Module 3 Lesson 1 Application

Let’s load the tidyverse, tidymodels, and palmerpenguins packages to begin.

library(tidyverse)
library(tidymodels)
library(palmerpenguins)

The data set

penguins

# A tibble: 344 × 8
   species island    bill_length_mm bill_depth_mm flipper_length_mm body_mass_g
   <fct>   <fct>              <dbl>         <dbl>             <int>       <int>
 1 Adelie  Torgersen           39.1          18.7               181        3750
 2 Adelie  Torgersen           39.5          17.4               186        3800
 3 Adelie  Torgersen           40.3          18                 195        3250
 4 Adelie  Torgersen           NA            NA                  NA          NA
 5 Adelie  Torgersen           36.7          19.3               193        3450
 6 Adelie  Torgersen           39.3          20.6               190        3650
 7 Adelie  Torgersen           38.9          17.8               181        3625
 8 Adelie  Torgersen           39.2          19.6               195        4675
 9 Adelie  Torgersen           34.1          18.1               193        3475
10 Adelie  Torgersen           42            20.2               190        4250
# ℹ 334 more rows
# ℹ 2 more variables: sex <fct>, year <int>

glimpse(penguins)

Rows: 344
Columns: 8
$ species           <fct> Adelie, Adelie, Adelie, Adelie, Adelie, Adelie, Adel…
$ island            <fct> Torgersen, Torgersen, Torgersen, Torgersen, Torgerse…
$ bill_length_mm    <dbl> 39.1, 39.5, 40.3, NA, 36.7, 39.3, 38.9, 39.2, 34.1, …
$ bill_depth_mm     <dbl> 18.7, 17.4, 18.0, NA, 19.3, 20.6, 17.8, 19.6, 18.1, …
$ flipper_length_mm <int> 181, 186, 195, NA, 193, 190, 181, 195, 193, 190, 186…
$ body_mass_g       <int> 3750, 3800, 3250, NA, 3450, 3650, 3625, 4675, 3475, …
$ sex               <fct> male, female, female, NA, female, male, female, male…
$ year              <int> 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007…

datapeng <- penguins |>
        drop_na() |>
        select(-year)

Data Budget

set.seed(18)
datapeng_split <- initial_split(datapeng, prop = 0.8, strata = sex)
datapeng_train <- training(datapeng_split)
datapeng_test <- testing(datapeng_split)

Cross Validation

set.seed(18)
samples_peng <- vfold_cv(datapeng_train, strata = sex)

Model Specification

model_peng <-
        logistic_reg() |>
        set_engine("glm") |>
        set_mode("classification")

Workflow

workflow_peng <-
        workflow() |>
        add_formula(sex ~.) |>
        add_model(model_peng)

Fit Resamples and collect metrics

fit_peng <-
        fit_resamples(
                workflow_peng,
                samples_peng
        )
fit_peng |>
        collect_metrics()

# A tibble: 2 × 6
  .metric  .estimator  mean     n std_err .config             
  <chr>    <chr>      <dbl> <int>   <dbl> <chr>               
1 accuracy binary     0.910    10  0.0147 Preprocessor1_Model1
2 roc_auc  binary     0.970    10  0.0109 Preprocessor1_Model1

Final Fit and Performance

final_peng <-
        last_fit(
                workflow_peng,
                datapeng_split
        )

final_peng |>
        collect_metrics()

# A tibble: 2 × 4
  .metric  .estimator .estimate .config             
  <chr>    <chr>          <dbl> <chr>               
1 accuracy binary         0.925 Preprocessor1_Model1
2 roc_auc  binary         0.985 Preprocessor1_Model1

Confusion Matrix

final_peng |>
        collect_predictions() |>
        conf_mat(`sex`, .pred_class) |>
        autoplot(type = "heatmap")