Created
August 15, 2020 06:45
-
-
Save zacharystansell/e181413d20d74e1e7f22f863ca0af672 to your computer and use it in GitHub Desktop.
Big_5_Personality_By_Country
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
library("tidyverse") | |
library("data.table") | |
library("ggplot2") | |
library("ggpubr") | |
library("dplyr") | |
library("magrittr") | |
library("countrycode") | |
# Data normalizing func | |
normalize <- function(x) 100*(x-min(x))/(max(x)-min(x)) | |
data <- fread( | |
# Read data pulled down from site | |
"~/PROJECTS/FUN/personality/data-final.csv", | |
sep = "\t", | |
#na.strings=("NA"), | |
stringsAsFactors = FALSE | |
) %>% | |
# Remove some rows with data I'm not using | |
select(c(1:50, 101:110)) %>% | |
filter( | |
IPC == 1, | |
as.numeric(as.character(introelapse)) < 60, | |
as.numeric(as.character(testelapse)) < 900, | |
as.numeric(as.character(endelapse)) < 60, | |
) %>% | |
group_by(country) %>% | |
# Require at least 1000 individuals, filter any inds without a country | |
filter(n() > 1000 && country != "NONE") %>% | |
droplevels() %>% | |
# change factors to numeric | |
mutate_at(c(1:50), as.numeric, ) %>% | |
# Calc scores based on https://ipip.ori.org/new_ipip-50-item-scale.htm | |
mutate( | |
O = normalize(OPN1 - OPN2 + OPN3 - OPN4 + OPN5 - OPN6 + OPN7 + OPN8 + OPN9 + OPN10), | |
C = normalize(CSN1 - CSN2 + CSN3 - CSN4 + CSN5 - CSN6 + CSN7 - CSN8 + CSN9 + CSN10), | |
E = normalize(EXT1 - EXT2 + EXT3 - EXT4 + EXT5 - EXT6 + EXT7 - EXT8 + EXT9 - EXT10), | |
A = normalize(AGR1 + AGR2 - AGR3 + AGR4 - AGR5 + AGR6 - AGR7 + AGR8 + AGR9 + AGR10), | |
N = normalize(EST1 - EST2 + EST3 - EST4 + EST5 + EST6 + EST7 + EST8 + EST9 + EST10) | |
) | |
#recode country names | |
data$country <- countrycode(data$country, "iso2c","country.name") | |
data <- data %>% | |
mutate(country = recode(country, | |
`Hong Kong SAR China` = "Hong Kong", | |
`United States` = "U.S.", | |
`United Kingdom` = "U.K.", | |
`United Arab Emirates` = "U.A.E.")) | |
O <- | |
ggplot(data, aes( | |
x = O, | |
y = reorder(country, O), | |
fill = country | |
)) + geom_violin() + theme_minimal() + theme(legend.position = "none") + labs(title = "Openess",x="", y = "") | |
C <- | |
ggplot(data, aes( | |
x = C, | |
y = reorder(country, C), | |
fill = country | |
)) + geom_violin() + theme_minimal() + theme(legend.position = "none") + labs(title = | |
"Conscientiousness",x="", y = "") | |
E <- | |
ggplot(data, aes( | |
x = E, | |
y = reorder(country, E), | |
fill = country | |
)) + geom_violin() + theme_minimal() + theme(legend.position = "none") + labs(title = | |
"Extroversion",x="", y = "") | |
A <- | |
ggplot(data, aes( | |
x = A, | |
y = reorder(country, A), | |
fill = country | |
)) + geom_violin() + theme_minimal() + theme(legend.position = "none") + labs(title = | |
"Agreeableness",x="", y = "") | |
N <- | |
ggplot(data, aes( | |
x = N, | |
y = reorder(country, N), | |
fill = country | |
)) + geom_violin() + theme_minimal() + theme(legend.position = "none") + labs(title = | |
"Neuroticism",x="", y = "") | |
ggsave( | |
"OCEAN.png", | |
plot = ggarrange(O, C, E, A, N , nrow = 1), | |
height = 15, | |
width = 15, | |
dpi = 300 | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment