Laboratorio Bio-demografico

class: center, middle, inverse, title-slide

# Laboratorio Bio-demografico
## Lezione 13 - Altre visualizzazioni
### Nicola Barban <br> Alma Mater Studiorum Università di Bologna <br> Dipartimento di Scienze Statistiche
### 16 Marzo 2021<br> <img src="../img/UniBo-Universita-di-Bologna.png" style="width:20.0%" />

---

# pacchetti usati in questa lezione

* `library(geofacet)`
* `library(ggplot2)`
* `library(treemapify)`
* `library(gapminder)`
* `library(tidyverse)`

---
# Geofaceting

![](https://ryanhafen.com/blog/geofacet/images/us_ranks.png)
---
# Why geofaceting?

* We can plot multiple variables or values per geographic entity – you can plot practically anything you can imagine inside each panel.
* We can use more effective visual encoding schemes than just color.

https://ryanhafen.com/blog/geofacet/
https://www.demographic-research.org/volumes/vol41/17/41-17.pdf

---
# Usare il comando source

```r
source("Incidenza_covid_regionale.R")
```
---
# Italy geofacet

```r
library(geofacet)
library(ggplot2)

head(italy_grid3)
```

```
##   row col code          name
## 1   1   1  VAL Valle d'Aosta
## 2   1   3  TRE        Trento
## 3   1   4  BLZ       Bolzano
## 4   2   1  PIE      Piemonte
## 5   2   2  LOM     Lombardia
## 6   2   3  VEN        Veneto
```
---

```r
ggplot(state_ranks, aes(variable, rank, fill = variable)) +
  geom_col() +
  coord_flip() +
  theme_bw() +
  facet_geo(~ state)
```

<img src="lezione13_files/figure-html/unnamed-chunk-3-1.png" width="50%" />
---
Prepariamo la griglia per la nostra visualizzazione

```r
italy_grid3 <- italy_grid3 %>% 
  mutate(area=code) %>% 
  mutate(area=recode(area, 
                      "EMI"= "EMR", "FRI"="FVG", "BLZ"="PAB", "TRE"="PAT", "VAL"="VDA"             ))
```
---

```r
plot_reg0+  facet_geo(~ area, grid = "italy_grid3", label ="name" )
```

---
# Visualizzare dati multidimensionali
www.mortality.org

```r
LT_ITA<-read_table2("LT_Italy.csv")
```
---
# Riclassifico gli intervalli per età

```r
breaks=c(0,2.5, seq(from=7, to=107, by=5),110)
ITA<-LT_ITA %>% 
  group_by(Year) %>% 
  mutate(age= breaks )
```
---
# visualizzo un anno solamente

```r
ITA_1872 <- ITA %>% 
  filter(Year==1872)
# Plot
ggplot(ITA_1872,aes(x=age, y=mx))+
  geom_line(col="darkred")+
  labs(title = "Mortalità 1872",
       x="age", y="tasso di mortalità")
```

<img src="lezione13_files/figure-html/unnamed-chunk-8-1.png" width="50%" />
---

```r
base0<-ggplot(ITA, aes(x=age, y=mx, group=Year))+
  geom_line(col="grey", alpha=0.2)+
  scale_y_log10()+
  theme_bw()
```
---

```r
base0+
  geom_line(data=subset(ITA,Year==1872), aes(col="1872"))+
   geom_line(data=subset(ITA,Year==1918), aes(col="1918"))+
  geom_line(data=subset(ITA,Year==2000), aes(col="2000"))+
labs(title = "Mortalità 1872-1918-2000",
     x="age", y="tasso di mortalità (log10)")+
  scale_color_manual("Anno",values=c("darkred","darkblue","darkgreen"),
                       label=c("1872", "1918", "2000"))
```

<img src="lezione13_files/figure-html/unnamed-chunk-10-1.png" width="50%" />
---

```r
base_e<-ggplot(ITA, aes(x=age, y=(ex), group=Year))+
  geom_line(col="grey", alpha=0.2)+theme_bw()
```
---

```r
base_e+
  geom_line(data=subset(ITA,Year==1872), aes(col="1872"))+
   geom_line(data=subset(ITA,Year==1918), aes(col="1918"))+
  geom_line(data=subset(ITA,Year==2000), aes(col="2000"))+
labs(title = "Aspettativa di vita 1872-1918-2000",
     x="age", y="aspettativa di vita")+
  scale_color_manual("Anno",values=c("darkred","darkblue","darkgreen"),
                       label=c("1872", "1918", "2000"))
```

<img src="lezione13_files/figure-html/unnamed-chunk-12-1.png" width="50%" />
---

# Contour plot

```r
v<- ITA %>% 
  ggplot(aes(y=age, x=Year, z=log10(mx*10^5)))
 v+  geom_contour()
```

<img src="lezione13_files/figure-html/unnamed-chunk-13-1.png" width="50%" />
---
# Contour filled

```r
 V<-v+ geom_contour_filled( show.legend = NA)+
     ggtitle("Probabilità di morte per età e anno")+
    labs(subtitle="Italia", caption="Human mortality database (https://www.mortality.org)")+ labs(fill = "Tassi di mortalità (scala logaritmica)") 
```
---

```r
V+geom_contour(col="white", size=0.1)
```

<img src="lezione13_files/figure-html/unnamed-chunk-15-1.png" width="50%" />
---

```r
E<- ITA %>% 
  ggplot(aes(y=age, x=Year, z=ex))+
  geom_contour_filled( show.legend = NA)+
     ggtitle("Aspettativa di vita per età e anno")+
    labs(subtitle="Italia", caption="Human mortality database (https://www.mortality.org)")+ labs(fill = "Aspettativa di vita ") 
```
---

```r
E
```

---
# Treemapify

```r
#install.packages("treemapify")
library(treemapify)
library(gapminder)
data(gapminder)
T0<-gapminder %>% 
  filter(year==2002) %>% 
  ggplot( aes(area = pop, fill = continent, label = country)) +
  geom_treemap()+
  geom_treemap_text(fontface = "italic", colour = "white", place = "centre",
                    grow = TRUE)
```

---

```r
T0
```

---

```r
T1<-gapminder %>% 
  filter(year==2002) %>% 
  ggplot(  aes(area = gdpPercap*pop, fill = continent, label = country)) +
  geom_treemap()+
  geom_treemap_text( colour = "white", place = "centre",
                    grow = TRUE)
```
---

```r
T1
```

<img src="lezione13_files/figure-html/unnamed-chunk-21-1.png" width="50%" />
---

```r
ieri= Sys.Date()-1
covid_regioni %>% 
  mutate(data=as.Date(data)) %>% 
  filter(data==ieri) %>% 
  ggplot(  aes(area = totale_casi, fill = totale_casi, label = denominazione_regione)) +
  geom_treemap()+
  geom_treemap_text( colour = "white", place = "centre",
                    grow = TRUE)
```