Visualisation and other cool things with R

class: center, middle, inverse, title-slide

# Visualisation<br>and other cool things with R
### Antoine Bichat
### Mines Nancy<br>December 15, 2017

---

class: center, middle, inverse

#Good practices

---
##Writing code

* Use the arrow for assignation and equal sign for argument setting

* Leave space after commas, and around arrows and equal signs

* Use line breaks

```r
x <- rnorm(n = 100, mean = 3, sd = 0.1)

hist(x, col = "grey", border = "black", breaks = 30,
     main = "Normal distribution", xlab = "", ylab = "Frequency")
```

---
## Pipe operator %>%

```r
# install.packages("magrittr")
library(magrittr)
```

* To express clearly a sequence of multiple operations

* `x %>% f` is equivalent to `f(x)`

* `x %>% f(y)` is equivalent to `f(x, y)`

```r
round(mean(sqrt(1:9), na.rm = TRUE), digits = 2)
```

```
## [1] 2.15
```

```r
1:9 %>%
  sqrt %>%
  mean(na.rm = TRUE) %>%
  round(digits = 2)
```

```
## [1] 2.15
```

---
class: center, middle
<blockquote class="twitter-tweet" data-lang="fr" align="center"><p lang="en" dir="ltr">This is a reason for pipes.  <a href="https://twitter.com/hashtag/rstats?src=hash&amp;ref_src=twsrc%5Etfw">#rstats</a> <a href="https://t.co/SFKVN2GpZZ">pic.twitter.com/SFKVN2GpZZ</a></p>&mdash; Tajti András (@atajti) <a href="https://twitter.com/atajti/status/889112630673235968?ref_src=twsrc%5Etfw">23 juillet 2017</a></blockquote>
<br>
<blockquote class="twitter-tweet" data-lang="fr" align="center"><p lang="en" dir="ltr">And once again, Stackoverflow reminds us why we REALLY need the pipe. <a href="https://twitter.com/hashtag/RStats?src=hash&amp;ref_src=twsrc%5Etfw">#RStats</a> <a href="https://twitter.com/hashtag/tidyverse?src=hash&amp;ref_src=twsrc%5Etfw">#tidyverse</a> <a href="https://t.co/diXgQiVMhO">pic.twitter.com/diXgQiVMhO</a></p>&mdash; Colin Fay (@_ColinFay) <a href="https://twitter.com/_ColinFay/status/889901747480793090?ref_src=twsrc%5Etfw">25 juillet 2017</a></blockquote>

---
<img src="so-logo.png" alt="Drawing" style="width: 410px;"/>

.center[
<img src="so-meme.png" alt="Drawing" style="width: 380px;"/>
]

---
class: middle, center, inverse

#Tips with R and RStudio

---
### Keybord shortcuts

* Ctrl+L: clears console

* Ctrl+Enter: runs selection

* Ctrl+Shift+C: (un)comments selection

* Ctrl+D: deletes selection

* Alt+- : inserts arrow with spaces

.footnote[
[*] It's Command on Macs.
]
--

### Code shortcuts

* `rm(list = ls())` removes all objects from the current workspace

* `graphics.off()` shuts down all open graphics devices

* `cat("\014")` clears console

---
## Not recommended code tips

```r
sqrt(x <- 4) ; x ; 3 -> y ; y
```

```
## [1] 2
```

```
## [1] 4
```

```
## [1] 3
```
---

## Useful code tips

```r
(x <- LETTERS[1:4])
```

```
## [1] "A" "B" "C" "D"
```

```r
x %<>% tolower
x
```

```
## [1] "a" "b" "c" "d"
```

```r
dput(x)
```

```
## c("a", "b", "c", "d")
```

---
## Time and {beepr}

```r
T1 <- Sys.time()
m4 <- rnorm(n = 100000)^4
T2 <- Sys.time()
difftime(T2, T1)
```

```
## Time difference of 0.05402994 secs
```

```r
mean(m4)
```

```
## [1] 2.982003
```

```r
# install.packages("beepr")
library(beepr)
beep()
```

---
##TeleR

.center[
<img src="teleR1.png" alt="Drawing" style="height: 490px;"/>
<img src="teleR2.png" alt="Drawing" style="height: 490px;"/>
]

---
class: middle, center, inverse

#Visualisation
##With [**ggplot2**](http://ggplot2.org/)

---
## Iris dataset

<div id="htmlwidget-bf061a4964ee27e5e789" style="width:100%;height:auto;" class="datatables html-widget"></div>
<script type="application/json" data-for="htmlwidget-bf061a4964ee27e5e789">{"x":{"filter":"none","fillContainer":false,"data":[["1","2","3","4","5","6","7","8","9","10","11","12","13","14","15","16","17","18","19","20","21","22","23","24","25","26","27","28","29","30","31","32","33","34","35","36","37","38","39","40","41","42","43","44","45","46","47","48","49","50","51","52","53","54","55","56","57","58","59","60","61","62","63","64","65","66","67","68","69","70","71","72","73","74","75","76","77","78","79","80","81","82","83","84","85","86","87","88","89","90","91","92","93","94","95","96","97","98","99","100","101","102","103","104","105","106","107","108","109","110","111","112","113","114","115","116","117","118","119","120","121","122","123","124","125","126","127","128","129","130","131","132","133","134","135","136","137","138","139","140","141","142","143","144","145","146","147","148","149","150"],[5.1,4.9,4.7,4.6,5,5.4,4.6,5,4.4,4.9,5.4,4.8,4.8,4.3,5.8,5.7,5.4,5.1,5.7,5.1,5.4,5.1,4.6,5.1,4.8,5,5,5.2,5.2,4.7,4.8,5.4,5.2,5.5,4.9,5,5.5,4.9,4.4,5.1,5,4.5,4.4,5,5.1,4.8,5.1,4.6,5.3,5,7,6.4,6.9,5.5,6.5,5.7,6.3,4.9,6.6,5.2,5,5.9,6,6.1,5.6,6.7,5.6,5.8,6.2,5.6,5.9,6.1,6.3,6.1,6.4,6.6,6.8,6.7,6,5.7,5.5,5.5,5.8,6,5.4,6,6.7,6.3,5.6,5.5,5.5,6.1,5.8,5,5.6,5.7,5.7,6.2,5.1,5.7,6.3,5.8,7.1,6.3,6.5,7.6,4.9,7.3,6.7,7.2,6.5,6.4,6.8,5.7,5.8,6.4,6.5,7.7,7.7,6,6.9,5.6,7.7,6.3,6.7,7.2,6.2,6.1,6.4,7.2,7.4,7.9,6.4,6.3,6.1,7.7,6.3,6.4,6,6.9,6.7,6.9,5.8,6.8,6.7,6.7,6.3,6.5,6.2,5.9],[3.5,3,3.2,3.1,3.6,3.9,3.4,3.4,2.9,3.1,3.7,3.4,3,3,4,4.4,3.9,3.5,3.8,3.8,3.4,3.7,3.6,3.3,3.4,3,3.4,3.5,3.4,3.2,3.1,3.4,4.1,4.2,3.1,3.2,3.5,3.6,3,3.4,3.5,2.3,3.2,3.5,3.8,3,3.8,3.2,3.7,3.3,3.2,3.2,3.1,2.3,2.8,2.8,3.3,2.4,2.9,2.7,2,3,2.2,2.9,2.9,3.1,3,2.7,2.2,2.5,3.2,2.8,2.5,2.8,2.9,3,2.8,3,2.9,2.6,2.4,2.4,2.7,2.7,3,3.4,3.1,2.3,3,2.5,2.6,3,2.6,2.3,2.7,3,2.9,2.9,2.5,2.8,3.3,2.7,3,2.9,3,3,2.5,2.9,2.5,3.6,3.2,2.7,3,2.5,2.8,3.2,3,3.8,2.6,2.2,3.2,2.8,2.8,2.7,3.3,3.2,2.8,3,2.8,3,2.8,3.8,2.8,2.8,2.6,3,3.4,3.1,3,3.1,3.1,3.1,2.7,3.2,3.3,3,2.5,3,3.4,3],[1.4,1.4,1.3,1.5,1.4,1.7,1.4,1.5,1.4,1.5,1.5,1.6,1.4,1.1,1.2,1.5,1.3,1.4,1.7,1.5,1.7,1.5,1,1.7,1.9,1.6,1.6,1.5,1.4,1.6,1.6,1.5,1.5,1.4,1.5,1.2,1.3,1.4,1.3,1.5,1.3,1.3,1.3,1.6,1.9,1.4,1.6,1.4,1.5,1.4,4.7,4.5,4.9,4,4.6,4.5,4.7,3.3,4.6,3.9,3.5,4.2,4,4.7,3.6,4.4,4.5,4.1,4.5,3.9,4.8,4,4.9,4.7,4.3,4.4,4.8,5,4.5,3.5,3.8,3.7,3.9,5.1,4.5,4.5,4.7,4.4,4.1,4,4.4,4.6,4,3.3,4.2,4.2,4.2,4.3,3,4.1,6,5.1,5.9,5.6,5.8,6.6,4.5,6.3,5.8,6.1,5.1,5.3,5.5,5,5.1,5.3,5.5,6.7,6.9,5,5.7,4.9,6.7,4.9,5.7,6,4.8,4.9,5.6,5.8,6.1,6.4,5.6,5.1,5.6,6.1,5.6,5.5,4.8,5.4,5.6,5.1,5.1,5.9,5.7,5.2,5,5.2,5.4,5.1],[0.2,0.2,0.2,0.2,0.2,0.4,0.3,0.2,0.2,0.1,0.2,0.2,0.1,0.1,0.2,0.4,0.4,0.3,0.3,0.3,0.2,0.4,0.2,0.5,0.2,0.2,0.4,0.2,0.2,0.2,0.2,0.4,0.1,0.2,0.2,0.2,0.2,0.1,0.2,0.2,0.3,0.3,0.2,0.6,0.4,0.3,0.2,0.2,0.2,0.2,1.4,1.5,1.5,1.3,1.5,1.3,1.6,1,1.3,1.4,1,1.5,1,1.4,1.3,1.4,1.5,1,1.5,1.1,1.8,1.3,1.5,1.2,1.3,1.4,1.4,1.7,1.5,1,1.1,1,1.2,1.6,1.5,1.6,1.5,1.3,1.3,1.3,1.2,1.4,1.2,1,1.3,1.2,1.3,1.3,1.1,1.3,2.5,1.9,2.1,1.8,2.2,2.1,1.7,1.8,1.8,2.5,2,1.9,2.1,2,2.4,2.3,1.8,2.2,2.3,1.5,2.3,2,2,1.8,2.1,1.8,1.8,1.8,2.1,1.6,1.9,2,2.2,1.5,1.4,2.3,2.4,1.8,1.8,2.1,2.4,2.3,1.9,2.3,2.5,2.3,1.9,2,2.3,1.8],["setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","setosa","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","versicolor","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica","virginica"]],"container":"<table class=\"display\">\n  <thead>\n    <tr>\n      <th> <\/th>\n      <th>Sepal.Length<\/th>\n      <th>Sepal.Width<\/th>\n      <th>Petal.Length<\/th>\n      <th>Petal.Width<\/th>\n      <th>Species<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":7,"columnDefs":[{"className":"dt-right","targets":[1,2,3,4]},{"orderable":false,"targets":0}],"order":[],"autoWidth":false,"orderClasses":false,"lengthMenu":[7,10,25,50,100]}},"evals":[],"jsHooks":[]}</script>

---
##Scatterplot

```r
# install.packages("ggplot2")
library(ggplot2)
ggplot(iris) + geom_point(aes(x = Sepal.Length, y = Petal.Length))
```

---
##Scatterplot with legend

```r
ggplot(iris) + 
  geom_point(aes(x = Sepal.Length, y = Petal.Length, 
                 color = Species, shape = Species)) +
  labs(x = "Sepal length", y = "Petal Length") +
  theme_bw()
```

---
## Histogram

```r
ggplot(iris) + 
  geom_histogram(aes(x = Sepal.Length), 
                 fill = "grey50", color = "black") +
  labs(x = "Sepal length", y = "Count") +
  theme_bw()
```

---
## Histogram with facetting

```r
ggplot(iris) + 
  geom_histogram(aes(x = Sepal.Length, fill = Species), 
                 color = "black") +
  facet_grid(.~Species) +
  labs(x = "Sepal length", y = "Count") +
  theme_bw()
```

---
## Boxplot

```r
p <- ggplot(iris) + 
  geom_boxplot(aes(x = Species, y = Sepal.Length, fill = Species),
               alpha = 0.7) +
  scale_fill_manual(values = c("firebrick", "forestgreen", "royalblue")) +
  labs(x = "Species", y = "Sepal length") 
p + theme_bw()
```

---
##Theory of data visualisation

ggplot stands for __Grammar of Graphics__

<br>

```
ggplot(data = <DATA>) + 
  <GEOM_FUNCTION>(mapping = aes(<MAPPINGS>), 
                  stat = <STAT>, position = <POSITION>) +
  <COORDINATE_FUNCTION> +
  <FACET_FUNCTION>
```

<br>

You can uniquely describe any plot as a combination of these 7 parameters.

---
<br>
<br>
<blockquote class="twitter-tweet" data-lang="fr" align="center"><p lang="en" dir="ltr">Then comes the inevitable &quot;rotate ggplot2 axes&quot; google, which brings me to this life-saving <a href="https://twitter.com/StackOverflow?ref_src=twsrc%5Etfw">@StackOverflow</a> post: <a href="https://t.co/ZuZH52wsYZ">https://t.co/ZuZH52wsYZ</a></p>&mdash; Tanya Cashorali (@tanyacash21) <a href="https://twitter.com/tanyacash21/status/910241426453270528?ref_src=twsrc%5Etfw">19 septembre 2017</a></blockquote>

---
class: center, middle, inverse
# Data manipulation
##with the [**tidyverse**](https://www.tidyverse.org/)

---
##Tidyverse ?

```r
# install.packages("tidyverse")
library(tidyverse)
```

Tidyverse is a collection of packages designed for data science

<br>

We will use {ggplot2}, {dplyr} and {tidyr}

<br>

It imports the `%>%` pipe from {magrittr} but not the `%<>%` pipe

<br>

There are also the {purrr}, {readr} and {tibble} packages

---
## Diamonds dataset

```r
data(diamonds) # {ggplot2}
```

<table>
 <thead>
  <tr>
   <th style="text-align:right;"> carat </th>
   <th style="text-align:left;"> cut </th>
   <th style="text-align:left;"> color </th>
   <th style="text-align:left;"> clarity </th>
   <th style="text-align:right;"> depth </th>
   <th style="text-align:right;"> table </th>
   <th style="text-align:right;"> price </th>
   <th style="text-align:right;"> x </th>
   <th style="text-align:right;"> y </th>
   <th style="text-align:right;"> z </th>
  </tr>
 </thead>
<tbody>
  <tr>
   <td style="text-align:right;"> 0.23 </td>
   <td style="text-align:left;"> Ideal </td>
   <td style="text-align:left;"> E </td>
   <td style="text-align:left;"> SI2 </td>
   <td style="text-align:right;"> 61.5 </td>
   <td style="text-align:right;"> 55 </td>
   <td style="text-align:right;"> 326 </td>
   <td style="text-align:right;"> 3.95 </td>
   <td style="text-align:right;"> 3.98 </td>
   <td style="text-align:right;"> 2.43 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.21 </td>
   <td style="text-align:left;"> Premium </td>
   <td style="text-align:left;"> E </td>
   <td style="text-align:left;"> SI1 </td>
   <td style="text-align:right;"> 59.8 </td>
   <td style="text-align:right;"> 61 </td>
   <td style="text-align:right;"> 326 </td>
   <td style="text-align:right;"> 3.89 </td>
   <td style="text-align:right;"> 3.84 </td>
   <td style="text-align:right;"> 2.31 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.23 </td>
   <td style="text-align:left;"> Good </td>
   <td style="text-align:left;"> E </td>
   <td style="text-align:left;"> VS1 </td>
   <td style="text-align:right;"> 56.9 </td>
   <td style="text-align:right;"> 65 </td>
   <td style="text-align:right;"> 327 </td>
   <td style="text-align:right;"> 4.05 </td>
   <td style="text-align:right;"> 4.07 </td>
   <td style="text-align:right;"> 2.31 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.29 </td>
   <td style="text-align:left;"> Premium </td>
   <td style="text-align:left;"> I </td>
   <td style="text-align:left;"> VS2 </td>
   <td style="text-align:right;"> 62.4 </td>
   <td style="text-align:right;"> 58 </td>
   <td style="text-align:right;"> 334 </td>
   <td style="text-align:right;"> 4.20 </td>
   <td style="text-align:right;"> 4.23 </td>
   <td style="text-align:right;"> 2.63 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.31 </td>
   <td style="text-align:left;"> Good </td>
   <td style="text-align:left;"> J </td>
   <td style="text-align:left;"> SI2 </td>
   <td style="text-align:right;"> 63.3 </td>
   <td style="text-align:right;"> 58 </td>
   <td style="text-align:right;"> 335 </td>
   <td style="text-align:right;"> 4.34 </td>
   <td style="text-align:right;"> 4.35 </td>
   <td style="text-align:right;"> 2.75 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.24 </td>
   <td style="text-align:left;"> Very Good </td>
   <td style="text-align:left;"> J </td>
   <td style="text-align:left;"> VVS2 </td>
   <td style="text-align:right;"> 62.8 </td>
   <td style="text-align:right;"> 57 </td>
   <td style="text-align:right;"> 336 </td>
   <td style="text-align:right;"> 3.94 </td>
   <td style="text-align:right;"> 3.96 </td>
   <td style="text-align:right;"> 2.48 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.24 </td>
   <td style="text-align:left;"> Very Good </td>
   <td style="text-align:left;"> I </td>
   <td style="text-align:left;"> VVS1 </td>
   <td style="text-align:right;"> 62.3 </td>
   <td style="text-align:right;"> 57 </td>
   <td style="text-align:right;"> 336 </td>
   <td style="text-align:right;"> 3.95 </td>
   <td style="text-align:right;"> 3.98 </td>
   <td style="text-align:right;"> 2.47 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.26 </td>
   <td style="text-align:left;"> Very Good </td>
   <td style="text-align:left;"> H </td>
   <td style="text-align:left;"> SI1 </td>
   <td style="text-align:right;"> 61.9 </td>
   <td style="text-align:right;"> 55 </td>
   <td style="text-align:right;"> 337 </td>
   <td style="text-align:right;"> 4.07 </td>
   <td style="text-align:right;"> 4.11 </td>
   <td style="text-align:right;"> 2.53 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.22 </td>
   <td style="text-align:left;"> Fair </td>
   <td style="text-align:left;"> E </td>
   <td style="text-align:left;"> VS2 </td>
   <td style="text-align:right;"> 65.1 </td>
   <td style="text-align:right;"> 61 </td>
   <td style="text-align:right;"> 337 </td>
   <td style="text-align:right;"> 3.87 </td>
   <td style="text-align:right;"> 3.78 </td>
   <td style="text-align:right;"> 2.49 </td>
  </tr>
  <tr>
   <td style="text-align:right;"> 0.23 </td>
   <td style="text-align:left;"> Very Good </td>
   <td style="text-align:left;"> H </td>
   <td style="text-align:left;"> VS1 </td>
   <td style="text-align:right;"> 59.4 </td>
   <td style="text-align:right;"> 61 </td>
   <td style="text-align:right;"> 338 </td>
   <td style="text-align:right;"> 4.00 </td>
   <td style="text-align:right;"> 4.05 </td>
   <td style="text-align:right;"> 2.39 </td>
  </tr>
</tbody>
</table>

---
## group_by() and summarise()

```r
diamonds %>% 
  group_by(cut) %>% 
  summarise(Mean = mean(carat), Max = max(carat)) %>% 
  knitr::kable(format = 'html')
```

<table>
 <thead>
  <tr>
   <th style="text-align:left;"> cut </th>
   <th style="text-align:right;"> Mean </th>
   <th style="text-align:right;"> Max </th>
  </tr>
 </thead>
<tbody>
  <tr>
   <td style="text-align:left;"> Fair </td>
   <td style="text-align:right;"> 1.0461366 </td>
   <td style="text-align:right;"> 5.01 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Good </td>
   <td style="text-align:right;"> 0.8491847 </td>
   <td style="text-align:right;"> 3.01 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Very Good </td>
   <td style="text-align:right;"> 0.8063814 </td>
   <td style="text-align:right;"> 4.00 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Premium </td>
   <td style="text-align:right;"> 0.8919549 </td>
   <td style="text-align:right;"> 4.01 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Ideal </td>
   <td style="text-align:right;"> 0.7028370 </td>
   <td style="text-align:right;"> 3.50 </td>
  </tr>
</tbody>
</table>

---
## filter(), mutate(), arrange(), and select()

```r
diamonds %>%
  filter(x>0 & y>0 & z>0) %>%
  mutate(vol = x*y*z) %>%
  arrange(vol) %>%
  select(carat, cut, color, x, y, z, vol) %>%
  head %>% 
  knitr::kable(format = 'html')
```

---
## Use with {ggplot2}

```r
color_cut <- diamonds %>% 
  group_by(color, cut) %>%
  summarise(price = mean(price))

ggplot(color_cut, aes(x = color, y = price)) +
  geom_line(aes(group = cut), color = "grey80") +
  geom_point(aes(color = cut)) +
  theme_bw()
```

---

```r
diamonds_count <- diamonds %>% 
  group_by(color) %>%
  summarise(count = n())

ggplot() +
  geom_bar(data = diamonds, 
           aes(x = color, fill = color), color = "black") +
  geom_text(data = diamonds_count, 
            aes(label = count, x = color, y = count/2)) +
  theme_bw() +
  theme(axis.title.x = element_blank(), legend.position = "none") +
  labs(y = "Count")
```

---
## Tidy data

.center[
<img src="tidy.png" alt="Drawing" style="height: 240px;"/>
]

1. Each variable forms a column

2. Each observation forms a row

3. Each type of observational unit forms a table

---
##Messy data

.center[
<img src="messydata.png" alt="Drawing" style="height: 490px;"/>
]

---
## Grades dataset

```r
set.seed(1)

Name <- c("Jasmine", "Kate", "Mike", "Peter", "Thomas")
Test1 <- rnorm(n = 5, mean = c(11, 15, 16, 10, 8), sd = 2) %>% round
Test2 <- rnorm(n = 5, mean = c(11, 15, 16, 10, 8), sd = 2) %>% round
Test3 <- rnorm(n = 5, mean = c(11, 15, 16, 10, 8), sd = 2) %>% round
Test4 <- rnorm(n = 5, mean = c(11, 15, 16, 10, 8), sd = 2) %>% round
Test5 <- rnorm(n = 5, mean = c(11, 15, 16, 10, 8), sd = 2) %>% round

grades <- data.frame(Name, Test1, Test2, Test3, Test4, Test5)
```

<table>
 <thead>
  <tr>
   <th style="text-align:left;"> Name </th>
   <th style="text-align:right;"> Test1 </th>
   <th style="text-align:right;"> Test2 </th>
   <th style="text-align:right;"> Test3 </th>
   <th style="text-align:right;"> Test4 </th>
   <th style="text-align:right;"> Test5 </th>
  </tr>
 </thead>
<tbody>
  <tr>
   <td style="text-align:left;"> Jasmine </td>
   <td style="text-align:right;"> 10 </td>
   <td style="text-align:right;"> 9 </td>
   <td style="text-align:right;"> 14 </td>
   <td style="text-align:right;"> 11 </td>
   <td style="text-align:right;"> 13 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Kate </td>
   <td style="text-align:right;"> 15 </td>
   <td style="text-align:right;"> 16 </td>
   <td style="text-align:right;"> 16 </td>
   <td style="text-align:right;"> 15 </td>
   <td style="text-align:right;"> 17 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Mike </td>
   <td style="text-align:right;"> 14 </td>
   <td style="text-align:right;"> 17 </td>
   <td style="text-align:right;"> 15 </td>
   <td style="text-align:right;"> 18 </td>
   <td style="text-align:right;"> 16 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Peter </td>
   <td style="text-align:right;"> 13 </td>
   <td style="text-align:right;"> 11 </td>
   <td style="text-align:right;"> 6 </td>
   <td style="text-align:right;"> 12 </td>
   <td style="text-align:right;"> 6 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Thomas </td>
   <td style="text-align:right;"> 9 </td>
   <td style="text-align:right;"> 7 </td>
   <td style="text-align:right;"> 10 </td>
   <td style="text-align:right;"> 9 </td>
   <td style="text-align:right;"> 9 </td>
  </tr>
</tbody>
</table>

---
## Tidy datasets with {tidyr}

```r
grades_gather <- grades %>% 
  gather(key = Test, value = Grade, -Name)
```

<div id="htmlwidget-dc703e12195084a968e9" style="width:100%;height:auto;" class="datatables html-widget"></div>
<script type="application/json" data-for="htmlwidget-dc703e12195084a968e9">{"x":{"filter":"none","fillContainer":false,"data":[["1","2","3","4","5","6","7","8","9","10","11","12","13","14","15","16","17","18","19","20","21","22","23","24","25"],["Jasmine","Kate","Mike","Peter","Thomas","Jasmine","Kate","Mike","Peter","Thomas","Jasmine","Kate","Mike","Peter","Thomas","Jasmine","Kate","Mike","Peter","Thomas","Jasmine","Kate","Mike","Peter","Thomas"],["Test1","Test1","Test1","Test1","Test1","Test2","Test2","Test2","Test2","Test2","Test3","Test3","Test3","Test3","Test3","Test4","Test4","Test4","Test4","Test4","Test5","Test5","Test5","Test5","Test5"],[10,15,14,13,9,9,16,17,11,7,14,16,15,6,10,11,15,18,12,9,13,17,16,6,9]],"container":"<table class=\"display\">\n  <thead>\n    <tr>\n      <th> <\/th>\n      <th>Name<\/th>\n      <th>Test<\/th>\n      <th>Grade<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":7,"columnDefs":[{"className":"dt-right","targets":3},{"orderable":false,"targets":0}],"order":[],"autoWidth":false,"orderClasses":false,"lengthMenu":[7,10,25,50,100]}},"evals":[],"jsHooks":[]}</script>

---

```r
ggplot(grades_gather) +
  geom_bar(aes(x = Test, y = Grade, fill = Name), 
           color = "black", stat = "identity") +
  facet_grid(.~Name) +
  guides(fill = FALSE) + 
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))
```

---
class: middle, center, inverse
#Practice makes perfect

---
##Glucose dataset

```r
Glucose <- read.table("Glucose.txt")
```

<div id="htmlwidget-3e12195084a968e94b75" style="width:100%;height:auto;" class="datatables html-widget"></div>
<script type="application/json" data-for="htmlwidget-3e12195084a968e94b75">{"x":{"filter":"none","fillContainer":false,"data":[["1","2","3","4","5","6","7","8","9","10","11","12","13","14","15","16","17","18","19","20","21","22","23","24","25","26","27","28","29","30","31","32","33","34","35","36","37","38","39","40","41","42","43","44","45","46","47","48","49","50","51","52","53","54","55","56","57","58","59","60","61","62","63","64","65","66","67","68","69","70","71","72","73","74","75","76","77","78","79","80","81","82","83","84","85","86","87","88","89","90","91","92","93","94","95","96","97","98","99","100","101","102","103","104","105","106","107","108","109","110","111","112","113","114","115","116","117","118","119","120","121","122","123","124","125","126","127","128","129","130","131","132","133","134","135","136","137","138","139","140","141","142","143","144","145","146","147","148","149","150","151","152","153","154","155","156","157","158","159","160","161","162","163","164","165","166","167","168","169","170","171","172","173","174","175","176","177","178","179","180","181","182","183","184","185","186","187","188","189","190","191","192","193","194","195","196","197","198","199","200","201","202","203","204","205","206","207","208","209","210","211","212","213","214","215","216","217","218","219","220","221","222","223","224","225","226","227","228","229","230","231","232","233","234","235","236","237","238","239","240","241","242","243","244","245","246","247","248","249","250","251","252","253","254","255","256","257","258","259","260","261","262","263","264","265","266","267","268","269","270","271","272","273","274","275","276","277","278","279","280","281","282","283","284","285","286","287","288","289","290","291","292","293","294","295","296","297","298","299","300","301","302","303","304","305","306","307","308","309","310","311","312","313","314","315","316","317","318","319","320","321","322","323","324","325","326","327","328","329","330","331","332","333","334","335","336","337","338","339","340","341","342","343","344","345","346","347","348","349","350","351","352","353","354","355","356","357","358","359","360","361","362","363","364","365","366","367","368","369","370","371","372","373","374","375","376","377","378"],[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6],[-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,-0.25,0,0.5,1,1.5,2,3,4,5,6,7,-0.25,0,0.5,1,1.5,2,3,4,5,6,7],[4.9,4.5,7.84,5.46,5.08,4.32,3.91,3.99,4.15,4.41,4.91,4.18,9,9.74,6.95,6.92,4.66,3.45,4.2,4.63,4.22,4.92,8.09,6.74,4.3,4.28,4.59,4.49,5.29,4.95,4.34,4.05,3.78,8.71,7.12,6.17,4.22,4.31,3.15,3.64,3.88,5.03,4.99,9.1,10.03,9.2,8.31,7.92,4.86,4.63,3.52,4.17,4.6,4.72,9.53,10.02,10.25,9.29,5.45,4.82,4.09,3.52,3.92,4.61,4.65,7.9,6.13,4.45,4.17,4.96,4.36,4.26,4.13,4.16,3.42,7.09,6.98,6.13,5.36,6.13,3.67,4.37,4.31,4.52,4.22,8.46,9.12,7.5,6.02,4.66,4.69,4.26,4.29,4.47,3.94,4.14,7.82,8.68,6.22,5.1,5.16,4.38,4.22,4.27,4.51,4.5,8.74,8.8,7.1,8.2,7.42,5.79,4.85,4.94,2.07,4.33,4.1,4.36,6.92,9.06,8.11,5.69,5.91,5.65,4.58,3.79,5.37,5.35,7.94,5.64,5.06,5.49,4.77,4.48,4.39,4.45,4.95,4.4,7,7.8,7.78,7.3,5.82,5.14,3.59,4,4.47,4.47,7.95,7.21,6.35,5.58,4.57,3.9,3.44,4.18,4.32,4.19,4.22,7.45,8.07,6.84,6.86,4.79,3.87,3.6,4.92,4.87,5.12,6.32,9.48,9.88,6.28,5.58,5.26,4.1,4.25,4.55,4.42,4.07,5.48,9.05,8.04,7.19,4.87,5.4,4.35,4.51,4.66,5.1,5.22,7.2,4.95,4.45,3.88,3.65,4.21,null,4.44,3.82,4,6.56,6.48,5.66,7.74,4.45,4.07,3.73,3.58,4.27,4.33,6.61,6.89,5.64,4.85,4.82,3.82,4.31,3.81,2.92,4.31,4.45,7.34,6.75,7.55,6.42,5.75,4.56,4.3,3.92,4.55,4.44,5.56,8.39,7.85,7.4,6.23,4.59,4.31,3.96,4.05,4.38,4.54,8.86,10.01,10.47,9.91,6.11,4.37,3.38,4.02,3.84,5.34,4.91,5.69,8.21,2.97,4.3,4.18,4.93,5.16,5.54,3.76,4.7,6.76,4.98,5.02,5.95,4.9,4.79,5.25,5.42,4.81,4.85,6.08,8.28,5.73,5.68,4.66,4.62,4.85,4.69,4.86,4.3,4.71,7.44,7.08,6.3,6.5,4.5,4.36,4.83,4.5,4.79,4.82,9.29,8.99,8.15,5.71,5.24,4.95,5.06,5.24,4.74,5.06,5.04,8.86,9.97,8.45,6.58,4.74,4.28,4.04,4.34,4.35,5.24,5.04,8.72,4.85,5.57,6.33,4.81,4.55,4.48,5.15,4.13,3.95,5.53,8.55,7.09,5.34,5.56,4.23,3.95,4.29,4.61,4.68,6.01,7.35,6.38,6.16,4.41,4.96,4.33,4.54,4.81,4.45,4.12,7.14,5.68,6.07,5.96,5.2,4.83,4.5,4.71,4.33,4.48,8.06,8.49,4.5,7.15,5.91,4.27,4.78,null,5.72,4.43,4.75,6.95,6.64,7.72,7.03,6.38,5.17,4.71,5.14,5.19],["10am","10am","10am","10am","10am","10am","10am","10am","10am","10am","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10am","10am","10am","10am","10am","10am","10am","10am","10am","10am","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10am","10am","10am","10am","10am","10am","10am","10am","10am","10am","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10am","10am","10am","10am","10am","10am","10am","10am","10am","10am","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10am","10am","10am","10am","10am","10am","10am","10am","10am","10am","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10am","10am","10am","10am","10am","10am","10am","10am","10am","10am","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","2pm","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6am","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","6pm","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","2am","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm","10pm"]],"container":"<table class=\"display\">\n  <thead>\n    <tr>\n      <th> <\/th>\n      <th>Subject<\/th>\n      <th>Time<\/th>\n      <th>conc<\/th>\n      <th>Meal<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":7,"columnDefs":[{"className":"dt-right","targets":[1,2,3]},{"orderable":false,"targets":0}],"order":[],"autoWidth":false,"orderClasses":false,"lengthMenu":[7,10,25,50,100]}},"evals":[],"jsHooks":[]}</script>

---

---

```r
Glucose %>%
  mutate(Subject = as.factor(Subject)) %>%
  ggplot(aes(Time, conc, color = Subject)) + 
    geom_point() + 
    geom_line() + 
    facet_wrap(~Meal) +
    theme_bw() +
    labs(x = "Time", y = "Concentration")
```

---
<img src="index_files/figure-html/glucose4-1.svg" style="display: block; margin: auto;" />

---

```r
Glucose_stat <- Glucose %>%
  group_by(Time) %>%
  summarise(mean = mean(conc, na.rm = TRUE), median = median(conc, na.rm = TRUE),
            q5 = quantile(conc, probs = 0.05, na.rm = TRUE),
            q95 = quantile(conc, probs = 0.95, na.rm = TRUE))

ggplot(Glucose_stat, aes(x = Time)) +
  geom_errorbar(aes(ymin = q5, ymax = q95)) +
  geom_line(aes(y = mean), color = "blue") +
  geom_point(aes(y = median), color = "red", size = 5) +
  scale_x_continuous(breaks = c(-0.25, 0, 0.5, 1, 1.5, 2, 3, 4, 5, 6, 7)) +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(y = "Concentration", title = "Summary of Concentration over time",
       caption = "5th and 95th percentile are in black, median is in red and mean in blue.")
```

---
## Pokemon dataset

```r
Pokemon <- read.table("Pokemon.txt")
Pokemon %<>% mutate(Generation = as.factor(Generation))
```

<table>
 <thead>
  <tr>
   <th style="text-align:left;"> Name </th>
   <th style="text-align:left;"> Type.1 </th>
   <th style="text-align:left;"> Type.2 </th>
   <th style="text-align:right;"> Total </th>
   <th style="text-align:right;"> HP </th>
   <th style="text-align:right;"> Attack </th>
   <th style="text-align:left;"> Generation </th>
   <th style="text-align:left;"> Legendary </th>
  </tr>
 </thead>
<tbody>
  <tr>
   <td style="text-align:left;"> Bulbasaur </td>
   <td style="text-align:left;"> Grass </td>
   <td style="text-align:left;"> Poison </td>
   <td style="text-align:right;"> 318 </td>
   <td style="text-align:right;"> 45 </td>
   <td style="text-align:right;"> 49 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Ivysaur </td>
   <td style="text-align:left;"> Grass </td>
   <td style="text-align:left;"> Poison </td>
   <td style="text-align:right;"> 405 </td>
   <td style="text-align:right;"> 60 </td>
   <td style="text-align:right;"> 62 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Venusaur </td>
   <td style="text-align:left;"> Grass </td>
   <td style="text-align:left;"> Poison </td>
   <td style="text-align:right;"> 525 </td>
   <td style="text-align:right;"> 80 </td>
   <td style="text-align:right;"> 82 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> VenusaurMega Venusaur </td>
   <td style="text-align:left;"> Grass </td>
   <td style="text-align:left;"> Poison </td>
   <td style="text-align:right;"> 625 </td>
   <td style="text-align:right;"> 80 </td>
   <td style="text-align:right;"> 100 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Charmander </td>
   <td style="text-align:left;"> Fire </td>
   <td style="text-align:left;"> NA </td>
   <td style="text-align:right;"> 309 </td>
   <td style="text-align:right;"> 39 </td>
   <td style="text-align:right;"> 52 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Charmeleon </td>
   <td style="text-align:left;"> Fire </td>
   <td style="text-align:left;"> NA </td>
   <td style="text-align:right;"> 405 </td>
   <td style="text-align:right;"> 58 </td>
   <td style="text-align:right;"> 64 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> Charizard </td>
   <td style="text-align:left;"> Fire </td>
   <td style="text-align:left;"> Flying </td>
   <td style="text-align:right;"> 534 </td>
   <td style="text-align:right;"> 78 </td>
   <td style="text-align:right;"> 84 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
  <tr>
   <td style="text-align:left;"> CharizardMega Charizard X </td>
   <td style="text-align:left;"> Fire </td>
   <td style="text-align:left;"> Dragon </td>
   <td style="text-align:right;"> 634 </td>
   <td style="text-align:right;"> 78 </td>
   <td style="text-align:right;"> 130 </td>
   <td style="text-align:left;"> 1 </td>
   <td style="text-align:left;"> FALSE </td>
  </tr>
</tbody>
</table>

---

---

```r
ggplot(Pokemon, aes(x = Generation, y = Total, fill = Generation)) + 
  geom_violin(aes(fill = Generation)) +
  geom_boxplot(alpha = 0) +
  geom_jitter(width = 0.3) +
  scale_fill_discrete(guide = FALSE) +
  labs(x = "Generation", y = "Total statistics") +
  theme_bw()
```

---

---

```r
Pokemon_poison <- Pokemon %>%
  filter(Type.1 == "Poison" | Type.2 == "Poison") %>%
  arrange(desc(Total))

ggplot(Pokemon_poison, aes(x = Attack, y = Sp..Atk)) +
  geom_smooth(method = "lm", color = "purple") +
  geom_point(color = "purple") +
  geom_text(aes(label = Name), check_overlap = TRUE) +
  theme_bw() +
  labs(y = "Special attack")
```

---

---

```r
ggplot(Pokemon, aes(x = 1, fill = Legendary)) + 
  geom_bar(position = "stack") +
  coord_polar(theta = "y") +
  theme_void() +
  labs(x = NULL, y = NULL)
```

---

---

```r
pkmn_total_summary <- Pokemon %>% 
  group_by(Generation) %>%
  summarise(Mean = mean(Total), Median = median(Total),
            q25 = quantile(Total, 0.25), q75 = quantile(Total, 0.75)) %>%
  gather(key = Statistic, value = Value, -Generation)

ggplot() + 
  geom_histogram(data = Pokemon, aes(x = Total, fill = Generation), 
                 bins = 80, col = "black") +
  geom_vline(data = pkmn_total_summary, 
             aes(xintercept = Value, linetype = Statistic)) +
  facet_grid(Generation~., scales = "free_y") +
  guides(fill = FALSE) +
  labs(x = "Total statistics", y = "Count") +
  theme_bw()
```

---
class: middle, center, inverse
# Going further and references

---
### ggplot2

* ggplot2: Elegant Graphics for Data Analysis (Hadley Wickham)

* [**R User Grenoble presentation**](https://privefl.github.io/R-presentation/ggplot2.html)

### Tidy data

* [**Tidy data**](http://tidyr.tidyverse.org/articles/tidy-data.html)

* [**Messy data**](https://medium.com/@miles.mcbain/tidying-the-australian-same-sex-marriage-postal-survey-data-with-r-5d35cea07962)

### Visualisation

* [**The Worst Chart In The World**](http://www.businessinsider.fr/us/pie-charts-are-the-worst-2013-6/)

---
class: center, middle, inverse

# Thanks for your attention :)

<a href="mailto:antoine.bichat@mines-nancy.org">antoine.bichat@mines-nancy.org</a>

.footnote[Slides created via the R package [**xaringan**](https://github.com/yihui/xaringan).]