LBB_IP_Space_Travellers.Rmd

---
title: "Space Travellers Data Analysis 2023"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows # rows/columns
    vertical_layout: scroll # fill/scroll
---

```{r setup, include=FALSE}
# clear-up the environment
rm(list = ls())

# ---- (1) LIBRARY & SETUP ----
# library & read data
library(httr)    
set_config(use_proxy(url="10.3.100.207",port=8080))

library(flexdashboard)
library(dplyr)
library(ggplot2) # visualisasi
library(scales) # untuk tampilan digit (memberikan koma dll)
library(glue)
library(plotly) 
library(lubridate) # working with datetime
options(scipen = 100) # supaya output tidak menampilkan notasi ilmiah (10-e10)

# **📘 Referensi:**
# Source Data : https://www.kaggle.com/datasets/kaushiksinghrawat/humans-to-have-visited-space
# membaca data
space <- read.csv("data_input/space_travellers.csv", stringsAsFactors = T)
```

Row 
----------


### Top 20 Countries of Space Travellers

```{r}
# Plot 1 Lollipop: Top 20 Countries of Space Travellers

# Data Preparation
# dplyr
space_traveller <- space %>% 
  select(-X.) %>%  # Membuang kolom 'X.' karena tidak memberikan informasi penting (hanya nomor urut data)
  mutate(Date = as.Date(Date), # Mengubah tipe data
         Year = year(Date)) # Mengestrak Tahun dari kolom 'Date' dan membuat kolom baru 'Year' 

# Membuat label kalimat untuk informasi periode data yang diambil
data_start_date <- min(space_traveller$Date)
data_end_date <-max(space_traveller$Date)

period_data <- glue('{format(data_start_date, "%d %b %Y")}', 
                    ' - ',
                   '{format(data_end_date, "%d %b %Y")}')

# Membuat fungsi untuk mengkategorikan tahun (setiap 10 thn)
convert_decade <- function(y){ 
    if(y > 2020 & y <= 2023)
      {
      y <- "2021 - 2023" # Space Travel antara thn 2021 - 2023
    }
    else 
      if(y > 2010 & y <= 2020)
      {
      y <- "2011 - 2020" # Space Travel antara thn 2021 - 2023
    }
    else 
      if(y > 2000 & y <= 2010)
      {
      y <- "2001 - 2010" # Space Travel antara thn 2001 - 2010
    }
    else 
      if(y > 1990 & y <= 2000)
      {
      y <- "1991 - 2000" # Space Travel antara thn 1991 - 2000
    }
    else 
      if(y > 1980 & y <= 1990)
      {
      y <- "1981 - 1990" # Space Travel antara thn 1981 - 1990
    }
    else 
      if(y > 1970 & y <= 1980)
      {
      y <- "1971 - 1980" # Space Travel antara thn 1971 - 1980
    }
    else 
      if(y > 1960 & y <= 1970)
      {
      y <- "1961 - 1970" # Space Travel antara thn 1971 - 1980
      }
}

# Membuat kolom berisikan value periode space traveller
space_traveller$Period_Travel <- sapply(X = space_traveller$Year, 
                            FUN = convert_decade)
space_traveller$Period_Travel <- as.factor(space_traveller$Period_Travel)

# data transformation
space_traveller_count <- space_traveller %>% 
  group_by(Nationality) %>% 
  summarise(freq = n()) %>%
  ungroup() %>% 
  arrange(-freq) %>% # arrange(desc(freq))
  head(20) %>% 
  # menambahkan label untuk tooltip
  mutate(label = glue(
    "Total of {freq} Space Travellers
     Country: {Nationality}"
  ))
  
# membuat plot statis
plot1 <- ggplot(data = space_traveller_count, 
                aes(x = freq,
                    y = reorder(Nationality, freq),
                    color = freq,
                    text = label)) +
  geom_point(size = 3) +
  geom_segment(aes(x = 0,
                   xend = freq,
                   yend = Nationality),
                   size = 1.0) +
  scale_color_gradient(low = "red", 
                       high = "blue") +
  labs(title = glue('Top 20 Countries Space Travellers (',
                    '{period_data}', ')'),
       x = "Number of Travellers",
       y = NULL) +
  theme_minimal() +
  theme(legend.position = "none") 

# membuat plot interaktif
ggplotly(plot1, tooltip = "text")
```

Row 

-----------------------------------------------------------------------

### Top 3 Countries with Most Space Travellers Every Decades

```{r}
# Plot 2 : Grouped Bar Charts : Top 3 Countries with Most Space Travellers Every Decades

# data transformation
# Memfilter Data Top 3 Negara dengan Jumlah Space Travellers (Astronouts) terbanyak dalam setiap periode 10 tahun
space_traveller_top3 <- space_traveller %>% 
  group_by(Period_Travel) %>% 
  count(Nationality) %>% 
  rename(No_Space_Travellers = n) %>% 
  arrange(Period_Travel, desc(No_Space_Travellers)) %>% 
  slice(1:3) %>% 
  ungroup()


# menambahkan label untuk tooltip
space_traveller_top3 <- space_traveller_top3 %>% 
  mutate(label = glue(
    "Total Space Travellers: {No_Space_Travellers} pax
     Country: {Nationality}"
  ))

plot2 <- ggplot(data = space_traveller_top3, 
                    aes(x = Period_Travel,
                        y = No_Space_Travellers,
                        text = label)
                ) +
  geom_col(aes(fill = Nationality), position = "dodge") +
  labs(title = glue('Top 3 Countries with Most Space Travellers'), 
       x = "Decade Period",
       y = "Number of Travellers") +
  theme_minimal() +
  theme(legend.position = "none") 


# plot interaktif: ggplotly
ggplotly(plot2, tooltip = "text")
```

Row 
----------

### Trend Space Launch Performance By Countries which Listed on Top 3 since 2000 

```{r}
# Plot 3 Line: Trend Comparison for 3 Top Countries since Year 2000 on Space Launch Performance

# List kategori 3 batch periode terakhir (diatas tahun 2000)
last_3_decades <- tail(unique(space_traveller$Period_Travel),3)
# Subset nama top 3 countries since 2000
top_3_countries_since_2000 <- unique(filter(.data = space_traveller_top3, Period_Travel %in% last_3_decades)$Nationality)

# data transformation
trend_space_traveller_top3_countries <- filter(space_traveller, 
                                               Nationality %in% top_3_countries_since_2000) %>% 
  group_by(Year) %>% 
  count(Nationality) %>% 
  rename(No_Space_Travellers = n) %>% 
  ungroup()

# menambahkan label untuk tooltip
trend_space_traveller_top3_countries <- trend_space_traveller_top3_countries %>% 
  mutate(label = glue(
    "{No_Space_Travellers} Space Travellers
     Year: {Year}"
  ))

plot3 <- ggplot(data = trend_space_traveller_top3_countries, 
       mapping = aes(x = Year, y = No_Space_Travellers, color = Nationality)) +
  geom_line() +
  geom_point(col = "black", aes(text = label)) +
  scale_y_continuous(labels = NULL) +
  facet_wrap(facets = "Nationality", nrow = 3, scales = "free_y") +
  labs(title = glue('Space Launch Performance Comparison By Top 3 Countries since Year 2000'), 
       x = "Year",
       y = "Number of Travellers") +
  theme_minimal() +
  theme(legend.position = "none") 

# plot interaktif: ggplotly
ggplotly(plot3, tooltip = "text")
```


```{r}
glimpse(space_traveller)
```

```{r}
summary(space_traveller)
```