Outputs & Tables

class: title-slide, center, middle

02

# Outputs & Tables

## R Markdown for Medicine

### Alison Hill &#183; RStudio

#### [rmd4medicine.netlify.com/](https://rmd4medicine.netlify.com/)

---
class: middle, center

#

# Go here and log in (free):

https://rstd.io/rmd4medicine-cloud

---
layout: true

<div class="my-footer">https://rstd.io/rmd4medicine-cloud</div>

---

.left-column[

 
 ?
 
]

.right-column[

# How does R Markdown work?

1. 🤷

1. I press knit, a document appears, and I believe that anything happening in between could be actual magic.

1. `knitr` executes the code and converts `.Rmd` to `.md`; **Pandoc** renders the `.md` file to the output format you want.

]

---
class: top

.left-column[

 
 ?

]

.right-column[

# How *does* R Markdown work?

1. 🤷 (✔️)

1. ["I press knit, a document appears, and I believe that anything happening in between could be actual magic."](https://twitter.com/allison_horst/status/1070323369600442368?s=20) (🧙‍♂️)

1. `knitr` executes the code and converts `.Rmd` to `.md`; **Pandoc** renders the `.md` file to the output format you want. (✔️)

]

---
class: middle, center

> "In a nutshell, R Markdown stands on the shoulders of `knitr` and **Pandoc**.

> The former executes the computer code embedded in Markdown, and converts R Markdown to Markdown.

> The latter renders Markdown to the output format you want (such as PDF, HTML, Word, and so on)."

> &mdash; [R Markdown: The Definitive Guide](https://bookdown.org/yihui/rmarkdown/)

---
class: center, middle

# Foreshadowing

???

but first a pop quiz...

---
class: pop-quiz

# Pop quiz

Which of the following is **NOT** a part of R Markdown basic anatomy?

1. Metadata

1. Text

1. CSS

1. Code

1. Output

---
class: your-turn

# Your turn

## Mad libs style &mdash; with a neighbor

```markdown
 ___________ is written at the top between `---` in ________.
    noun                                             syntax
                                                     
  ______ is written in Markdown.
   noun         
  
  ______ is written in R (or other programming language).
   noun   
   
  The ______ package evaluates the code and produces the ______.
       noun                                               noun
```

_psst: answers on next slide..._

---
class: your-turn

# Your turn

## Answers

```markdown
 Metadata is written at the top between `---` in YAML.
   (noun)                                      (syntax)
                                                     
  Text is written in Markdown.
 (noun)         
  
  Code is written in R (or other programming language).
 (noun)   
   
  The knitr package evaluates the code and produces the output.
     (noun)                                             (noun) 
```

---
class: your-turn

# Your turn

Find a partner and look at `02-progress.Rmd` together. 
Look at the source, then 🧶 **Knit**.

Answer the following questions:

1. What is the output **format**?

1. Are there any output **options**?

1. Are any `knitr` **global** chunk options set?

1. Anything in the code look foreign to you?

1. Anything in the output (or not in the output) surprise you?

---
class: middle, center, inverse

1

# Output formats

---
class: middle, center

???

Built in formats (in the `rmarkdown` package)

versus

extensions (different packages that extend output formats available to you)

---
class: middle, center

https://rmarkdown.rstudio.com/docs/reference/index.html#section-output-formats

---
class: your-turn

# Your turn

## Use a different built-in format

.pull-left[

Use the drop-down menu for the 🧶 **Knit** button and try:

1. Knit to Word

1. Knit to PDF

]

.pull-right[
<img src="images/knit-dropdown.png" width="60%" style="display: block; margin: auto;" />

]

---

# Temp check 🌡

Does your current YAML look like this?

```yaml
---
author: Your name here
title: Your title here
output:
  html_document:
    toc: true
    toc_float: true
    theme: flatly
  word_document: default
  pdf_document: default
---
```

???

This is a great way to "control" your knit button!

Notice that when you knit, it respects those output options in your YAML.

This way you "save" your output options

---
class: your-turn

# Your turn

## Add output options with your YAML

.pull-left[

You just used the drop-down 🧶 **Knit** button to knit to Word and PDF.

1. Change your YAML to the right...

1. Be __very careful__ about indentation and `:` here!!

1. 🧶 **Knit** to Word again- is there a TOC?

]

.pull-right[

```yaml
---
author: Your name here
title: Your title here
output:
  html_document:
    toc: true
    toc_float: true
    theme: flatly
  word_document:
    toc: true
  pdf_document: default
---
```

]

---

# What is hard about YAML?

.pull-left[
![](https://media.giphy.com/media/Nt2cPxzpKhbCE/giphy.gif)
]

.pull-right[
+ Indentations matter

+ Rarely informative error messages

+ Knowing which output options are relevant for different formats (i.e., Word, PDF, HTML, etc.)

+ Easy to forget the right `key`

+ Easy to forget the possible `values` for a given `key`
]
---
class: your-turn

# Your turn

## Use an extension package

1. Edit your YAML again! Change the `output:` key to only `distill::distill_article`

1. Save the document; click on the dropdown 🧶 **Knit** button- what do you notice?

1. 🧶 **Knit** to distill_article.

**If this was easy**, add a table of contents too.

_psst...answers on the next slide..._

.footnote[(note: this requires you to install the [`distill` package](https://rstudio.github.io/distill/) on your own computer)]

???

At this point, I'm going to stick with the distill_article output format for the rest of this session.

---
class: your-turn

# Your turn

## Answer

.pull-left[
```yaml
---
author: Your name here
title: Your title here
output: distill::distill_article
---
```
]

.pull-right[
```yaml
---
author: Your name here
title: Your title here
output:
  distill::distill_article:
    toc: true
---
```
]

---
class: middle

# Pop quiz

.pull-left[
How do you add a single output **format** to your YAML?

```yaml
---
output: html_document: default
---
output: html_document
---
```

]

.pull-right[
How do you add an output **option** to a format in your YAML?

```yaml
---
output: 
  html_document: 
    toc: true
---
output: 
  html_document(toc=true)
---
```

]

---
class: middle

# Pop quiz

.pull-left[
How do you add another output **format** to your YAML?

```yaml
---
output: 
  html_document: default
  word_document: default
---
output: 
  html_document()
  word_document()
---
```

]

.pull-right[
How do you now add output **options** to your YAML?

```yaml
---
output: 
  html_document: 
    toc: true
  word_document: default
---
output: 
  html_document(toc=true)
  word_document(default)
---
```

]

---
class: middle, center, inverse

# Tables

![](https://media.giphy.com/media/i9c6lFmOSXKZW/giphy.gif)

---
class: middle, center, inverse

2

# Custom typed tables

---
class: center

# Markdown tables

.pull-left[

```markdown
| Time          | Session | Topic    |
|:--------------|:-------:|---------:|
| _left_        | _center_| _right_  |
| 01:00 - 01:50 | 1       | Anatomy  |
| 01:50 - 02:00 |         | *Break*  |
| 02:00 - 02:45 | 2       | Tables   |
| 02:45 - 03:00 |         | *Break*  |

```
]

.pull-right[

| Time          | Session | Topic    |
|:--------------|:-------:|---------:|
| _left_        | _center_| _right_  |
| 01:00 - 01:50 | 1       | Anatomy  |
| 01:50 - 02:00 |         | *Break*  |
| 02:00 - 02:45 | 2       | Tables   |
| 02:45 - 03:00 |         | *Break*  |

]

---
class: your-turn

# Your turn

## Type up a Markdown table

Find this section:

```markdown
<--TODO: add markdown table of treatment arms here-->
```

.pull-left[

Using pipes `|`, make this table:

| Arm | Drug   |
|:----|:-------|
| A   | IFL    |
| F   | FOLFOX |
| G   | IROX   |

]

.pull-right[

![](https://qph.fs.quoracdn.net/main-qimg-637b91293b153c5cd40419c0872c2186)

]

_psst...answers on the next slide..._

---
class: your-turn

# Your turn

## Answers

.pull-left[
```markdown
| Arm | Drug   |
|:----|:-------|
| A   | IFL    |
| F   | FOLFOX |
| G   | IROX   |
```
]

.pull-right[
```markdown
|Arm|Drug|
|:---|:---|
|A|IFL|
|F|FOLFOX|
|G|IROX|
```
]

Spacing actually doesn't matter - it mainly helps your eyeballs.

---
class: center, middle

# Two table types

.pull-left[

### for your eyes mainly

]

.pull-right[

### for other people's eyes too

<img src="images/tables-them.jpg" width="3691" />
]

---

.pull-left[

![](images/imani-_TuIdedBPwQ-unsplash.jpg)
]

.pull-right[
![](images/gear_shift.jpg)
]

.footnote[Images from [Unsplash](https://unsplash.com/photos/_TuIdedBPwQ) and [Wikipedia](https://commons.wikimedia.org/wiki/File:FIAT_500L_gear_shift.jpg)]

---
class: middle, center, inverse

3

# EDA Tables

---

# Let's try using data now

```r
mockdata <- read_csv(here::here("static/mockpaper/data/mockdata.csv")) %>%
 mutate(fu_fct = fct_recode(as.factor(fu_stat), 
 "Lived" = "1", 
 "Died" = "2")) %>% 
 mutate_at(vars(starts_with("ae_")), ~as.factor(.))
#> Parsed with column specification:
#> cols(
#> .default = col_double(),
#> arm = col_character(),
#> sex = col_character(),
#> race = col_character(),
#> age_ord = col_character(),
#> site = col_character(),
#> country = col_character(),
#> ethnicity = col_character(),
#> name = col_character(),
#> first_name = col_character(),
#> last_name = col_character()
#> )
#> See spec(...) for full column specifications.
```

---

# EDA tables: `skimr`

```r
library(skimr)

mockdata %>% 
  select(age, fu_fct) %>% 
  skimr::skim()
#> Skim summary statistics
#>  n obs: 1499 
#>  n variables: 2 
#> 
#> ── Variable type:factor ─────────────────────────────────────────────────
#>  variable missing complete    n n_unique                 top_counts
#>    fu_fct       0     1499 1499        2 Die: 1356, Liv: 143, NA: 0
#>  ordered
#>    FALSE
#> 
#> ── Variable type:numeric ────────────────────────────────────────────────
#>  variable missing complete    n  mean    sd p0 p25 p50 p75 p100     hist
#>       age       0     1499 1499 59.99 11.52 19  52  61  68   88 ▁▁▂▅▇▇▅▁
```

---

````
```{r results='asis'}
mockdata %>% 
  select(age, fu_fct) %>% 
  skimr::skim() %>% 
  kable()
```
````

Skim summary statistics  
 n obs: 1499    
 n variables: 2

Variable type: factor

| variable | missing | complete |  n   | n_unique |         top_counts         | ordered |
|----------|---------|----------|------|----------|----------------------------|---------|
|  fu_fct  |    0    |   1499   | 1499 |    2     | Die: 1356, Liv: 143, NA: 0 |  FALSE  |

Variable type: numeric

| variable | missing | complete |  n   | mean  |  sd   | p0 | p25 | p50 | p75 | p100 |   hist   |
|----------|---------|----------|------|-------|-------|----|-----|-----|-----|------|----------|
|   age    |    0    |   1499   | 1499 | 59.99 | 11.52 | 19 | 52  | 61  | 68  |  88  | ▁▁▂▅▇▇▅▁ |

---

# EDA tables: `janitor`

Good for 1- and 2-way frequency tables with categorical variables

Count number of participants by `arm`, then add by status (`fu_fct`) too

.pull-left[

```r
mockdata %>% 
  tabyl(arm)
#>        arm   n   percent
#>     A: IFL 428 0.2855237
#>  F: FOLFOX 691 0.4609740
#>    G: IROX 380 0.2535023
```

]

.pull-right[

```r
mockdata %>% 
  tabyl(arm) %>% 
  adorn_totals("row") %>%
  adorn_pct_formatting()
#>        arm    n percent
#>     A: IFL  428   28.6%
#>  F: FOLFOX  691   46.1%
#>    G: IROX  380   25.4%
#>      Total 1499  100.0%
```

]

---

.pull-left[

````
```{r results='asis'}
mockdata %>% 
  tabyl(arm, fu_fct) %>%
  knitr::kable()
```
````

|arm       | Lived| Died|
|:---------|-----:|----:|
|A: IFL    |    18|  410|
|F: FOLFOX |    99|  592|
|G: IROX   |    26|  354|

]

.pull-right[

````
```{r results='asis'}
mockdata %>% 
  tabyl(arm, fu_fct) %>% 
  adorn_totals("row") %>%
  adorn_percentages("row") %>%
  adorn_pct_formatting(digits = 2) %>%
  adorn_ns() %>%
  knitr::kable()
```
````

|arm       |Lived        |Died          |
|:---------|:------------|:-------------|
|A: IFL    |4.21%  (18)  |95.79%  (410) |
|F: FOLFOX |14.33%  (99) |85.67%  (592) |
|G: IROX   |6.84%  (26)  |93.16%  (354) |
|Total     |9.54% (143)  |90.46% (1356) |

]

---
class: your-turn

# Your turn

## Fix this `tabyl`

Find this section:
```markdown
<--TODO: make this print better with knitr::kable + code chunks-->
```

Make this `tabyl` print nicely when knitted.

```r
mockdata %>% 
  tabyl(arm) %>% 
  adorn_totals("row") %>%
  adorn_pct_formatting() 
```

_psst: answers on next slide..._

---
class: your-turn

# Answer

````
```{r results='asis'}
mockdata %>% 
  tabyl(arm) %>% 
  adorn_totals("row") %>%
  adorn_pct_formatting() %>% 
  knitr::kable()
```
````

|arm       |    n|percent |
|:---------|----:|:-------|
|A: IFL    |  428|28.6%   |
|F: FOLFOX |  691|46.1%   |
|G: IROX   |  380|25.4%   |
|Total     | 1499|100.0%  |

---
class: middle, center, inverse

4

# Table One

---

# Table One from `arsenal`

```r
tableby(arm ~ sex, data = mockdata) 
#> tableby Object
#> 
#> Function Call:
#> tableby(formula = arm ~ sex, data = mockdata)
#> 
#> Variable(s):
#> arm ~ sex
```

```r
tableby(arm ~ sex, data = mockdata) %>% 
  summary()
#> 
#> 
#> |                         | A: IFL (N=428) | F: FOLFOX (N=691) | G: IROX (N=380) | Total (N=1499) | p value|
#> |:------------------------|:--------------:|:-----------------:|:---------------:|:--------------:|-------:|
#> |**sex**                  |                |                   |                 |                |   0.190|
#> |&nbsp;&nbsp;&nbsp;Female |  151 (35.3%)   |    280 (40.5%)    |   152 (40.0%)   |  583 (38.9%)   |        |
#> |&nbsp;&nbsp;&nbsp;Male   |  277 (64.7%)   |    411 (59.5%)    |   228 (60.0%)   |  916 (61.1%)   |        |
```

---

# One more step!

For R Markdown pretty printing...

````
```{r results='asis'}
tableby(arm ~ sex, data = mockdata) %>% 
  summary()
```
````

|                         | A: IFL (N=428) | F: FOLFOX (N=691) | G: IROX (N=380) | Total (N=1499) | p value|
|:------------------------|:--------------:|:-----------------:|:---------------:|:--------------:|-------:|
|**sex**                  |                |                   |                 |                |   0.190|
|&nbsp;&nbsp;&nbsp;Female |  151 (35.3%)   |    280 (40.5%)    |   152 (40.0%)   |  583 (38.9%)   |        |
|&nbsp;&nbsp;&nbsp;Male   |  277 (64.7%)   |    411 (59.5%)    |   228 (60.0%)   |  916 (61.1%)   |        |

???

This is a new knitr chunk option- the results option.

---
class: your-turn

# Your turn

## Make a table one

Find this section:

```markdown
<--TODO: add age and bmi here-->
```

1. Add the variables `age` and `bmi` to the table. (__hint:__ use the formula `arm ~ sex + var1 + var2`)

1. Look at the next code chunk. It uses a different package, `tableone::CreateTableOne`. You only need one "table one", so pick which one you using your code chunks (don't delete!).

1. Add/subtract variables from your table one as you like.

(Note: leave this `layout="l-body-outset"` part alone- I'll explain!)

---
class: middle, center, inverse

5

# Table Two

---
class: your-turn

# Your turn

## Table two

Find this section:
```
<--TODO: add adverse events table-->
```

1. Find the code chunk started for you.

1. Code and print a table called `ae_tab` that summarizes 2+ variables that start with `ae_`.

__If this was easy__, edit the `summary()` function to modify the number of [digits](https://cran.r-project.org/web/packages/arsenal/vignettes/tableby.html#modify-the-number-of-digits-used). Or add [labels](https://cran.r-project.org/web/packages/arsenal/vignettes/tableby.html#add-labels).

_psst...answers on next slide..._

---
class: your-turn

# Answer

````
```{r results='asis', layout="l-body-outset"}
ae_tab <- mockdata %>% 
 tableby(
 arm ~ ae_blood_clot + ae_vomiting + ae_diarrhea + ae_neuropathy + ae_low_wbc, 
 data = .) %>% 
 summary(digits = 2, 
 digits.p = 3, 
 digits.pct = 1)
ae_tab
```
````

---

| | A: IFL (N=428) | F: FOLFOX (N=691) | G: IROX (N=380) | Total (N=1499) | p value|
|:-------------------|:--------------:|:-----------------:|:---------------:|:--------------:|-------:|
|**ae_blood_clot** | | | | | 0.742|
|&nbsp;&nbsp;&nbsp;0 | 411 (96.0%) | 658 (95.2%) | 365 (96.1%) | 1434 (95.7%) | |
|&nbsp;&nbsp;&nbsp;1 | 17 (4.0%) | 33 (4.8%) | 15 (3.9%) | 65 (4.3%) | |
|**ae_vomiting** | | | | | 0.006|
|&nbsp;&nbsp;&nbsp;0 | 339 (79.2%) | 571 (82.6%) | 333 (87.6%) | 1243 (82.9%) | |
|&nbsp;&nbsp;&nbsp;1 | 89 (20.8%) | 120 (17.4%) | 47 (12.4%) | 256 (17.1%) | |
|**ae_diarrhea** | | | | | 0.001|
|&nbsp;&nbsp;&nbsp;0 | 339 (79.2%) | 546 (79.0%) | 333 (87.6%) | 1218 (81.3%) | |
|&nbsp;&nbsp;&nbsp;1 | 89 (20.8%) | 145 (21.0%) | 47 (12.4%) | 281 (18.7%) | |
|**ae_neuropathy** | | | | | < 0.001|
|&nbsp;&nbsp;&nbsp;0 | 354 (82.7%) | 580 (83.9%) | 347 (91.3%) | 1281 (85.5%) | |
|&nbsp;&nbsp;&nbsp;1 | 74 (17.3%) | 111 (16.1%) | 33 (8.7%) | 218 (14.5%) | |
|**ae_low_wbc** | | | | | < 0.001|
|&nbsp;&nbsp;&nbsp;0 | 354 (82.7%) | 551 (79.7%) | 347 (91.3%) | 1252 (83.5%) | |
|&nbsp;&nbsp;&nbsp;1 | 74 (17.3%) | 140 (20.3%) | 33 (8.7%) | 247 (16.5%) | |

---
class: middle, center

# ⏱

# Time for a break!