paper 2_data preparation

Author

Sophia Wang

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/ruoleiw0921/homework5

library(dplyr)
library(readr)
library(reshape2)


Attaching package: 'reshape2'

The following object is masked from 'package:tidyr':

    smiths

library(esquisse)

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

path_to_sheet

[1] "/Users/ruoleiw0921/homework5/data-raw/CM_Data_Explorer.xlsx"

read_key_minerals_sheet <- partial(
  .f = read_excel,
  path = path_to_sheet,
  sheet = "1 Total demand for key minerals",
  col_names = FALSE
)

# now all we have to do is provide the range
sheet_header <- read_key_minerals_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 |> 
  # transpose the data
  t() |>
  # turn it back into a tibble
  as_tibble() |>
  # make them meaningful
  rename(scenario = V1, year = V2) |>
  # fill scenario down
  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`.

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

mineral_name <- read_key_minerals_sheet(range = "A7") |> 
  pull()

New names:
• `` -> `...1`

mineral_name

[1] "Copper"

mineral_info <- read_key_minerals_sheet(range = "A8:W18")

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`

mineral_info

# A tibble: 11 × 23
   ...1         ...2 ...3     ...4    ...5    ...6    ...7    ...8    ...9 ...10
   <chr>       <dbl> <lgl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl> <lgl>
 1 Solar PV  6.82e+2 NA    7.79e+2 9.07e+2 9.25e+2 9.59e+2 1.12e+3 1.26e+3 NA   
 2 Wind      3.94e+2 NA    4.28e+2 6.46e+2 5.95e+2 5.32e+2 6.39e+2 7.21e+2 NA   
 3 Other lo… 8.50e+1 NA    6.90e+1 1.08e+2 8.69e+1 8.47e+1 1.10e+2 1.17e+2 NA   
 4 Electric… 3.73e+2 NA    5.80e+2 1.04e+3 1.22e+3 1.42e+3 1.46e+3 1.35e+3 NA   
 5 Grid bat… 2.04e+1 NA    3.84e+1 8.27e+1 1.54e+2 2.25e+2 2.38e+2 2.20e+2 NA   
 6 Electric… 4.18e+3 NA    4.58e+3 6.51e+3 6.51e+3 6.58e+3 7.11e+3 6.98e+3 NA   
 7 Hydrogen… 3.20e-3 NA    3.88e-3 6.76e-3 6.53e-3 6.99e-3 8.90e-3 1.45e-2 NA   
 8 Total cl… 5.74e+3 NA    6.47e+3 9.30e+3 9.49e+3 9.80e+3 1.07e+4 1.06e+4 NA   
 9 Other us… 1.98e+4 NA    2.03e+4 2.15e+4 2.20e+4 2.34e+4 2.51e+4 2.57e+4 NA   
10 Total de… 2.55e+4 NA    2.68e+4 3.08e+4 3.15e+4 3.32e+4 3.58e+4 3.64e+4 NA   
11 Share of… 2.25e-1 NA    2.42e-1 3.01e-1 3.01e-1 2.96e-1 2.98e-1 2.93e-1 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>

mineral_info_col_names <- names(mineral_info)

mineral_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(mineral_info_col_names = mineral_info_col_names)

sheet_headers_and_col_names

# A tibble: 23 × 3
   scenario                 year  mineral_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

mineral_info_long <- mineral_info |> 
  rename(indicator = `...1`) |> 
  pivot_longer(cols = -indicator,
               names_to = "mineral_info_col_names") |> 
  add_column(mineral_name)

mineral_info_long

# A tibble: 242 × 4
   indicator mineral_info_col_names value mineral_name
   <chr>     <chr>                  <dbl> <chr>       
 1 Solar PV  ...2                    682. Copper      
 2 Solar PV  ...3                     NA  Copper      
 3 Solar PV  ...4                    779. Copper      
 4 Solar PV  ...5                    907. Copper      
 5 Solar PV  ...6                    925. Copper      
 6 Solar PV  ...7                    959. Copper      
 7 Solar PV  ...8                   1122. Copper      
 8 Solar PV  ...9                   1262. Copper      
 9 Solar PV  ...10                    NA  Copper      
10 Solar PV  ...11                   923. Copper      
# ℹ 232 more rows

combined_data <- mineral_info_long |> 
  left_join(sheet_headers_and_col_names, by = join_by(mineral_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 = case_when(
    indicator == "Share of clean technologies in total demand" ~ "Percent",
    .default = "kiloton"
    ),
    # convert the year column from character to numeric
    year = as.integer(year)
  ) |> 
  select(mineral_name, indicator, scenario, unit, year, value)

combined_data

# A tibble: 209 × 6
   mineral_name indicator scenario                   unit     year value
   <chr>        <chr>     <chr>                      <chr>   <int> <dbl>
 1 Copper       Solar PV  Current Year               kiloton  2022  682.
 2 Copper       Solar PV  Stated policies scenario   kiloton  2025  779.
 3 Copper       Solar PV  Stated policies scenario   kiloton  2030  907.
 4 Copper       Solar PV  Stated policies scenario   kiloton  2035  925.
 5 Copper       Solar PV  Stated policies scenario   kiloton  2040  959.
 6 Copper       Solar PV  Stated policies scenario   kiloton  2045 1122.
 7 Copper       Solar PV  Stated policies scenario   kiloton  2050 1262.
 8 Copper       Solar PV  Announced pledges scenario kiloton  2025  923.
 9 Copper       Solar PV  Announced pledges scenario kiloton  2030 1177.
10 Copper       Solar PV  Announced pledges scenario kiloton  2035 1369.
# ℹ 199 more rows

read_iea_mineral_table <-
  function(mineral_name_range, mineral_info_range) {
    mineral_name <-
      read_key_minerals_sheet(range = mineral_name_range) |>
      pull()
    
    mineral_info <- read_key_minerals_sheet(range = mineral_info_range)
    
    mineral_info_col_names <- names(mineral_info)
    
    mineral_info_long <- mineral_info |>
      rename(indicator = `...1`) |>
      pivot_longer(cols = -indicator,
                   names_to = "mineral_info_col_names") |>
      add_column(mineral_name)
    
    combined_data <- mineral_info_long |>
      left_join(sheet_headers_and_col_names, by = join_by(mineral_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 = case_when(
          indicator == "Share of clean technologies in total demand" ~ "Percent",
          .default = "kiloton"
        ),
        # convert the year column from character to numeric
        year = as.integer(year)
      ) |>
      select(mineral_name, indicator, scenario, unit, year, value)
    
    combined_data
  }

copper_table <- read_iea_mineral_table(
  mineral_name_range = "A7",
  mineral_info_range = "A8:W18"
)

New names:
New names:
• `` -> `...1`

cobalt_table <- read_iea_mineral_table(
  mineral_name_range = "A21",
  mineral_info_range = "A22:W29"
)

New names:
New names:
• `` -> `...1`

lithium_table <- read_iea_mineral_table(
  mineral_name_range = "A32",
  mineral_info_range = "A33:W38"
)

New names:
New names:
• `` -> `...1`

nickel_table <- read_iea_mineral_table(
  mineral_name_range = "A41",
  mineral_info_range = "A42:W51"
)

New names:
New names:
• `` -> `...1`

neodymium_table <- read_iea_mineral_table(
  mineral_name_range = "A54",
  mineral_info_range = "A55:W60"
)

New names:
New names:
• `` -> `...1`

final_iea_minerals_table <- copper_table |> 
  bind_rows(cobalt_table) |> 
  bind_rows(lithium_table) |>
  bind_rows(nickel_table) |>
  bind_rows(neodymium_table)

final_iea_minerals_table

# A tibble: 779 × 6
   mineral_name indicator scenario                   unit     year value
   <chr>        <chr>     <chr>                      <chr>   <int> <dbl>
 1 Copper       Solar PV  Current Year               kiloton  2022  682.
 2 Copper       Solar PV  Stated policies scenario   kiloton  2025  779.
 3 Copper       Solar PV  Stated policies scenario   kiloton  2030  907.
 4 Copper       Solar PV  Stated policies scenario   kiloton  2035  925.
 5 Copper       Solar PV  Stated policies scenario   kiloton  2040  959.
 6 Copper       Solar PV  Stated policies scenario   kiloton  2045 1122.
 7 Copper       Solar PV  Stated policies scenario   kiloton  2050 1262.
 8 Copper       Solar PV  Announced pledges scenario kiloton  2025  923.
 9 Copper       Solar PV  Announced pledges scenario kiloton  2030 1177.
10 Copper       Solar PV  Announced pledges scenario kiloton  2035 1369.
# ℹ 769 more rows

write_csv(final_iea_minerals_table,here("data", "iea_total_demand_for_critical_minerals.csv"))

cleaned_total_demand <- here("data", "iea_total_demand_for_critical_minerals.csv") |> 
  read_csv()

Rows: 779 Columns: 6
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (4): mineral_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.

cleaned_total_demand

# A tibble: 779 × 6
   mineral_name indicator scenario                   unit     year value
   <chr>        <chr>     <chr>                      <chr>   <dbl> <dbl>
 1 Copper       Solar PV  Current Year               kiloton  2022  682.
 2 Copper       Solar PV  Stated policies scenario   kiloton  2025  779.
 3 Copper       Solar PV  Stated policies scenario   kiloton  2030  907.
 4 Copper       Solar PV  Stated policies scenario   kiloton  2035  925.
 5 Copper       Solar PV  Stated policies scenario   kiloton  2040  959.
 6 Copper       Solar PV  Stated policies scenario   kiloton  2045 1122.
 7 Copper       Solar PV  Stated policies scenario   kiloton  2050 1262.
 8 Copper       Solar PV  Announced pledges scenario kiloton  2025  923.
 9 Copper       Solar PV  Announced pledges scenario kiloton  2030 1177.
10 Copper       Solar PV  Announced pledges scenario kiloton  2035 1369.
# ℹ 769 more rows

The echo: false option disables the printing of code (only output is displayed).