tyleransom · February 8, 2026 03:20
diff --git a/obesity-seed-oils-g20-plot.R b/obesity-seed-oils-g20-plot.R
 # Obesity vs Seed Oil Consumption - G20 Countries 2022
 # 
 # Required files (included in this gist):
 #   - seed-oils-6-largest-2022-all-countries.csv
 #   - obesityAll2022.csv
 #
 # Required packages (install if needed):
 # install.packages(c("tidyverse", "countrycode"))

 library(tidyverse)
 library(countrycode)

 # Read in seed oils (local file)
 df.seed <- read_csv("seed-oils-6-largest-2022-all-countries.csv") %>% 
    filter(Area != "China") %>%  # Remove generic China entries
    mutate(ISO = countrycode(Area, "country.name", "iso3c"))

 df.seed <- df.seed %>%
    mutate(Area = case_when(
        Area == "China" ~ "China, mainland",
        TRUE ~ Area
    )) %>%
    distinct()

 # Read in obesity (local file)
 df.obesity <- read_csv("obesityAll2022.csv")

 # Merge the datasets and filter for G20
 df <- df.obesity %>%
    left_join(df.seed, by = c("country"="ISO")) %>%
    drop_na() %>%
    filter(`Element Code`==645,
           is_g20.x) %>%    # Using the obesity dataset's G20 indicator 
    mutate(Area = replace(Area, Area=="United States of America", "USA"),
           Area = replace(Area, Area=="United Kingdom of Great Britain and Northern Ireland", "UK"))

 # All G20 countries should be labeled
 countries_to_label <- unique(df$Area)

 # Calculate slope and R2
 model <- lm(`obesity rate GHO` ~ value, data = df)
 slope <- round(coef(model)[2], 2)
 intercept <- round(coef(model)[1], 2)
 r2 <- round(summary(model)$r.squared, 2)

 # Create the scatter plot
 ggplot(df, aes(x = value, y = `obesity rate GHO`, label = Area)) +
    geom_point() +
    geom_smooth(method = "lm", se = FALSE, color = "blue", linewidth = 1) +
    geom_text(aes(label = Area),
              hjust = -0.1, vjust = 0.5, size = 3) +
    scale_x_continuous(limits = c(0, 35)) +
    annotate("text", x = 30, y = 10,
             label = paste0("y = ", intercept, " + ", slope, "x\nR² = ", r2),
             size = 4, fontface = "bold") +
    labs(x = "Omega-6 PUFA Vegetable Oil Availability in 2022 (kg/capita annually)",
         y = "Obesity Rate in 2022 (%)") +
    theme_minimal()

 # Save the plot as PNG
 ggsave(filename = "obesity-seed-oils-g20-countries-2022.png",
       width = 5, height = 5, dpi = 300)
diff --git a/obesity-seed-oils-plot.R b/obesity-seed-oils-plot.R
 # Obesity vs Seed Oil Consumption - All Countries 2022
 # 
 # Required files (included in this gist):
 #   - seed-oils-6-largest-2022-all-countries.csv
 #   - obesityAll2022.csv
 #
 # Required packages (install if needed):
 # install.packages(c("tidyverse", "countrycode"))

 library(tidyverse)
 library(countrycode)

 # Read in seed oils (local file)
 df.seed <- read_csv("seed-oils-6-largest-2022-all-countries.csv") %>% 
    filter(Area != "China") %>%  # Remove generic China entries
    mutate(ISO = countrycode(Area, "country.name", "iso3c"))

 df.seed <- df.seed %>%
    mutate(Area = case_when(
        Area == "China" ~ "China, mainland",
        TRUE ~ Area
    )) %>%
    distinct()

 # Read in obesity (local file)
 df.obesity <- read_csv("obesityAll2022.csv")

 # Merge the datasets
 df <- df.obesity %>%
    left_join(df.seed, by = c("country"="ISO")) %>%
    drop_na() %>%
    filter(`Element Code`==645) %>%
    mutate(Area = replace(Area, Area=="United States of America", "USA"),
           Area = replace(Area, Area=="United Kingdom of Great Britain and Northern Ireland", "UK"))

 # Calculate slope and R2
 model <- lm(`obesity rate GHO` ~ value, data = df)
 slope <- round(coef(model)[2], 2)
 intercept <- round(coef(model)[1], 2)
 r2 <- round(summary(model)$r.squared, 2)

 countries_to_label <- c("Japan", "Czechia", "Bulgaria", "Tonga", "Argentina", 
                        "Qatar", "Samoa", "Nauru", "Tuvalu", "French Polynesia", 
                        "Bahamas", "UK", "USA", "Egypt", "Saudi Arabia", "Canada")

 # Create the scatter plot
 ggplot(df, aes(x = value, y = `obesity rate GHO`, label = Area)) +
    geom_point() +
    geom_smooth(method = "lm", se = FALSE, color = "blue", linewidth = 1) +
    geom_text(data = filter(df, Area %in% countries_to_label),
              aes(label = Area),
              hjust = -0.1, vjust = 0.5, size = 3) +
    scale_x_continuous(limits = c(0, 35)) +
    annotate("text", x = 30, y = 10,
             label = paste0("y = ", intercept, " + ", slope, "x\nR² = ", r2),
             size = 4, fontface = "bold") +
    labs(x = "Omega-6 PUFA Vegetable Oil Availability in 2022 (kg/capita annually)",
         y = "Obesity Rate in 2022 (%)") +
    theme_minimal()

 # Save the plot as PNG
 ggsave(filename = "obesity-seed-oils-all-countries-2022.png",
       width = 5, height = 5, dpi = 300)
diff --git a/obesityAll2022.csv b/obesityAll2022.csv
diff --git a/seed-oils-6-largest-2022-all-countries.csv b/seed-oils-6-largest-2022-all-countries.csv
	# Obesity vs Seed Oil Consumption - G20 Countries 2022
	#
	# Required files (included in this gist):
	# - seed-oils-6-largest-2022-all-countries.csv
	# - obesityAll2022.csv
	#
	# Required packages (install if needed):
	# install.packages(c("tidyverse", "countrycode"))

	library(tidyverse)
	library(countrycode)

	# Read in seed oils (local file)
	df.seed <- read_csv("seed-oils-6-largest-2022-all-countries.csv") %>%
	filter(Area != "China") %>% # Remove generic China entries
	mutate(ISO = countrycode(Area, "country.name", "iso3c"))

	df.seed <- df.seed %>%
	mutate(Area = case_when(
	Area == "China" ~ "China, mainland",
	TRUE ~ Area
	)) %>%
	distinct()

	# Read in obesity (local file)
	df.obesity <- read_csv("obesityAll2022.csv")

	# Merge the datasets and filter for G20
	df <- df.obesity %>%
	left_join(df.seed, by = c("country"="ISO")) %>%
	drop_na() %>%
	filter(`Element Code`==645,
	is_g20.x) %>% # Using the obesity dataset's G20 indicator
	mutate(Area = replace(Area, Area=="United States of America", "USA"),
	Area = replace(Area, Area=="United Kingdom of Great Britain and Northern Ireland", "UK"))

	# All G20 countries should be labeled
	countries_to_label <- unique(df$Area)

	# Calculate slope and R2
	model <- lm(`obesity rate GHO` ~ value, data = df)
	slope <- round(coef(model)[2], 2)
	intercept <- round(coef(model)[1], 2)
	r2 <- round(summary(model)$r.squared, 2)

	# Create the scatter plot
	ggplot(df, aes(x = value, y = `obesity rate GHO`, label = Area)) +
	geom_point() +
	geom_smooth(method = "lm", se = FALSE, color = "blue", linewidth = 1) +
	geom_text(aes(label = Area),
	hjust = -0.1, vjust = 0.5, size = 3) +
	scale_x_continuous(limits = c(0, 35)) +
	annotate("text", x = 30, y = 10,
	label = paste0("y = ", intercept, " + ", slope, "x\nR² = ", r2),
	size = 4, fontface = "bold") +
	labs(x = "Omega-6 PUFA Vegetable Oil Availability in 2022 (kg/capita annually)",
	y = "Obesity Rate in 2022 (%)") +
	theme_minimal()

	# Save the plot as PNG
	ggsave(filename = "obesity-seed-oils-g20-countries-2022.png",
	width = 5, height = 5, dpi = 300)
	# Obesity vs Seed Oil Consumption - All Countries 2022
	#
	# Required files (included in this gist):
	# - seed-oils-6-largest-2022-all-countries.csv
	# - obesityAll2022.csv
	#
	# Required packages (install if needed):
	# install.packages(c("tidyverse", "countrycode"))

	library(tidyverse)
	library(countrycode)

	# Read in seed oils (local file)
	df.seed <- read_csv("seed-oils-6-largest-2022-all-countries.csv") %>%
	filter(Area != "China") %>% # Remove generic China entries
	mutate(ISO = countrycode(Area, "country.name", "iso3c"))

	df.seed <- df.seed %>%
	mutate(Area = case_when(
	Area == "China" ~ "China, mainland",
	TRUE ~ Area
	)) %>%
	distinct()

	# Read in obesity (local file)
	df.obesity <- read_csv("obesityAll2022.csv")

	# Merge the datasets
	df <- df.obesity %>%
	left_join(df.seed, by = c("country"="ISO")) %>%
	drop_na() %>%
	filter(`Element Code`==645) %>%
	mutate(Area = replace(Area, Area=="United States of America", "USA"),
	Area = replace(Area, Area=="United Kingdom of Great Britain and Northern Ireland", "UK"))

	# Calculate slope and R2
	model <- lm(`obesity rate GHO` ~ value, data = df)
	slope <- round(coef(model)[2], 2)
	intercept <- round(coef(model)[1], 2)
	r2 <- round(summary(model)$r.squared, 2)

	countries_to_label <- c("Japan", "Czechia", "Bulgaria", "Tonga", "Argentina",
	"Qatar", "Samoa", "Nauru", "Tuvalu", "French Polynesia",
	"Bahamas", "UK", "USA", "Egypt", "Saudi Arabia", "Canada")

	# Create the scatter plot
	ggplot(df, aes(x = value, y = `obesity rate GHO`, label = Area)) +
	geom_point() +
	geom_smooth(method = "lm", se = FALSE, color = "blue", linewidth = 1) +
	geom_text(data = filter(df, Area %in% countries_to_label),
	aes(label = Area),
	hjust = -0.1, vjust = 0.5, size = 3) +
	scale_x_continuous(limits = c(0, 35)) +
	annotate("text", x = 30, y = 10,
	label = paste0("y = ", intercept, " + ", slope, "x\nR² = ", r2),
	size = 4, fontface = "bold") +
	labs(x = "Omega-6 PUFA Vegetable Oil Availability in 2022 (kg/capita annually)",
	y = "Obesity Rate in 2022 (%)") +
	theme_minimal()

	# Save the plot as PNG
	ggsave(filename = "obesity-seed-oils-all-countries-2022.png",
	width = 5, height = 5, dpi = 300)
country	year	obesity rate GHO	is_g7	is_g20	is_oecd
AFG	2022	19.22259	FALSE	FALSE	FALSE
AGO	2022	11.47373	FALSE	FALSE	FALSE
ALB	2022	23.36019	FALSE	FALSE	FALSE
AND	2022	18.09918	FALSE	FALSE	FALSE
ARE	2022	32.07922	FALSE	FALSE	FALSE
ARG	2022	35.3552	FALSE	TRUE	FALSE
ARM	2022	24.50904	FALSE	FALSE	FALSE
ASM	2022	75.20533	FALSE	FALSE	FALSE
ATG	2022	33.2509	FALSE	FALSE	FALSE
AUS	2022	30.24391	FALSE	TRUE	TRUE
AUT	2022	15.36754	FALSE	FALSE	TRUE
AZE	2022	26.54888	FALSE	FALSE	FALSE
BDI	2022	5.02191	FALSE	FALSE	FALSE
BEL	2022	20.02537	FALSE	FALSE	TRUE
BEN	2022	11.16586	FALSE	FALSE	FALSE
BFA	2022	6.74531	FALSE	FALSE	FALSE
BGD	2022	5.30312	FALSE	FALSE	FALSE
BGR	2022	20.58764	FALSE	FALSE	FALSE
BHR	2022	36.12672	FALSE	FALSE	FALSE
BHS	2022	47.25754	FALSE	FALSE	FALSE
BIH	2022	21.19391	FALSE	FALSE	FALSE
BLR	2022	21.37462	FALSE	FALSE	FALSE
BLZ	2022	42.32287	FALSE	FALSE	FALSE
BMU	2022	32.98985	FALSE	FALSE	FALSE
BOL	2022	28.68037	FALSE	FALSE	FALSE
BRA	2022	28.14184	FALSE	TRUE	FALSE
BRB	2022	38.0248	FALSE	FALSE	FALSE
BRN	2022	31.71067	FALSE	FALSE	FALSE
BTN	2022	12.17731	FALSE	FALSE	FALSE
BWA	2022	18.29088	FALSE	FALSE	FALSE
CAF	2022	9.29614	FALSE	FALSE	FALSE
CAN	2022	26.22712	TRUE	TRUE	TRUE
CHE	2022	12.11141	FALSE	FALSE	TRUE
CHL	2022	38.91461	FALSE	FALSE	TRUE
CHN	2022	8.27953	FALSE	TRUE	FALSE
CIV	2022	11.64304	FALSE	FALSE	FALSE
CMR	2022	14.8825	FALSE	FALSE	FALSE
COD	2022	6.64055	FALSE	FALSE	FALSE
COG	2022	8.53728	FALSE	FALSE	FALSE
COK	2022	68.92372	FALSE	FALSE	FALSE
COL	2022	23.61547	FALSE	FALSE	TRUE
COM	2022	16.27774	FALSE	FALSE	FALSE
CPV	2022	15.77243	FALSE	FALSE	FALSE
CRI	2022	31.38761	FALSE	FALSE	TRUE
CUB	2022	21.76093	FALSE	FALSE	FALSE
CYP	2022	22.93653	FALSE	FALSE	FALSE
CZE	2022	25.97952	FALSE	FALSE	TRUE
DEU	2022	20.40371	TRUE	TRUE	TRUE
DJI	2022	11.34678	FALSE	FALSE	FALSE
DMA	2022	31.34077	FALSE	FALSE	FALSE
DNK	2022	13.27851	FALSE	FALSE	TRUE
DOM	2022	29.34005	FALSE	FALSE	FALSE
DZA	2022	23.81499	FALSE	FALSE	FALSE
ECU	2022	27.37855	FALSE	FALSE	FALSE
EGY	2022	44.2702	FALSE	FALSE	FALSE
ERI	2022	4.83257	FALSE	FALSE	FALSE
ESP	2022	15.66913	FALSE	FALSE	TRUE
EST	2022	22.16319	FALSE	FALSE	TRUE
ETH	2022	2.82277	FALSE	FALSE	FALSE
FIN	2022	21.50907	FALSE	FALSE	TRUE
FJI	2022	33.83844	FALSE	FALSE	FALSE
FRA	2022	9.69848	TRUE	TRUE	TRUE
FSM	2022	47.10044	FALSE	FALSE	FALSE
GAB	2022	21.01852	FALSE	FALSE	FALSE
GBR	2022	26.82025	TRUE	TRUE	TRUE
GEO	2022	34.65963	FALSE	FALSE	FALSE
GHA	2022	12.93131	FALSE	FALSE	FALSE
GIN	2022	9.53418	FALSE	FALSE	FALSE
GMB	2022	14.933	FALSE	FALSE	FALSE
GNB	2022	11.47051	FALSE	FALSE	FALSE
GNQ	2022	17.67374	FALSE	FALSE	FALSE
GRC	2022	27.9815	FALSE	FALSE	TRUE
GRD	2022	30.25213	FALSE	FALSE	FALSE
GRL	2022	27.03736	FALSE	FALSE	FALSE
GTM	2022	26.81024	FALSE	FALSE	FALSE
GUY	2022	28.45774	FALSE	FALSE	FALSE
HND	2022	29.49242	FALSE	FALSE	FALSE
HRV	2022	30.61658	FALSE	FALSE	FALSE
HTI	2022	10.68923	FALSE	FALSE	FALSE
HUN	2022	31.70393	FALSE	FALSE	TRUE
IDN	2022	11.22787	FALSE	TRUE	FALSE
IND	2022	7.26789	FALSE	TRUE	FALSE
IRL	2022	28.34655	FALSE	FALSE	TRUE
IRN	2022	24.26659	FALSE	FALSE	FALSE
IRQ	2022	40.48525	FALSE	FALSE	FALSE
ISL	2022	21.23441	FALSE	FALSE	TRUE
ISR	2022	22.49071	FALSE	FALSE	TRUE
ITA	2022	17.29186	TRUE	TRUE	TRUE
JAM	2022	33.80702	FALSE	FALSE	FALSE
JOR	2022	38.507	FALSE	FALSE	FALSE
JPN	2022	5.5393	TRUE	TRUE	TRUE
KAZ	2022	18.37642	FALSE	FALSE	FALSE
KEN	2022	12.41028	FALSE	FALSE	FALSE
KGZ	2022	26.5997	FALSE	FALSE	FALSE
KHM	2022	4.36388	FALSE	FALSE	FALSE
KIR	2022	46.30317	FALSE	FALSE	FALSE
KNA	2022	45.64439	FALSE	FALSE	FALSE
KOR	2022	7.33054	FALSE	TRUE	TRUE
KWT	2022	41.41697	FALSE	FALSE	FALSE
LAO	2022	8.00987	FALSE	FALSE	FALSE
LBN	2022	29.78156	FALSE	FALSE	FALSE
LBR	2022	17.01377	FALSE	FALSE	FALSE
LBY	2022	36.7072	FALSE	FALSE	FALSE
LCA	2022	33.46513	FALSE	FALSE	FALSE
LKA	2022	10.56364	FALSE	FALSE	FALSE
LSO	2022	20.99823	FALSE	FALSE	FALSE
LTU	2022	25.35532	FALSE	FALSE	TRUE
LUX	2022	18.4344	FALSE	FALSE	TRUE
LVA	2022	24.2725	FALSE	FALSE	TRUE
MAR	2022	21.78435	FALSE	FALSE	FALSE
MDA	2022	22.97021	FALSE	FALSE	FALSE
MDG	2022	4.26251	FALSE	FALSE	FALSE
MDV	2022	17.29768	FALSE	FALSE	FALSE
MEX	2022	36.02991	FALSE	TRUE	TRUE
MHL	2022	45.90313	FALSE	FALSE	FALSE
MKD	2022	27.53899	FALSE	FALSE	FALSE
MLI	2022	11.37264	FALSE	FALSE	FALSE
MLT	2022	32.28799	FALSE	FALSE	FALSE
MMR	2022	7.42634	FALSE	FALSE	FALSE
MNE	2022	17.99588	FALSE	FALSE	FALSE
MNG	2022	24.10874	FALSE	FALSE	FALSE
MOZ	2022	10.26296	FALSE	FALSE	FALSE
MRT	2022	22.68795	FALSE	FALSE	FALSE
MUS	2022	19.22863	FALSE	FALSE	FALSE
MWI	2022	7.73552	FALSE	FALSE	FALSE
MYS	2022	22.09537	FALSE	FALSE	FALSE
NAM	2022	16.9652	FALSE	FALSE	FALSE
NER	2022	5.97468	FALSE	FALSE	FALSE
NGA	2022	12.35621	FALSE	FALSE	FALSE
NIC	2022	33.62729	FALSE	FALSE	FALSE
NIU	2022	66.57667	FALSE	FALSE	FALSE
NLD	2022	14.54182	FALSE	FALSE	TRUE
NOR	2022	19.14644	FALSE	FALSE	TRUE
NPL	2022	6.98949	FALSE	FALSE	FALSE
NRU	2022	69.9186	FALSE	FALSE	FALSE
NZL	2022	33.62131	FALSE	FALSE	TRUE
OMN	2022	31.09542	FALSE	FALSE	FALSE
PAK	2022	23.0065	FALSE	FALSE	FALSE
PAN	2022	36.07102	FALSE	FALSE	FALSE
PER	2022	27.28843	FALSE	FALSE	FALSE
PHL	2022	8.74173	FALSE	FALSE	FALSE
PLW	2022	41.14166	FALSE	FALSE	FALSE
PNG	2022	20.51736	FALSE	FALSE	FALSE
POL	2022	27.4997	FALSE	FALSE	TRUE
PRI	2022	41.13383	FALSE	FALSE	FALSE
PRK	2022	10.7961	FALSE	FALSE	FALSE
PRT	2022	21.79111	FALSE	FALSE	TRUE
PRY	2022	32.95919	FALSE	FALSE	FALSE
PSE	2022	37.56084	FALSE	FALSE	FALSE
PYF	2022	48.09347	FALSE	FALSE	FALSE
QAT	2022	43.14167	FALSE	FALSE	FALSE
ROU	2022	34.03971	FALSE	FALSE	FALSE
RUS	2022	24.19482	FALSE	TRUE	FALSE
RWA	2022	4.92348	FALSE	FALSE	FALSE
SAU	2022	40.59908	FALSE	TRUE	FALSE
SDN	2022	17.005	FALSE	FALSE	FALSE
SEN	2022	10.20714	FALSE	FALSE	FALSE
SGP	2022	13.87663	FALSE	FALSE	FALSE
SLB	2022	22.60238	FALSE	FALSE	FALSE
SLE	2022	7.13001	FALSE	FALSE	FALSE
SLV	2022	30.88003	FALSE	FALSE	FALSE
SOM	2022	14.61383	FALSE	FALSE	FALSE
SRB	2022	22.50792	FALSE	FALSE	FALSE
SSD	2022	8.60383	FALSE	FALSE	FALSE
STP	2022	16.45528	FALSE	FALSE	FALSE
SUR	2022	29.01503	FALSE	FALSE	FALSE
SVK	2022	26.82425	FALSE	FALSE	TRUE
SVN	2022	19.44181	FALSE	FALSE	TRUE
SWE	2022	15.26701	FALSE	FALSE	TRUE
SWZ	2022	30.08669	FALSE	FALSE	FALSE
SYC	2022	29.36169	FALSE	FALSE	FALSE
SYR	2022	33.94172	FALSE	FALSE	FALSE
TCD	2022	6.69228	FALSE	FALSE	FALSE
TGO	2022	11.56099	FALSE	FALSE	FALSE
THA	2022	15.38461	FALSE	FALSE	FALSE
TJK	2022	23.79315	FALSE	FALSE	FALSE
TKL	2022	69.81812	FALSE	FALSE	FALSE
TKM	2022	21.4022	FALSE	FALSE	FALSE
TLS	2022	2.35035	FALSE	FALSE	FALSE
TON	2022	71.65012	FALSE	FALSE	FALSE
TTO	2022	28.05278	FALSE	FALSE	FALSE
TUN	2022	26.83223	FALSE	FALSE	FALSE
TUR	2022	33.30083	FALSE	TRUE	TRUE
TUV	2022	64.19953	FALSE	FALSE	FALSE
TZA	2022	12.58325	FALSE	FALSE	FALSE
UGA	2022	7.90456	FALSE	FALSE	FALSE
UKR	2022	23.63479	FALSE	FALSE	FALSE
URY	2022	33.34379	FALSE	FALSE	FALSE
USA	2022	41.98672	TRUE	TRUE	TRUE
UZB	2022	30.02845	FALSE	FALSE	FALSE
VCT	2022	33.24897	FALSE	FALSE	FALSE
VEN	2022	22.71592	FALSE	FALSE	FALSE
VNM	2022	2.01574	FALSE	FALSE	FALSE
VUT	2022	21.280639999999998	FALSE	FALSE	FALSE
WSM	2022	62.42939	FALSE	FALSE	FALSE
YEM	2022	13.65372	FALSE	FALSE	FALSE
ZAF	2022	30.81971	FALSE	TRUE	FALSE
ZMB	2022	11.07855	FALSE	FALSE	FALSE
ZWE	2022	14.21078	FALSE	FALSE	FALSE
NA	2022	28.63679	FALSE	FALSE	FALSE
NA	2022	15.78523	FALSE	FALSE	FALSE
NA	2022	33.7716	FALSE	FALSE	FALSE
NA	2022	8.46088	FALSE	FALSE	FALSE
NA	2022	9.62438	FALSE	FALSE	FALSE
NA	2022	15.82855	FALSE	FALSE	FALSE
NA	2022	12.08424	FALSE	FALSE	FALSE
NA	2022	7.99807	FALSE	FALSE	FALSE
NA	2022	22.64571	FALSE	FALSE	FALSE
NA	2022	12.0944	FALSE	FALSE	FALSE
NA	2022	25.88038	FALSE	FALSE	FALSE