HEGP
/
dataviz

<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">
  <head>
    <title>Lab 07 - Données temporelles et textuelles</title>
    <meta charset="utf-8" />
    <meta name="author" content="Antoine Neuraz" />
    <link href="libs/remark-css-0.0.1/default.css" rel="stylesheet" />
    <link rel="stylesheet" href="css/my_style.css" type="text/css" />
  </head>
  <body>
    <textarea id="source">


## TODO

#### 1. charger le dataset `us_city_populations` de la librairie `vizoR`

#### 2. tracer un line chart de l'évolution de la population des villes US

#### 3. Mettez en évidence les 5 plus grandes villes (hint: package gghighlight)
[introduction gghighlight](https://cran.r-project.org/web/packages/gghighlight/vignettes/gghighlight.html)

#### 4. Appliquez les principes de design de Tufte 

##### 5. BONUS: affichez le nom des villes directement à la fin de la ligne

#### 6. Réalisez un streamgraph des 5 plus grandes villes US (hint: package ggTimeSeries)

---

## TODO 2

#### Trouver une 3e visualization pertinente pour montrer l'évolution de la population des villes US. 

---


```r
data("us_city_populations")

n_cities = 5

last_ranks &lt;- us_city_populations %&gt;% 
  filter(Year == max(Year)) %&gt;%
  mutate(last_rank = Rank) %&gt;% 
  select(City, last_rank)

to_plot &lt;- left_join(us_city_populations, last_ranks, by= 'City') 

right_axis &lt;-  to_plot %&gt;% 
  group_by(City) %&gt;% 
  top_n(1, Year) %&gt;% 
  ungroup() %&gt;%
  top_n(n_cities, -last_rank)

ends &lt;- right_axis %&gt;%
  pull(Population) 

labels &lt;-  right_axis %&gt;%
  pull(City)
```

---
class: full

```r
p &lt;- ggplot(to_plot, aes(x=Year, y = Population, 
                         group = City, color = City)) + 
  geom_line(size=1) + 
  scale_x_continuous("", expand=c(0,0))+
  scale_y_continuous("",
                     labels=scales::comma_format(big.mark = " "),
                     sec.axis = sec_axis(~ ., 
                                         breaks = ends, 
                                         labels = labels ))+
  scale_color_viridis_d()+
  theme_elegant_dark()+
  theme(legend.position = "none",
        plot.margin = unit(c(1,3,1,1), "lines"), 
        axis.line.y = element_blank(),
        axis.line.x = element_blank(), 
        axis.ticks.x = element_line(), 
        panel.grid.major.y = element_line(color= 'grey30', size = .2) ) + 
  gghighlight(max(last_rank) &lt;= n_cities, 
              use_direct_label = FALSE, 
              label_key = City,
              unhighlighted_colour = "grey20")
```
---
class: full

```r
p
```

![](lab7-temporal_data_files/figure-html/unnamed-chunk-3-1.png)&lt;!-- --&gt;
---

class: full

```r
library(ggTimeSeries)
p &lt;- to_plot %&gt;% filter(City %in% labels) %&gt;%
  ggplot(aes(x = Year, y = Population, group = City, fill = City)) +
  scale_y_continuous("", labels = scales::comma_format(big.mark = " "))+
  stat_steamgraph() +
  theme_elegant_dark() + 
  scale_fill_viridis_d() + 
  theme(plot.margin = unit(c(1,3,1,1), "lines"), 
        axis.line.y = element_blank(),
        axis.line.x = element_blank(), 
        axis.ticks.x = element_line(), 
        panel.grid.major.y = element_line(color= 'grey30', size = .2) ) 
```

---
class: full 

```r
p
```

![](lab7-temporal_data_files/figure-html/unnamed-chunk-5-1.png)&lt;!-- --&gt;
---
class: inverse, center, middle
# Barchart race

---
## Load data

```r
data("us_city_populations")

n_cities = 10
 
top_cities &lt;-us_city_populations %&gt;% filter(Rank &lt;= n_cities) %&gt;%
  select(City, State, Region) %&gt;% distinct()
```

---
## Create all missing dates

```r
# create a data frame with all the years between min and max Year
all_years &lt;- data.frame(Year = seq(min(us_city_populations$Year), 
                                   max(us_city_populations$Year), 1))

# combine top_cities and all_years
all_combos &lt;- merge(top_cities, all_years, all = T)

# combine all_combos with the original dataset
res_interp &lt;- merge(us_city_populations, all_combos, all.y = T)
```

## Interpolate the Populations when missing (linear interpolation here)

```r
res_interp  &lt;- res_interp  %&gt;%
  group_by(City) %&gt;%
  mutate(Population=approx(Year,Population,Year)$y)
```

---
## Filter data

```r
to_plot &lt;- res_interp %&gt;%
  group_by(Year) %&gt;%
  arrange(-Population) %&gt;%
  mutate(Rank=row_number()) %&gt;%
  filter(Rank&lt;=n_cities)
```

---
## Ease transitions


```r
to_plot_trans &lt;- to_plot %&gt;%
  group_by(City) %&gt;%
  arrange(Year) %&gt;%
  mutate(lag_rank = lag(Rank, 1),
         change = ifelse(Rank &gt; lag(Rank, 1), 1, 0),
         change = ifelse(Rank &lt; lag(Rank, 1), -1, 0)) %&gt;%
  mutate(transition = ifelse(lead(change, 1) == -1, -.9, 0),
         transition = ifelse(lead(change,2) == -1, -.5, transition),
         transition = ifelse(lead(change,3) == -1, -.3, transition),
         transition = ifelse(lead(change, 1) == 1, .9, transition),
         transition = ifelse(lead(change,2) == 1, .5, transition),
         transition = ifelse(lead(change,3) == 1, .3, transition)) %&gt;%
  mutate(trans_rank = Rank + transition)
```


---
## Make the plot
.small[

```r
p &lt;- to_plot_trans %&gt;%
  ggplot(aes(x = -trans_rank,y = Population, group =City)) +
   geom_tile(aes(y = Population / 2, height = Population, fill = Region), 
             width = 0.9) +
  geom_text(aes(label = City), 
            hjust = "right", colour = "white", 
            fontface="bold", nudge_y = -100000) +
  geom_text(aes(label = scales::comma(Population,big.mark = ' ')), 
            hjust = "left", nudge_y = 100000, colour = "grey90") +
  coord_flip(clip="off") +
  hrbrthemes::scale_fill_ipsum() +
  scale_x_discrete("") +
  scale_y_continuous("",labels=scales::comma_format(big.mark = " ")) +
  theme_elegant_dark(base_size = 20) +
  theme(
    panel.grid.minor.x=element_blank(),
    axis.line = element_blank(),
    panel.grid.major= element_line(color='lightgrey', size=.2),
    legend.position = c(0.6, 0.2),
    plot.margin = margin(1,1,1,2,"cm"),
    plot.title = element_text(hjust = 0),
    axis.text.y=element_blank(),
    legend.text = element_text(size = 15),
    legend.background = element_blank()) +
  # gganimate code to transition by year:
  transition_time(Year) +
  ease_aes('cubic-in-out') +
  labs(title='Evolution des plus grandes villes US',
       subtitle='Population en {round(frame_time,0)}')
```
]
---

```r
animate(p, nframes = 400, fps = 25, end_pause = 30, width = 1200)
anim_save("bar_race.gif", animation = last_animation())
```

![:scale 80%](bar_race.gif)
    </textarea>
<style data-target="print-only">@media screen {.remark-slide-container{display:block;}.remark-slide-scaler{box-shadow:none;}}</style>
<script src="https://remarkjs.com/downloads/remark-latest.min.js"></script>
<script src="addons/macros.js"></script>
<script>var slideshow = remark.create({
"ratio": "4:3",
"countIncrementalSlides": false,
"self-contained": true
});
if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {
  window.dispatchEvent(new Event('resize'));
});
(function(d) {
  var s = d.createElement("style"), r = d.querySelector(".remark-slide-scaler");
  if (!r) return;
  s.type = "text/css"; s.innerHTML = "@page {size: " + r.style.width + " " + r.style.height +"; }";
  d.head.appendChild(s);
})(document);

(function(d) {
  var el = d.getElementsByClassName("remark-slides-area");
  if (!el) return;
  var slide, slides = slideshow.getSlides(), els = el[0].children;
  for (var i = 1; i < slides.length; i++) {
    slide = slides[i];
    if (slide.properties.continued === "true" || slide.properties.count === "false") {
      els[i - 1].className += ' has-continuation';
    }
  }
  var s = d.createElement("style");
  s.type = "text/css"; s.innerHTML = "@media print { .has-continuation { display: none; } }";
  d.head.appendChild(s);
})(document);
// delete the temporary CSS (for displaying all slides initially) when the user
// starts to view slides
(function() {
  var deleted = false;
  slideshow.on('beforeShowSlide', function(slide) {
    if (deleted) return;
    var sheets = document.styleSheets, node;
    for (var i = 0; i < sheets.length; i++) {
      node = sheets[i].ownerNode;
      if (node.dataset["target"] !== "print-only") continue;
      node.parentNode.removeChild(node);
    }
    deleted = true;
  });
})();</script>

<script>
(function() {
  var links = document.getElementsByTagName('a');
  for (var i = 0; i < links.length; i++) {
    if (/^(https?:)?\/\//.test(links[i].getAttribute('href'))) {
      links[i].target = '_blank';
    }
  }
})();
</script>

<script>
slideshow._releaseMath = function(el) {
  var i, text, code, codes = el.getElementsByTagName('code');
  for (i = 0; i < codes.length;) {
    code = codes[i];
    if (code.parentNode.tagName !== 'PRE' && code.childElementCount === 0) {
      text = code.textContent;
      if (/^\\\((.|\s)+\\\)$/.test(text) || /^\\\[(.|\s)+\\\]$/.test(text) ||
          /^\$\$(.|\s)+\$\$$/.test(text) ||
          /^\\begin\{([^}]+)\}(.|\s)+\\end\{[^}]+\}$/.test(text)) {
        code.outerHTML = code.innerHTML;  // remove <code></code>
        continue;
      }
    }
    i++;
  }
};
slideshow._releaseMath(document);
</script>
<!-- dynamically load mathjax for compatibility with self-contained -->
<script>
(function () {
  var script = document.createElement('script');
  script.type = 'text/javascript';
  script.src  = 'https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-MML-AM_CHTML';
  if (location.protocol !== 'file:' && /^https?:/.test(script.src))
    script.src  = script.src.replace(/^https?:/, '');
  document.getElementsByTagName('head')[0].appendChild(script);
})();
</script>
  </body>
</html>