Script para obtenção, limpeza e visualização dos dados sobre a presença de oléo em praias do Nordeste brasileiro

scrape_derramento_oleo_brasil_2019.R

############################################################
#                                                          #
#                  instalação dos pacotes                  #
#                                                          #
############################################################

# ipak function: install and load multiple R packages.
# Check to see if packages are installed. 
# Install them if they are not, then load them into the R session.
# Forked from: https://gist.github.com/stevenworthington/3178163
ipak <- function(pkg) {
  new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
  if (length(new.pkg)){
    install.packages(new.pkg, dependencies = TRUE)
  }
  suppressPackageStartupMessages(sapply(pkg, require, character.only = TRUE))
}

ipak(c("tidyverse", "tidylog", "readxl", "here", "biogeo", "plotly"))

theme_set(theme_light(base_size = 14))

############################################################
#                                                          #
#                    download dos dados                    #
#                                                          #
############################################################

link <- "https://www.ibama.gov.br/phocadownload/notas/2019/2019-10-28_LOCALIDADES_AFETADAS.xlsx"

get_data <- function(link_data, dest_folder){
  if (!dir.exists(dest_folder)){
    dir.create(dest_folder)
  }
  
  dest_and_name <- paste0(dest_folder, "/", basename(link_data))
  
  if (!file.exists(dest_and_name)){
    download.file(url = link_data, destfile = dest_and_name)
  } else {
    message("Arquivo ", dest_and_name, " já existe")
  }
}

get_data(
  link_data = link, 
  dest_folder = "derramento-de-oleo"
  )

############################################################
#                                                          #
#               leitura e limpeza dos dados                #
#                                                          #
############################################################

df <- 
  read_xlsx(
    path = here("derramento-de-oleo", "2019-10-28_LOCALIDADES_AFETADAS.xlsx")
    ) %>% 
  rename_all(str_to_lower)

clean_coord <- function(coord){
  coord <- iconv(coord, "utf-8", "ascii", sub="") %>% {
    gsub(pattern = "(')|(\")", replacement = "", x = .)
  }
  return(coord)
}

df_clean <- 
  df %>% 
  mutate(
    latitude = clean_coord(latitude),
    longitude = clean_coord(longitude)
    ) %>% 
  separate(
    col = latitude, 
    into = c("lat_graus", "lat_minutos", "lat_segundos", "lat_letra"), 
    sep = " ", 
    convert = TRUE
    ) %>%
  separate(
    col = longitude, 
    into = c("long_graus", "long_minutos", "long_segundos", "long_letra"), 
    sep = " ", 
    convert = TRUE
    ) %>% 
  mutate(
    latitude = dms2dd(
      dd = lat_graus, 
      mm = lat_minutos, 
      ss = lat_segundos, 
      ns = lat_letra
      ),
    longitude = dms2dd(
      dd = long_graus, 
      mm = long_minutos, 
      ss = long_segundos, 
      ns = long_letra
    )
    ) %>%
  select(-starts_with("lat_"), -starts_with("long_")) 

############################################################
#                                                          #
#                       visualização                       #
#                                                          #
############################################################

df_clean %>% 
  group_by(estado) %>% 
  count() %>% 
  ungroup() %>% 
  mutate(estado = fct_reorder(estado, n)) %>% 
  ggplot(aes(x = estado, y = n)) +
  geom_col() +
  coord_flip() +
  labs(
    x = "",
    y = "Número de registros",
    title = "Registros por Estado", 
    caption = "Fonte: https://www.ibama.gov.br/notas/2047-manchas-de-oleo-no-litoral-do-nordeste"
  )

############################################################
#                                                          #
#                           mapa                           #
#                                                          #
############################################################

shape_brasil <- borders(
  database = "world", 
  regions = "Brazil",
  fill = "white", 
  colour = "grey90" 
  )

mapa_oleo <- 
  df_clean %>%
  ggplot() + 
  shape_brasil + 
  theme_bw() + 
  labs(
    x = "Longitude", 
    y = "Latitude"
    ) +
  theme(
    panel.border = element_blank(),
    panel.grid.major = element_line(colour = "grey80"),
    panel.grid.minor = element_blank()
    ) +
  coord_map() +
  geom_point(
      aes(
        x = longitude, 
        y = latitude,
        colour = status
        ), 
        alpha = 0.5, 
        size = 3
        ) 

# mapa estático
mapa_oleo
  
# mapa estático por status
mapa_oleo +
  facet_wrap( ~status)

############################################################
#                                                          #
#                     mapa interativo                      #
#                                                          #
############################################################

ggplotly(mapa_oleo)