issues with some computations A: x80 B: x80 C: x80
There were issues with some computations A: x81 B: x80 C: x80
There were issues with some computations A: x82 B: x80 C: x80
There were issues with some computations A: x83 B: x80 C: x80
There were issues with some computations A: x84 B: x80 C: x80
There were issues with some computations A: x85 B: x80 C: x80
There were issues with some computations A: x85 B: x81 C: x80
There were issues with some computations A: x85 B: x82 C: x80
There were issues with some computations A: x85 B: x83 C: x80
There were issues with some computations A: x85 B: x84 C: x80
There were issues with some computations A: x85 B: x85 C: x80
There were issues with some computations A: x85 B: x85 C: x81
There were issues with some computations A: x85 B: x85 C: x82
There were issues with some computations A: x85 B: x85 C: x83
There were issues with some computations A: x85 B: x85 C: x84
There were issues with some computations A: x85 B: x85 C: x85
There were issues with some computations A: x86 B: x85 C: x85
There were issues with some computations A: x87 B: x85 C: x85
There were issues with some computations A: x88 B: x85 C: x85
There were issues with some computations A: x89 B: x85 C: x85
There were issues with some computations A: x90 B: x85 C: x85
There were issues with some computations A: x90 B: x86 C: x85
There were issues with some computations A: x90 B: x87 C: x85
There were issues with some computations A: x90 B: x88 C: x85
There were issues with some computations A: x90 B: x89 C: x85
There were issues with some computations A: x90 B: x90 C: x85
There were issues with some computations A: x90 B: x90 C: x86
There were issues with some computations A: x90 B: x90 C: x87
There were issues with some computations A: x90 B: x90 C: x88
There were issues with some computations A: x90 B: x90 C: x89
There were issues with some computations A: x90 B: x90 C: x90
There were issues with some computations A: x91 B: x90 C: x90
There were issues with some computations A: x92 B: x90 C: x90
There were issues with some computations A: x93 B: x90 C: x90
There were issues with some computations A: x94 B: x90 C: x90
There were issues with some computations A: x95 B: x90 C: x90
There were issues with some computations A: x95 B: x91 C: x90
There were issues with some computations A: x95 B: x92 C: x90
There were issues with some computations A: x95 B: x93 C: x90
There were issues with some computations A: x95 B: x94 C: x90
There were issues with some computations A: x95 B: x95 C: x90
There were issues with some computations A: x95 B: x95 C: x91
There were issues with some computations A: x95 B: x95 C: x92
There were issues with some computations A: x95 B: x95 C: x93
There were issues with some computations A: x95 B: x95 C: x94
There were issues with some computations A: x95 B: x95 C: x95
There were issues with some computations A: x96 B: x95 C: x95
There were issues with some computations A: x97 B: x95 C: x95
There were issues with some computations A: x98 B: x95 C: x95
There were issues with some computations A: x99 B: x95 C: x95
There were issues with some computations A: x100 B: x95 C: x95
There were issues with some computations A: x100 B: x96 C: x95
There were issues with some computations A: x100 B: x97 C: x95
There were issues with some computations A: x100 B: x98 C: x95
There were issues with some computations A: x100 B: x99 C: x95
There were issues with some computations A: x100 B: x100 C: x95
There were issues with some computations A: x100 B: x100 C: x96
There were issues with some computations A: x100 B: x100 C: x97
There were issues with some computations A: x100 B: x100 C: x98
There were issues with some computations A: x100 B: x100 C: x99
There were issues with some computations A: x100 B: x100 C: x100
There were issues with some computations A: x101 B: x100 C: x100
There were issues with some computations A: x102 B: x100 C: x100
There were issues with some computations A: x103 B: x100 C: x100
There were issues with some computations A: x104 B: x100 C: x100
There were issues with some computations A: x105 B: x100 C: x100
There were issues with some computations A: x105 B: x101 C: x100
There were issues with some computations A: x105 B: x102 C: x100
There were issues with some computations A: x105 B: x103 C: x100
There were issues with some computations A: x105 B: x104 C: x100
There were issues with some computations A: x105 B: x105 C: x100
There were issues with some computations A: x105 B: x105 C: x101
There were issues with some computations A: x105 B: x105 C: x102
There were issues with some computations A: x105 B: x105 C: x103
There were issues with some computations A: x105 B: x105 C: x104
There were issues with some computations A: x105 B: x105 C: x105
There were issues with some computations A: x106 B: x105 C: x105
There were issues with some computations A: x107 B: x105 C: x105
There were issues with some computations A: x108 B: x105 C: x105
There were issues with some computations A: x109 B: x105 C: x105
There were issues with some computations A: x110 B: x105 C: x105
There were issues with some computations A: x110 B: x106 C: x105
There were issues with some computations A: x110 B: x107 C: x105
There were issues with some computations A: x110 B: x108 C: x105
There were issues with some computations A: x110 B: x109 C: x105
There were issues with some computations A: x110 B: x110 C: x105
There were issues with some computations A: x110 B: x110 C: x106
There were issues with some computations A: x110 B: x110 C: x107
There were issues with some computations A: x110 B: x110 C: x108
There were issues with some computations A: x110 B: x110 C: x109
There were issues with some computations A: x110 B: x110 C: x110
There were issues with some computations A: x111 B: x110 C: x110
There were issues with some computations A: x112 B: x110 C: x110
There were issues with some computations A: x113 B: x110 C: x110
There were issues with some computations A: x114 B: x110 C: x110
There were issues with some computations A: x115 B: x110 C: x110
There were issues with some computations A: x115 B: x111 C: x110
There were issues with some computations A: x115 B: x112 C: x110
There were issues with some computations A: x115 B: x113 C: x110
There were issues with some computations A: x115 B: x114 C: x110
There were issues with some computations A: x115 B: x115 C: x110
There were issues with some computations A: x115 B: x115 C: x111
There were issues with some computations A: x115 B: x115 C: x112
There were issues with some computations A: x115 B: x115 C: x113
There were issues with some computations A: x115 B: x115 C: x114
There were issues with some computations A: x115 B: x115 C: x115
There were issues with some computations A: x116 B: x115 C: x115
There were issues with some computations A: x117 B: x115 C: x115
There were issues with some computations A: x118 B: x115 C: x115
There were issues with some computations A: x119 B: x115 C: x115
There were issues with some computations A: x120 B: x115 C: x115
There were issues with some computations A: x120 B: x116 C: x115
There were issues with some computations A: x120 B: x117 C: x115
There were issues with some computations A: x120 B: x118 C: x115
There were issues with some computations A: x120 B: x119 C: x115
There were issues with some computations A: x120 B: x120 C: x115
There were issues with some computations A: x120 B: x120 C: x116
There were issues with some computations A: x120 B: x120 C: x117
There were issues with some computations A: x120 B: x120 C: x118
There were issues with some computations A: x120 B: x120 C: x119
There were issues with some computations A: x120 B: x120 C: x120
There were issues with some computations A: x121 B: x120 C: x120
There were issues with some computations A: x122 B: x120 C: x120
There were issues with some computations A: x123 B: x120 C: x120
There were issues with some computations A: x124 B: x120 C: x120
There were issues with some computations A: x125 B: x120 C: x120
There were issues with some computations A: x125 B: x121 C: x120
There were issues with some computations A: x125 B: x122 C: x120
There were issues with some computations A: x125 B: x123 C: x120
There were issues with some computations A: x125 B: x124 C: x120
There were issues with some computations A: x125 B: x125 C: x120
There were issues with some computations A: x125 B: x125 C: x121
There were issues with some computations A: x125 B: x125 C: x122
There were issues with some computations A: x125 B: x125 C: x123
There were issues with some computations A: x125 B: x125 C: x124
There were issues with some computations A: x125 B: x125 C: x125
There were issues with some computations A: x125 B: x125 C: x125show_best(rf_results, metric = "roc_auc")## # A tibble: 5 × 9
## mtry trees min_n .metric .estimator mean n std_err .config
## <int> <int> <int> <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 2 612 20 roc_auc binary 0.844 5 0.0103 Preprocessor1_Model1…
## 2 2 800 20 roc_auc binary 0.843 5 0.0103 Preprocessor1_Model1…
## 3 2 425 15 roc_auc binary 0.843 5 0.00984 Preprocessor1_Model0…
## 4 2 425 20 roc_auc binary 0.843 5 0.0103 Preprocessor1_Model1…
## 5 2 237 20 roc_auc binary 0.843 5 0.0107 Preprocessor1_Model1…With hyperparameter tuning, we get the roc_auc to .8435
- Use the hyperparameter values that provide the best results in #2 to finalize your workflow. Train this finalized workflow on the entire spam training data and identify the top 20 most influential predictors.
# get optimal hyperparameters
rf_best_hyperparameters <- select_best(rf_results, metric = "roc_auc")
# create final workflow object
final_rf_wf <- workflow() %>%
add_recipe(rf_recipe) %>%
add_model(rf_mod) %>%
finalize_workflow(rf_best_hyperparameters)
# fit final workflow object
rf_final_fit <- final_rf_wf %>%
fit(data = rf_train)
# plot feature importance
rf_final_fit %>%
extract_fit_parsnip() %>%
vip(num_features = 20)
With our random forest model, we find the most important features to be
tenure, total charges, and contract
rf_final_fit %>%
predict(rf_test) %>%
bind_cols(rf_test %>% select(Status)) %>%
conf_mat(truth = Status, estimate = .pred_class)## Truth
## Prediction Current Left
## Current 1393 276
## Left 147 281