Created
May 11, 2023 13:59
-
-
Save graebnerc/e4fc9795d4b57f3de2bacd120e563af8 to your computer and use it in GitHub Desktop.
#S12 - Recap
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This contains the script developed during the recap session. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
here::i_am("R/recap.R") | |
library(dplyr) | |
library(data.table) | |
library(here) | |
library(tidyr) | |
library(ggplot2) | |
# How to deal with large files - some hints----------- | |
gdp_file <- here("data/raw/API_NY.GDP.PCAP.PP.KD_DS2_en_csv_v2_5359165.csv") | |
gdp_data_raw <- data.table::fread(file = gdp_file) | |
# Use overview functions: | |
head(gdp_data, n = 2) | |
names(gdp_data) | |
str(gdp_data) | |
dplyr::glimpse(gdp_data) | |
# Check the unique values of the columns: | |
unique(gdp_data$`Indicator Name`) | |
unique(gdp_data$V67) | |
# Taking into account all this information suggests to augment the import call: | |
gdp_data_raw <- data.table::fread( | |
file = gdp_file, | |
header = TRUE # To ensure the column names are correct | |
) %>% | |
tibble::as_tibble(.) %>% # Facilitates printing | |
select( # Remove redundant columns | |
-c("Country Name", | |
"Indicator Name", "Indicator Code", | |
"V67") | |
) | |
# Then continue working with the data: | |
gdp_data_tidy <- gdp_data_raw %>% | |
tidyr::pivot_longer( | |
cols = -"Country Code", | |
names_to = "year", | |
values_to = "GDP_percapita") | |
# Country codes-------------- | |
library(countrycode) | |
gdp_data_countrynames <- gdp_data_tidy %>% | |
dplyr::mutate( | |
countryname = countrycode::countrycode( | |
`Country Code`, origin = "iso3c", destination = "country.name") | |
) %>% | |
dplyr::mutate(# For manual correction do, e.g.: | |
countryname = ifelse(`Country Code` == "WLD", "World", countryname) | |
) | |
head(gdp_data_countrynames) | |
# Check potential duplicates! | |
# Scatter plot--------------- | |
wine_data <- DataScienceExercises::wine2dine | |
ggplot( | |
data = wine_data, | |
mapping = aes( | |
y = `residual sugar`, | |
x = alcohol, | |
color = kind) | |
) + | |
geom_point() + | |
theme_bw() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment