archive 2023 nyr slides

_freeze/archive/2023-07-nyr/01-introduction/execute-results/html.json

@@ -0,0 +1,21 @@
+{
+  "hash": "3ea97871f74836d15d22db5ec0939940",
+  "result": {
+    "markdown": "---\ntitle: \"1 - Introduction\"\nsubtitle: \"Machine learning with tidymodels\"\nformat:\n  revealjs: \n    slide-number: true\n    footer: <https://workshops.tidymodels.org>\n    include-before-body: header.html\n    include-after-body: footer-annotations.html\n    theme: [default, tidymodels.scss]\n    width: 1280\n    height: 720\nknitr:\n  opts_chunk: \n    echo: true\n    collapse: true\n    comment: \"#>\"\n---\n\n\n\n\n::: r-fit-text\nWelcome!\n:::\n\n## Who are you?\n\n-   You can use the magrittr `%>%` or base R `|>` pipe\n\n-   You are familiar with functions from dplyr, tidyr, ggplot2\n\n-   You have exposure to basic statistical concepts\n\n-   You do **not** need intermediate or expert familiarity with modeling or ML\n\n## Who are tidymodels?\n\n-   Simon Couch\n-   Hannah Frick\n-   Emil Hvitfeldt\n-   Max Kuhn\n\n. . .\n\nMany thanks to Davis Vaughan, Julia Silge, David Robinson, Julie Jung, Alison Hill, and Desirée De Leon for their role in creating these materials!\n\n## Asking for help\n\n. . .\n\n🟪 \"I'm stuck and need help!\"\n\n. . .\n\n🟩 \"I finished the exercise\"\n\n\n## 👀 {.annotation}\n\n![](images/pointing.svg){.absolute top=\"0\" right=\"0\"}\n\n## Tentative plan for this workshop\n\n::: columns\n::: {.column width=\"50%\"}\n-   *Today:* \n\n    - Your data budget\n    - What makes a model\n    - Evaluating models\n:::\n::: {.column width=\"50%\"}\n-   *Tomorrow:*\n    \n    - Feature engineering\n    - Tuning hyperparameters\n    - Racing methods\n    - Iterative search methods\n:::\n:::\n\n##  {.center}\n\n### Introduce yourself to your neighbors 👋\n\n<br></br>\n\nCheck Slack (`#ml-ws-2023`) for an RStudio Cloud link.\n\n## What is machine learning?\n\n![](https://imgs.xkcd.com/comics/machine_learning.png){fig-align=\"center\"}\n\n::: footer\n<https://xkcd.com/1838/>\n:::\n\n## What is machine learning?\n\n![](images/what_is_ml.jpg){fig-align=\"center\"}\n\n::: footer\nIllustration credit: <https://vas3k.com/blog/machine_learning/>\n:::\n\n## What is machine learning?\n\n![](images/ml_illustration.jpg){fig-align=\"center\"}\n\n::: footer\nIllustration credit: <https://vas3k.com/blog/machine_learning/>\n:::\n\n## Your turn {transition=\"slide-in\"}\n\n![](images/parsnip-flagger.jpg){.absolute top=\"0\" right=\"0\" width=\"150\" height=\"150\"}\n\n. . .\n\n*How are statistics and machine learning related?*\n\n*How are they similar? Different?*\n\n\n::: {.cell}\n::: {.cell-output-display}\n```{=html}\n<div class=\"countdown\" id=\"statistics-vs-ml\" data-update-every=\"1\" tabindex=\"0\" style=\"right:0;bottom:0;\">\n<div class=\"countdown-controls\"><button class=\"countdown-bump-down\">&minus;</button><button class=\"countdown-bump-up\">&plus;</button></div>\n<code class=\"countdown-time\"><span class=\"countdown-digits minutes\">03</span><span class=\"countdown-digits colon\">:</span><span class=\"countdown-digits seconds\">00</span></code>\n</div>\n```\n:::\n:::\n\n\n::: notes\nthe \"two cultures\"\n\nmodel first vs. data first\n\ninference vs. prediction\n:::\n\n## What is tidymodels? ![](hexes/tidymodels.png){.absolute top=-20 right=0 width=\"64\" height=\"74.24\"}\n\n\n::: {.cell}\n\n```{.r .cell-code}\nlibrary(tidymodels)\n#> ── Attaching packages ──────────────────────────── tidymodels 1.1.0 ──\n#> ✔ broom        1.0.5          ✔ rsample      1.1.1.9000\n#> ✔ dials        1.2.0          ✔ tibble       3.2.1     \n#> ✔ dplyr        1.1.2          ✔ tidyr        1.3.0     \n#> ✔ infer        1.0.4          ✔ tune         1.1.1.9001\n#> ✔ modeldata    1.1.0          ✔ workflows    1.1.3     \n#> ✔ parsnip      1.1.0.9003     ✔ workflowsets 1.0.1     \n#> ✔ purrr        1.0.1          ✔ yardstick    1.2.0.9001\n#> ✔ recipes      1.0.6\n#> ── Conflicts ─────────────────────────────── tidymodels_conflicts() ──\n#> ✖ purrr::discard() masks scales::discard()\n#> ✖ dplyr::filter()  masks stats::filter()\n#> ✖ dplyr::lag()     masks stats::lag()\n#> ✖ recipes::step()  masks stats::step()\n#> • Use tidymodels_prefer() to resolve common conflicts.\n```\n:::\n\n\n##  {background-image=\"images/tm-org.png\" background-size=\"contain\"}\n\n## The whole game\n\nPart of any modelling process is\n\n* Splitting your data into training and test set\n* Using a resampling scheme\n* Fitting models\n* Assessing performance\n* Choosing a model\n* Fitting and assessing the final model\n\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-split.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-model-1.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n:::notes\nStress that we are **not** fitting a model on the entire training set other than for illustrative purposes in deck 2.\n:::\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-model-n.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-resamples.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-select.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-final-fit.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n## The whole game\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](images/whole-game-final-performance.jpg){fig-align='center' width=3543}\n:::\n:::\n\n\n\n## Let's install some packages\n\nIf you are using your own laptop instead of RStudio Cloud:\n\n\n::: {.cell}\n\n```{.r .cell-code}\ninstall.packages(\"pak\")\n\npkgs <- c(\"bonsai\", \"doParallel\", \"embed\", \"finetune\", \"lightgbm\", \"lme4\", \n          \"parallelly\", \"plumber\", \"probably\", \"ranger\", \"rpart\", \"rpart.plot\", \n          \"stacks\", \"textrecipes\", \"tidymodels\", \"tidymodels/modeldatatoo\", \n          \"vetiver\")\npak::pak(pkgs)\n```\n:::\n\n\n. . .\n\nCheck Slack (`#ml-ws-2023`) for an RStudio Cloud link.\n\n\n## Our versions\n\n\n::: {.cell}\n\n:::\n\n\nbonsai (0.2.1.9000, Github (tidymodels/bonsai@aab79), broom (1.0.5, local), dials (1.2.0, CRAN), doParallel (1.0.17, CRAN), dplyr (1.1.2, CRAN), embed (1.0.0, CRAN), finetune (1.1.0.9000, Github (tidymodels/finetune@52d), ggplot2 (3.4.2, CRAN), lightgbm (3.3.5, CRAN), lme4 (1.1-33, CRAN), modeldata (1.1.0, CRAN), modeldatatoo (0.1.0.9000, Github (tidymodels/modeldatatoo), parallelly (1.36.0, CRAN), parsnip (1.1.0.9003, Github (tidymodels/parsnip@e627), plumber (1.2.1, CRAN), probably (1.0.2, CRAN), purrr (1.0.1, CRAN), ranger (0.15.1, CRAN), recipes (1.0.6, CRAN), rpart (4.1.19, CRAN), rpart.plot (3.1.1, CRAN), rsample (1.1.1.9000, Github (tidymodels/rsample@afc4), scales (1.2.1, CRAN), stacks (1.0.2.9000, local), textrecipes (1.0.2, CRAN), tibble (3.2.1, CRAN), tidymodels (1.1.0, CRAN), tidyr (1.3.0, CRAN), tune (1.1.1.9001, Github (tidymodels/tune@fea8b02), vetiver (0.2.0, CRAN), workflows (1.1.3, CRAN), workflowsets (1.0.1, CRAN), yardstick (1.2.0.9001, Github (tidymodels/yardstick@6c), and Quarto (1.3.433)\n",
+    "supporting": [],
+    "filters": [
+      "rmarkdown/pagebreak.lua"
+    ],
+    "includes": {
+      "include-in-header": [
+        "<link href=\"../../site_libs/countdown-0.4.0/countdown.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/countdown-0.4.0/countdown.js\"></script>\n"
+      ],
+      "include-after-body": [
+        "\n<script>\n  // htmlwidgets need to know to resize themselves when slides are shown/hidden.\n  // Fire the \"slideenter\" event (handled by htmlwidgets.js) when the current\n  // slide changes (different for each slide format).\n  (function () {\n    // dispatch for htmlwidgets\n    function fireSlideEnter() {\n      const event = window.document.createEvent(\"Event\");\n      event.initEvent(\"slideenter\", true, true);\n      window.document.dispatchEvent(event);\n    }\n\n    function fireSlideChanged(previousSlide, currentSlide) {\n      fireSlideEnter();\n\n      // dispatch for shiny\n      if (window.jQuery) {\n        if (previousSlide) {\n          window.jQuery(previousSlide).trigger(\"hidden\");\n        }\n        if (currentSlide) {\n          window.jQuery(currentSlide).trigger(\"shown\");\n        }\n      }\n    }\n\n    // hookup for slidy\n    if (window.w3c_slidy) {\n      window.w3c_slidy.add_observer(function (slide_num) {\n        // slide_num starts at position 1\n        fireSlideChanged(null, w3c_slidy.slides[slide_num - 1]);\n      });\n    }\n\n  })();\n</script>\n\n"
+      ]
+    },
+    "engineDependencies": {},
+    "preserve": {},
+    "postProcess": true
+  }
+}