---
title: "Data visualization: Treemaps with {treemap}, {d3treeR} and {highcharter}"
output:
flexdashboard::flex_dashboard:
storyboard: true
orientation: columns
source_code: embed
vertical_layout: fill
theme: paper
---
```{r setup, include=FALSE}
library(flexdashboard)
library(tidyverse)
library(plotly)
library(leaflet)
library(rnaturalearth)
library(treemap)
library(d3treeR)
library(highcharter)
library(readxl)
library(stringr)
library(knitr)
library(DT)
library(viridisLite)
options(scipen=10000)
```
Peru
===========================================================================
Column {data-width=300}
---------------------------------------------------------------------------
\
This dashboard is a continuation of a [previous post](https://rquer.netlify.com/sunburst_treemaps
On the other hand, the map of Peru is created using {leaflet}. The tootips have been customized to show the name of each region when the user hovers over a region. When clicking on one region it will show the total GVA of the region selected and the % with respect to the total GVA of the country. The provider of the base map is `Esri.WorldShadedRelief`.
The dashboard presents the data in DaTables using {DT}. It is also possible to customize DataTables, as we will show in the examples. DataTables provides filtering, sorting, pagination and other features.
We will use again data related to the **regional and sectoral productive structure of Peru for 2018**. Data comes from the Peruvian National Institute of Statistics and Informatics ([INEI](https://www.inei.gob.pe/)).
The INEI distinguishes 12 major economic / productive sectors:
- Agriculture, Livestock, Hunting and Forestry.
- Fishing and Aquaculture.
- Extraction of Minerals, Gas and Oil.
- Manufacturing.
- Electricity, Gas and Water.
- Construction.
- Commerce.
- Transportation, Storage, Mail and Messaging.
- Accommodation and Restaurants.
- Telecommunications and Other Information Services.
- Public Administration and Defence.
- Other Services.
\
Column
---------------------------------------------------------------------------
### Gross Value Added by region (in constant 2007 PEN thousands) and % of total GVA, 2018
```{r}
library(readxl)
peru_mapa_vab2018 <- read_excel("C:/Users/Usuario/Desktop/r_que_r/r_que_r/content/datasets/peru_mapa_vab2018.xlsx")
peru_mapa_vab2018$Vab_perc <- formatC(peru_mapa_vab2018$Vab_perc, digits=3)
peru_mapa_vab2018$Vab_perc <- as.numeric(peru_mapa_vab2018$Vab_perc)
peru_mapa_vab2018$vab_2018<- format(peru_mapa_vab2018$vab_2018, big.mark = ",")
peru_map_region <- rnaturalearth::ne_states(country = "Peru", returnclass = "sf") %>%
select(name, iso_3166_2, geometry) %>%
left_join(peru_mapa_vab2018,
by = "name")
peru_map_region %>%
leaflet() %>%
addProviderTiles(providers$Esri.WorldShadedRelief) %>%
addPolygons(
weight = 1,
label = ~ name,
color = "darkgreen",
popup = ~paste("Region:", name,
"",
"GVA:", vab_2018,
"",
"% GVA:", Vab_perc))
```
Column
---------------------------------------------------------------------------
### Productive Economic Structure by region, 2018. (GVA in constant 2007 PEN thousands)
```{r}
Peru_vab_sectores <- read_excel("C:/Users/Usuario/Desktop/r_que_r/r_que_r/content/datasets/Peru_vab_sectores_2.xlsx")
names(Peru_vab_sectores) = c("Regions", "AGR", "PES", "EXT", "MAN", "ELEC", "CONS", "COM", "TRANS", "REST", "TELEC", "ADPUB", "OS")
x<-Peru_vab_sectores %>%
group_by(Regions) %>%
mutate(total= AGR + PES + EXT + MAN + ELEC + CONS + COM + TRANS + REST + TELEC + ADPUB + OS) %>%
arrange(total) %>%
ungroup()
x$Regions = factor(x$Regions, levels = x$Regions)
plotly::plot_ly(data = x,
y = ~ Regions,
x = ~ AGR,
orientation = 'h',
name = 'Agriculture, Livestock, Hunting and Forestry',
type = 'bar') %>%
plotly::add_trace( x = ~ PES,
name = "Fishing and Aquaculture") %>%
plotly::add_trace( x = ~ EXT,
name = "Extraction of Minerals, Gas and Oil") %>%
plotly::add_trace( x = ~ MAN,
name = "Manufacturing") %>%
plotly::add_trace( x = ~ ELEC,
name = "Electricity, Gas and Water") %>%
plotly::add_trace( x = ~ CONS,
name = "Construction") %>%
plotly::add_trace( x = ~ COM,
name = "Commerce") %>%
plotly::add_trace( x = ~ TRANS,
name = "Transportation, Storage, Mail and Messaging") %>%
plotly::add_trace( x = ~ REST,
name = "Accommodation and Restaurants") %>%
plotly::add_trace( x = ~ TELEC,
name = "Telecommunications and Other Information Services") %>%
plotly::add_trace( x = ~ ADPUB,
name = "Public Administration and Defence") %>%
plotly::add_trace( x = ~ OS,
name = "Other Services") %>%
plotly::layout(title = " Gross Value Added by region and sector \n (constant 2007 PEN thousands)",
barmode = 'stack',
legend = list(x = 0.5, y = 0.1),
yaxis = list(title = ""),
xaxis = list(title = "Source: INEI | Lima includes Callao en Lima Province"),
hovermode = "compare",
margin = list(
l = 20,
r = 10,
b = 10,
t = 80,
pad = 2
))
```
datatable- DT
====================================================================================
Columna {data-width=700}
---------------------------------------------------------------------------
\
### Datatable with fixed column, `info = T`, `sort = T`, and values centered.
\
```{r}
Peru_vab_sectores <- read_excel("C:/Users/Usuario/Desktop/r_que_r/r_que_r/content/datasets/Peru_vab_sectores_2.xlsx")
datatable(Peru_vab_sectores,
rownames = F,
extensions = "FixedColumns",
options = list(
info = TRUE,
sort = TRUE,
fixedColumns = list(leftColumns = 1),
columnDefs = list(list(className = 'dt-center', targets = 1:12))
)
)
```
\
Columna {data-width=300}
---------------------------------------------------------------------------
\
### Datatable with `filter= bottom`, `class= 'cell-border stripe'`, `searching= T`
\
```{r}
Peru_sectores <- Peru_vab_sectores %>%
gather(key = "sector", value = "vab", 2:13)
datatable(Peru_sectores,
filter = "bottom",
rownames = FALSE,
class = 'cell-border stripe',
extensions = "FixedColumns",
options = list(
searching = TRUE,
info = TRUE,
sort = TRUE,
fixedColumns = list(leftColumns = 1))
)
```
Few questions about the data
=================================================================================
Column
------------------------------------------------------------------------------
### **1. REGIONAL CONTRIBUTION TO NATIONAL GVA (DESC)**
```{r}
a <- Peru_sectores %>%
group_by(Regions) %>%
summarise(vab_regional = sum(vab)) %>%
mutate(total= sum(vab_regional), percent = 100*(vab_regional/total)) %>%
arrange(desc(percent)) %>%
select(Regions, percent) %>%
ungroup()
a$percent <- formatC(a$percent, format = "f", digits = 2)
datatable(a)
```
### **2. SECTORAL CONTRIBUTION TO NATIONAL GVA (DESC)**
```{r}
b <- Peru_sectores %>%
group_by(sector) %>%
summarise(vab_regional = sum(vab)) %>%
mutate(total= sum(vab_regional), percent = 100*(vab_regional/total)) %>%
arrange(desc(percent)) %>%
select(sector, percent) %>%
ungroup()
b$percent <- formatC(b$percent, format = "f", digits = 2)
datatable(b)
```
Column
------------------------------------------------------------------------------
### **3. SECTORAL CONTRIBUTION OF EACH REGION TO NATIONAL GVA (DESC)**
```{r}
c <- Peru_sectores %>%
mutate(suma_total= sum(vab), percent= 100*(vab/suma_total)) %>%
select(Regions, sector,percent) %>%
arrange(desc(percent))
c$percent <- formatC(c$percent, format = "f", digits = 2)
datatable(c)
```
### **4. SECTORAL CONTRIBUTION TO REGIONAL GVA (DESC by region)**
```{r}
d <- Peru_sectores %>%
group_by(Regions) %>%
mutate(suma_total= sum(vab), percent= 100*(vab/suma_total)) %>%
select(Regions, sector, percent) %>%
arrange(Regions, desc(percent)) %>%
ungroup()
d$percent <- formatC(d$percent, format = "f", digits = 2)
datatable(d)
```
Column
------------------------------------------------------------------------------
### **5. REGIONAL CONTRIBUTION TO SECTORAL GVA (DESC by sector)**
```{r}
e <- Peru_sectores %>%
group_by(sector) %>%
mutate(suma_total= sum(vab), percent= 100*(vab/suma_total)) %>%
select(sector, Regions, percent) %>%
arrange(sector, desc(percent)) %>%
ungroup()
e$percent <- formatC(e$percent, format = "f", digits = 2)
datatable(e)
```
### **6. SECTOR IN EACH REGION THAT CONTRIBUTES MOST TO NATIONAL GVA (DESC by %)**
```{r}
f <- Peru_sectores %>%
mutate(suma_total= sum(vab), percent= 100*(vab/suma_total)) %>%
select(Regions, sector, percent) %>%
arrange(desc(percent)) %>%
group_by(Regions) %>%
top_n(1) %>%
ungroup()
f$percent <- formatC(f$percent, format = "f", digits = 2)
datatable(f)
```
{treemap}
====================================================================================
### Example I. Sectoral Level
```{r, fig.width=14, fig.height=8}
tree_sectores <- treemap(
Peru_sectores,
index=c("sector","Regions"),
vSize="vab",
title = "GVA, economic sector and region, 2018 ",
vColor="sector",
type="index",
force.print.labels = F,
border.col = c("black", "white"),
border.lwds = c(3,2),
align.labels = list(
c("center","center"),
c("center", "top")
)
)
```
{treemap} II
====================================================================================
### Example II. Regional Level
```{r, fig.width=14, fig.height=8}
tree_regions <- treemap(
Peru_sectores,
index=c("Regions", "sector"),
vSize="vab",
title = "GVA, region and economic sector, 2018 ",
vColor="vab",
type="value",
palette = "BuPu",
force.print.labels = F,
border.col = c("black", "white"),
border.lwds = c(3,2),
align.labels = list(
c("center","center"),
c("center", "top")
)
)
```
{d3treeR}
====================================================================================
### Example I. Sectoral Level
```{r}
d3tree(tree_sectores,
rootname = "GVA, economic sector and region, 2018")
```
{d3treeR} II
====================================================================================
### Example II. Regional Level
```{r}
d3tree(tree_regions,
rootname = "GVA, region and economic sector, 2018")
```
{highcharter}
====================================================================================
### Example I. Sectoral Level
```{r}
hctreemap(tree_sectores, allowDrillToNode = TRUE) %>%
hc_title(text = "GVA, economic sector and region, 2018") %>%
hc_tooltip(pointFormat = "{point.name}:
GVA: {point.value:,.0f}") %>%
hc_exporting(enabled = TRUE)
```
{highcharter} II
====================================================================================
### Example II. Regional Level
```{r}
hctreemap(tree_regions, allowDrillToNode = TRUE) %>%
hc_title(text = "GVA, region and economic sector, 2018") %>%
hc_tooltip(pointFormat = "{point.name}:
GVA: {point.value:,.0f}") %>%
hc_exporting(enabled = TRUE)
```
