Scripts containing the code developed during the 7th lectore on project management and data import, as well as solutions to the exercises

#T7 - Lecture notes (FaSe 2022)

Scripts containing the code developed during the 7th lectore on project management and data import, as well as solutions to the exercises

import_data.R

here::i_am("R/the_here_script.R")
# Script assumes the following directory structure:
# R/import_data.R
# data/raw/fread_expls-1.csv
# It also includes the solution to the final exercise below

here::i_am("R/import_data.R")
library(here)
library(data.table)
library(tibble)

data_path <- here("data/raw/fread_expls-1.csv")
expl_data_1 <- fread(file = data_path)
expl_data_1 <- tibble::as_tibble(expl_data_1) # Not strictly necessary but useful
expl_data_1

data_path_2 <- here("data/raw/fread_expls-2.csv")
expl_data_2 <- fread(file = data_path_2) # Default values do not work...
expl_data_2 # ... as you can see here

expl_data_2 <- fread(file = data_path_2, sep = "'", dec = ":")
expl_data_2 <- tibble::as_tibble(expl_data_2)
expl_data_2

data_path_3 <- here("data/raw/fread_expls-3.csv")
expl_data_3 <- fread(file = data_path_3) 
expl_data_3 <- tibble::as_tibble(expl_data_3)
head(expl_data_3) # column commoditycode is missing leading zero!

expl_data_3 <- fread(
  file = data_path_3, 
  colClasses = c(rep("character", 2), rep("double", 2))
  ) 

# Alternative only referring one column to change:
expl_data_3 <- fread(
  file = data_path_3, 
  colClasses = c("commoditycode"="character", "cgroup"="factor")
) 

expl_data_3 <- tibble::as_tibble(expl_data_3)
head(expl_data_3)
str(expl_data_3)

the_here_script.R

here::i_am("R/the_here_script.R")
library(ggplot2)

test_plot <- ggplot() + theme_dark() + labs(title = "An empty plot")
test_plot 

plot_name <- here::here("output/dark_plot.pdf")
plot_name_jpg <- here::here("output/dark_plot.jpg")
plot_name_png <- here::here("output/dark_plot.png")

ggsave(filename = plot_name, plot = test_plot, width = 6, height = 3)
ggsave(filename = plot_name_jpg)
ggsave(filename = plot_name_png)