── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.4 ✔ readr 2.1.5
✔ forcats 1.0.0 ✔ stringr 1.5.1
✔ ggplot2 3.5.1 ✔ tibble 3.2.1
✔ lubridate 1.9.4 ✔ tidyr 1.3.1
✔ purrr 1.0.4
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
── Attaching packages ────────────────────────────────────── tidymodels 1.3.0 ──
✔ broom 1.0.7 ✔ rsample 1.2.1.9000
✔ dials 1.4.0.9000 ✔ tune 1.3.0.9000
✔ infer 1.0.7 ✔ workflows 1.2.0.9000
✔ modeldata 1.4.0 ✔ workflowsets 1.1.0
✔ parsnip 1.3.0.9000 ✔ yardstick 1.3.2
✔ recipes 1.1.1.9000
── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
✖ scales::discard() masks purrr::discard()
✖ dplyr::filter() masks stats::filter()
✖ recipes::fixed() masks stringr::fixed()
✖ dplyr::lag() masks stats::lag()
✖ yardstick::spec() masks readr::spec()
✖ recipes::step() masks stats::step()
library (naniar)library (GGally)
Registered S3 method overwritten by 'GGally':
method from
+.gg ggplot2
<- read_csv ("wisc_bc_data.csv" )
Rows: 569 Columns: 32
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (1): diagnosis
dbl (31): id, radius_mean, texture_mean, perimeter_mean, area_mean, smoothne...
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.
<- wbcd |> select (- id) |> mutate (diagnosis = as_factor (diagnosis))
# A tibble: 569 × 31
diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_mean
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 B 12.3 12.4 78.8 464. 0.103
2 B 10.6 19.0 69.3 346. 0.0969
3 B 11.0 16.8 70.9 373. 0.108
4 B 11.3 13.4 73 385. 0.116
5 B 15.2 13.2 97.6 712. 0.0796
6 B 11.6 19.0 74.2 410. 0.0855
7 B 11.5 23.9 74.5 404. 0.0926
8 M 13.8 23.8 91.6 598. 0.132
9 B 10.5 19.3 67.4 336. 0.0999
10 B 11.1 15.0 71.5 374. 0.103
# ℹ 559 more rows
# ℹ 25 more variables: compactness_mean <dbl>, concavity_mean <dbl>,
# points_mean <dbl>, symmetry_mean <dbl>, dimension_mean <dbl>,
# radius_se <dbl>, texture_se <dbl>, perimeter_se <dbl>, area_se <dbl>,
# smoothness_se <dbl>, compactness_se <dbl>, concavity_se <dbl>,
# points_se <dbl>, symmetry_se <dbl>, dimension_se <dbl>, radius_worst <dbl>,
# texture_worst <dbl>, perimeter_worst <dbl>, area_worst <dbl>, …
|> filter (is_na (diagnosis))
# A tibble: 0 × 31
# ℹ 31 variables: diagnosis <fct>, radius_mean <dbl>, texture_mean <dbl>,
# perimeter_mean <dbl>, area_mean <dbl>, smoothness_mean <dbl>,
# compactness_mean <dbl>, concavity_mean <dbl>, points_mean <dbl>,
# symmetry_mean <dbl>, dimension_mean <dbl>, radius_se <dbl>,
# texture_se <dbl>, perimeter_se <dbl>, area_se <dbl>, smoothness_se <dbl>,
# compactness_se <dbl>, concavity_se <dbl>, points_se <dbl>,
# symmetry_se <dbl>, dimension_se <dbl>, radius_worst <dbl>, …
<- initial_split (wbcd, prop = 0.8 )
<Training/Testing/Total>
<455/114/569>
<- training (wbcd_split)head (wbcd_train)
# A tibble: 6 × 31
diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_mean
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 M 14.2 23.8 92.9 611. 0.0946
2 M 18.6 17.6 124. 1076 0.110
3 B 13.6 13.2 87.9 569. 0.0965
4 B 11.0 17.2 71.7 372. 0.0891
5 B 10.8 9.71 68.8 358. 0.0959
6 M 21.2 23.0 137. 1404 0.0943
# ℹ 25 more variables: compactness_mean <dbl>, concavity_mean <dbl>,
# points_mean <dbl>, symmetry_mean <dbl>, dimension_mean <dbl>,
# radius_se <dbl>, texture_se <dbl>, perimeter_se <dbl>, area_se <dbl>,
# smoothness_se <dbl>, compactness_se <dbl>, concavity_se <dbl>,
# points_se <dbl>, symmetry_se <dbl>, dimension_se <dbl>, radius_worst <dbl>,
# texture_worst <dbl>, perimeter_worst <dbl>, area_worst <dbl>,
# smoothness_worst <dbl>, compactness_worst <dbl>, concavity_worst <dbl>, …
<- testing (wbcd_split)head (wbcd_test)
# A tibble: 6 × 31
diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_mean
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 B 15.2 13.2 97.6 712. 0.0796
2 B 14.6 22.7 96.4 657. 0.0847
3 B 15.7 13.9 102 762. 0.0946
4 B 12.2 13.3 79.1 456. 0.107
5 B 10.9 18.6 70.4 370 0.100
6 B 15.1 16.4 99.6 674. 0.115
# ℹ 25 more variables: compactness_mean <dbl>, concavity_mean <dbl>,
# points_mean <dbl>, symmetry_mean <dbl>, dimension_mean <dbl>,
# radius_se <dbl>, texture_se <dbl>, perimeter_se <dbl>, area_se <dbl>,
# smoothness_se <dbl>, compactness_se <dbl>, concavity_se <dbl>,
# points_se <dbl>, symmetry_se <dbl>, dimension_se <dbl>, radius_worst <dbl>,
# texture_worst <dbl>, perimeter_worst <dbl>, area_worst <dbl>,
# smoothness_worst <dbl>, compactness_worst <dbl>, concavity_worst <dbl>, …
|> count (diagnosis) |> mutate (prop = n/ sum (n))
# A tibble: 2 × 3
diagnosis n prop
<fct> <int> <dbl>
1 B 357 0.627
2 M 212 0.373
|> count (diagnosis) |> mutate (prop = n/ sum (n))
# A tibble: 2 × 3
diagnosis n prop
<fct> <int> <dbl>
1 B 283 0.622
2 M 172 0.378
|> count (diagnosis) |> mutate (prop = n/ sum (n))
# A tibble: 2 × 3
diagnosis n prop
<fct> <int> <dbl>
1 B 74 0.649
2 M 40 0.351
<- recipe (diagnosis ~ ., data = wbcd_train) |> step_normalize (all_predictors ())
── Recipe ──────────────────────────────────────────────────────────────────────
Number of variables by role
• Centering and scaling for: all_predictors()
# A tibble: 31 × 4
variable type role source
<chr> <list> <chr> <chr>
1 radius_mean <chr [2]> predictor original
2 texture_mean <chr [2]> predictor original
3 perimeter_mean <chr [2]> predictor original
4 area_mean <chr [2]> predictor original
5 smoothness_mean <chr [2]> predictor original
6 compactness_mean <chr [2]> predictor original
7 concavity_mean <chr [2]> predictor original
8 points_mean <chr [2]> predictor original
9 symmetry_mean <chr [2]> predictor original
10 dimension_mean <chr [2]> predictor original
# ℹ 21 more rows
