Homework 4

Pre-Homework Exercises:

options(repos = c(CRAN = "https://cran.rstudio.com/"))
usethis::use_blank_slate()
# Load the necessary packages
install.packages("tidyverse")

The downloaded binary packages are in
    /var/folders/25/scx22j0150v_7hw79jvjm8gh0000gn/T//RtmpfL6iaY/downloaded_packages

install.packages("countrycode")

The downloaded binary packages are in
    /var/folders/25/scx22j0150v_7hw79jvjm8gh0000gn/T//RtmpfL6iaY/downloaded_packages

install.packages("janitor")

The downloaded binary packages are in
    /var/folders/25/scx22j0150v_7hw79jvjm8gh0000gn/T//RtmpfL6iaY/downloaded_packages

library(tidyr)
library(dplyr)

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

library(countrycode)
library(ggplot2)
library(RColorBrewer)
library(countrycode)
library(dplyr)
library(ggplot2)
library(janitor) 

Attaching package: 'janitor'

The following objects are masked from 'package:stats':

    chisq.test, fisher.test

library(viridis)

Loading required package: viridisLite

usethis::use_blank_slate()

library(tidyverse) # because, always

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats   1.0.0     ✔ readr     2.1.5
✔ lubridate 1.9.3     ✔ stringr   1.5.1
✔ purrr     1.0.2     ✔ tibble    3.2.1

── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(janitor) # for clean_names() - makes variable names snake_case

imf_climate_dashboards_green_debt_url <- "https://opendata.arcgis.com/datasets/8e2772e0b65f4e33a80183ce9583d062_0.csv"

green_debt <- imf_climate_dashboards_green_debt_url |> 
  read_csv() 

Rows: 355 Columns: 42
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (12): Country, ISO2, ISO3, Indicator, Unit, Source, CTS_Code, CTS_Name, ...
dbl (30): ObjectId, F1985, F1986, F1987, F1990, F1991, F1992, F1993, F1994, ...

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.

green_debt

# A tibble: 355 × 42
   ObjectId Country         ISO2  ISO3  Indicator Unit  Source CTS_Code CTS_Name
      <dbl> <chr>           <chr> <chr> <chr>     <chr> <chr>  <chr>    <chr>   
 1        1 Argentina       AR    ARG   Green Bo… Bill… Refin… ECFFI    Green B…
 2        2 Australia       AU    AUS   Green Bo… Bill… Refin… ECFFI    Green B…
 3        3 Austria         AT    AUT   Green Bo… Bill… Refin… ECFFI    Green B…
 4        4 Austria         AT    AUT   Sovereig… Bill… Refin… ECFF     Green B…
 5        5 Bangladesh      BD    BGD   Green Bo… Bill… Refin… ECFFI    Green B…
 6        6 Belarus, Rep. … BY    BLR   Green Bo… Bill… Refin… ECFFI    Green B…
 7        7 Belarus, Rep. … BY    BLR   Sovereig… Bill… Refin… ECFF     Green B…
 8        8 Belgium         BE    BEL   Green Bo… Bill… Refin… ECFFI    Green B…
 9        9 Belgium         BE    BEL   Sovereig… Bill… Refin… ECFF     Green B…
10       10 Bermuda         BM    BMU   Green Bo… Bill… Refin… ECFFI    Green B…
# ℹ 345 more rows
# ℹ 33 more variables: CTS_Full_Descriptor <chr>, Type_of_Issuer <chr>,
#   Use_of_Proceed <chr>, Principal_Currency <chr>, F1985 <dbl>, F1986 <dbl>,
#   F1987 <dbl>, F1990 <dbl>, F1991 <dbl>, F1992 <dbl>, F1993 <dbl>,
#   F1994 <dbl>, F1999 <dbl>, F2000 <dbl>, F2002 <dbl>, F2003 <dbl>,
#   F2004 <dbl>, F2007 <dbl>, F2008 <dbl>, F2009 <dbl>, F2010 <dbl>,
#   F2011 <dbl>, F2012 <dbl>, F2013 <dbl>, F2014 <dbl>, F2015 <dbl>, …

# we want to compare these two indicators
indicators_we_want <- c("Green Bond Issuances by Country", "Sovereign Green Bond Issuances")

green_debt_subset <- green_debt |> 
  # from the janitor package -- makes variables snake_case so they are easier to work with
  clean_names() |> 
  # filter for the vector of indicators we defined above
  filter(indicator %in% indicators_we_want) |> 
  # "f\\d{4}" is a regular expression (regex) that searches for all columns that are f + four digits.
  # Ask ChatGPT to explain this to you.
  select(country, iso3, indicator, matches("f\\d{4}")) 

green_debt_subset 

# A tibble: 107 × 32
   country iso3  indicator f1985 f1986 f1987 f1990 f1991 f1992 f1993 f1994 f1999
   <chr>   <chr> <chr>     <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1 Argent… ARG   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 2 Austra… AUS   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 3 Austria AUT   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 4 Austria AUT   Sovereig…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 5 Bangla… BGD   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 6 Belaru… BLR   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 7 Belaru… BLR   Sovereig…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 8 Belgium BEL   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 9 Belgium BEL   Sovereig…    NA    NA    NA    NA    NA    NA    NA    NA    NA
10 Bermuda BMU   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
# ℹ 97 more rows
# ℹ 20 more variables: f2000 <dbl>, f2002 <dbl>, f2003 <dbl>, f2004 <dbl>,
#   f2007 <dbl>, f2008 <dbl>, f2009 <dbl>, f2010 <dbl>, f2011 <dbl>,
#   f2012 <dbl>, f2013 <dbl>, f2014 <dbl>, f2015 <dbl>, f2016 <dbl>,
#   f2017 <dbl>, f2018 <dbl>, f2019 <dbl>, f2020 <dbl>, f2021 <dbl>,
#   f2022 <dbl>

green_debt_subset |> 
  pivot_longer(
    cols = matches("f\\d{4}")
  )

# A tibble: 3,103 × 5
   country   iso3  indicator                       name  value
   <chr>     <chr> <chr>                           <chr> <dbl>
 1 Argentina ARG   Green Bond Issuances by Country f1985    NA
 2 Argentina ARG   Green Bond Issuances by Country f1986    NA
 3 Argentina ARG   Green Bond Issuances by Country f1987    NA
 4 Argentina ARG   Green Bond Issuances by Country f1990    NA
 5 Argentina ARG   Green Bond Issuances by Country f1991    NA
 6 Argentina ARG   Green Bond Issuances by Country f1992    NA
 7 Argentina ARG   Green Bond Issuances by Country f1993    NA
 8 Argentina ARG   Green Bond Issuances by Country f1994    NA
 9 Argentina ARG   Green Bond Issuances by Country f1999    NA
10 Argentina ARG   Green Bond Issuances by Country f2000    NA
# ℹ 3,093 more rows

green_bonds_tidy <- green_debt_subset |> 
  pivot_longer(
    # select all columns with f + 4 numbers 
    cols = matches("f\\d{4}"),
    
    # change from default ("names")
    names_to = "year",
    # same with the values
    values_to = "issuance_bn_usd",
    
    # readr::parse_number is a handy function that changes the character string 
    # "f2222" into the number 2222. Very useful! 
    names_transform = readr::parse_number,
    
    # green bonds are new-ish, we can drop all those NA values in the 80s and 90s for now.
    values_drop_na = TRUE
  )

3.5.0.1 Homework problem 1:

green_debt_subset

# A tibble: 107 × 32
   country iso3  indicator f1985 f1986 f1987 f1990 f1991 f1992 f1993 f1994 f1999
   <chr>   <chr> <chr>     <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1 Argent… ARG   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 2 Austra… AUS   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 3 Austria AUT   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 4 Austria AUT   Sovereig…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 5 Bangla… BGD   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 6 Belaru… BLR   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 7 Belaru… BLR   Sovereig…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 8 Belgium BEL   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
 9 Belgium BEL   Sovereig…    NA    NA    NA    NA    NA    NA    NA    NA    NA
10 Bermuda BMU   Green Bo…    NA    NA    NA    NA    NA    NA    NA    NA    NA
# ℹ 97 more rows
# ℹ 20 more variables: f2000 <dbl>, f2002 <dbl>, f2003 <dbl>, f2004 <dbl>,
#   f2007 <dbl>, f2008 <dbl>, f2009 <dbl>, f2010 <dbl>, f2011 <dbl>,
#   f2012 <dbl>, f2013 <dbl>, f2014 <dbl>, f2015 <dbl>, f2016 <dbl>,
#   f2017 <dbl>, f2018 <dbl>, f2019 <dbl>, f2020 <dbl>, f2021 <dbl>,
#   f2022 <dbl>

# Pivot data to long format
green_debt_long <- green_debt_subset |>
  pivot_longer(
  cols = matches("f\\d{4}"),
# change from default ("names")
   names_to = "year" ,
# same with the values
  values_to = "issuance_bn_usd" ,
# readr::parse_number is a handy function that changes the character string 
# "f2222" into the number 2222. Very useful! 
 names_transform = readr::parse_number ,
# green bonds are new-ish, we can drop all those NA values in the 80s and 90s for now.
 values_drop_na = TRUE
)
green_debt_long

# A tibble: 465 × 5
   country   iso3  indicator                        year issuance_bn_usd
   <chr>     <chr> <chr>                           <dbl>           <dbl>
 1 Argentina ARG   Green Bond Issuances by Country  2017          0.974 
 2 Argentina ARG   Green Bond Issuances by Country  2020          0.0500
 3 Argentina ARG   Green Bond Issuances by Country  2021          0.916 
 4 Argentina ARG   Green Bond Issuances by Country  2022          0.207 
 5 Australia AUS   Green Bond Issuances by Country  2014          0.526 
 6 Australia AUS   Green Bond Issuances by Country  2015          0.413 
 7 Australia AUS   Green Bond Issuances by Country  2016          0.531 
 8 Australia AUS   Green Bond Issuances by Country  2017          2.53  
 9 Australia AUS   Green Bond Issuances by Country  2018          2.22  
10 Australia AUS   Green Bond Issuances by Country  2019          1.98  
# ℹ 455 more rows

# Step 2: Add region to green_debt_long
green_debt_long <- green_debt_long |>
  mutate(region = countrycode(iso3, "iso3c", "region"))

# Step 3: Calculate cumulative issuance by region
green_debt_cumulative <- green_debt_long |>
  group_by(region) |>
  summarize(cumulative_issuance = sum(issuance_bn_usd, na.rm = TRUE))

# Step 4: Create a ggplot visualization
region_plot <- ggplot(green_debt_cumulative, aes(x = reorder(region, cumulative_issuance), y = cumulative_issuance)) +
  geom_col(fill = "forestgreen") +
  coord_flip() +
  theme_minimal() +
  scale_y_continuous(labels = scales::label_dollar(suffix = " bn"),
                     expand = c(0,0)) +
  labs(title = "Cumulative Green Bond Issuance by Region",
       subtitle = "Europe and Central Asia are leading the pack",
       x = "Region",
       y = "Cumulative Issuance",
       caption = "Data Source: IMF Climate Finance Dashboard|Insight: NP Mnguni")
region_plot

3.5.0.2 Homework problem 2:

# 1. Clean the variable names
green_debt_hw2 <- green_debt |>
  clean_names()

# 2. Filter out "Not Applicable" observations from 'type_of_issuer'
green_debt_filtered_hw2 <- green_debt_hw2 |>
  filter(type_of_issuer != "Not Applicable")

# 3. Pivot the data from wide to long format
green_debt_long_hw2 <- green_debt_filtered_hw2 |>
  pivot_longer(
    cols = starts_with("f"), 
    names_to = "year", 
    values_to = "issuance",
    names_prefix = "f",
    names_transform = list(year = as.integer)
  ) |>
  drop_na(issuance) # This drops all NA values, ensuring only years with issuances are kept

# 4. (Optional) Summarize data if needed - here we sum by type of issuer and year
green_debt_summary_hw2 <- green_debt_long_hw2 |>
  group_by(type_of_issuer, year) |>
  summarize(total_issuance = sum(issuance, na.rm = TRUE), .groups = 'drop')

# 5. Create a data visualization
# For example, a line graph showing the trend of issuances over time for each type of issuer
issuance_trend_plot <- ggplot(green_debt_summary_hw2, aes(x = year, y = total_issuance, color = type_of_issuer)) +
  geom_line() +
  theme_minimal() +
  labs(title = "Trend of Green Bond Issuances Over Time by Issuer Type",
       x = "Year",
       y = "Total Issuance",
       color = "Type of Issuer")

# Print the plot
issuance_trend_plot

# Summarize data by type_of_issuer and year
green_debt_summary_hw2 <- green_debt_long_hw2 |>
  group_by(type_of_issuer, year) |>
  summarize(total_issuance = sum(issuance, na.rm = TRUE), .groups = 'drop') |>
  clean_names() # This will also convert 'type_of_issuer' values to snake_case
green_debt_summary_hw2

# A tibble: 98 × 3
   type_of_issuer  year total_issuance
   <chr>          <int>          <dbl>
 1 Banks           1985         0.03  
 2 Banks           1986         0.3   
 3 Banks           1987         0.0751
 4 Banks           1990         0     
 5 Banks           1999         0.0482
 6 Banks           2000         0.0533
 7 Banks           2002         0.148 
 8 Banks           2003         0.01  
 9 Banks           2004         0.109 
10 Banks           2013         0.757 
# ℹ 88 more rows

# Now pivot wider
issuer_factoids <- green_debt_summary_hw2 |>
  pivot_wider(
    names_from = type_of_issuer, 
    values_from = total_issuance
    # No need for names_transform because clean_names() has already been used
  ) |> 
clean_names() 

issuer_factoids

# A tibble: 29 × 8
    year  banks international_organization local_and_state_government
   <int>  <dbl>                      <dbl>                      <dbl>
 1  1985 0.03                        NA                       NA     
 2  1986 0.3                         NA                       NA     
 3  1987 0.0751                      NA                       NA     
 4  1990 0                           NA                       NA     
 5  1999 0.0482                      NA                       NA     
 6  2000 0.0533                      NA                       NA     
 7  2002 0.148                       NA                       NA     
 8  2003 0.01                        NA                       NA     
 9  2004 0.109                       NA                       NA     
10  2013 0.757                        7.18                     0.0475
# ℹ 19 more rows
# ℹ 4 more variables: nonfinancial_corporations <dbl>,
#   other_financial_corporations <dbl>, sovereign <dbl>,
#   state_owned_entities <dbl>

# Now you can use these new column names directly in R code
# Let's say we want to calculate the multiple and percentage more for two types of issuers
# Replace 'nonfinancial_corporations' and 'state_owned_entities' with actual snake_case names from your data

issuer_factoids <- issuer_factoids |>
           mutate(
             # Multiples: Banks issued X times more than Nonfinancial corporations
             banks_x_than_nonfinancial_corporations = banks / nonfinancial_corporations,
             # Percent more: Nonfinancial corporations issued X% more than Banks
             banks_pct_more_than_nonfinancial_corporations = (banks/nonfinancial_corporations- 1) * 100
           )
         
         # Replace 'nonfinancial_corporations' and 'banks' with actual cleaned column names from pivot_wider
         # Now you can create your factoids
         factoids <- issuer_factoids |>
           summarise(
             banks_x_times_nonfinancial = first(banks_x_than_nonfinancial_corporations),
             
             banks_pct_over_nonfinancial = first(banks_pct_more_than_nonfinancial_corporations )
           )
  
         
  #factoids
         print(factoids)

# A tibble: 1 × 2
  banks_x_times_nonfinancial banks_pct_over_nonfinancial
                       <dbl>                       <dbl>
1                        1.2                          20

    #Banks issued" 1.2 times more than Nonfinancial corporations
    #Nonfinancial corporations issued 20% more than Banks

3.5.0.3 Homework problem 3: green bond proceeds

 #3.5.0.3 Homework problem 3: 
      # Pivot the data from wide to long format for use_of_proceed
       green_debt_long_proceed <- green_debt_hw2 |> 
         filter(use_of_proceed != "Not Applicable") |>  
         pivot_longer(
           cols = starts_with("f"),
           names_to = "year",
           values_to = "share",
           names_prefix = "f",
           names_transform = list(year = as.integer)
         ) 
       green_debt_long_proceed 

# A tibble: 4,002 × 15
   object_id country iso2  iso3  indicator        unit  source cts_code cts_name
       <dbl> <chr>   <chr> <chr> <chr>            <chr> <chr>  <chr>    <chr>   
 1       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 2       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 3       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 4       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 5       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 6       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 7       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 8       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 9       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
10       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
# ℹ 3,992 more rows
# ℹ 6 more variables: cts_full_descriptor <chr>, type_of_issuer <chr>,
#   use_of_proceed <chr>, principal_currency <chr>, year <int>, share <dbl>

   green_debt_long_proceed <- green_debt_hw2 |>
         filter(use_of_proceed != "Not Applicable") |> 
         pivot_longer(
           cols = starts_with("f"),
           names_to = "year",
           values_to = "share",
           names_prefix = "f",
           names_transform = list(year = as.integer)
         )  
       green_debt_long_proceed 

# A tibble: 4,002 × 15
   object_id country iso2  iso3  indicator        unit  source cts_code cts_name
       <dbl> <chr>   <chr> <chr> <chr>            <chr> <chr>  <chr>    <chr>   
 1       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 2       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 3       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 4       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 5       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 6       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 7       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 8       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 9       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
10       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
# ℹ 3,992 more rows
# ℹ 6 more variables: cts_full_descriptor <chr>, type_of_issuer <chr>,
#   use_of_proceed <chr>, principal_currency <chr>, year <int>, share <dbl>

       green_debt_wide <- green_debt_long_proceed |>
         filter(year==2022,unit=="Share") |> 
         pivot_wider(
           names_from = use_of_proceed,
           values_from = share,
           values_fill = list(amount = 0) # Filling missing values with 0
         ) |> clean_names()
       green_debt_wide

# A tibble: 69 × 82
   object_id country iso2  iso3  indicator        unit  source cts_code cts_name
       <dbl> <chr>   <chr> <chr> <chr>            <chr> <chr>  <chr>    <chr>   
 1       209 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 2       211 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 3       213 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 4       215 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 5       217 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 6       219 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 7       221 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 8       223 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
 9       225 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
10       227 World   <NA>  WLD   Cumulative Gree… Share Refin… ECFF     Green B…
# ℹ 59 more rows
# ℹ 73 more variables: cts_full_descriptor <chr>, type_of_issuer <chr>,
#   principal_currency <chr>, year <int>, access_to_essential_services <dbl>,
#   acquiring_and_distribution_of_vaccine <dbl>, acquisition <dbl>,
#   affordable_basic_infrastructure <dbl>, agriculture <dbl>,
#   alternative_energy <dbl>, aquatic_biodiversity_conservation <dbl>,
#   capital_expenditure <dbl>, capital_expenditure_financing_expenses <dbl>, …

   # Assuming object_id is the first column and year is the last column FROM HERE
       green_debt_wide_long <- green_debt_wide |>
         pivot_longer(
           cols = access_to_essential_services:other, # Pivot all columns except 'object_id' and 'year'
           names_to = "use_of_proceeds",
           values_to = "share"
         ) |>
         drop_na(share)
       
       # Select the range of columns first, then pivot
       green_debt_wide_long <- green_debt_wide |>
         select(access_to_essential_services:other) |>  # Select only the columns you want to keep
         pivot_longer(
           cols = everything(),  # Pivot all columns except 'year'
           names_to = "use_of_proceeds",
           values_to = "share"
         ) |>
         drop_na(use_of_proceeds, share)  # Drop rows where 'use_of_proceeds' or 'share' is NA
       
       # View the resulting long dataframe
       green_debt_wide_long

# A tibble: 37 × 2
   use_of_proceeds                                                      share
   <chr>                                                                <dbl>
 1 access_to_essential_services                                     0.00562  
 2 acquiring_and_distribution_of_vaccine                            0.000175 
 3 acquisition                                                      0.00324  
 4 affordable_basic_infrastructure                                  0.0000187
 5 agriculture                                                      0.000220 
 6 alternative_energy                                               0.0113   
 7 aquatic_biodiversity_conservation                                0.0331   
 8 capital_expenditure                                              0.000657 
 9 capital_expenditure_financing_expenses                           0.000794 
10 carbon_reduction_through_reforestation_and_avoided_deforestation 0.00218  
# ℹ 27 more rows

       # Calculate the total share for each category
       category_totals <- green_debt_wide_long |>
         group_by(use_of_proceeds) |>
         summarize(total_share = sum(share)) |>
         ungroup()
       
       # Define a cutoff point for the smallest categories to be grouped into 'Other'
       cutoff <- 0.1  # This is an arbitrary cutoff, adjust based on your data
       
       # Create a new category grouping the smallest ones into 'Other'
       green_debt_wide_long_s <- green_debt_wide_long |>
         left_join(category_totals, by = "use_of_proceeds") |>
         mutate(use_of_proceeds = if_else(total_share < cutoff, "other", use_of_proceeds)) |>
         group_by(use_of_proceeds) |>
         summarize(share = sum(share)) |>
         ungroup()
       
       # Now create the pie chart
       pie_chart <- ggplot(green_debt_wide_long_s, aes(x = "", y = share, fill = use_of_proceeds)) +
         geom_bar(stat = "identity", width = 1) +
         coord_polar("y", start = 0) +
         theme_void() +
         labs(title = "Green Bond Issuance by Use of Proceeds for 2022", fill = "Use of Proceeds") +
         scale_fill_viridis_d()
       
       # Display the pie chart
       print (pie_chart)

      # Procceeds are largely used for clean transport

3.5.0.3 Homework problem 3: green bond proceeds

# First, pivot the data from wide to long format
 green_debt_long_currency <- green_debt_hw2 |>
    pivot_longer(
         cols = starts_with("f"), 
         names_to = "year", 
        values_to = "share",
        names_prefix = "f",
         names_transform = list(year = as.integer)
    )
       
        # Filter rows where the unit is "Share"
         long_currency_filtered <- green_debt_long_currency |> 
         filter(unit == "Share")
        
      # You don't need to filter share != "NA" as it will be NA, not the string "NA"
        # Also, you don't need to select again if you're not changing the columns
         green_debt_wide <- long_currency_filtered |>
          filter(principal_currency != "Not Applicable") 
         # Calculate the total share for each currency
         category_totals <- green_debt_wide |>
         group_by(principal_currency) |>
          summarize(total_share = sum(as.numeric(share), na.rm = TRUE)) |>
          ungroup()
       
        # Define a cutoff point for the smallest categories to be grouped into 'Other'
        cutoff <- 0.1  # Adjust based on your data
       
         # Group the smallest currencies into 'Other'
         green_debt_wide_s <- green_debt_wide |>
          left_join(category_totals, by = "principal_currency") |>
          mutate(principal_currency = if_else(total_share < cutoff, "Other", principal_currency)) |>
         group_by(principal_currency) |>
         summarize(share = sum(as.numeric(share), na.rm = TRUE)) |>
          ungroup()
       green_debt_wide_s

# A tibble: 4 × 2
  principal_currency share
  <chr>              <dbl>
1 Chinese Yuan       0.142
2 Euro               0.427
3 Other              0.176
4 US Dollar          0.254

        # Calculate percentages for each principal_currency
         green_debt_wide_s <- green_debt_wide_s |>
          mutate(percentage = share / sum(share) * 100)
       
        # Create the pie chart with percentages and bright colors
         pie_chart_currency <- ggplot(green_debt_wide_s, aes(x = "", y = share, fill = principal_currency)) +
         geom_bar(stat = "identity", width = 1) +
          coord_polar("y", start = 0) +
          theme_void() +
           labs(title = "Green Bond Issuance by Currency for 2022", fill = "Currency") +
         scale_fill_brewer(palette = "Set2") +  # Use a bright color palette from RColorBrewer
          geom_text(aes(label = sprintf("%0.1f%%", percentage)), position = position_stack(vjust = 0.5))
       
         # Display the pie chart
 print(pie_chart_currency)

 #Currency doesnt appear to be changing over time, its largely in Euros and Chinese Yuan.