Question Formation + Exploratory Data Analysis
Jing Yan
2022-11-08
#Create folder path for data access
folder_path <- partial(here, "03_data_processed")
folder_path() %>% list.files()## [1] "country_features_2022-10.csv" "emissions_dataset_full.csv"
## [3] "emissions_dataset.csv" "Green_bond_full_dataset.csv"
## [5] "imf_weo_by_country_2022_oct.csv"#Import data
emissions_dataset <- folder_path("emissions_dataset.csv") %>%
read_csv()## New names:
## Rows: 2820 Columns: 32
## ── Column specification
## ────────────────────────────────────────────────────────
## Delimiter: "," chr (3): country_name, iso3c, em_dm dbl (29): ...1, year,
## gdp_usd_current_prices, gdp_ppp_current_prices, gdp_pc...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`emissions_dataset_full <- folder_path("emissions_dataset_full.csv") %>%
read_csv()## New names:
## Rows: 6702 Columns: 32
## ── Column specification
## ────────────────────────────────────────────────────────
## Delimiter: "," chr (1): iso3c dbl (31): ...1, year, gdp_usd_current_prices,
## gdp_ppp_current_prices, gdp_pc...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`imf_weo_by_country_2022 <- folder_path("imf_weo_by_country_2022_oct.csv") %>%
read_csv()## New names:
## Rows: 414000 Columns: 10
## ── Column specification
## ────────────────────────────────────────────────────────
## Delimiter: "," chr (7): country_name, iso3c, short_name_unit, short_name,
## short_unit, categ... dbl (3): ...1, year, value
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`country_features_2022 <- folder_path("country_features_2022-10.csv") %>%
read_csv()## New names:
## Rows: 217 Columns: 9
## ── Column specification
## ────────────────────────────────────────────────────────
## Delimiter: "," chr (4): country_name, iso3c, wb_income_group, wb_region dbl
## (5): ...1, debt_gross_percent_of_gdp, nominal_gdp_bn_ppp, nominal_gdp_pe...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`Green_bond_full_dataset <- folder_path("Green_bond_full_dataset.csv") %>%
read_csv()## New names:
## Rows: 5006 Columns: 21
## ── Column specification
## ────────────────────────────────────────────────────────
## Delimiter: "," chr (18): description, maturity_date, coupon_class, currency,
## ESG_bond_type,... dbl (3): ...1, amount_outstanding_usd, issued_amount_usd
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`#Get subsets of Green_bond_full_dataset
green_bond_issued_amount_10 <- Green_bond_full_dataset %>%
group_by(country_of_issue) %>%
summarize(issued_amount_usd = sum(issued_amount_usd)) %>%
arrange(desc(issued_amount_usd)) %>%
slice (1:10)
green_bond_outstanding_amount_10 <- Green_bond_full_dataset %>%
group_by(country_of_issue) %>%
summarize(amount_outstanding_usd = sum(amount_outstanding_usd)) %>%
arrange(desc(amount_outstanding_usd)) %>%
slice (1:10)#Define gppr_theme() function
theme_gppr <- function(){
font <- "Georgia" #assign font family up front
theme_pander() %+replace% #replace elements we want to change
theme(
#text elements
plot.title = element_text( #title
family = font, #set font family
size = 16, #set font size
face = 'bold', #bold typeface
hjust = 0, #left align
vjust = 0), #raise slightly
plot.subtitle = element_text( #subtitle
family = font, #font family
size = 12), #font size
plot.caption = element_text( #caption
family = font, #font family
size = 9, #font size
hjust = 1), #right align
axis.title = element_text( #axis titles
family = font, #font family
size = 10), #font size
axis.text = element_text( #axis text
family = font, #axis famuly
size = 9), #font size
axis.text.x = element_text( #margin for axis text
margin=margin(5, b = 10))
)
}#Horizontal barplot in terms of Top 10 countries with the highest issuance amount of green bonds
green_bond_issued_amount_10 %>%
ggplot(aes(fct_reorder(country_of_issue, issued_amount_usd),issued_amount_usd)) +
geom_col() +
coord_flip() +
scale_y_continuous(labels = comma) +
scale_x_discrete (guide = guide_axis(n.dodge=1.75)) +
labs(
x = "",
y = "Issued amount of Green bonds in USD",
title = "Who are the largest issuers of green bonds?",
subtitle = "Top 10 countries with the highest issuance amount of green bonds",
caption = "Data source: Refinitiv"
)+
theme_gppr()
#Horizontal barplot in terms of top 10 countries with the highest outstanding amount of green bonds
green_bond_outstanding_amount_10 %>%
ggplot(aes(fct_reorder(country_of_issue, amount_outstanding_usd),amount_outstanding_usd)) +
geom_col() +
coord_flip() +
scale_y_continuous(labels = comma) +
scale_x_discrete (guide = guide_axis(n.dodge=1.75)) +
labs(
x = "",
y = "Outstanding amount of Green bonds in USD",
title = "Who are the largest issuers of green bond?",
subtitle = "Top 10 countries with the highest outstanding amount of green bonds",
caption = "Data source: Refinitiv"
)+
theme_gppr()
#Get a subset of Green_bond_full_dataset
green_bond_issued_and_outstanding <- Green_bond_full_dataset %>%
group_by(country_of_issue) %>%
summarize(issued_amount_usd = sum(issued_amount_usd),
amount_outstanding_usd = sum(amount_outstanding_usd)) %>%
arrange(desc(amount_outstanding_usd))#Lollipop plot to stress the differences between issue amount and outstanding amount of green bonds
ggplot(green_bond_issued_and_outstanding) +
geom_segment( aes(x=country_of_issue, xend=country_of_issue, y=amount_outstanding_usd, yend=issued_amount_usd), color="grey") +
geom_point( aes(x=country_of_issue, y=amount_outstanding_usd), color=rgb(0.2,0.7,0.1,0.5), size=3 ) +
geom_point( aes(x=country_of_issue, y=issued_amount_usd), color=rgb(0.7,0.2,0.1,0.5), size=3 ) +
coord_flip()+
theme_grey() +
theme(
legend.position = "none",
) +
xlab("") +
ylab("Amount of Green Bonds in USD")
#join country_features_2022 and get a subset of Green_bond_full_dataset
green_bond_country_features <- Green_bond_full_dataset %>%
left_join(country_features_2022, by = "iso3c") %>%
group_by(country_of_issue, wb_income_group, wb_region)%>%
summarize(issued_amount_usd_mean = mean(issued_amount_usd),
amount_outstanding_usd_mean = mean(amount_outstanding_usd))## `summarise()` has grouped output by 'country_of_issue', 'wb_income_group'. You
## can override using the `.groups` argument.green_bond_country_features ## # A tibble: 56 × 5
## # Groups: country_of_issue, wb_income_group [56]
## country_of_issue wb_income_group wb_region issued_a…¹ amoun…²
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Argentina Upper Middle Latin America & Caribbean 2.37e7 2.19e7
## 2 Australia High East Asia & Pacific 3.85e8 3.41e8
## 3 Austria High Europe & Central Asia 1.97e8 1.88e8
## 4 Bangladesh Lower Middle South Asia 2.95e8 2.95e8
## 5 Belgium High Europe & Central Asia 1.07e9 1.07e9
## 6 Brazil Upper Middle Latin America & Caribbean 5.54e7 5.25e7
## 7 Canada High North America 4.70e8 4.51e8
## 8 Chile High Latin America & Caribbean 6.15e7 5.46e7
## 9 China Upper Middle East Asia & Pacific 2.06e8 1.30e8
## 10 Colombia Upper Middle Latin America & Caribbean 7.49e7 6.58e7
## # … with 46 more rows, and abbreviated variable names ¹​issued_amount_usd_mean,
## # ²​amount_outstanding_usd_mean
## # ℹ Use `print(n = ...)` to see more rows#generate ridgeline plot for income groups
ggplot(green_bond_country_features, aes(x = issued_amount_usd_mean, y = wb_income_group, fill = wb_income_group)) +
geom_density_ridges_gradient(scale = 3, rel_min_height = 0.01) +
labs(title = 'The distribution of issuance amount of green bonds for income groups') +
theme_ridges() +
theme(
legend.position="none",
panel.spacing = unit(0.1, "lines"),
strip.text.x = element_text(size = 8)
)## Picking joint bandwidth of 71400000
#generate ridgeline plot for region groups
ggplot(green_bond_country_features, aes(x = issued_amount_usd_mean, y = wb_region, fill = wb_region)) +
geom_density_ridges_gradient(scale = 3, rel_min_height = 0.01) +
labs(title = 'The distribution of issuance amount of green bonds for region groups') +
theme_ridges() +
theme(
legend.position="none",
panel.spacing = unit(0.1, "lines"),
strip.text.x = element_text(size = 8)
)## Picking joint bandwidth of 67500000
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.