In enpjp/PrepareDataForETL: Prepares Data for Extract Transform and Load

# Set code chunk options for all chunks
# These can be overridden at the chunk level, but setting global options 
# ensures consistency of chunk behaviour.
# To print a version of this document without code set echo = FALSE. 
#Include false will ignore the code chunk completely!
knitr::opts_chunk$set(include = TRUE, 
                      echo = TRUE, 
                      warning=FALSE, 
                      message=FALSE, 
                      error=FALSE, 
                      results='asis')

# Explicitly load libraries here. Missing libraries are installed with the 
# install.packages() function at the command line or through the 
# Tools >> install packages menu of R studio.
# Note that install.packages requires the named ;library to be enclosed in
# quotation marks.

library(rgdal) # Need this for the geospatial code.
library(ggmap)
library(raster)
library(tidyverse)
library(plyr)
library(broom)
library(ggpolypath)
library(PrepareDataForETL)

Map

The shape files for all UK counties are available from National Biodiversity Network (2018) Mapping - Watsonian Vice Counties - National Biodiversity Network. Available at: https://nbn.org.uk/tools-and-resources/nbn-toolbox/watsonian-vice-county-boundaries/ (Accessed: 11 February 2019).

# Run this chunk to do a quick check plot.

my.polyline.data <-readOGR( "map/Derbyshire_polyline.shp") 
# Note that sometimes we need a "." to point to the current directory.
# This is a driver dependent issue that varies according to installation.
# my.polyline.data <-readOGR(".","VC55/Leicestershire_polyline.shp")

# Now a test plot
plot(my.polyline.data, col = "black")

# Now to transform into dataframe
my.polyline.df <- tidy(my.polyline.data) # Need to load broom for this

# Our data frame is in ordnance survey units and the columns 
# are mislabelled as lat long
# Now to reproject the units as Lat Long in WGS84
# Rename the columns
    colnames(my.polyline.df)[colnames(my.polyline.df)=="long"] <- "Easting"
    colnames(my.polyline.df)[colnames(my.polyline.df)=="lat" ] <- "Northing"
# Now extract the co-ordinate columns
temp.df.coords <-my.polyline.df[,c("Easting","Northing")]
# And make sure they are numeric
    temp.df.coords[[1]] %>% as.numeric
    temp.df.coords[[2]] %>% as.numeric
# We happen to know that the data is UK national grid so use the proj4string 
    # = CRS("+init=epsg:27700")
    temp.sp.coords <- sp::SpatialPoints(temp.df.coords, sp::CRS("+init=epsg:27700"))

# So now we reproject the data in WGS84
    temp.sp.coords.84 <- sp::spTransform(temp.sp.coords, sp::CRS("+init=epsg:4326"))
    temp.sp.coord.df <- as.data.frame(temp.sp.coords.84)
    temp.sp.coords.output <- set_colnames(temp.sp.coord.df, c("long","lat"))

# Now join this back to the dataframe putting it at the front of the df.
    my.polyline.df <- cbind(temp.sp.coords.output,my.polyline.df)
# The dataframe now has both sets of coordinates available which may be useful. 
    #Use lat long for plotting with ggplot.

# We have lost the @Data slot so need to add it back.
# Create a temporary dataframe with all the data
  temp_df <- data.frame(my.polyline.data@data)

# Create and append "id" column with the same index as my.polyline.df 
  temp_df$id <- seq(0,nrow(temp_df)-1)

# Now join the data
  my.polyline.df <- join(my.polyline.df, temp_df, by="id")

temp.my.map <- ggplot(data = my.polyline.df) + # Set the data source
  geom_path( aes(x = long, y = lat, group = group)) + # Plot the polygon lines
  coord_equal() + # Set equal scaling for both axes.
  coord_map(projection = "mercator") + # Set a mercator projection
  theme(axis.line=element_blank(), # Override the default theme
      axis.text.x=element_blank(), # No x axis
      axis.text.y=element_blank(), # No y axis
      axis.ticks=element_blank(),  # No axis tick
      axis.title.x=element_blank(),# No x axis title
      axis.title.y=element_blank(),# No y axis title
      legend.position="right",# Legend right (if we have a legend)
      panel.background=element_blank(), # No background colour
      panel.border=element_blank(), # No borader colour
      panel.grid.major=element_blank(), # No major grid lines
      panel.grid.minor=element_blank() # No minor grid lines
    )

# Using separate chunks to suppress unwanted output.

temp.my.map

# Clean up

rm(list = ls(pattern = "temp*"))

# Finally save the object by uncommenting this line
dir.create("data-raw")
saveRDS(my.polyline.df, file = "data-raw/my.polyline.df.rds")

# usethis::use_data(my.polyline.df.rds, overwrite = TRUE) 
# Use this to actually add the data to a package.