Problem 1.1
Use the workflow developed in this chapter to import and tidy worksheet 2.3 EV from the dataset.
# The easiest way to get readr is to install the whole tidyverse: options (repos = c (CRAN = "https://cran.rstudio.com/" ))install.packages ("tidyverse" )
The downloaded binary packages are in
/var/folders/2p/9wzbkfqj1699rqy549yz78sh0000gn/T//Rtmp56Ea4I/downloaded_packages
# Alternatively, install just readr: install.packages ("readr" )
The downloaded binary packages are in
/var/folders/2p/9wzbkfqj1699rqy549yz78sh0000gn/T//Rtmp56Ea4I/downloaded_packages
install.packages ("purrr" )
The downloaded binary packages are in
/var/folders/2p/9wzbkfqj1699rqy549yz78sh0000gn/T//Rtmp56Ea4I/downloaded_packages
install.packages ("readxl" )
The downloaded binary packages are in
/var/folders/2p/9wzbkfqj1699rqy549yz78sh0000gn/T//Rtmp56Ea4I/downloaded_packages
library (here) # for using relative file paths
here() starts at /Users/fangjun/Desktop/Sais/Year2/Term2/Sustainable Finance/W5/data-raw
library (purrr)library (readxl)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
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats 1.0.0 ✔ readr 2.1.5
✔ ggplot2 3.4.4 ✔ stringr 1.5.1
✔ lubridate 1.9.3 ✔ 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 (here)<- here ("CM_Data_Explorer.xlsx" )
[1] "/Users/fangjun/Desktop/Sais/Year2/Term2/Sustainable Finance/W5/data-raw/CM_Data_Explorer.xlsx"
library (purrr)library (readxl)<- partial (# provide the function, in this case readxl::read_excel() .f = read_excel,# provide any arguments you want filled in path = path_to_sheet,sheet = "2.3 EV" ,col_names = FALSE # now all we have to do is provide the range <- read_EV_sheet (range = "A4:W5" )
New names:
• `` -> `...1`
• `` -> `...2`
• `` -> `...3`
• `` -> `...4`
• `` -> `...5`
• `` -> `...6`
• `` -> `...7`
• `` -> `...8`
• `` -> `...9`
• `` -> `...10`
• `` -> `...11`
• `` -> `...12`
• `` -> `...13`
• `` -> `...14`
• `` -> `...15`
• `` -> `...16`
• `` -> `...17`
• `` -> `...18`
• `` -> `...19`
• `` -> `...20`
• `` -> `...21`
• `` -> `...22`
• `` -> `...23`
# A tibble: 2 × 23
...1 ...2 ...3 ...4 ...5 ...6 ...7 ...8 ...9 ...10 ...11 ...12 ...13
<lgl> <dbl> <lgl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <lgl> <chr> <dbl> <dbl>
1 NA NA NA State… NA NA NA NA NA NA Anno… NA NA
2 NA 2022 NA 2025 2030 2035 2040 2045 2050 NA 2025 2030 2035
# ℹ 10 more variables: ...14 <dbl>, ...15 <dbl>, ...16 <dbl>, ...17 <lgl>,
# ...18 <chr>, ...19 <dbl>, ...20 <dbl>, ...21 <dbl>, ...22 <dbl>,
# ...23 <dbl>
library (tidyr)library (dplyr)<- sheet_header |> # transpose the data t () |> # turn it back into a tibble as_tibble () |> # make them meaningful rename (scenario = V1, year = V2) |> # fill scenario down: If there are any NA (missing) values in the scenario column, this function will fill those NA values with the last observed non-NA value above them fill (scenario) |> #insert "Current" at top replace_na (list (scenario = "Current Year" ))
Warning: The `x` argument of `as_tibble.matrix()` must have unique column names if
`.name_repair` is omitted as of tibble 2.0.0.
ℹ Using compatibility `.name_repair`.
# A tibble: 23 × 2
scenario year
<chr> <chr>
1 Current Year <NA>
2 Current Year 2022
3 Current Year <NA>
4 Stated policies scenario 2025
5 Stated policies scenario 2030
6 Stated policies scenario 2035
7 Stated policies scenario 2040
8 Stated policies scenario 2045
9 Stated policies scenario 2050
10 Stated policies scenario <NA>
# ℹ 13 more rows
<- read_EV_sheet (range = "A7" ) |> pull ()
New names:
• `` -> `...1`
[1] "Constrained nickel supply"
<- read_EV_sheet (range = "A8:W19" )
New names:
• `` -> `...1`
• `` -> `...2`
• `` -> `...3`
• `` -> `...4`
• `` -> `...5`
• `` -> `...6`
• `` -> `...7`
• `` -> `...8`
• `` -> `...9`
• `` -> `...10`
• `` -> `...11`
• `` -> `...12`
• `` -> `...13`
• `` -> `...14`
• `` -> `...15`
• `` -> `...16`
• `` -> `...17`
• `` -> `...18`
• `` -> `...19`
• `` -> `...20`
• `` -> `...21`
• `` -> `...22`
• `` -> `...23`
# A tibble: 12 × 23
...1 ...2 ...3 ...4 ...5 ...6 ...7 ...8 ...9 ...10
<chr> <dbl> <lgl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <lgl>
1 Copper 3.81e+2 NA 6.17e+2 1.39e+3 1.74e+3 2.23e+3 2.42e+3 2.31e+3 NA
2 Cobalt 6.35e+1 NA 6.12e+1 3.80e+1 2.91e+1 3.54e+1 4.09e+1 4.74e+1 NA
3 Graphite 5.57e+2 NA 9.36e+2 1.59e+3 1.78e+3 1.69e+3 1.49e+3 1.08e+3 NA
4 Lithium 6.96e+1 NA 1.23e+2 2.19e+2 3.07e+2 4.07e+2 4.50e+2 4.13e+2 NA
5 Manganese 7.45e+1 NA 5.39e+1 1.56e+2 3.36e+2 5.33e+2 7.12e+2 8.58e+2 NA
6 Nickel 3.13e+2 NA 5.54e+2 5.13e+2 5.89e+2 6.30e+2 6.92e+2 6.88e+2 NA
7 Silicon 8.70e+0 NA 4.05e+1 1.39e+2 2.24e+2 3.52e+2 3.74e+2 3.73e+2 NA
8 Neodymium 3.96e+0 NA 7.25e+0 1.22e+1 1.51e+1 1.88e+1 2.18e+1 2.29e+1 NA
9 Dysprosi… 4.13e-1 NA 7.41e-1 1.21e+0 1.48e+0 1.84e+0 2.13e+0 2.23e+0 NA
10 Praseody… 5.94e-1 NA 1.09e+0 1.83e+0 2.27e+0 2.83e+0 3.27e+0 3.43e+0 NA
11 Terbium 8.06e-2 NA 1.48e-1 2.52e-1 3.14e-1 3.91e-1 4.52e-1 4.74e-1 NA
12 Total EV 1.47e+3 NA 2.39e+3 4.06e+3 5.02e+3 5.91e+3 6.21e+3 5.80e+3 NA
# ℹ 13 more variables: ...11 <dbl>, ...12 <dbl>, ...13 <dbl>, ...14 <dbl>,
# ...15 <dbl>, ...16 <dbl>, ...17 <lgl>, ...18 <dbl>, ...19 <dbl>,
# ...20 <dbl>, ...21 <dbl>, ...22 <dbl>, ...23 <dbl>
library (tidyverse)<- names (EV_info)
[1] "...1" "...2" "...3" "...4" "...5" "...6" "...7" "...8" "...9"
[10] "...10" "...11" "...12" "...13" "...14" "...15" "...16" "...17" "...18"
[19] "...19" "...20" "...21" "...22" "...23"
<- sheet_header_processed |> add_column (EV_info_col_names = EV_info_col_names)
# A tibble: 23 × 3
scenario year EV_info_col_names
<chr> <chr> <chr>
1 Current Year <NA> ...1
2 Current Year 2022 ...2
3 Current Year <NA> ...3
4 Stated policies scenario 2025 ...4
5 Stated policies scenario 2030 ...5
6 Stated policies scenario 2035 ...6
7 Stated policies scenario 2040 ...7
8 Stated policies scenario 2045 ...8
9 Stated policies scenario 2050 ...9
10 Stated policies scenario <NA> ...10
# ℹ 13 more rows
<- EV_info |> rename (indicator = ` ...1 ` ) |> pivot_longer (cols = - indicator,names_to = "EV_info_col_names" ) |> add_column (EV_name)
# A tibble: 264 × 4
indicator EV_info_col_names value EV_name
<chr> <chr> <dbl> <chr>
1 Copper ...2 381. Constrained nickel supply
2 Copper ...3 NA Constrained nickel supply
3 Copper ...4 617. Constrained nickel supply
4 Copper ...5 1389. Constrained nickel supply
5 Copper ...6 1736. Constrained nickel supply
6 Copper ...7 2233. Constrained nickel supply
7 Copper ...8 2418. Constrained nickel supply
8 Copper ...9 2313. Constrained nickel supply
9 Copper ...10 NA Constrained nickel supply
10 Copper ...11 732. Constrained nickel supply
# ℹ 254 more rows
<- EV_info_long |> left_join (sheet_headers_and_col_names, by = join_by (EV_info_col_names)) |> # filter out what were empty columns (where years are NA) #There's a blannk column in Excel filter (! is.na (year)) |> # case_when is supercharged if else mutate (unit = "kiloton" ,# convert the year column from character to numeric year = as.integer (year)|> select (EV_name, indicator, scenario, unit, year, value)
# A tibble: 228 × 6
EV_name indicator scenario unit year value
<chr> <chr> <chr> <chr> <int> <dbl>
1 Constrained nickel supply Copper Current Year kilo… 2022 381.
2 Constrained nickel supply Copper Stated policies scenar… kilo… 2025 617.
3 Constrained nickel supply Copper Stated policies scenar… kilo… 2030 1389.
4 Constrained nickel supply Copper Stated policies scenar… kilo… 2035 1736.
5 Constrained nickel supply Copper Stated policies scenar… kilo… 2040 2233.
6 Constrained nickel supply Copper Stated policies scenar… kilo… 2045 2418.
7 Constrained nickel supply Copper Stated policies scenar… kilo… 2050 2313.
8 Constrained nickel supply Copper Announced pledges scen… kilo… 2025 732.
9 Constrained nickel supply Copper Announced pledges scen… kilo… 2030 2113.
10 Constrained nickel supply Copper Announced pledges scen… kilo… 2035 3587.
# ℹ 218 more rows
Building the function
<- "A7" <- "A8:W19" <- read_EV_sheet (range = EV_name_range) |> pull ()
New names:
• `` -> `...1`
<- read_EV_sheet (range = EV_info_range)
New names:
• `` -> `...1`
• `` -> `...2`
• `` -> `...3`
• `` -> `...4`
• `` -> `...5`
• `` -> `...6`
• `` -> `...7`
• `` -> `...8`
• `` -> `...9`
• `` -> `...10`
• `` -> `...11`
• `` -> `...12`
• `` -> `...13`
• `` -> `...14`
• `` -> `...15`
• `` -> `...16`
• `` -> `...17`
• `` -> `...18`
• `` -> `...19`
• `` -> `...20`
• `` -> `...21`
• `` -> `...22`
• `` -> `...23`
<- names (EV_info)<- EV_info |> rename (indicator = ` ...1 ` ) |> pivot_longer (cols = - indicator,names_to = "EV_info_col_names" ) |> add_column (EV_name)<- EV_info_long |> left_join (sheet_headers_and_col_names, by = join_by (EV_info_col_names)) |> # filter out what were empty columns (where years are NA) filter (! is.na (year)) |> # case_when is supercharged if else mutate (unit = "kiloton" ,# convert the year column from character to numeric year = as.integer (year)|> select (EV_name, indicator, scenario, unit, year, value)
# A tibble: 228 × 6
EV_name indicator scenario unit year value
<chr> <chr> <chr> <chr> <int> <dbl>
1 Constrained nickel supply Copper Current Year kilo… 2022 381.
2 Constrained nickel supply Copper Stated policies scenar… kilo… 2025 617.
3 Constrained nickel supply Copper Stated policies scenar… kilo… 2030 1389.
4 Constrained nickel supply Copper Stated policies scenar… kilo… 2035 1736.
5 Constrained nickel supply Copper Stated policies scenar… kilo… 2040 2233.
6 Constrained nickel supply Copper Stated policies scenar… kilo… 2045 2418.
7 Constrained nickel supply Copper Stated policies scenar… kilo… 2050 2313.
8 Constrained nickel supply Copper Announced pledges scen… kilo… 2025 732.
9 Constrained nickel supply Copper Announced pledges scen… kilo… 2030 2113.
10 Constrained nickel supply Copper Announced pledges scen… kilo… 2035 3587.
# ℹ 218 more rows
<- function (EV_name_range, EV_info_range) {<- read_EV_sheet (range = EV_name_range) |> pull ()<- read_EV_sheet (range = EV_info_range)<- names (EV_info)<- EV_info |> rename (indicator = ` ...1 ` ) |> pivot_longer (cols = - indicator,names_to = "EV_info_col_names" ) |> add_column (EV_name)<- EV_info_long |> left_join (sheet_headers_and_col_names, by = join_by (EV_info_col_names)) |> # filter out what were empty columns (where years are NA) filter (! is.na (year)) |> # case_when is supercharged if else mutate (unit = "kiloton" ,# convert the year column from character to numeric year = as.integer (year)|> select (EV_name, indicator, scenario, unit, year, value)
<- read_iea_EV_table (EV_name_range = "A7" ,EV_info_range = "A8:W19"
New names:
New names:
• `` -> `...1`
<- read_iea_EV_table (EV_name_range = "A22" ,EV_info_range = "A23:W34"
New names:
New names:
• `` -> `...1`
<- read_iea_EV_table (EV_name_range = "A37" ,EV_info_range = "A38:W49"
New names:
New names:
• `` -> `...1`
<- read_iea_EV_table (EV_name_range = "A52" ,EV_info_range = "A53:W64"
New names:
New names:
• `` -> `...1`
<- read_iea_EV_table (EV_name_range = "A67" ,EV_info_range = "A68:W79"
New names:
New names:
• `` -> `...1`
<- read_iea_EV_table (EV_name_range = "A82" ,EV_info_range = "A83:W94"
New names:
New names:
• `` -> `...1`
<- Constrained_nickel_supply_table |> bind_rows (Wider_use_of_silicon_rich_anodes_table) |> bind_rows (Faster_uptake_of_solid_state_batteries_table) |> bind_rows (Lower_battery_sizes_table) |> bind_rows (Limited_battery_size_reduction_table) |> bind_rows (STEPS_Base_case_table)
# A tibble: 1,368 × 6
EV_name indicator scenario unit year value
<chr> <chr> <chr> <chr> <int> <dbl>
1 Constrained nickel supply Copper Current Year kilo… 2022 381.
2 Constrained nickel supply Copper Stated policies scenar… kilo… 2025 617.
3 Constrained nickel supply Copper Stated policies scenar… kilo… 2030 1389.
4 Constrained nickel supply Copper Stated policies scenar… kilo… 2035 1736.
5 Constrained nickel supply Copper Stated policies scenar… kilo… 2040 2233.
6 Constrained nickel supply Copper Stated policies scenar… kilo… 2045 2418.
7 Constrained nickel supply Copper Stated policies scenar… kilo… 2050 2313.
8 Constrained nickel supply Copper Announced pledges scen… kilo… 2025 732.
9 Constrained nickel supply Copper Announced pledges scen… kilo… 2030 2113.
10 Constrained nickel supply Copper Announced pledges scen… kilo… 2035 3587.
# ℹ 1,358 more rows
Problem 1.1.2
library (dplyr)library (ggplot2)%>% filter (indicator %in% c ("Cobalt" , "Copper" )) %>% ggplot () + aes (x = indicator, y = value, fill = indicator, colour = indicator) + geom_col () + scale_fill_manual (values = c (Cobalt = "#D6B067" , Copper = "#6BBEB3" )) + scale_color_manual (values = c (Cobalt = "#D6B067" , Copper = "#6BBEB3" )) + labs (x = "Indicator" , y = "Value" , title = "Copper vs. Cobalt Under Constrained Nickel Supply" , subtitle = "Copper takes the lead across policy scenarios" , caption = "Jun!" ) + theme_minimal () + facet_wrap (vars (scenario))
library (dplyr)library (ggplot2)%>% filter (indicator %in% c ("Cobalt" , "Copper" )) %>% filter (! (scenario %in% "Current Year" )) %>% ggplot () + aes (x = year, y = value, fill = indicator, colour = indicator) + geom_point (shape = "circle" , size = 1.75 ) + geom_smooth (span = 0.85 ) + scale_fill_hue (direction = 1 ) + scale_color_hue (direction = 1 ) + labs (x = "Year" , y = "Value" , title = "Copper vs. Cobalt under lower battery size scenario" , subtitle = "Copper takes the lead under three policy scenarios" , caption = "Jun!" ) + theme (axis.text.x = element_text (angle = 45 , hjust = 1 , size = 8 )) + theme_minimal () + facet_wrap (vars (scenario))
`geom_smooth()` using method = 'loess' and formula = 'y ~ x'
%>% filter (indicator %in% c ("Cobalt" , "Copper" )) %>% filter (scenario %in% "Net Zero Emissions by 2050 scenario" ) %>% ggplot () + aes (x = year,y = value,fill = indicator,colour = indicator+ geom_line () + scale_fill_hue (direction = 1 ) + scale_color_hue (direction = 1 ) + labs (x = "Year" ,y = "Value" ,title = "Copper vs. Cobalt under net zero emission scenario" ,subtitle = "Copper takes the lead and reach peak before 2045" ,caption = "Jun!" + theme_minimal () + theme (axis.text.x = element_text (angle = 45 , hjust = 1 , size = 8 )) + facet_wrap (vars (EV_name))
%>% filter (indicator %in% c ("Cobalt" , "Copper" )) %>% filter (scenario %in% c ("Stated policies scenario" , "Current Year" )) %>% ggplot () + aes (x = year, y = value, colour = indicator) + geom_point (shape = "circle" , size = 1.5 ) + geom_smooth (span = 0.75 ) + scale_color_hue (direction = 1 ) + labs (x = "Year" , y = "Value" , title = "Copper vs. Cobalt under faster uptake of solid state batteries scenario" , caption = "Jun!" ) + theme_minimal ()
`geom_smooth()` using method = 'loess' and formula = 'y ~ x'
library (dplyr)library (ggplot2)%>% filter (indicator %in% c ("Cobalt" , "Copper" )) %>% filter (scenario %in% "Announced pledges scenario" ) %>% ggplot () + aes (x = year, y = value, fill = indicator, colour = indicator) + geom_point (shape = "circle" , size = 1.5 ) + geom_smooth (span = 0.84 ) + scale_fill_hue (direction = 1 ) + scale_color_hue (direction = 1 ) + labs (x = "Year" , y = "Value" , title = "Copper vs. Cobalt under announced pledge scenario" , subtitle = "The gap is widening" , caption = "Jun!" ) + theme_minimal () + facet_wrap (vars (EV_name))
`geom_smooth()` using method = 'loess' and formula = 'y ~ x'
Warning: Removed 12 rows containing non-finite values (`stat_smooth()`).
Warning: Removed 12 rows containing missing values (`geom_point()`).
