In FahroziFahrozi/indoelectdata: Exploring and visualization the election data for Indonesia

knitr::opts_chunk$set(
  collapse = TRUE,
  warning = FALSE,
  message = FALSE,
  comment = "#>"
)

Exploring the Indonesia census data 2010

This vignette documents used how to access and explore the census data in Indonesia in 2010, using the lastest census data update 2015, and shows a few interesting varibles to visualization and exploring.

Import csv files

library(tidyverse)
library(readxl)
library(knitr)
library(ggplot2)
library(indoelectdata)

data(IDNS2010)

in this part to answer the question which provinces has the high unemployement rate in Indonesia

data_dictionary <- data.frame(
  Variable = names(IDNS2010), 
  details= c(
    "ID",
    "Provinces", 
    "PopulationIDN",
    "TotalHousehold",
    "PopulationMen",
    "PopulationWomen",
    "Household",
    "Incomeff",
    "Incomemerchant",
    "Incomegov",
    "Incomepriv",
    "Incomeentrep",
    "Incomefreelancer",
    "Medianage",
    "RatioParticp",
    "Unemployment2015",
    "Unemployment2016",
    "Unemployment2017",
    "Unemployment2018",
    "PopulationProjection2010",
    "PopulationProjection2015",
    "PopulationProjection2020",
    "PopulationProjection2025",
    "PopulationProjection2030",
    "PopulationProjection2035",
    "No"
    ))

library(knitr)
kable(data_dictionary)

So let's just look at some nice and simple plots using ggplot2.

library(ggthemes)
IDNS <- IDNS2010_download()

ggplot(data=IDNS2010[1:6,],
       aes(x = reorder(Provinces, -Unemployment2015),
           y = Unemployment2015,
           colour = Provinces))+
  geom_boxplot() +
  labs(x = "Provinces",
       y = "% Unemployment") +
  theme_minimal() +
  theme(legend.position = "none")+
  coord_flip()

the results above showed that province Aceh has the high percentage for unempolyment rate with almost 15% from the population.

Total votes

mostly people in Indonesia working as gov employee, and they said that be a government employee is the goal job, so in this part, in this interesting to show about the income for govenrment employees based on ID area

ggplot(data=IDNS2010[1:6,],
       aes(x = reorder(ID, -Incomegov),
           y = Incomegov,
           colour = ID))+
  geom_boxplot() +
  geom_jitter(alpha = 0.35,
              size = 2,
              width = 0.3) +
  labs(x = "ID",
       y = "Incomegov (RP)") +
  theme_minimal() +
  theme(legend.position = "none")+
  coord_flip()

from the result above showed that province Banten with ID area (16) has the high income in government employee with average 4,3 million rupiah/month and DKI jakarta the second province with the high income in government employee with average 4,2 million rupiah/month

Population Men

in this part we want to see which provinces has the highest men population in Indonesia

ggplot(data=IDNS2010[1:6,],
       aes(x = reorder(Provinces, -PopulationMen),
           y = PopulationMen,
           colour = Provinces))+
  geom_boxplot() +
  geom_jitter(alpha = 0.35,
              size = 2,
              width = 0.3) +
  theme_minimal() +
  labs(x = "Provinces", 
       y = "Population Men") +
  theme(legend.position = "none") +
  coord_flip()

Province of Sumatera Utara has the highest men population in Indonesia

Population Women

in this part we want to see which provinces has the highest women population in Indonesia

ggplot(data= IDNS2010[1:6,],
       aes(x = reorder(Provinces, -PopulationWomen),
           y = PopulationWomen,
           colour = Provinces))+
  geom_boxplot() +
  geom_jitter(alpha = 0.35,
              size = 2,
              width = 0.3) +
  theme_minimal() +
  labs(x = "Provinces", y = "Population women") +
  theme(legend.position = "none") +
  coord_flip()

it's similar with men population, Sumatera utara has the highest women population

in this part to see how the population projection in 2010, 2020, and 2025

in this part to answer what the future size and structur of the population look like

library (tidyr)
library(dplyr)

IDNS <- IDNS2010 %>%
  select(PopulationProjection2010, 
         PopulationProjection2020, 
         PopulationProjection2025) %>%
  gather(key = "Projection",
        value = "total") 

  ggplot(data = IDNS,
         aes(x = reorder(Projection, -total),
             y = total,
             colour = Projection)) +
  geom_jitter(alpha = 0.35,
              size = 2,
              width = 0.3) +
  theme_minimal() +
  labs(x = "population projection", y = "total")+
  theme(legend.position = "none") +
  coord_flip()

from the populaltion projection above we can see that the population projection for future will growth in 2025

FahroziFahrozi/indoelectdata documentation built on Nov. 21, 2019, 1:55 a.m.