Introduction to tidymodels

class: center, middle, title-slide

# Introduction to tidymodels
## NHS-R Conference 2021
### Emil Hvitfeldt
### 2021-11-02

---

<header class="header header--fixed" role="banner">
<nav class="distill-site-nav distill-site-header">
<div class="nav-left">
<a href="index.html" class="title">NHS tidymodels workshop</a>
</div>
<div class="nav-right">
<a href="index.html">Home</a>
<div class="nav-dropdown">
<button class="nav-dropbtn">
Slides
 
<span class="down-arrow">▾</span>
</button>
<div class="nav-dropdown-content">
<a href="1-introduction.html">1: Introduction</a>
<hr/>
<a href="2-models.html">2: Models</a>
<hr/>
<a href="3-features.html">3: Features</a>
<hr/>
<a href="4-resampling.html">4: Resampling</a>
<hr/>
<a href="5-tuning.html">5: Tuning</a>
</div>
</div>
<a href="https://github.com/EmilHvitfeldt/nhs-tidymodels-workshop">
<i class="fab fa-github" aria-hidden="true"></i>
</a>
<a href="javascript:void(0);" class="nav-toggle">☰</a>
</div>
</nav>
</header>

<div style = "position:fixed; visibility: hidden">
`$$\require{color}\definecolor{purple}{rgb}{0.525490196078431, 0.419607843137255, 0.749019607843137}$$`
`$$\require{color}\definecolor{green}{rgb}{0.0117647058823529, 0.650980392156863, 0.415686274509804}$$`
`$$\require{color}\definecolor{orange}{rgb}{0.949019607843137, 0.580392156862745, 0.254901960784314}$$`
`$$\require{color}\definecolor{white}{rgb}{1, 1, 1}$$`
</div>

# Our goals for this workshop

* Introduce tidymodels and its general philosophy on modeling.

* Help you become proficient with the core packages for modeling.

* Point you to places to learn more and get help.

---

# Why tidymodels?

There are several other modeling frameworks in R that try to:

* create a uniform, cohesive, and unsurprising set of modeling APIs
 
Examples are .pkg[caret], .pkg[mlr3], and others.

* .pkg[caret] is more favorable for people who prefer base R/traditional interfaces.
* .pkg[mlr3] is more pythonic and also has many features.
* .pkg[tidymodels] would probably be preferable to those who place importance on a tidy _R_ interface, a large number of features, and the idea that the interfaces should enable the "pit of success".

---

# The tidymodels package

There are a lot of tidymodels packages but about 90% of the work is done by 5 packages. (.pkg[rsample], .pkg[recipes], .pkg[parsnip], .pkg[tune], and .pkg[yardstick])

The best way to get started with tidymodels is to use the .pkg[tidymodels] meta-package. It loads the core packages plus some tidyverse packages.

Some helpful links:

* List of [all tidymodels functions](https://www.tidymodels.org/find/#search-all-of-tidymodels)
 * List of [all parsnip models](https://www.tidymodels.org/find/parsnip/)
 * List of [all recipe steps](https://www.tidymodels.org/find/recipes/)

---

# The tidymodels package

```r
library(tidymodels)
```

```r
── Attaching packages ─────────────────────────────────────────────────── tidymodels 0.1.4 ──
✓ broom        0.7.9      ✓ recipes      0.1.17
✓ dials        0.0.10     ✓ rsample      0.1.0 
✓ dplyr        1.0.7      ✓ tibble       3.1.5 
✓ ggplot2      3.3.5      ✓ tidyr        1.1.4 
✓ infer        1.0.0      ✓ tune         0.1.6 
✓ modeldata    0.1.1      ✓ workflows    0.2.4 
✓ parsnip      0.1.7      ✓ workflowsets 0.1.0 
✓ purrr        0.3.4      ✓ yardstick    0.0.8 
── Conflicts ────────────────────────────────────────────────────── tidymodels_conflicts() ──
x purrr::discard() masks scales::discard()
x dplyr::filter()  masks stats::filter()
x dplyr::lag()     masks stats::lag()
x recipes::step()  masks stats::step()
• Use tidymodels_prefer() to resolve common conflicts.
```

---

# Managing name conflicts

```r
tidymodels_prefer(quiet = FALSE)
```

```
## [conflicted] Will prefer dplyr::filter over any other package
## [conflicted] Will prefer dplyr::select over any other package
## [conflicted] Will prefer dplyr::slice over any other package
## [conflicted] Will prefer dplyr::rename over any other package
## [conflicted] Will prefer dials::neighbors over any other package
## [conflicted] Will prefer plsmod::pls over any other package
## [conflicted] Will prefer purrr::map over any other package
## [conflicted] Will prefer recipes::step over any other package
## [conflicted] Will prefer themis::step_downsample over any other package
## [conflicted] Will prefer themis::step_upsample over any other package
## [conflicted] Will prefer tune::tune over any other package
## [conflicted] Will prefer yardstick::precision over any other package
## [conflicted] Will prefer yardstick::recall over any other package
```

---

# Base R and tidyverse differences

.pull-left[
Base R/caret

```r
mtcars <- mtcars[order(mtcars$cyl),]
mtcars <- mtcars[, "mpg", drop = FALSE]

# ──────────────────────────────────────────────

mtcars$mp        # matches incomplete arg
mtcars[, "mpg"]  # a vector

# ──────────────────────────────────────────────

num_args <- function(x) length(formals(x))

num_args(caret::trainControl) + 
  num_args(caret:::train.default)
```

```
38
```
]
.pull-right[
tidyverse/tidymodels

```r
mtcars %>% 
  arrange(cyl) %>% 
  select(mpg)

# ──────────────────────────────────────────────

tb_cars <- as_tibble(mtcars)
tb_cars$mp        # fails
tb_cars[, "mpg"]  # A tibble

# ──────────────────────────────────────────────

num_args(linear_reg) + num_args(set_engine) + 
  num_args(tune_grid) + num_args(control_grid) + 
  num_args(vfold_cv)
```
```
23
```
]

---
# Example data set

These data are used in our [Feature Engineering and Selection](https://bookdown.org/max/FES/chicago-intro.html) book.

Several years worth of pre-pandemic data were assembled to try to predict the daily number of people entering the Clark and Lake elevated ("L") train station in Chicago.

For predictors,

* the 14-day lagged ridership at this and other stations (units: thousands of rides/day)
* weather data
* home/away game schedules for Chicago teams
* the date

The data are in `modeldata`. See `?Chicago`.

---

# Hands-On: Explore the Data

Take a look at these data for a few minutes and see if you can find any interesting characteristics in the predictors or the outcome.

```r
library(tidymodels)
data("Chicago")
dim(Chicago)
```

```
## [1] 5698   50
```

```r
stations
```

```
##  [1] "Austin"           "Quincy_Wells"     "Belmont"         
##  [4] "Archer_35th"      "Oak_Park"         "Western"         
##  [7] "Clark_Lake"       "Clinton"          "Merchandise_Mart"
## [10] "Irving_Park"      "Washington_Wells" "Harlem"          
## [13] "Monroe"           "Polk"             "Ashland"         
## [16] "Kedzie"           "Addison"          "Jefferson_Park"  
## [19] "Montrose"         "California"
```

---
layout: false
class: inverse, middle, center

# [`tidymodels.org`](https://www.tidymodels.org/)

# _Tidy Modeling with R_ ([`tmwr.org`](https://www.tmwr.org/))