2626< meta name ="author " content ="Melissa Lee " />
2727
2828
29- < meta name ="date " content ="2020-12-16 " />
29+ < meta name ="date " content ="2021-01-12 " />
3030
3131 < meta name ="viewport " content ="width=device-width, initial-scale=1 " />
3232 < meta name ="apple-mobile-web-app-capable " content ="yes " />
@@ -484,33 +484,33 @@ <h2><span class="header-section-number">7.3</span> Evaluating accuracy</h2>
484484< div class ="sourceCode " id ="cb207 "> < pre class ="sourceCode r "> < code class ="sourceCode r "> < span id ="cb207-1 "> < a href ="classification-continued.html#cb207-1 "> </ a > < span class ="kw "> glimpse</ span > (cancer_train)</ span > </ code > </ pre > </ div >
485485< pre > < code > ## Rows: 427
486486## Columns: 12
487- ## $ ID <dbl> 842302, 842517, 84300903, 84348301, 84358402, 843786, 844359, 84458202, 84501 …
488- ## $ Class <fct> M, M, M, M, M, M, M, M, M, M, M, M, M, M, M, B, B, M, M, M, M, M, M, M, M, M, …
489- ## $ Radius <dbl> 17.990, 20.570, 19.690, 11.420, 20.290, 12.450, 18.250, 13.710, 12.460, 16.02 …
490- ## $ Texture <dbl> 10.38, 17.77, 21.25, 20.38, 14.34, 15.70, 19.98, 20.83, 24.04, 23.24, 17.89, …
491- ## $ Perimeter <dbl> 122.80, 132.90, 130.00, 77.58, 135.10, 82.57, 119.60, 90.20, 83.97, 102.70, 1 …
492- ## $ Area <dbl> 1001.0, 1326.0, 1203.0, 386.1, 1297.0, 477.1, 1040.0, 577.9, 475.9, 797.8, 78 …
493- ## $ Smoothness <dbl> 0.11840, 0.08474, 0.10960, 0.14250, 0.10030, 0.12780, 0.09463, 0.11890, 0.118 …
494- ## $ Compactness <dbl> 0.27760, 0.07864, 0.15990, 0.28390, 0.13280, 0.17000, 0.10900, 0.16450, 0.239 …
495- ## $ Concavity <dbl> 0.30010, 0.08690, 0.19740, 0.24140, 0.19800, 0.15780, 0.11270, 0.09366, 0.227 …
496- ## $ Concave_Points <dbl> 0.14710, 0.07017, 0.12790, 0.10520, 0.10430, 0.08089, 0.07400, 0.05985, 0.085 …
497- ## $ Symmetry <dbl> 0.2419, 0.1812, 0.2069, 0.2597, 0.1809, 0.2087, 0.1794, 0.2196, 0.2030, 0.152 …
498- ## $ Fractal_Dimension <dbl> 0.07871, 0.05667, 0.05999, 0.09744, 0.05883, 0.07613, 0.05742, 0.07451, 0.082 …</ code > </ pre >
487+ ## $ ID <dbl> 842302, 842517, 84300903, 84348301, 84358402, 843786, 844359, 84458202…
488+ ## $ Class <fct> M, M, M, M, M, M, M, M, M, M, M, M, M, M, M, B, B, M, M, M, M, M, M, M…
489+ ## $ Radius <dbl> 17.990, 20.570, 19.690, 11.420, 20.290, 12.450, 18.250, 13.710, 12.460…
490+ ## $ Texture <dbl> 10.38, 17.77, 21.25, 20.38, 14.34, 15.70, 19.98, 20.83, 24.04, 23.24, …
491+ ## $ Perimeter <dbl> 122.80, 132.90, 130.00, 77.58, 135.10, 82.57, 119.60, 90.20, 83.97, 10 …
492+ ## $ Area <dbl> 1001.0, 1326.0, 1203.0, 386.1, 1297.0, 477.1, 1040.0, 577.9, 475.9, 79 …
493+ ## $ Smoothness <dbl> 0.11840, 0.08474, 0.10960, 0.14250, 0.10030, 0.12780, 0.09463, 0.11890…
494+ ## $ Compactness <dbl> 0.27760, 0.07864, 0.15990, 0.28390, 0.13280, 0.17000, 0.10900, 0.16450…
495+ ## $ Concavity <dbl> 0.30010, 0.08690, 0.19740, 0.24140, 0.19800, 0.15780, 0.11270, 0.09366…
496+ ## $ Concave_Points <dbl> 0.14710, 0.07017, 0.12790, 0.10520, 0.10430, 0.08089, 0.07400, 0.05985…
497+ ## $ Symmetry <dbl> 0.2419, 0.1812, 0.2069, 0.2597, 0.1809, 0.2087, 0.1794, 0.2196, 0.2030…
498+ ## $ Fractal_Dimension <dbl> 0.07871, 0.05667, 0.05999, 0.09744, 0.05883, 0.07613, 0.05742, 0.07451…</ code > </ pre >
499499< div class ="sourceCode " id ="cb209 "> < pre class ="sourceCode r "> < code class ="sourceCode r "> < span id ="cb209-1 "> < a href ="classification-continued.html#cb209-1 "> </ a > < span class ="kw "> glimpse</ span > (cancer_test)</ span > </ code > </ pre > </ div >
500500< pre > < code > ## Rows: 142
501501## Columns: 12
502- ## $ ID <dbl> 844981, 84799002, 848406, 849014, 8510426, 8511133, 853401, 854002, 855167, 8 …
503- ## $ Class <fct> M, M, M, M, B, M, M, M, M, M, M, B, B, M, M, M, B, M, M, B, B, B, M, M, B, B, …
504- ## $ Radius <dbl> 13.000, 14.540, 14.680, 19.810, 13.540, 15.340, 18.630, 19.270, 13.440, 13.28 …
505- ## $ Texture <dbl> 21.82, 27.54, 20.13, 22.15, 14.36, 14.26, 25.11, 26.47, 21.58, 20.28, 18.70, …
506- ## $ Perimeter <dbl> 87.50, 96.73, 94.74, 130.00, 87.46, 102.50, 124.80, 127.90, 86.18, 87.32, 120 …
507- ## $ Area <dbl> 519.8, 658.8, 684.5, 1260.0, 566.3, 704.4, 1088.0, 1162.0, 563.0, 545.2, 1033 …
508- ## $ Smoothness <dbl> 0.12730, 0.11390, 0.09867, 0.09831, 0.09779, 0.10730, 0.10640, 0.09401, 0.081 …
509- ## $ Compactness <dbl> 0.19320, 0.15950, 0.07200, 0.10270, 0.08129, 0.21350, 0.18870, 0.17190, 0.060 …
510- ## $ Concavity <dbl> 0.18590, 0.16390, 0.07395, 0.14790, 0.06664, 0.20770, 0.23190, 0.16570, 0.031 …
511- ## $ Concave_Points <dbl> 0.093530, 0.073640, 0.052590, 0.094980, 0.047810, 0.097560, 0.124400, 0.07593 …
512- ## $ Symmetry <dbl> 0.2350, 0.2303, 0.1586, 0.1582, 0.1885, 0.2521, 0.2183, 0.1853, 0.1784, 0.197 …
513- ## $ Fractal_Dimension <dbl> 0.07389, 0.07077, 0.05922, 0.05395, 0.05766, 0.07032, 0.06197, 0.06261, 0.055 …</ code > </ pre >
502+ ## $ ID <dbl> 844981, 84799002, 848406, 849014, 8510426, 8511133, 853401, 854002, 85 …
503+ ## $ Class <fct> M, M, M, M, B, M, M, M, M, M, M, B, B, M, M, M, B, M, M, B, B, B, M, M…
504+ ## $ Radius <dbl> 13.000, 14.540, 14.680, 19.810, 13.540, 15.340, 18.630, 19.270, 13.440…
505+ ## $ Texture <dbl> 21.82, 27.54, 20.13, 22.15, 14.36, 14.26, 25.11, 26.47, 21.58, 20.28, …
506+ ## $ Perimeter <dbl> 87.50, 96.73, 94.74, 130.00, 87.46, 102.50, 124.80, 127.90, 86.18, 87.…
507+ ## $ Area <dbl> 519.8, 658.8, 684.5, 1260.0, 566.3, 704.4, 1088.0, 1162.0, 563.0, 545.…
508+ ## $ Smoothness <dbl> 0.12730, 0.11390, 0.09867, 0.09831, 0.09779, 0.10730, 0.10640, 0.09401…
509+ ## $ Compactness <dbl> 0.19320, 0.15950, 0.07200, 0.10270, 0.08129, 0.21350, 0.18870, 0.17190…
510+ ## $ Concavity <dbl> 0.18590, 0.16390, 0.07395, 0.14790, 0.06664, 0.20770, 0.23190, 0.16570…
511+ ## $ Concave_Points <dbl> 0.093530, 0.073640, 0.052590, 0.094980, 0.047810, 0.097560, 0.124400, …
512+ ## $ Symmetry <dbl> 0.2350, 0.2303, 0.1586, 0.1582, 0.1885, 0.2521, 0.2183, 0.1853, 0.1784…
513+ ## $ Fractal_Dimension <dbl> 0.07389, 0.07077, 0.05922, 0.05395, 0.05766, 0.07032, 0.06197, 0.06261…</ code > </ pre >
514514< p > We can see from < code > glimpse</ code > in the code above that the training set contains 427
515515observations, while the test set contains 142 observations. This corresponds to
516516a train / test split of 75% / 25%, as desired.</ p >
@@ -545,17 +545,17 @@ <h2><span class="header-section-number">7.3</span> Evaluating accuracy</h2>
545545< span id ="cb212-9 "> < a href ="classification-continued.html#cb212-9 "> </ a > < span class ="st "> </ span > < span class ="kw "> fit</ span > (< span class ="dt "> data =</ span > cancer_train)</ span >
546546< span id ="cb212-10 "> < a href ="classification-continued.html#cb212-10 "> </ a > </ span >
547547< span id ="cb212-11 "> < a href ="classification-continued.html#cb212-11 "> </ a > knn_fit</ span > </ code > </ pre > </ div >
548- < pre > < code > ## ══ Workflow [trained] ════════════════════════════════════════════════════════════════════════════════════
548+ < pre > < code > ## ══ Workflow [trained] ═════════════════════════════════════════════════════════════════════════════
549549## Preprocessor: Recipe
550550## Model: nearest_neighbor()
551551##
552- ## ── Preprocessor ──────────────────────────────────────────────────────────────────────────────────────────
552+ ## ── Preprocessor ───────────────────────────────────────────────────────────────────────────────────
553553## 2 Recipe Steps
554554##
555555## ● step_scale()
556556## ● step_center()
557557##
558- ## ── Model ─────────────────────────────────────────────────────────────────────────────────────────────────
558+ ## ── Model ──────────────────────────────────────────────────────────────────────────────────────────
559559##
560560## Call:
561561## kknn::train.kknn(formula = formula, data = data, ks = ~3, kernel = ~"rectangular")
@@ -582,19 +582,20 @@ <h2><span class="header-section-number">7.3</span> Evaluating accuracy</h2>
582582< span id ="cb214-2 "> < a href ="classification-continued.html#cb214-2 "> </ a > < span class ="st "> </ span > < span class ="kw "> bind_cols</ span > (cancer_test)</ span >
583583< span id ="cb214-3 "> < a href ="classification-continued.html#cb214-3 "> </ a > cancer_test_predictions</ span > </ code > </ pre > </ div >
584584< pre > < code > ## # A tibble: 142 x 13
585- ## .pred_class ID Class Radius Texture Perimeter Area Smoothness Compactness Concavity Concave_Points
586- ## <fct> <dbl> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
587- ## 1 M 8.45e5 M 13 21.8 87.5 520. 0.127 0.193 0.186 0.0935
588- ## 2 M 8.48e7 M 14.5 27.5 96.7 659. 0.114 0.160 0.164 0.0736
589- ## 3 B 8.48e5 M 14.7 20.1 94.7 684. 0.0987 0.072 0.0740 0.0526
590- ## 4 M 8.49e5 M 19.8 22.2 130 1260 0.0983 0.103 0.148 0.0950
591- ## 5 B 8.51e6 B 13.5 14.4 87.5 566. 0.0978 0.0813 0.0666 0.0478
592- ## 6 M 8.51e6 M 15.3 14.3 102. 704. 0.107 0.214 0.208 0.0976
593- ## 7 M 8.53e5 M 18.6 25.1 125. 1088 0.106 0.189 0.232 0.124
594- ## 8 M 8.54e5 M 19.3 26.5 128. 1162 0.0940 0.172 0.166 0.0759
595- ## 9 B 8.55e5 M 13.4 21.6 86.2 563 0.0816 0.0603 0.0311 0.0203
596- ## 10 M 8.56e5 M 13.3 20.3 87.3 545. 0.104 0.144 0.0985 0.0616
597- ## # … with 132 more rows, and 2 more variables: Symmetry <dbl>, Fractal_Dimension <dbl></ code > </ pre >
585+ ## .pred_class ID Class Radius Texture Perimeter Area Smoothness Compactness Concavity
586+ ## <fct> <dbl> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
587+ ## 1 M 8.45e5 M 13 21.8 87.5 520. 0.127 0.193 0.186
588+ ## 2 M 8.48e7 M 14.5 27.5 96.7 659. 0.114 0.160 0.164
589+ ## 3 B 8.48e5 M 14.7 20.1 94.7 684. 0.0987 0.072 0.0740
590+ ## 4 M 8.49e5 M 19.8 22.2 130 1260 0.0983 0.103 0.148
591+ ## 5 B 8.51e6 B 13.5 14.4 87.5 566. 0.0978 0.0813 0.0666
592+ ## 6 M 8.51e6 M 15.3 14.3 102. 704. 0.107 0.214 0.208
593+ ## 7 M 8.53e5 M 18.6 25.1 125. 1088 0.106 0.189 0.232
594+ ## 8 M 8.54e5 M 19.3 26.5 128. 1162 0.0940 0.172 0.166
595+ ## 9 B 8.55e5 M 13.4 21.6 86.2 563 0.0816 0.0603 0.0311
596+ ## 10 M 8.56e5 M 13.3 20.3 87.3 545. 0.104 0.144 0.0985
597+ ## # … with 132 more rows, and 3 more variables: Concave_Points <dbl>, Symmetry <dbl>,
598+ ## # Fractal_Dimension <dbl></ code > </ pre >
598599< p > < strong > 5. Compute the accuracy</ strong > </ p >
599600< p > Finally we can assess our classifier’s accuracy. To do this we use the < code > metrics</ code > function
600601from < code > tidymodels</ code > to get the statistics about the quality of our model, specifying
0 commit comments