Quarto5

4.5.0.1 Homework problem 1 (Import and tidy worksheet 2.3_EV)

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── 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(readxl)
library(here)

here() starts at /Users/lars

library(dplyr)

path_to_sheet <- here("data-raw", "CM_Data_Explorer.xlsx")
path_to_sheet

[1] "/Users/lars/data-raw/CM_Data_Explorer.xlsx"

read_2.3_EV_sheet <- partial(
  .f = read_excel,
  path = path_to_sheet,
  sheet = "2.3 EV",
  col_names = FALSE
)
sheet_header <- read_2.3_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`

sheet_header

# 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>

sheet_header_processed <- sheet_header |> 
  t() |>
  as_tibble() |>
  rename(scenario = V1, year = V2) |>
  fill(scenario) |>
  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`.

sheet_header_processed

# 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

application_name <- read_2.3_EV_sheet(range = "A7") |> 
  pull()

New names:
• `` -> `...1`

application_name

[1] "Constrained nickel supply"

application_info <- read_2.3_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`

application_info

# 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>

application_info_col_names <- names(application_info)
application_info_col_names

 [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_headers_and_col_names <- sheet_header_processed |> 
  add_column(application_info_col_names = application_info_col_names)
sheet_headers_and_col_names

# A tibble: 23 × 3
   scenario                 year  application_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

application_info_long <- application_info |> 
  rename(indicator = `...1`) |> 
  pivot_longer(cols = -indicator,
               names_to = "application_info_col_names") |> 
  add_column(application_name)
application_info_long

# A tibble: 264 × 4
   indicator application_info_col_names value application_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

read_iea_application_table_copper_cobalt <-
  function(application_name_range, application_info_range) {
    application_name <-
      read_2.3_EV_sheet(range = application_name_range) |>
      pull()
    application_info <- read_2.3_EV_sheet(range = application_info_range)
    application_info_col_names <- names(application_info)
    application_info_long <- application_info |>
      rename(indicator = `...1`) |>
      pivot_longer(cols = -indicator,
                   names_to = "application_info_col_names") |>
      add_column(application_name)
    combined_data <- application_info_long |>
      left_join(sheet_headers_and_col_names, by = join_by(application_info_col_names)) |>
      filter(indicator == "Copper" | indicator == "Cobalt") |>
      filter(!is.na(year)) |>
      mutate(unit = "kiloton",year = as.integer(year)) |> 
      select(application_name, indicator, scenario, unit, year, value)
    combined_data
  }

constrained_nickel_supply_table <- read_iea_application_table_copper_cobalt(
  application_name_range = "A7",
  application_info_range = "A8:W19"
)

New names:
New names:
• `` -> `...1`

wider_use_of_silicon_rich_anodes_table <- read_iea_application_table_copper_cobalt(
  application_name_range = "A22",
  application_info_range = "A23:W34"
)

New names:
New names:
• `` -> `...1`

faster_uptake_of_solid_state_batteries_table <- read_iea_application_table_copper_cobalt(
  application_name_range = "A37",
  application_info_range = "A38:W49"
)

New names:
New names:
• `` -> `...1`

lower_battery_sizes_table <- read_iea_application_table_copper_cobalt(
  application_name_range = "A52",
  application_info_range = "A53:W64"
)

New names:
New names:
• `` -> `...1`

limited_battery_size_reduction_table <- read_iea_application_table_copper_cobalt(
  application_name_range = "A67",
  application_info_range = "A68:W79"
)

New names:
New names:
• `` -> `...1`

steps_base_case_table <- read_iea_application_table_copper_cobalt(
  application_name_range = "A82",
  application_info_range = "A83:W94"
)

New names:
New names:
• `` -> `...1`

final_iea_applications_table_copper_cobalt <- 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)
final_iea_applications_table_copper_cobalt

# A tibble: 228 × 6
   application_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

write_csv(final_iea_applications_table_copper_cobalt,here("data", "iea_demand_for_copper_and_cobalt.csv"))

4.5.0.1 Homework problem 1 (Compelling data visualizations)

our_cleaned_data <- here("data", "iea_demand_for_copper_and_cobalt.csv") |> 
  read_csv()

Rows: 228 Columns: 6
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (4): application_name, indicator, scenario, unit
dbl (2): 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.

our_cleaned_data

# A tibble: 228 × 6
   application_name          indicator scenario                unit   year value
   <chr>                     <chr>     <chr>                   <chr> <dbl> <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

# Compelling data visualizations 1 (Total Demand For Copper vs. Cobalt in EV)
ggplot(our_cleaned_data) +
  aes(x = value, y = indicator) +
  geom_boxplot(fill = "red") +
  labs(
    x = "Demand in Kt",
    y = "Mineral Type",
    title = "Total Demand For Copper vs. Cobalt in EV",
    caption = "Haotian Duan"
  ) +
  theme_minimal()

Warning: Removed 24 rows containing non-finite values (`stat_boxplot()`).

# Compelling data visualizations 2 (Demand For Copper vs. Cobalt in Different Scenario)
ggplot(our_cleaned_data) +
  aes(x = indicator, y = value) +
  geom_boxplot(fill = "blue") +
  labs(
    x = "Mineral Type",
    y = "Demand in Kt",
    title = "Demand For Copper vs. Cobalt in Different Scenario",
    caption = "Haotian Duan"
  ) +
  theme_minimal() +
  facet_wrap(vars(scenario))

Warning: Removed 24 rows containing non-finite values (`stat_boxplot()`).

# Compelling data visualizations 3 (Demand For Copper vs. Cobalt in Different Application)
ggplot(our_cleaned_data) +
  aes(x = indicator, y = value) +
  geom_boxplot(fill = "green") +
  labs(
    x = "Mineral Type",
    y = "Demand in Kt",
    title = "Demand For Copper vs. Cobalt in Different Application",
    caption = "Haotian Duan"
  ) +
  theme_minimal() +
  facet_wrap(vars(application_name))

Warning: Removed 24 rows containing non-finite values (`stat_boxplot()`).

# Compelling data visualizations 4 (The Trend of Copper vs. Cobalt Demand by Years)
sum_data <- our_cleaned_data |>
  filter(!is.na(value)) |>
  group_by(year, indicator) |>
  mutate(year_demand = sum(value))

ggplot(sum_data) +
  aes(
    x = year,
    y = year_demand,
    colour = indicator,
    group = indicator
  ) +
  geom_line() +
  scale_color_hue(direction = 1) +
  labs(
    x = "Year",
    y = "Demand in Kt",
    title = "The Trend of Demand by Years",
    caption = "Haotian Duan"
  ) +
  theme_minimal() +
  theme(legend.position = "left")

# Compelling data visualizations 5 (The Trend of Copper vs. Cobalt Demand by Years in Different Scenario)
ggplot(sum_data) +
  aes(
    x = year,
    y = year_demand,
    colour = indicator,
    group = indicator
  ) +
  geom_line() +
  scale_color_viridis_d(option = "viridis", direction = 1) +
  labs(
    x = "Year",
    y = "Demand in Kt",
    title = "The Trend of Demand by Years in Different Scenario",
    caption = "Haotian Duan"
  ) +
  theme_minimal() +
  theme(legend.position = "left") +
  facet_wrap(vars(scenario))

# Compelling data visualizations 5 (The Trend of Copper vs. Cobalt Demand by Years in Different Scenario)