The Tidyverse, Part 2

# The Tidyverse, Part 2
## “R is not in some far-off place.”
### Otho Mantegazza<br>2019-11-20

---

---

```r
*squirrels_tidy
```
]
.pull-right-reveal[

```
## # A tibble: 3,023 x 36
##     long   lat unique_squirrel… hectare shift
##    <dbl> <dbl> <chr>            <chr>   <chr>
##  1 -74.0  40.8 37F-PM-1014-03   37F     PM   
##  2 -74.0  40.8 37E-PM-1006-03   37E     PM   
##  3 -74.0  40.8 2E-AM-1010-03    02E     AM   
##  4 -74.0  40.8 5D-PM-1018-05    05D     PM   
##  5 -74.0  40.8 39B-AM-1018-01   39B     AM   
##  6 -74.0  40.8 33H-AM-1019-02   33H     AM   
##  7 -74.0  40.8 6G-PM-1020-02    06G     PM   
##  8 -74.0  40.8 35C-PM-1013-03   35C     PM   
##  9 -74.0  40.8 7B-AM-1008-09    07B     AM   
## 10 -74.0  40.8 32E-PM-1017-14   32E     PM   
## # … with 3,013 more rows, and 31 more variables:
## #   date <date>, hectare_squirrel_number <dbl>,
## #   age <chr>, primary_fur_color <chr>,
## #   highlight_fur_color <chr>,
## #   combination_of_primary_and_highlight_color <chr>,
## #   color_notes <chr>, location <chr>, height <dbl>,
## #   specific_location <chr>, running <lgl>,
## #   chasing <lgl>, climbing <lgl>, eating <lgl>,
## #   foraging <lgl>, other_activities <chr>,
## #   kuks <lgl>, quaas <lgl>, moans <lgl>,
## #   tail_flags <lgl>, …
```
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
* drop_na(height)
```
]
.pull-right-reveal[

```
## # A tibble: 2,909 x 36
##     long   lat unique_squirrel… hectare shift
##    <dbl> <dbl> <chr>            <chr>   <chr>
##  1 -74.0  40.8 37E-PM-1006-03   37E     PM   
##  2 -74.0  40.8 2E-AM-1010-03    02E     AM   
##  3 -74.0  40.8 5D-PM-1018-05    05D     PM   
##  4 -74.0  40.8 33H-AM-1019-02   33H     AM   
##  5 -74.0  40.8 6G-PM-1020-02    06G     PM   
##  6 -74.0  40.8 35C-PM-1013-03   35C     PM   
##  7 -74.0  40.8 7B-AM-1008-09    07B     AM   
##  8 -74.0  40.8 36H-AM-1010-02   36H     AM   
##  9 -74.0  40.8 33F-AM-1008-02   33F     AM   
## 10 -74.0  40.8 21C-PM-1006-01   21C     PM   
## # … with 2,899 more rows, and 31 more variables:
## #   date <date>, hectare_squirrel_number <dbl>,
## #   age <chr>, primary_fur_color <chr>,
## #   highlight_fur_color <chr>,
## #   combination_of_primary_and_highlight_color <chr>,
## #   color_notes <chr>, location <chr>, height <dbl>,
## #   specific_location <chr>, running <lgl>,
## #   chasing <lgl>, climbing <lgl>, eating <lgl>,
## #   foraging <lgl>, other_activities <chr>,
## #   kuks <lgl>, quaas <lgl>, moans <lgl>,
## #   tail_flags <lgl>, …
```
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
* ggplot(aes(x = age,
*            y = height))
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_4-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
* geom_point()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_5-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_point() +  
* geom_boxplot()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_6-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_point() +  
  geom_boxplot() +  
* labs(title = "Height Above Ground of Squirrels by Age",
*      y = "Feet from Ground",
*      caption = "Data from data.cityofnewyork.us")
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_9-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_point() +  
  geom_boxplot() +  
  labs(title = "Height Above Ground of Squirrels by Age",  
       y = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
* theme_gray(base_size = 18)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_10-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_point() +  
  geom_boxplot() +  
  labs(title = "Height Above Ground of Squirrels by Age",  
       y = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  theme_gray(base_size = 18) +  
* coord_flip()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_11-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_point() +  
  geom_boxplot() +  
  labs(title = "Height Above Ground of Squirrels by Age",  
       y = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  theme_gray(base_size = 18) +  
  coord_flip() +  
* scale_y_sqrt()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-height-boxplot_12-1.svg)
]

---

```r
*squirrels_tidy
```
]
.pull-right-reveal[

```r
squirrels_tidy %>%  
* drop_na(height)
```
]
.pull-right-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
* filter(height > 0)
```
]
.pull-right-reveal[

```
## # A tibble: 792 x 36
##     long   lat unique_squirrel… hectare shift
##    <dbl> <dbl> <chr>            <chr>   <chr>
##  1 -74.0  40.8 2E-AM-1010-03    02E     AM   
##  2 -74.0  40.8 5D-PM-1018-05    05D     PM   
##  3 -74.0  40.8 11D-AM-1010-03   11D     AM   
##  4 -74.0  40.8 7H-AM-1006-05    07H     AM   
##  5 -74.0  40.8 16C-PM-1018-03   16C     PM   
##  6 -74.0  40.8 17F-AM-1007-07   17F     AM   
##  7 -74.0  40.8 18A-PM-1018-01   18A     PM   
##  8 -74.0  40.8 31H-PM-1008-02   31H     PM   
##  9 -74.0  40.8 8H-AM-1017-06    08H     AM   
## 10 -74.0  40.8 34F-AM-1007-01   34F     AM   
## # … with 782 more rows, and 31 more variables:
## #   date <date>, hectare_squirrel_number <dbl>,
## #   age <chr>, primary_fur_color <chr>,
## #   highlight_fur_color <chr>,
## #   combination_of_primary_and_highlight_color <chr>,
## #   color_notes <chr>, location <chr>, height <dbl>,
## #   specific_location <chr>, running <lgl>,
## #   chasing <lgl>, climbing <lgl>, eating <lgl>,
## #   foraging <lgl>, other_activities <chr>,
## #   kuks <lgl>, quaas <lgl>, moans <lgl>,
## #   tail_flags <lgl>, …
```
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
* ggplot(aes(x = age,
*            y = height))
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_5-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
* geom_quasirandom()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_6-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_quasirandom() +  
* theme_gray(base_size = 18)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_7-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_quasirandom() +  
  theme_gray(base_size = 18) +  
* labs(title = "Height Above Ground of Squirrels by Age",
*      y = "Feet from Ground",
*      caption = "Data from data.cityofnewyork.us")
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_10-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_quasirandom() +  
  theme_gray(base_size = 18) +  
  labs(title = "Height Above Ground of Squirrels by Age",  
       y = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
* coord_flip()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_11-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_quasirandom() +  
  theme_gray(base_size = 18) +  
  labs(title = "Height Above Ground of Squirrels by Age",  
       y = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  coord_flip() +  
* scale_y_sqrt()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_12-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = age,  
             y = height)) +  
  geom_quasirandom() +  
  theme_gray(base_size = 18) +  
  labs(title = "Height Above Ground of Squirrels by Age",  
       y = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  coord_flip() +  
  scale_y_sqrt() +  
* stat_summary(fun.y = "median",
*              geom = "point",
*              size = 10,
*              alpha = .9,
*              colour = "#FF6C0D")
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-beeswarm_17-1.svg)
]

---

```r
*squirrels_tidy
```
]
.pull-right-reveal[

```r
squirrels_tidy %>%  
* drop_na(height)
```
]
.pull-right-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
* filter(height > 0)
```
]
.pull-right-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
* ggplot(aes(x = height))
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_4-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = height)) +  
* geom_density(fill = "grey40",
*              alpha = .6,
*              adjust = 1/2)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_7-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = height)) +  
  geom_density(fill = "grey40",  
               alpha = .6,  
               adjust = 1/2) +  
*   labs(title = "Height Above Ground of Squirrels by Age",
*      x = "Feet from Ground",
*      caption = "Data from data.cityofnewyork.us")
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_10-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = height)) +  
  geom_density(fill = "grey40",  
               alpha = .6,  
               adjust = 1/2) +  
    labs(title = "Height Above Ground of Squirrels by Age",  
       x = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
* theme_bw(base_size = 18)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_11-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = height)) +  
  geom_density(fill = "grey40",  
               alpha = .6,  
               adjust = 1/2) +  
    labs(title = "Height Above Ground of Squirrels by Age",  
       x = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  theme_bw(base_size = 18) +  
* facet_grid(age ~ .)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_12-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = height)) +  
  geom_density(fill = "grey40",  
               alpha = .6,  
               adjust = 1/2) +  
    labs(title = "Height Above Ground of Squirrels by Age",  
       x = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  theme_bw(base_size = 18) +  
  facet_grid(age ~ .) +  
* stat_sum(
*   aes(y =  -.005,
*       size = 1,
*       colour = ..n..,
*       label = "|"),
*   geom = "text",
*   fontface = "bold",
*   show.legend = F)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_20-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  drop_na(height) %>%  
  filter(height > 0) %>%  
  ggplot(aes(x = height)) +  
  geom_density(fill = "grey40",  
               alpha = .6,  
               adjust = 1/2) +  
    labs(title = "Height Above Ground of Squirrels by Age",  
       x = "Feet from Ground",  
       caption = "Data from data.cityofnewyork.us") +  
  theme_bw(base_size = 18) +  
  facet_grid(age ~ .) +  
  stat_sum(  
    aes(y =  -.005,  
        size = 1,  
        colour = ..n..,  
        label = "|"),  
    geom = "text",  
    fontface = "bold",  
    show.legend = F) +  
* scale_colour_viridis_c()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrel-histogram_21-1.svg)
]

---

# GGPLOT2 for Data Visualization

GGPLOT2 is a library for graphical representation of Data.

- It is widely developed, you can use it to plot almost anything,
- It is based on the Layered Grammar of Graphics,
- It's designed both for exploratory viz and for communiacation

To get used to ggplot you must think in a layered way.

]
]

</p>
<a href="https://ggplot2.tidyverse.org" class="imagelink">
<img src="img/SVG/ggplot2.svg" alt="hex-ggplot" height="445" width="400"></a>
<p>

]
]

---

![](img/grammar-of-graphics.png)

Image credits: [@dgkeyes](https://twitter.com/dgkeyes), https://rfortherestofus.com/ . Found through [@W_R_Chase](https://twitter.com/W_R_Chase)

---

# The Grammar of Graphics

You map **data**...

1. to **Aesthetic** properties of objects,
2. according **Scale**, placed on **Coordinates**
3. Those objects are represented by **Geometric Shapes**.
4. You might need to use **statistical** transformations, to highlight those properties,
5. You might want to use **Facets** to represent multiple dimentions

---

Show the number of squirrels by their primary and highlight fur colour in a barchart.

- Map the **highlight fur colour** to the **x axis**. Can you make the x axis vertical?

- Map the **primary fur colour** to the **fill aesthetic** of the bars. Can you map them to to their real colours?

- What are you mapping to the y axis, can you order the bars by their height?
 
]

---

Use an histogram to visualize how are the black squirrels distributed along the longitude variable.

- If you map the longitude on the x axis, which variable are you mapping on the y axis?

- Are you using a statistical transformation?

]

---

Can you show where are the squirrels with a scatterplot?

- Map the **longitude** to the **x axis** and the **latitude** to the **y axis**.

- Map the colour of the points to the real fur colour of the squirrels.

- Can you also split the fur colours in facets?

- How can you avoid overplotting? Can you bin the squirrel position on the x and y axis?

]

---

```r
*squirrels_tidy
```
]
.pull-right-reveal[

```r
squirrels_tidy %>%  
* ggplot(aes(x = long,
*            y = lat))
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrels-geo_3-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  ggplot(aes(x = long,  
             y = lat)) +  
* geom_point(alpha = .1)
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrels-geo_4-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  ggplot(aes(x = long,  
             y = lat)) +  
  geom_point(alpha = .1) +  
* geom_hex(colour = "#FFFFFF",
*          size = .2,
*          binwidth = c(.0015,
*                       .001))
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrels-geo_8-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  ggplot(aes(x = long,  
             y = lat)) +  
  geom_point(alpha = .1) +  
  geom_hex(colour = "#FFFFFF",  
           size = .2,  
           binwidth = c(.0015,  
                        .001)) +  
* coord_quickmap()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrels-geo_9-1.svg)
]
---
count: false
.pull-left-reveal[

```r
squirrels_tidy %>%  
  ggplot(aes(x = long,  
             y = lat)) +  
  geom_point(alpha = .1) +  
  geom_hex(colour = "#FFFFFF",  
           size = .2,  
           binwidth = c(.0015,  
                        .001)) +  
  coord_quickmap() +  
* theme_bw()
```
]
.pull-right-reveal[
![](03-intro-to-the-tidyverse_files/figure-html/output_squirrels-geo_10-1.svg)
]