tidymodels-vorlage3

Aufgabe

Schreiben Sie eine prototypische Analyse für ein Vorhersagemodell, das sich als Vorlage für Analysen dieser Art eignet!

Verzichten Sie auf Resampling und Tuning.

Hinweise:

• Berechnen Sie ein Modell
• Tunen Sie keinen Parameter des Modells
• Verwenden Sie keine Kreuzvalidierung.
• Verwenden Sie Standardwerte, wo nicht anders angegeben.
• Fixieren Sie Zufallszahlen auf den Startwert 42.

Lösung

# Setup:
library(tidymodels)

── Attaching packages ────────────────────────────────────── tidymodels 1.1.1 ──

✔ broom        1.0.5     ✔ recipes      1.0.8
✔ dials        1.2.0     ✔ rsample      1.2.0
✔ dplyr        1.1.3     ✔ tibble       3.2.1
✔ ggplot2      3.4.4     ✔ tidyr        1.3.0
✔ infer        1.0.5     ✔ tune         1.1.2
✔ modeldata    1.2.0     ✔ workflows    1.1.3
✔ parsnip      1.1.1     ✔ workflowsets 1.0.1
✔ purrr        1.0.2     ✔ yardstick    1.2.0

── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
✖ purrr::discard() masks scales::discard()
✖ dplyr::filter()  masks stats::filter()
✖ dplyr::lag()     masks stats::lag()
✖ recipes::step()  masks stats::step()
• Dig deeper into tidy modeling with R at https://www.tmwr.org

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats   1.0.0     ✔ readr     2.1.4
✔ lubridate 1.9.3     ✔ stringr   1.5.0

── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ readr::col_factor() masks scales::col_factor()
✖ purrr::discard()    masks scales::discard()
✖ dplyr::filter()     masks stats::filter()
✖ stringr::fixed()    masks recipes::fixed()
✖ dplyr::lag()        masks stats::lag()
✖ readr::spec()       masks yardstick::spec()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(tictoc)  # Zeitmessung
library(easystats)   # NAs zählen

# Attaching packages: easystats 0.6.0 (red = needs update)
✔ bayestestR  0.13.1   ✔ correlation 0.8.4 
✔ datawizard  0.9.0    ✔ effectsize  0.8.6 
✔ insight     0.19.6   ✔ modelbased  0.8.6 
✔ performance 0.10.8   ✔ parameters  0.21.3
✔ report      0.5.7    ✖ see         0.8.0 

Restart the R-Session and update packages in red with `easystats::easystats_update()`.

# Data:
d_path <- "https://vincentarelbundock.github.io/Rdatasets/csv/palmerpenguins/penguins.csv"
d <- read_csv(d_path)

Rows: 344 Columns: 9
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (3): species, island, sex
dbl (6): rownames, bill_length_mm, bill_depth_mm, flipper_length_mm, body_ma...

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.

set.seed(42)
d_split <- initial_split(d)
d_train <- training(d_split)
d_test <- testing(d_split)


# model:
mod1 <-
  rand_forest(mode = "regression")


# cv:
set.seed(42)
rsmpl <- vfold_cv(d_train)


# recipe:
rec1 <- recipe(body_mass_g ~  ., data = d_train) |> 
  step_unknown(all_nominal_predictors(), new_level = "NA") |> 
  step_naomit(all_predictors()) |> 
  step_dummy(all_nominal_predictors()) |> 
  step_zv(all_predictors()) |> 
  step_normalize(all_predictors()) 



# workflow:
wf1 <-
  workflow() %>% 
  add_model(mod1) %>% 
  add_recipe(rec1)


# tuning:
tic()
wf1_fit <-
  wf1 %>% 
  last_fit(split = d_split)

→ A | error:   Missing data in columns: bill_length_mm, bill_depth_mm, flipper_length_mm.
There were issues with some computations   A: x1
There were issues with some computations   A: x1

Warning: All models failed. Run `show_notes(.Last.tune.result)` for more
information.

toc()

0.594 sec elapsed

collect_metrics(wf1_fit)

NULL

Als Check: Das gepreppte/bebackene Rezept:

rec1_prepped <- prep(rec1)
d_train_baked <- bake(rec1_prepped, new_data = NULL)

d_train_baked |> 
  head()

# A tibble: 6 × 12
  rownames bill_length_mm bill_depth_mm flipper_length_mm    year body_mass_g
     <dbl>          <dbl>         <dbl>             <dbl>   <dbl>       <dbl>
1   -1.24          -1.53          0.386            -0.794 -1.29          3450
2    1.45           1.32          0.386            -0.365  1.14          3675
3   -0.212          0.401        -1.97              0.707 -1.29          4500
4   -0.993          0.343         0.887            -0.294 -0.0757        4150
5    0.530          0.879        -0.566             2.07  -0.0757        5800
6   -0.281         -0.957         0.787            -1.15   1.14          3650
# ℹ 6 more variables: species_Chinstrap <dbl>, species_Gentoo <dbl>,
#   island_Dream <dbl>, island_Torgersen <dbl>, sex_male <dbl>, sex_NA. <dbl>

describe_distribution(d_train_baked)

Variable          |      Mean |     SD |     IQR |              Range | Skewness | Kurtosis |   n | n_Missing
-------------------------------------------------------------------------------------------------------------
rownames          | -5.63e-17 |   1.00 |    1.70 |      [-1.72, 1.68] |    -0.01 |    -1.21 | 257 |         0
bill_length_mm    | -2.97e-16 |   1.00 |    1.68 |      [-2.28, 2.98] |     0.01 |    -0.79 | 257 |         0
bill_depth_mm     |  2.71e-16 |   1.00 |    1.60 |      [-2.02, 2.19] |    -0.11 |    -0.87 | 257 |         0
flipper_length_mm | -9.83e-16 |   1.00 |    1.64 |      [-1.94, 2.07] |     0.32 |    -1.02 | 257 |         0
year              | -6.89e-14 |   1.00 |    2.43 |      [-1.29, 1.14] |    -0.12 |    -1.51 | 257 |         0
body_mass_g       |   4200.97 | 792.54 | 1212.50 | [2700.00, 6300.00] |     0.49 |    -0.69 | 257 |         0
species_Chinstrap | -2.24e-17 |   1.00 |    0.00 |      [-0.50, 1.98] |     1.49 |     0.22 | 257 |         0
species_Gentoo    |  1.64e-17 |   1.00 |    2.07 |      [-0.76, 1.31] |     0.56 |    -1.70 | 257 |         0
island_Dream      | -5.50e-17 |   1.00 |    2.08 |      [-0.75, 1.34] |     0.60 |    -1.66 | 257 |         0
island_Torgersen  |  1.72e-17 |   1.00 |    0.00 |      [-0.41, 2.43] |     2.04 |     2.18 | 257 |         0
sex_male          | -5.86e-17 |   1.00 |    2.00 |      [-0.96, 1.03] |     0.07 |    -2.01 | 257 |         0
sex_NA.           |  1.45e-17 |   1.00 |    0.00 |      [-0.15, 6.46] |     6.35 |    38.63 | 257 |         0

---

Categories:

• tidymodels
• statlearning
• template
• string