#install our packages
install.packages("tidyverse")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("tidyquant")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("lubridate")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("plotly")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("esquisse")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("here")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("janitor")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("ggthemes")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("ggrepel")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("gt")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("countrycode")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
install.packages("wbstats")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)
#load our packages
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(tidyquant)
## Loading required package: lubridate
##
## Attaching package: 'lubridate'
##
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
##
## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
##
##
## Attaching package: 'xts'
##
## The following objects are masked from 'package:dplyr':
##
## first, last
##
##
## Attaching package: 'PerformanceAnalytics'
##
## The following object is masked from 'package:graphics':
##
## legend
##
## Loading required package: quantmod
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(lubridate)
library(plotly)
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
library(esquisse)
library(here)
## here() starts at /cloud/project
library(janitor)
##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library(ggthemes)
library(ggrepel)
library(gt)
library(countrycode)
library(wbstats)
options(scipen=10) # forces regular notation vs scientific notation (ie5)
#Load the IMF/WB country groups, and load the full emissions dataset
folder_path <- partial(here, "00_data", "sov_debt_paris_alignment")
imf_wb_country_groups <- folder_path("imf_wb_country_groups.rds") %>%
read_rds()
emissions_dataset_full <- folder_path("emissions_dataset_full.rds") %>%
read_rds()
emissions_dataset <- folder_path("emissions_dataset.rds") %>%
read_rds()
#Calculate interesting summary statistics for at least one group
emissions_dataset_full%>%
#I want to group by years
group_by(year)%>%
#I want to see the average, minimum, maximum & mean value of the gdp ues current prices in each year
summarise(average_gdp_usd_current_prices=mean(gdp_usd_current_prices,na.rm = TRUE),
max_gdp_usd_current_prices=max(gdp_usd_current_prices,na.rm = TRUE),
min_gdp_usd_current_prices=min(gdp_usd_current_prices,na.rm = TRUE),
median_gdp_usd_current_prices=median(gdp_usd_current_prices,na.rm = TRUE)
)
## # A tibble: 30 × 5
## year average_gdp_usd_current_prices max_gdp_usd_current_pr…¹ min_g…² media…³
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1990 149. 5963. 0.043 7.45
## 2 1991 154. 6158. 0.047 6.97
## 3 1992 150. 6520. 0.048 7.16
## 4 1993 152. 6859. 0.047 7.25
## 5 1994 162. 7287. 0.055 8.00
## 6 1995 175. 7640. 0.056 8.47
## 7 1996 179. 8073. 0.067 8.38
## 8 1997 177. 8578. 0.067 9.75
## 9 1998 175. 9063. 0.066 9.76
## 10 1999 181. 9631. 0.069 10.6
## # … with 20 more rows, and abbreviated variable names
## # ¹​max_gdp_usd_current_prices, ²​min_gdp_usd_current_prices,
## # ³​median_gdp_usd_current_prices
Three professional charts.
Charts1: Top 8 emission countries by cumulative CO2 per capita in
2018
emissions_dataset %>%
# filter the year in 2018
filter(year == 2018) %>%
# get the top 8 by cumulative Co2 per capita
slice_max(order_by = cumulative_co2_per_capita, n = 8) %>%
# fct_reorder will sort x by cumulative Co2 per capita
ggplot(aes(x = fct_reorder(.f = country_name,.x = cumulative_co2_per_capita,
.desc = TRUE),
# fill will change the color by whether a country is EM or DM
y = cumulative_co2_per_capita, fill = em_dm)) +
# just get used to the `stat = identity` thing for bar charts, default is `count`
geom_bar(stat = "identity") +
geom_text(aes(label = format(cumulative_co2_per_capita, digits = 7, big.mark = ",")), vjust = -0.2) +
# expand the y limits so the text doesn't get cut off
scale_y_continuous(limits = c(0, 1500), breaks = scales::pretty_breaks(n = 10)) +
# change the color
scale_fill_manual(values = c("Developed Markets" = "006090", "Emerging Markets" = "#007090")) +
# a minimal theme with mostly white space
theme_minimal() +
labs(title = "Top 8 Emission Countries in 2018",
subtitle = "based on cumulative CO2 per capita",
x = "Country",
y = "Cumulative CO2 per capita (tons)",
fill = "", # this gets rid of the `em_dm` tag on top of the legend,
caption = "Data from WB/IMF, Analysis by Yulin"
) +
# moves the legend from the side (default) to the bottom.
theme(legend.position = "bottom")
Chart2: Top8 emission countries by cumulative CO2 in 2018
emissions_dataset %>%
# filter the year in 2018
filter(year == 2018) %>%
# get the top 8 by cumulative CO2
slice_max(order_by = cumulative_co2, n = 8) %>%
# fct_reorder will sort x by cumulative Co2
ggplot(aes(x = fct_reorder(.f = country_name,.x = cumulative_co2,
.desc = TRUE),
# fill will change the color by whether a country is EM or DM
y = cumulative_co2, fill = em_dm)) +
# just get used to the `stat = identity` thing for bar charts, default is `count`
geom_bar(stat = "identity") +
geom_text(aes(label = format(cumulative_co2, digits = 7, big.mark = ",")), vjust = -0.2) +
# expand the y limits so the text doesn't get cut off
scale_y_continuous(limits = c(0,450000), breaks = scales::pretty_breaks(n = 10)) +
# change the color
scale_fill_manual(values = c("Developed Markets" = "007020", "Emerging Markets" = "#005020")) +
# a minimal theme with mostly white space
theme_minimal() +
labs(title = "Top 8 Emission Countries in 2018",
subtitle = "based on cumulative CO2",
x = "Country",
y = "Cumulative CO2 (tons)",
fill = "", # this gets rid of the `em_dm` tag on top of the legend,
caption = "Data from WB/IMF, Analysis by Yulin"
) +
# moves the legend from the side (default) to the bottom.
theme(legend.position = "bottom")
Chart3: Top10 trde CO2 country in 2018
emissions_dataset %>%
# filter the year in 2018
filter(year == 2018) %>%
# get the top 10 by trade CO2
slice_max(order_by = trade_co2, n = 10) %>%
# fct_reorder will sort x by trade co2
ggplot(aes(x = fct_reorder(.f = country_name,.x = trade_co2,
.desc = TRUE),
# fill will change the color by whether a country is EM or DM
y = trade_co2, fill = em_dm)) +
# just get used to the `stat = identity` thing for bar charts, default is `count`
geom_bar(stat = "identity") +
geom_text(aes(label = format(trade_co2, digits = 7, big.mark = ",")), vjust = -0.2) +
# expand the y limits so the text doesn't get cut off
scale_y_continuous(limits = c(0,400), breaks = scales::pretty_breaks(n = 10)) +
# change the colour
scale_fill_manual(values = c("Developed Markets" = "002020", "Emerging Markets" = "002000")) +
# a minimal theme with mostly white space
theme_minimal() +
labs(title = "Top 10 Trade CO2 Contry",
subtitle = "Year 2018",
x = "Country",
y = "Trade CO2",
fill = "", # this gets rid of the `em_dm` tag on top of the legend,
caption = "Data from WB/IMF, Analysis by Yulin"
) +
# moves the legend from the side (default) to the bottom.
theme(legend.position = "bottom")
